WO2021095672A1 - 情報処理装置および情報処理方法 - Google Patents
情報処理装置および情報処理方法 Download PDFInfo
- Publication number
- WO2021095672A1 WO2021095672A1 PCT/JP2020/041676 JP2020041676W WO2021095672A1 WO 2021095672 A1 WO2021095672 A1 WO 2021095672A1 JP 2020041676 W JP2020041676 W JP 2020041676W WO 2021095672 A1 WO2021095672 A1 WO 2021095672A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- captured image
- information processing
- information
- normal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/27—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands using photo-electric detection ; circuits for computing concentration
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/60—Extraction of image or video features relating to illumination properties, e.g. using a reflectance or lighting model
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
Definitions
- This disclosure relates to an information processing device and an information processing method.
- Patent Document 1 a technique for analyzing the color and stains on the skin surface by utilizing the difference in the incident angle of the lighting unit is known (for example, Patent Document 1). Further, there is known a technique of reducing out-of-focus and distortion at the time of photographing the skin surface by arranging transparent glass at a predetermined distance from the tip dome of the microscope (for example, Patent Document 2).
- the quality of the image taken by the microscope can be improved.
- the conventional technology only improves the quality of a flat image, and it is difficult to obtain a 3D image that reproduces a minute shape (unevenness) of an object.
- a non-contact 3D measuring device, a 3D scanner, or the like is used as a device for measuring a minute shape of an object, but there is a problem that the cost is relatively high when these are introduced.
- the cost of the distance measuring device by the ToF (Time of Flight) method is relatively low, the accuracy may not be sufficient.
- an information processing device and an information processing method capable of improving the accuracy of shape measurement are provided.
- an information processing device includes a control unit.
- the control unit acquires an image captured by the sensor of the target.
- the captured image is an image obtained from reflected light of light radiated to the target from a plurality of light sources arranged at different positions.
- the control unit extracts a flat region from the captured image based on the brightness value of the captured image.
- the control unit calculates shape information regarding the shape of the surface of the target based on the information regarding the sensor and the flat region of the captured image.
- FIG. 32 It is a figure for demonstrating the learning method of the learning apparatus which concerns on 9th Embodiment. It is a figure which shows the structural example of the control part of the information processing apparatus which concerns on 10th Embodiment of this disclosure. It is a block diagram which shows an example of the schematic structure of the body information acquisition system of a patient using a capsule type endoscope to which the technique (the present technique) which concerns on this disclosure can be applied. It is a figure which shows an example of the schematic structure of the endoscopic surgery system to which the technique (the present technique) which concerns on this disclosure can apply. It is a block diagram which shows an example of the functional structure of the camera head and CCU shown in FIG. 32.
- the surface shape is directly formed from the RGB image.
- a method of calculating (depth to the surface) is known. However, when the depth is calculated directly from the RGB image by CNN, there is uncertainty and it is difficult to improve the accuracy.
- FIG. 1 is a diagram for explaining a calculation method for calculating the depth from a captured image. The method described with reference to FIG. 1 is performed, for example, by the information processing apparatus 200.
- the information processing apparatus 200 first acquires an captured image captured by the microscope (step S1). At this time, the information processing apparatus 200 also acquires information about the microscope, for example.
- the information processing device 200 calculates a normal (normal information) on the surface of the target based on the captured image (step S2).
- the information processing device 200 obtains normal information as output data by inputting an captured image into a learning device (model) learned by using, for example, CNN or the like.
- the information processing device 200 calculates the distance (depth information) to the surface of the target based on the normal information (step S3). If the distance between the microscope sensor, which is one of the information about the microscope, and the target is known, the information processing apparatus 200 can measure the distance to the surface of the target based on the normal information.
- the distance between the microscope sensor and the target is a known value corresponding to the length of the head mount portion.
- the information processing apparatus 200 calculates the depth to the target surface based on the normal information by minimizing W in the following equation (1).
- Each parameter of the equation (1) is as follows.
- p x direction of the calculated normal
- q y direction of the calculated normal
- Z x partial differential of the desired depth in the x direction (x direction of the normal)
- Z y Partial differential of the desired depth in the y direction (y direction of the normal)
- Z xx Twice partial differential of the desired depth in the x direction (partial differential of the normal in the x direction in the x direction)
- Z yy Twice partial differential of the desired depth in the y direction (partial differential of the normal in the y direction in the y direction)
- Z xy Partial differential of the desired depth in the x and y directions twice
- x and y indicate the coordinates on the captured image
- the x direction is, for example, the horizontal direction of the captured image
- the y direction is the vertical direction of the captured image.
- the following equation (3) is obtained by expanding the equation (2), and the depth to the target surface is calculated by performing the inverse Fourier transform of the equation (3).
- the information processing apparatus 200 calculates the distance (depth) to the surface of the target by using the equation conversion of the equations (1) to (3) described above.
- the depth is calculated on the assumption that the weights ( ⁇ , ⁇ ) of the cost term are small, that is, the sum of the absolute values of the normals is small and the sum of the absolute values of the normal derivatives is small.
- the assumption that the sum of the absolute values of the normals is small (hereinafter, also referred to as Assumption 1) means that the target surface for which the depth is calculated is flat.
- the assumption that the sum of the absolute values of the derivatives of the normals is small hereinafter, also referred to as assumption 2) means that the curvature of the target surface for which the depth is calculated is small. That is, in the above-mentioned calculation method, the depth to the target is calculated on the assumption that the rough surface shape of the target for which the depth is calculated is a flat surface.
- FIG. 2 is a table for explaining the rough shape of the target surface.
- the actual shape of the target surface is shown by a dotted line
- the rough shape of the target surface is shown by a straight line.
- the normal of the target surface is indicated by an arrow.
- the horizontal direction of the target is the x direction
- the vertical direction is the z direction (depth).
- the rough shape of the target surface is the shape of the entire captured image of the target surface, and the rough shape of the target surface is flat means that there is little variation when looking at the shape of the entire captured image of the target surface. .. It should be noted that the change in the local unevenness of the target surface is not included in the rough shape because it is a calculation target. The more the assumption of the cost term of the optimization formula shown in the above equation (1) is satisfied, that is, the closer the surface shape of the entire captured image of the target surface is to a flat surface, the more accurate the information processing apparatus 200 is to the depth to the target surface. Can be calculated.
- the object shown in (1) of the table in FIG. 2 has a shape in which a straight surface includes fine irregularities. Therefore, since the target shown in (1) satisfies both the above-mentioned assumptions 1 and 2 (indicated by " ⁇ " in the table), the information processing apparatus 200 calculates the depth of the target with high accuracy. Can be done.
- the object shown in (2) of the table in FIG. 2 has a shape in which a slightly upwardly curved surface includes fine irregularities. Therefore, the object shown in (2) slightly satisfies the above-mentioned assumption 1 (indicated by “ ⁇ ” in the table) and satisfies the assumption 2. Therefore, the information processing apparatus 200 can calculate the depth of the object shown in (2) with higher accuracy than in (1).
- the object shown in (3) of the table in FIG. 2 has a shape in which the left side is largely curved upward and the surface includes fine irregularities. Therefore, the object shown in (3) does not satisfy both assumptions 1 and 2 described above (indicated by "x" in the table). Therefore, the information processing apparatus 200 cannot accurately calculate the depth of the object shown in (3).
- the surface of the object shown in (4) of the table in FIG. 2 has a gradual surface.
- the object shown in (4) since the object shown in (4) has a shape in which the surface having a plurality of straight surfaces having different heights and directions includes fine irregularities, neither of the above assumptions 1 and 2 is satisfied. Therefore, the information processing apparatus 200 cannot accurately calculate the depth of the object shown in (4).
- the above-mentioned calculation method has a problem that the depth calculation accuracy is lowered if the assumption that the rough shape of the surface of the depth calculation target is flat is not satisfied.
- the discloser of the present case creates each embodiment of the present disclosure according to the information processing apparatus 200 capable of improving the accuracy of shape measurement by improving the accuracy of calculating the depth. I came to do it. Therefore, the details of each embodiment according to the present disclosure will be sequentially described below.
- FIG. 3 is a diagram for explaining an outline of the first embodiment of the present disclosure.
- the information processing apparatus 200A (not shown) according to the first embodiment extracts a region (flat region) satisfying the above assumptions 1 and 2 from the captured image to obtain shape information (depth information) relating to the surface shape of the target. Suppresses deterioration of accuracy and improves the accuracy of shape measurement.
- the information processing device 200A first acquires the captured image M11 in which the sensor 150 of the microscope 100 captures the target S.
- the captured image M11 is an image obtained from the reflected light of the light IA and IB emitted from the plurality of light sources 160A and 160B arranged at different positions on the target S.
- the microscope 100 will be briefly described. As shown in the left figure of FIG. 3, the microscope 100 includes a sensor 150, a head mount portion 10 which is a tubular mechanism installed between the sensor 150 and an imaging target, and a plurality of light sources 160A and 160B. , Have.
- the sensor 150 may be read as a lens, a camera, or the like.
- the microscope 100 is an imaging device used by a user holding the microscope 100 in his / her hand and bringing the sensor 150 toward the target S by bringing the head mount portion 10 into contact with the target S.
- the microscope 100 exposes the reflected light of the light IA and IB simultaneously irradiated to the target S from the light sources 160A and 160B, and images the target S. At this time, for example, when the rough shape of the surface of the target S is not flat, occlusion (a region not exposed to light) occurs on the surface of the target S.
- the light IA emitted from the light source 160A hits the region SA and the region SAB on the surface of the target S, but does not hit the region SB.
- the light IB emitted from the light source 160B hits the region SB and the region SAB on the surface of the target S, but does not hit the region SA.
- the region SAB where the light IA and IB from the plurality of light sources 160A and 160B both hit is a flat region without occlusion.
- the regions SA and SB where only one of the light sources 160A and 160B hits the light IA and IB are in the region SAB where both the light IA and IB hit.
- the brightness value is lower than that of the image, resulting in a dark image.
- the information processing apparatus 200A extracts the flat region SAB from the captured image M11 based on the brightness value of the captured image M11. For example, the information processing apparatus 200A extracts a region SAB in which the brightness value of the captured image M11 is equal to or greater than a threshold value as a flat region.
- the information processing device 200A calculates shape information (depth information) regarding the surface shape of the target S based on the information regarding the sensor 150 and the flat region SAB of the captured image M11. For example, the information processing apparatus 200A acquires the normal information of the flat region SAB by inputting the flat region SAB of the captured image M11 into the learner learned by using the CNN. The information processing apparatus 200A calculates the depth information to the surface of the target S by performing formula conversion using the above-mentioned formulas (1) to (3) for the acquired normal information.
- the information processing apparatus 200A can improve the accuracy of shape measurement by extracting the region satisfying the assumptions 1 and 2 of the equation (1) from the captured image M11.
- FIG. 4 is a block diagram showing a configuration example of the information processing system 1 according to the first embodiment of the present disclosure. As shown in FIG. 4, the information processing system 1 includes a microscope 100 and an information processing device 200A.
- the microscope 100 is an imaging device that the user holds in his / her hand and is used by pointing the sensor 150 at the imaging target S.
- the information processing device 200A calculates shape information regarding the surface shape of the imaging target S based on the captured image M11 captured by the microscope 100. Details of the information processing device 200A will be described later with reference to FIG.
- the microscope 100 and the information processing device 200A are connected using, for example, a cable.
- the microscope 100 and the information processing device 200A may be directly connected by wireless communication such as Bluetooth (registered trademark) or NFC (Near Field Communication).
- the microscope 100 and the information processing device 200A may be connected by wire or wirelessly, for example, via a network (not shown).
- the microscope 100 and the information processing device 200A may exchange captured images via an externally mounted storage medium such as a hard disk, a magnetic disk, a magneto-optical disk, an optical disk, a USB memory, or a memory card. ..
- the microscope 100 and the information processing device 200A may be integrally configured.
- the information processing device 200A may be arranged inside the main body of the microscope 100, for example.
- FIG. 5 is a diagram showing a configuration example of the microscope 100 according to the first embodiment of the present disclosure.
- the microscope 100 includes a sensor 150 and a head mount portion 10 which is a tubular mechanism installed between the sensor 150 and an image pickup target. Further, the microscope 100 has point light sources 160A and 160B (not shown) arranged at different positions.
- the head mount portion 10 is a mechanism that is mounted on the tip of the microscope 100.
- the head mount portion 10 is also referred to as, for example, a tip head or a lens barrel.
- the inside of the head mount portion 10 may be, for example, a mirror, and the light emitted from the point light sources 160A and 160B may be totally reflected by the side surface of the head mount portion 10.
- the user brings the head mount portion 10 into contact with the target S to image the target S.
- the distance between the sensor 150 and the target S is fixed, and it is possible to prevent the focus (focal length) from being deviated during imaging.
- the microscope 100 has point light sources 160A and 160B inside the head mount portion 10. As a result, the microscope 100 exposes the reflected light of the light IA and IB irradiated to the target S from the point light sources 160A and 160B, and images the target S.
- the point light source in the present specification ideally means a light source by a point, but in reality, a light source by a point cannot exist, so a light source having an extremely small size (within a few millimeters, etc.) Is included.
- a point light source is used as an example of a light source, but the light source is not limited to the point light source. Also, the number of light sources is not limited to two. There may be a plurality of light sources, and there may be three or more light sources as long as they are arranged at different positions.
- FIG. 6 is a block diagram showing a configuration example of the information processing apparatus 200A according to the first embodiment of the present disclosure.
- the information processing device 200A has a control unit 220 and a storage unit 230.
- the control unit 220 controls the operation of the information processing device 200A.
- the control unit 220 includes an acquisition unit 221, an area acquisition unit 225, a normal calculation unit 222, a depth calculation unit 223, and a display control unit 224.
- Each functional unit of the acquisition unit 221, the area acquisition unit 225, the normal calculation unit 222, the depth calculation unit 223, and the display control unit 224 is stored inside the control unit 220 by, for example, the control unit 220. This is realized by executing the program with RAM or the like as a work area.
- the internal structure of the control unit 220 is not limited to the configuration shown in FIG. 6, and may be another configuration as long as it is configured to perform information processing described later. Further, the connection relationship of each processing unit included in the control unit 220 is not limited to the connection relationship shown in FIG. 6, and may be another connection relationship.
- the acquisition unit 221 acquires the captured image M11 captured by the microscope 100 and information about the microscope 100.
- the information about the microscope 100 includes information about the structure of the microscope 100, such as the focal length f and the length d of the head mount portion 10.
- the acquisition unit 221 may control, for example, the point light sources 160A and 160B of the microscope 100 and the sensor 150.
- the acquisition unit 221 controls the point light sources 160A and 160B so that the light IA and IB are simultaneously irradiated from the point light sources 160A and 160B.
- the acquisition unit 221 controls the sensor 150 so that the sensor 150 images the target S while the light IA and IB are simultaneously irradiated from the point light sources 160A and 160B.
- the information processing device 200A may control the microscope 100.
- the acquisition unit 221 may acquire information on imaging conditions in addition to the captured image M11.
- the information regarding the imaging conditions is, for example, information indicating that the captured image M11 is an image captured while the light sources IA and IB are simultaneously irradiated from the point light sources 160A and 160B.
- the region acquisition unit 225 which will be described later, extracts the flat region SAB from the captured image M11 according to, for example, the imaging conditions.
- the region acquisition unit 225 extracts the flat region SAB from the captured image M11.
- the area acquisition unit 225 compares, for example, the luminance value L (x, y) of each pixel of the captured image M11 with the threshold value th.
- the area acquisition unit 225 uses a region including pixels having a luminance value L (x, y) of the threshold th or more as a processing region, and pixels having a luminance value L (x, y) of less than the threshold th.
- the included area is defined as the excluded area.
- FIG. 7 is a diagram showing an example of the brightness value of the captured image M11. In FIG. 7, the brightness values L (x, ⁇ ) and the pixels (x) when the y-axis value is set to the predetermined value “ ⁇ ”. , ⁇ ) is shown.
- L (x, y) (R (x, y) + 2G (x, y) + B (x, y)) / 4 It is calculated by.
- R (x, y) is the R (Red) component of the pixel value in the pixel (x, y)
- G (x, y) is the G (Green) component of the pixel value in the pixel (x, y)
- B (x, y) is a B (Blue) component of the pixel value in the pixel (x, y).
- the region acquisition unit 225 acquires a region determined to be a processing region as an extraction region (flat region SAB) extracted from the captured image M11 by comparing the brightness values L (x, y) and the threshold value th in all the pixels. To do.
- the area acquisition unit 225 sets the pixel when the brightness value L (x, y) of the pixel is equal to or greater than the threshold value th or more to be white, and the pixel when the brightness value L (x, y) is less than the threshold value th to be black.
- the mask image M12 shown in 8 is generated. Note that FIG. 8 is a diagram showing an example of the mask image M12 generated by the area acquisition unit 225.
- the region acquisition unit 225 compares the generated mask image M12 with the captured image M11, and extracts pixels in which the mask image M12 is white at the same coordinates from the captured image M11 to obtain a flat region. Get SAB.
- FIG. 9 is a diagram for explaining an example of acquiring a flat region SAB by the region acquisition unit 225.
- the area acquisition unit 255 sets the brightness value of the pixel when the brightness value L (x, y) of the pixel is equal to or more than the threshold value th to be “1”, and sets the brightness value of the pixel when the brightness value L (x, y) is less than the threshold value th.
- the mask image M12 may be generated.
- the area acquisition unit 255 acquires the flat area SAB by multiplying the captured image M11 and the mask image M12.
- the area acquisition unit 255 outputs the acquired flat area SAB to the normal calculation unit 222.
- the mask image M12 generated by the area acquisition unit 255 may be output to the normal calculation unit 222, and the normal calculation unit 222 may acquire the flat region SAB from the captured image M11 using the mask image M12. ..
- the normal calculation unit 222 calculates the normal information on the surface of the target S as a normal image based on the flat region SAB of the captured image M11.
- the normal calculation unit 222 generates a normal image using, for example, CNN.
- the normal calculation unit 222 generates a normal image using a learner learned in advance using CNN.
- the number of input channels of the learner 300 (see FIG. 11) is 3 channels corresponding to RGB of the input image (here, the flat region SAB) or 1 channel of the gray scale of the input image. Further, the number of output channels of the learner 300 is set to 3 channels corresponding to RGB of the output image (here, the normal image). Further, the resolution of the output image shall be equal to the resolution of the input image.
- FIG. 10 is a diagram for explaining an example of normal information.
- the normal line N shown in FIG. 10 is a normal vector in a predetermined pixel of the captured image M11 in which the target S is captured.
- the zenith angle of the normal N is ⁇ and the azimuth is ⁇
- the relationship of the following equation (4) holds. It is assumed that the normal N is a unit vector.
- the normal information is the normal N (x, y, z) in the above-mentioned Cartesian coordinate system, and is calculated for each pixel of the flat region SAB of the captured image M11, for example.
- the normal image is an image obtained by replacing the normal information of each pixel with RGB. That is, the normal image is an image obtained by replacing x of the normal N with R (red), y with G (green), and z with B (blue).
- the normal calculation unit 222 generates a normal image, which is an output image, by inputting the flat region SAB as an input image to the learner 300. It is assumed that the learner 300 is pre-generated by learning the weights in the CNN with the true value of learning as the normal.
- FIG. 11 is a diagram for explaining the learning device 300 according to the embodiment of the present disclosure.
- the control unit 220 of the information processing device 200A will be described as generating the learning device 300, but the learning device 300 is generated by, for example, another information processing device (not shown). May be done.
- the information processing apparatus 200A calculates the similarity between the output image M15 when the input image M14 is input to the learner 300 and the normal image M16 which is the true value (Ground Truth) of learning. To do.
- the information processing apparatus 200A calculates the least squares error (L2) between the output image M15 and the normal image M16, and performs the learning process with L2 as the loss.
- the information processing device 200A updates the weight of the learner 300 by, for example, backpropagating the calculated loss. As a result, the information processing apparatus 200A generates a learning device 300 that outputs a normal image when the captured image is input.
- the learning device 300 is generated using CNN, but the present invention is not limited to this.
- the learning device 300 may be generated by using various methods such as RNN (Recurrent Neural Network) in addition to CNN.
- RNN Recurrent Neural Network
- the weight of the learner 300 is updated by backpropagating the calculated loss, but the present invention is not limited to this.
- the weight of the learner 300 may be updated by using an arbitrary learning method such as a stochastic gradient descent method.
- the loss is set to the least squares error, but the error is not limited to this. The loss may be the minimum average error.
- the normal calculation unit 222 generates a normal image by using the generated learner 300.
- the normal calculation unit 222 outputs the calculated normal image to the depth calculation unit 223.
- the above P (length [ ⁇ m] per 1 pixel (1 pixel) of the captured image xy) is a parameter whose value is determined from the configuration of the sensor 150 of the imaging device (microscope 100).
- FIG. 12 is a diagram for explaining the length of the captured image per pixel.
- the depth calculation unit 223 calculates the depth of the target S for each pixel of the captured image M11, for example, based on the normal image and the information about the sensor 150.
- the information about the sensor 150 is, for example, information about the structure of the sensor 150, and specifically, information about the focal length of the sensor 150 and the distance between the sensor 150 and the target S described above.
- the imaging device is the microscope 100
- the distance between the sensor 150 and the target S is the length d of the head mount portion 10.
- the display control unit 224 displays various images on a display unit (not shown) such as a liquid crystal display.
- FIG. 13 is a diagram showing an example of an image M17 displayed on the display unit by the display control unit 224.
- the display control unit 224 causes the display unit to display, for example, an image M17 including an captured image M17a, a normal image M17b, a depth image M17c, an image M17d showing a depth graph, and a 3D image M17e of the target S. ..
- the captured image M17a is, for example, an image obtained by cutting out a flat region SAB from the captured image M11 captured by the microscope 100.
- the normal image M17b is an image in which the normal information of the captured image M17a is displayed in RGB.
- the depth image M17c is an image showing the depth of each pixel of the captured image M17a. For example, the lighter the color, the larger the depth (the distance from the sensor 150 to the target S is larger).
- the image M17d showing the depth graph is an image in which the depths in the straight lines shown in the normal image M17b, the depth image M17c, and the 3D image M17e of the target S are displayed as a graph.
- the 3D image M17e of the target S is an image in which the target S is three-dimensionally displayed based on the depth image M17c.
- the display control unit 224 may display a graph showing the depth or a three-dimensional image on the display unit in addition to the captured image, the generated normal image, and the depth image.
- the storage unit 230 is realized by a ROM (Read Only Memory) that stores programs and arithmetic parameters used for processing of the control unit 220, and a RAM (Random Access Memory) that temporarily stores parameters that change as appropriate.
- ROM Read Only Memory
- RAM Random Access Memory
- FIG. 14 is a flowchart for explaining an example of the depth calculation process according to the first embodiment of the present disclosure.
- the depth calculation process shown in FIG. 14 is realized by executing a program by the control unit 220 of the information processing apparatus 200A.
- the depth calculation process shown in FIG. 14 is executed after the microscope 100 has captured the captured image M11.
- the depth calculation process shown in FIG. 14 may be executed in response to an instruction from the user.
- control unit 220 acquires the captured image M11 from the microscope 100, for example (step S101).
- control unit 220 may acquire the captured image M11 from another device, for example, via a network (not shown).
- Examples of other devices include other information processing devices and cloud servers.
- the control unit 220 acquires information about the sensor 150 (step S102).
- the control unit 220 may acquire information about the sensor 150 from the microscope 100.
- the control unit 220 may acquire the sensor information from the storage unit 230. Further, the control unit 220 may acquire the sensor information by input from the user, for example.
- the control unit 220 acquires the flat region SAB from the acquired captured image M11 (step S103). Specifically, the control unit 220 extracts a region in which the brightness value of each pixel of the captured image M11 is equal to or higher than the threshold value th as a flat region SAB.
- the control unit 220 calculates the acquired normal area information of the flat region SAB (step S104). Specifically, the control unit 220 inputs the flat region SAB as an input image to the learner 300 to generate a normal image including normal information as an output image.
- the control unit 220 calculates the depth information based on the normal information and the information related to the sensor 150 (step S105). Specifically, the control unit 220 calculates the depth information by performing an equation conversion based on the above-mentioned equation (3) or the like on the normal information.
- the information processing device 200A includes a control unit 220.
- the control unit 220 acquires the captured image M11 obtained by the sensor 150 capturing the target S.
- the captured image M11 is an image obtained from the reflected light of the light IA and IB emitted from the plurality of point light sources 160A and 160B arranged at different positions on the target S.
- the control unit 220 extracts the flat region SAB from the captured image M11 based on the brightness value of the captured image M11.
- the control unit 220 calculates shape information (depth information) regarding the surface shape of the target S based on the information regarding the sensor 150 and the flat region SAB of the captured image M11.
- the information processing apparatus 200A acquires the flat region SAB from the captured image M11 obtained from the reflected light of the light IA and IB simultaneously irradiated to the target S from the plurality of point light sources 160A and 160B.
- the information processing apparatus 200A acquires the flat region SAB, assumptions 1 and 2 can be satisfied in the formula conversion in the depth calculation unit 223, and a decrease in the accuracy of the depth calculation can be suppressed. As a result, the information processing apparatus 200A can improve the accuracy of shape measurement.
- the information processing apparatus 200A calculates the depth based on the captured image M11 captured by the microscope 100 while the light IA and IB are simultaneously irradiated from the plurality of point light sources 160A and 160B. It was. In addition to the above example, the information processing apparatus 200A may calculate the depth based on the captured image captured by the microscope 100 while the light is emitted from one point light source. Therefore, in the second embodiment, the information processing apparatus 200A is an image captured from the reflected light of the light radiated to the target S from one of the plurality of point light sources 160A and 160B, and each of the point light sources 160A and 160B is captured.
- FIG. 15 is a diagram for explaining the captured images M21 and M22 acquired by the acquisition unit 221 according to the second embodiment of the present disclosure.
- the microscope 100 first irradiates light IA from a point light source 160A to image the target S. At this time, for example, if the rough shape of the surface of the target S does not appear flat, occlusion (a region not exposed to light) occurs on the surface of the target S.
- the acquisition unit 221 acquires the captured image M21 whose region SA2 is darker than that of the region SA1, as shown in FIG. 15, for example.
- the microscope 100 irradiates the light IB from the point light source 160B to image the target S.
- an occlusion (a region not exposed to light) is generated on the surface of the target S, as in the case of irradiating the light IA from the point light source 160A.
- the acquisition unit 221 acquires the captured image M22 in which the region SB2 is darker than the region SB1, as shown in FIG. 15, for example.
- the acquisition unit 221 acquires the captured images M21 and M22 taken by the microscope 100 by sequentially lighting the two point light sources 160A and 160B.
- the area acquisition unit 225 acquires the flat area SAB from the captured images M21 and M22 acquired by the acquisition unit 221.
- the flat region SAB is exposed to the light IA and IB of both the point light sources 160A and 160B.
- the occlusion region where at least one of the optical IA and IB does not hit is an uneven region.
- the flat region SAB is exposed to the light IA and IB from the point light sources 160A and 160B, so that the brightness values of the pixels of the flat region SAB in both the captured images M21 and M22 are almost the same. It will be the same value.
- the area acquisition unit 225 acquires the flat area SAB based on the brightness values of the captured images M21 and M22.
- the region acquisition unit 225 extracts a region in which there is no change in the luminance value or a small change (within the threshold value th2) in the corresponding pixels of the captured images M21 and M22 as a flat region SAB.
- FIG. 16 is a diagram for explaining acquisition of a flat region by the region acquisition unit 225 according to the second embodiment of the present disclosure.
- L1 (x, y) is the brightness value of the pixel (x, y) of the captured image M21
- L2 (x, y) is the brightness value of the pixel (x, y) of the captured image M22.
- FIG. 16 is a graph showing the relationship between the difference D and x when the y of the pixel is fixed to a predetermined value. As shown in FIG. 15, the horizontal direction of the captured images M21 and M22 is the x direction, and the vertical direction is the y direction.
- the brightness value of the captured image M21 is high and the brightness value of the captured image M22 is low (see FIG. 15). Therefore, the value of the difference D in the region SB2 becomes a large value in the positive direction.
- the brightness value of the captured image M21 is low and the brightness value of the captured image M22 is high (see FIG. 15). Therefore, the value of the difference D in the region SA2 becomes a large value in the negative direction.
- the difference D is close to zero.
- the area acquisition unit 225 sets the area SB2 in which the difference D is the threshold value th2 or more as an exclusion area in which the depth calculation is not performed. Further, the area acquisition unit 225 sets the area SA2 in which the difference D is equal to or less than the threshold value ⁇ th2 as an exclusion area in which the depth calculation is not performed. On the other hand, the area acquisition unit 225 sets an area in which the difference D is within the threshold value ⁇ th2 as a processing area for calculating the depth. The area acquisition unit 225 acquires an area determined to be a processing area as an extraction area (flat area SAB) to be extracted from the captured images M21 and M22.
- an extraction area flat area SAB
- the area acquisition unit 225 determines the absolute value abs (D) of the difference D described above as a threshold value, and the area including the pixels whose absolute value abs (D) of the difference D is the threshold value th2 or more is a black area.
- the mask image M12 shown in FIG. 8 is generated.
- the area acquisition unit 225 acquires a flat region SAB by, for example, comparing the mask image M12 and the captured image M21 and extracting pixels in which the mask image M12 is white at the same coordinates from the captured image M21.
- the region acquisition unit 225 may acquire the flat region SAB by comparing the mask image M12 and the captured image M22.
- the processing after the mask image M12 is generated is the same as that of the first embodiment.
- either one of the point light sources 160A and 160B is irradiated to perform imaging.
- the amount of light that hits the target S can be suppressed to be low as compared with the case of irradiating at the same time as in the first embodiment described above, the overall brightness of the captured images M21 and M22 is suppressed and the contrast is kept high. be able to. Therefore, it is possible to increase the difference between the brightness value of the region where the captured images M21 and M22 are exposed to the light and the brightness value of the occlusion region where the light is not applied. As a result, the region acquisition unit 225 can more easily acquire the flat region SAB from the captured images M21 and M22.
- the image acquisition time can be suppressed to half the time as compared with the second embodiment.
- the area acquisition unit 225 may, for example, align the captured images M21 and M22 before acquiring the flat region SAB. It will be necessary to perform the processing of. Therefore, when calculating the depth in real time, it is desirable to calculate the depth using the information processing apparatus 200A according to the first embodiment, which has a short image acquisition time and does not require processing such as alignment.
- the information processing apparatus 200A captures the captured images M21 and M22 obtained from the reflected light of the light IA and IB irradiated to the target S from one of the plurality of point light sources 160A and 160B. , Obtained for each point light source 160A and 160B.
- the information processing device 200A extracts a region in which the change in the luminance value (absolute value of the difference D) between the plurality of captured images M21 and M22 acquired for each of the point light sources 160A and 160B is less than the predetermined threshold value th2 as the flat region SAB. ..
- the information processing apparatus 200A can increase the contrast of the captured images M21 and M22, improve the extraction accuracy of the flat region SAB, and improve the accuracy of shape measurement.
- the microscope 100 includes two point light sources 160A and 160B has been described here as an example, the number of point light sources is not limited to two.
- the microscope 100 may include three or more point light sources.
- the microscope 100 images the target S by sequentially turning on three or more point light sources.
- the information processing device 200A acquires a plurality of captured images captured by the microscope 100.
- the information processing apparatus 200A flattens the region where the change in the luminance value is small between the acquired plurality of captured images, in other words, the region where the absolute value of the difference between the luminance values of the corresponding pixels of the plurality of captured images is less than the predetermined threshold value th2. Acquired as region SAB.
- the microscope 100 may select, for example, the farthest point light source from a plurality of point light sources and turn it on.
- the information processing apparatus 200A may acquire the flat region SAB after performing smoothing processing on the captured image. Therefore, in the third embodiment, an example in which the information processing apparatus 200A performs the smoothing process before acquiring the flat region SAB from the captured image will be described.
- the information processing device 200A according to the third embodiment has the same configuration and operation as the information processing device 200A according to the first embodiment except for the operation of the area acquisition unit 225. The explanation of is omitted.
- FIG. 17 is a diagram for explaining the smoothing process by the area acquisition unit 225 according to the third embodiment of the present disclosure.
- the captured image M31 acquired by the acquisition unit 221 includes local unevenness and noise of the target S.
- the local unevenness of the target S is a calculation target of the depth information in the depth calculation unit 223.
- the area acquisition unit 225 When the area acquisition unit 225 tries to determine the threshold value of the captured image M31 shown in FIG. 17 on a pixel-by-pixel basis, it is affected by the above-mentioned unevenness and noise, and the acquisition accuracy of the flat area SAB is lowered.
- the region acquisition unit 225 performs smoothing processing on the captured image M31 before acquiring the flat region SAB by performing the threshold value determination, and generates the smoothing image M32 as shown in the lower figure of FIG. Specifically, the region acquisition unit 225 generates a smoothing image M32 by applying a low-pass filter to the captured image M31. The area acquisition unit 225 performs a threshold value determination on the smoothing image M32 and generates the mask image M12 shown in FIG.
- the area acquisition unit 225 acquires, for example, a flat region SAB in the captured image M31 by comparing the mask image M12 and the captured image M31 and extracting pixels in which the mask image M12 is white at the same coordinates from the captured image M31. To do.
- the area acquisition unit 225 generates the mask image M12 based on the smoothing image M32, so that the mask image M12 can be generated while reducing the influence of fine irregularities and noise of the captured image M31. Further, when the region acquisition unit 225 acquires the flat region SAB of the captured image M31 using the mask image M12, the flat region SAB including local unevenness can be extracted, and the depth of the target S can be accurately determined. Can be calculated.
- the information processing apparatus 200A can suppress a decrease in the acquisition accuracy of the flat region SAB, and can improve the accuracy of shape measurement.
- the region acquisition unit 225 acquires the flat region SAB by determining the brightness value of the pixel as a threshold value is shown.
- the information processing apparatus 200A may acquire a flat region by dividing the captured image into a plurality of blocks. Therefore, in the fourth embodiment, an example in which the information processing apparatus 200A divides the captured image into a plurality of blocks will be described.
- the information processing device 200A according to the fourth embodiment has the same configuration and operation as the information processing device 200A according to the first embodiment except for the operation of the area acquisition unit 225. The explanation of is omitted.
- FIG. 18 is a diagram for explaining acquisition of a flat region by the region acquisition unit 225 according to the fourth embodiment of the present disclosure.
- the area acquisition unit 225 divides the captured image M41 acquired by the acquisition unit 221 into, for example, a plurality of blocks, and acquires one divided block M42 as a flat area.
- the area acquisition unit 225 determines the size of the block based on the information about the microscope 100, and divides the captured image M41 into blocks of the determined size.
- FIG. 19 is a diagram for explaining acquisition of a flat region by the region acquisition unit 225 according to the fourth embodiment of the present disclosure.
- the area acquisition unit 225 divides, for example, the captured image M41 into blocks of 5 mm ⁇ 5 mm or less.
- the actual length P [ ⁇ m] of 1 pixel of the captured image is the focal length f [mm] of the sensor 150, the length d [mm] of the housing (head mount portion 10), and the pixels of the sensor 150. It is calculated based on the pitch p [ ⁇ m].
- the focal length f 16 [mm] of the sensor 150
- the length d 100 [mm] of the head mount portion 10
- the pixel pitch p 5 [ ⁇ m] of the sensor 150
- the normal calculation unit 222 and the depth calculation unit 223 calculate the normal information and the depth information for all the divided blocks.
- the depth calculation process is the same as the calculation process shown in FIG. 13, except that the number of blocks (flat areas) to be calculated is different.
- the information processing apparatus 200A divides the captured image M41 into a plurality of blocks and calculates the depth. As a result, the information processing apparatus 200A can acquire a flat region satisfying the assumptions 1 and 2 in the above-mentioned equations (1) to (3), and can accurately calculate the depth. As described above, the information processing apparatus 200A according to the fourth embodiment can improve the accuracy of shape measurement.
- the size of the block is set to 5 mm ⁇ 5 mm, but the size is not limited to this.
- the imaging target of the microscope 100 may be other than human skin. Since the size of the block that can be regarded as flat differs depending on the imaging target, the block size may be different depending on the imaging target.
- the storage unit 230 stores a table in which the types of the imaging targets and the appropriate block size are associated with each other.
- the information processing apparatus 200A selects the block size according to the type of the image pickup target.
- the user may specify the size of the block.
- the size of the block is not limited to the above-mentioned example, and various sizes can be selected.
- the area acquisition unit 225 acquires a flat area by dividing the captured image into blocks.
- the information processing apparatus 200A may acquire a flat region according to the contrast value of the divided blocks. Therefore, in the fifth embodiment, an example in which the information processing apparatus 200A acquires a flat region according to the contrast value of the divided blocks will be described.
- the information processing device 200A according to the fifth embodiment has the same configuration and operation as the information processing device 200A according to the fourth embodiment except for the operation of the area acquisition unit 225. The explanation of is omitted.
- FIG. 20 is a diagram for explaining the depth of field of the sensor 150.
- the sensor 150 (camera) has a depth of field (a range of depths at which the subject can be photographed without blurring) according to the aperture of the lens.
- the optical system of the camera has a focal length f that enables the subject to be photographed clearly with the highest resolution by focusing.
- the surface M52 shown in FIG. 20 is an in-focus surface, that is, a surface that is in focus and can clearly photograph a subject with the highest resolution.
- the range from the surface M53 to the surface M51 is a depth range (depth of field) in which the subject can be photographed without blurring.
- FIG. 21 is a diagram for explaining acquisition of a flat region by the region acquisition unit 225 according to the fifth embodiment of the present disclosure.
- the depth of field P1 of the microscope 100 since the depth of field P1 of the microscope 100 is shallow, the surface of the object S included in the depth of field P1, that is, the object S whose distance from the sensor 150 is substantially the same in a rough shape. SD1 can be photographed without blurring.
- the target S not included in the depth of field P1, that is, the surfaces SD2 and SD3 whose distance from the sensor 150 is different from that of the surface SD1 is blurred and imaged.
- the area acquisition unit 225 acquires the imaging area included in the depth of field P1 as a flat area.
- the area acquisition unit 225 acquires a flat area by acquiring an imaged area that is in focus and is not blurred from the captured image. This point will be described with reference to FIG.
- FIG. 22 is a diagram for explaining acquisition of a flat region by the region acquisition unit 225 according to the fifth embodiment of the present disclosure.
- the area acquisition unit 225 divides the captured image M54 acquired by the acquisition unit 221 into a plurality of blocks.
- the size of the block to be divided here may be the same as or different from the size of the block of the fourth embodiment described above.
- the contrast value contrast is high in the area that is in focus and imaged without blurring, and the contrast value contrast is low in the area that is out of focus and imaged blurry. Therefore, the area acquisition unit 225 acquires a flat area based on the calculated contrast value contrast. Specifically, the area acquisition unit 225 compares the calculated contrast value contrast with the threshold value th3 for each block. As shown in FIG. 22, the area acquisition unit 225 extracts a block having a contrast value contrast of the threshold value th3 or more as a flat area for calculating the depth.
- the normal calculation unit 222 and the depth calculation unit 223 calculate the normal information and the depth information of the flat region acquired by the area acquisition unit 225.
- the calculation method is the same as that of the first embodiment.
- the normal calculation unit 222 and the depth calculation unit 223 may calculate the normal information and the depth information in block units.
- the normal calculation unit 222 and the depth calculation unit 223 collect the normal area and the depth information by collecting a plurality of blocks extracted by the area acquisition unit 225 as a flat area, that is, a plurality of blocks having a contrast value contrast of the threshold value th3 or more. It may be calculated.
- the information processing apparatus 200A divides the captured image M54 into a plurality of blocks.
- the information processing apparatus 200A acquires a flat region according to the contrast value contrast calculated for each divided block.
- the information processing apparatus 200A acquires the flat region according to the contrast value contrast of the captured image M54, thereby satisfying the assumptions 1 and 2 in the above equations (1) to (3).
- the depth can be calculated.
- the information processing apparatus 200A according to the fifth embodiment can improve the accuracy of shape measurement.
- the area acquisition unit 225 divides one captured image into a plurality of blocks and acquires a flat area according to the contrast value of each of the divided blocks is shown.
- the information processing apparatus 200A may divide a plurality of captured images having different depths of field into a plurality of blocks, and acquire a flat region according to the contrast value of each of the divided blocks. Therefore, in the sixth embodiment, an example in which the information processing apparatus 200A acquires a flat region according to the contrast value for each block of the plurality of captured images will be described.
- the information processing device 200A according to the sixth embodiment has the same configuration and operation as the information processing device 200A according to the fifth embodiment except for the operations of the acquisition unit 221 and the area acquisition unit 225, the same reference numerals are given. However, some explanations will be omitted.
- FIG. 23 is a diagram for explaining a plurality of captured images acquired by the acquisition unit 221 according to the sixth embodiment of the present disclosure.
- the acquisition unit 221 acquires a plurality of captured images having different depths of field.
- the microscope 100 acquires a plurality of captured images having different depths of field (focus planes).
- the microscope 100 captures three captured images by capturing the target S three times while moving the sensor 150 up and down.
- the microscope 100 for example, first captures an captured image having a depth of field closest to the sensor 150, and thirdly captures an captured image having a depth of field closest to the sensor 150.
- the microscope 100 acquires, for example, a captured image in which the depth of field is located between the first and second times for the second time.
- the depth of field and the number of images taken in FIG. 23 are examples, and are not limited thereto.
- the microscope 100 may capture two or four or more captured images.
- the range of the depth of field at the time of each imaging may be continuous or partially overlapped.
- the acquisition unit 221 controls, for example, the microscope 100 to acquire captured images M61 to M63 having different depths of field.
- FIG. 24 is a diagram for explaining acquisition of a flat region by the region acquisition unit 225 according to the sixth embodiment of the present disclosure.
- the acquisition unit 221 controls the microscope 100 to capture captured images having different depths of field as shown in FIG. 23, thereby acquiring captured images M61 to M63 as shown in FIG. 24. To do.
- the area acquisition unit 225 divides each of the captured images M61 to M63 into blocks.
- the area acquisition unit 225 calculates the contrast value contrast for each divided block.
- the area acquisition unit 225 compares the calculated contrast value contrast of the block with the threshold value th3, and extracts a block having the contrast value contrast of the threshold value th3 or more as a flat area.
- the region acquisition unit 225 extracts the region M61A including the block whose contrast value contrast of the captured image M61 is the threshold value th3 or more from the captured image M61. Similarly, the region acquisition unit 225 extracts the region M62A including the block whose contrast value contrast of the captured image M62 is the threshold value th3 or more from the captured image M62. Further, the region M63A including the block whose contrast value contrast of the captured image M63 is equal to or higher than the threshold value th3 is extracted from the captured image M63.
- the area acquisition unit 225 synthesizes the extracted areas M61A to M63A to generate an image M64 including a flat area.
- the area acquisition unit 225 generates the image M64 by synthesizing the areas in which the captured images M61 to M63 are in focus and are not blurred.
- the information processing apparatus 200A acquires a plurality of captured images having different depths of field.
- the information processing device 200A divides the acquired plurality of captured images into a plurality of blocks.
- the information processing apparatus 200A acquires a flat region according to the contrast value contrast for each divided block.
- the information processing apparatus 200A calculates the depth in the flat region satisfying the assumptions 1 and 2 in the above equations (1) to (3) by acquiring the flat region according to the contrast value contrast. Can be done. Further, the information processing apparatus 200A can expand the flat region according to the contrast value contrast by acquiring the flat region from a plurality of captured images.
- the area acquisition unit 225 synthesizes the areas M61A to M63A, but the present invention is not limited to this.
- the normal calculation unit 222 and the depth calculation unit 223 calculate the normal information and the depth information for each of the areas M61A to M63A, for example, when the display control unit 224 displays the result on the display unit, the areas M61A to M63A.
- the result of synthesizing the above may be displayed.
- the high frequency component may be extracted from the normal information calculated by the normal calculation unit 222. Therefore, in the seventh embodiment, an example of extracting the high frequency component from the normal information and calculating the depth information will be described.
- FIG. 25 is a diagram showing a configuration example of the information processing device 200B according to the seventh embodiment of the present disclosure.
- the information processing device 200B shown in FIG. 25 has the same components as the information processing device 200A shown in FIG. 6, except that the control unit 220B does not include the area acquisition unit 225 and includes the normal frequency separation unit 226B. ..
- the normal calculation unit 222 calculates the normal information in each pixel of the captured image acquired by the acquisition unit 221.
- the normal frequency separation unit 226B separates high frequency components (hereinafter, also referred to as normal high frequencies) from the normal information.
- the depth information to be calculated by the depth calculation unit 223 is information regarding the local uneven shape of the target S.
- the depth information calculated by the depth calculation unit 223 is a high-frequency component of the surface shape of the target S and does not include a low-frequency component.
- the normal frequency separation unit 226 removes a low frequency component which is a rough shape normal information from the normal information to generate a normal high frequency. Since the normal high frequency does not include a low frequency component (normal information of a rough shape), it satisfies the assumptions 1 and 2 of the above equations (1) to (3).
- FIG. 26 is a diagram for explaining frequency separation by the normal frequency separation unit 226B according to the seventh embodiment of the present disclosure.
- the normal information X as shown in the upper figure of FIG. 26 is input to the normal frequency separation unit 226B.
- the actual surface of the target S is shown by a dotted line
- the rough shape of the surface of the target S is shown by a solid line
- the normal line of the surface of the target S is shown by an arrow.
- the normal frequency separation unit 226B separates the high frequency component and the low frequency component of the normal information by using, for example, a convolution filter F (X), and extracts the normal high frequency Y shown in the middle figure of FIG.
- the convolution filter F (X) is a filter designed in advance so as to extract high frequency components when normal information is input.
- the depth calculation unit 223 converts the normal high frequency separated by the normal frequency separation unit 226B into an equation using the above equations (1) to (3) and the like, thereby satisfying Assumption 1 and Assumption 2.
- Information Z (see the figure below in FIG. 26) can be calculated.
- the information processing device 200B extracts high-frequency components from the normal information and calculates depth information based on the extracted high-frequency components.
- the information processing apparatus 200B can perform formula conversion using the above-mentioned equations (1) to (3) while satisfying assumptions 1 and 2, so that it is possible to suppress a decrease in the calculation accuracy of depth information. it can. Therefore, the information processing apparatus 200B can improve the accuracy of shape measurement as compared with the case where frequency separation is not performed.
- the depth information is calculated from the high frequency component of the normal information.
- the depth information may be calculated by using the low frequency component in addition to the high frequency component of the normal information. Therefore, in the eighth embodiment, an example of calculating the depth information by separating the high frequency component and the low frequency component from the normal information will be described.
- FIG. 27 is a diagram showing a configuration example of the information processing device 200C according to the eighth embodiment of the present disclosure.
- the information processing device 200C shown in FIG. 27 has the same components as the information processing device 200B shown in FIG. 25, except for the normal frequency separation unit 226C and the depth calculation unit 223C of the control unit 220C.
- the normal frequency separation unit 226C separates a high frequency component and a low frequency component (hereinafter, also referred to as normal low frequency) from the normal information and outputs each to the depth calculation unit 223C.
- normal low frequency a low frequency component
- the local uneven shape of the object S contributes to the high frequency component of the normal information.
- the rough shape of the object S contributes to the low frequency component of the normal information. This point will be described with reference to FIG. 28.
- FIG. 28 is a diagram for explaining frequency separation by the normal frequency separation unit 226C according to the eighth embodiment of the present disclosure.
- the normal information X as shown in FIG. 28A is input to the normal frequency separation unit 226C.
- the actual surface of the target S is shown by a dotted line
- the rough shape of the surface of the target S is shown by a solid line
- the normal line of the surface of the target S is shown by an arrow.
- the surface shape represented by the normal high frequency YH is a shape in which the rough shape (normal low frequency YL) is removed and the flat surface has local irregularities. It becomes.
- the convolution filter F (X) is a filter designed in advance so as to extract high frequency components when normal information is input.
- the depth calculation unit 223C performs equation conversion for each of the normal high frequency YH and the normal low frequency YL, and as shown in FIG. 28 (c), the high frequency component ZH (hereinafter, also referred to as depth high frequency) of the depth information and the depth high frequency.
- the low frequency component ZL (hereinafter, also referred to as depth low frequency) is calculated.
- the depth calculation unit 223C can accurately calculate the depth high frequency ZH.
- the normal low frequency YL is a low frequency component of the normal information X from which the normal high frequency YH has been removed, and is normal information representing a state in which a local uneven shape is removed from the surface shape of the target S. is there. Therefore, the depth calculation unit 223C can accurately calculate the depth low frequency ZL even if the formula conversion of the normal low frequency YL is performed with the assumptions 1 and 2 removed.
- the depth calculation unit 223C calculates the depth information Z shown in FIG. 28 (d) by synthesizing the calculated depth high frequency ZH and depth low frequency ZL.
- the information processing device 200C frequency-separates the normal information calculated from the captured image.
- the information processing device 200C calculates the depth information for each separated frequency, synthesizes the calculated depth information, and calculates the depth information of the target S.
- the information processing apparatus 200C can calculate the depth of the rough shape in addition to the depth of the local uneven shape. Further, the information processing apparatus 200C can calculate the depth information of the target S more accurately by synthesizing these depths.
- the depth calculation unit 223C can calculate the depth low frequency ZL with the influence of Assumption 1 and Assumption 2 small, and the values of ⁇ and ⁇ are set so that Assumption 1 and Assumption 2 do not affect the calculation of the depth low frequency ZL. May be a small value.
- FIG. 29 is a diagram for explaining a learning method of the learning device 300 according to the ninth embodiment. Since the information processing device 200A according to the ninth embodiment has the same configuration and operation as the information processing device 200A according to the first embodiment except for the operation of the normal calculation unit 222, the same reference numerals are given. The description of the part is omitted.
- the normal calculation unit 222 updates the weight of the learner 300 with the captured image M14 as input data and the normal image M16 as correct answer data (true value) for learning.
- the captured image M14 is captured by a device that captures an RGB image, such as a microscope 100.
- the normal image M16 is generated based on the shape information measured by a device that directly measures the surface shape of the target S, such as a non-contact 3D measuring instrument.
- the output image and the correct answer image obtained by inputting the input image to the learning device 300 may be deviated by several pixels. In this way, if the learning device 300 is trained in a state where the output image and the correct answer image are deviated from each other, the learning device 300 that outputs a blurred output image with respect to the input image is generated.
- the normal calculation unit 222 shifts the normal image M16 in the x-direction and the y-direction at the time of learning to determine the filter coefficient (weight) of the learner (CNN) 300, and after the shift, The degree of similarity between the normal image M16 and the output image M15 is calculated.
- the normal calculation unit 222 shifts the normal image M16 in the range of 0 to ⁇ x in the x direction and shifts the normal image M16 in the range of 0 to ⁇ y in the y direction.
- the normal calculation unit 222 calculates, for example, the least squares error between the shifted normal image M16 and the output image M15 for each shift amount.
- the normal calculation unit 222 updates the weight of the learner 300 with the minimum value of the calculated least squares errors as the final loss.
- the minimum average error between the shifted normal image M16 and the output image M15 may be calculated for each shift amount, and the minimum value of the calculated minimum average errors may be used as the final loss. ..
- the learner 300 is generated by updating the weight according to the degree of similarity between the shift image (normal image after shift) and the output image M15 obtained by shifting the true value image (normal image). More specifically, the learner 300 includes a plurality of shift images (also referred to as a shifted normal image and a correct candidate image) obtained by shifting a true value image (normal image) by a different shift amount (number of pixels). , The weight is updated and generated according to the similarity with the output image M15.
- the weight of the learning device 300 can be updated with the positions of both images without aligning the output image M15 of the learning device 300 and the normal image M16.
- the learning accuracy of the learning device 300 can be further improved.
- the normal information can be calculated more accurately, and the accuracy of the shape measurement of the information processing apparatus 200A is further improved. be able to.
- FIG. 30 is a diagram showing a configuration example of a control unit 220D of the information processing device 200A according to the tenth embodiment of the present disclosure.
- control unit 220D of the information processing apparatus 200A includes the area acquisition unit 225D instead of the area acquisition unit 225, and the depth synthesis unit 227. It is the same as the part 220.
- the area acquisition unit 225D divides the captured image M71 acquired by the acquisition unit 221 into three divided areas M71A to M71C.
- the number of regions divided by the region acquisition unit 225D is not limited to three, and may be two or four or more.
- the area acquisition unit 225D acquires the divided flat areas M72A to M72C for each of the divided areas M71A to M71C.
- the normal calculation unit 222 calculates the normal region images M73A to M73C based on the divided flat regions M72A to M72C, respectively, and the depth calculation unit 223 calculates the depth region images M74A to M74C based on the normal region images M73A to M73C. Is calculated.
- the depth composition unit 227 synthesizes the depth region images M74A to M74C to generate the depth image M75, and outputs the depth image M75 to the display control unit 224.
- the depth synthesizing unit 227 may synthesize the divided flat regions M72A to M72C and the normal region images M73A to M73C. Further, the processing in each part may be sequentially performed for each area, or may be performed in parallel for each area.
- the information processing apparatus 200A divides the captured image into a plurality of divided regions M71A to M71C, and acquires the divided flat regions M72A to M72C for each of the divided regions M71A to M71C. Further, the information processing apparatus 200A calculates the normal information and the depth information for each of the divided flat regions M72A to M72C.
- the size of the captured image (area) to be processed in each part can be reduced, the processing load can be reduced, and the processing speed can be improved.
- the head mount portion 10 is a tubular portion mounted on the tip of the microscope 100.
- the head mount portion 10 does not necessarily have to have a tubular shape as long as it is a structure for keeping the distance between the target S and the sensor 150 of the microscope 100 constant.
- FIG. 31 is a block diagram showing an example of a schematic configuration of a patient's internal information acquisition system using a capsule endoscope to which the technique according to the present disclosure (the present technique) can be applied.
- the internal information acquisition system 10001 is composed of a capsule endoscope 10100 and an external control device 10200.
- the capsule endoscope 10100 is swallowed by the patient at the time of examination.
- the capsule endoscope 10100 has an imaging function and a wireless communication function, and moves inside an organ such as the stomach or intestine by peristaltic movement or the like until it is naturally excreted from the patient, and inside the organ.
- Images (hereinafter, also referred to as internal organ images) are sequentially imaged at predetermined intervals, and information about the internal organ images is sequentially wirelessly transmitted to an external control device 10200 outside the body.
- the external control device 10200 comprehensively controls the operation of the internal information acquisition system 10001. Further, the external control device 10200 receives information about the internal image transmitted from the capsule endoscope 10100, and based on the information about the received internal image, displays the internal image on a display device (not shown). Generate image data for display.
- the internal information acquisition system 10001 in this way, it is possible to obtain an internal image of the inside of the patient at any time from the time when the capsule endoscope 10100 is swallowed until it is discharged.
- the capsule endoscope 10100 has a capsule-shaped housing 10101, and the light source unit 10111, the imaging unit 10112, the image processing unit 10113, the wireless communication unit 10114, the power feeding unit 10115, and the power supply unit are contained in the housing 10101.
- the 10116 and the control unit 10117 are housed.
- the light source unit 10111 is composed of, for example, a light source such as an LED (Light Emitting Diode), and irradiates the imaging field of view of the imaging unit 10112 with light.
- a light source such as an LED (Light Emitting Diode)
- LED Light Emitting Diode
- the image pickup unit 10112 is composed of an image pickup element and an optical system including a plurality of lenses provided in front of the image pickup element.
- the reflected light (hereinafter referred to as observation light) of the light applied to the body tissue to be observed is collected by the optical system and incident on the image sensor.
- the observation light incident on the image sensor is photoelectrically converted, and an image signal corresponding to the observation light is generated.
- the image signal generated by the image capturing unit 10112 is provided to the image processing unit 10113.
- the image processing unit 10113 is composed of a processor such as a CPU or GPU (Graphics Processing Unit), and performs various signal processing on the image signal generated by the imaging unit 10112.
- the image processing unit 10113 provides the signal-processed image signal to the wireless communication unit 10114 as RAW data.
- the wireless communication unit 10114 performs predetermined processing such as modulation processing on the image signal that has been signal-processed by the image processing unit 10113, and transmits the image signal to the external control device 10200 via the antenna 10114A. Further, the wireless communication unit 10114 receives a control signal related to drive control of the capsule endoscope 10100 from the external control device 10200 via the antenna 10114A. The wireless communication unit 10114 provides the control unit 10117 with a control signal received from the external control device 10200.
- the power feeding unit 10115 is composed of an antenna coil for receiving power, a power regeneration circuit that regenerates power from the current generated in the antenna coil, a booster circuit, and the like. In the power feeding unit 10115, electric power is generated using the principle of so-called non-contact charging.
- the power supply unit 10116 is composed of a secondary battery and stores the electric power generated by the power supply unit 10115.
- FIG. 31 in order to avoid complicating the drawings, illustrations such as arrows indicating the power supply destinations from the power supply unit 10116 are omitted, but the power stored in the power supply unit 10116 is the light source unit 10111. , Image processing unit 10112, image processing unit 10113, wireless communication unit 10114, and control unit 10117, and can be used to drive these.
- the control unit 10117 is composed of a processor such as a CPU, and is a control signal transmitted from the external control device 10200 to drive the light source unit 10111, the image pickup unit 10112, the image processing unit 10113, the wireless communication unit 10114, and the power supply unit 10115. Control as appropriate according to.
- the external control device 10200 is composed of a processor such as a CPU and a GPU, or a microcomputer or a control board on which a processor and a storage element such as a memory are mixedly mounted.
- the external control device 10200 controls the operation of the capsule endoscope 10100 by transmitting a control signal to the control unit 10117 of the capsule endoscope 10100 via the antenna 10200A.
- a control signal from the external control device 10200 can change the light irradiation conditions for the observation target in the light source unit 10111.
- the imaging conditions for example, the frame rate in the imaging unit 10112, the exposure value, etc.
- the content of processing in the image processing unit 10113 and the conditions for the wireless communication unit 10114 to transmit the image signal may be changed by the control signal from the external control device 10200. ..
- the external control device 10200 performs various image processing on the image signal transmitted from the capsule endoscope 10100, and generates image data for displaying the captured internal image on the display device.
- the image processing includes, for example, development processing (demosaic processing), high image quality processing (band enhancement processing, super-resolution processing, noise reduction processing, camera shake correction processing, etc.), enlargement processing (electronic zoom processing, etc.), etc., respectively.
- various signal processing can be performed.
- the external control device 10200 controls the drive of the display device to display the captured internal image based on the generated image data.
- the external control device 10200 may have the generated image data recorded in a recording device (not shown) or printed out in a printing device (not shown).
- the above is an example of an in-vivo information acquisition system to which the technology according to the present disclosure can be applied.
- the technique according to the present disclosure can be applied to, for example, the external control device 10200 among the configurations described above.
- the surface shape inside the body can be measured from the body image captured by the capsule endoscope 10100.
- FIG. 32 is a diagram showing an example of a schematic configuration of an endoscopic surgery system to which the technique according to the present disclosure (the present technique) can be applied.
- FIG. 32 illustrates how the surgeon (doctor) 11131 is performing surgery on patient 11132 on patient bed 11133 using the endoscopic surgery system 11000.
- the endoscopic surgery system 11000 includes an endoscope 11100, other surgical tools 11110 such as an abdominal tube 11111 and an energy treatment tool 11112, and a support arm device 11120 that supports the endoscope 11100.
- a cart 11200 equipped with various devices for endoscopic surgery.
- the endoscope 11100 is composed of a lens barrel 11101 in which a region having a predetermined length from the tip is inserted into the body cavity of the patient 11132, and a camera head 11102 connected to the base end of the lens barrel 11101.
- the endoscope 11100 configured as a so-called rigid mirror having a rigid barrel 11101 is illustrated, but the endoscope 11100 may be configured as a so-called flexible mirror having a flexible barrel. Good.
- An opening in which an objective lens is fitted is provided at the tip of the lens barrel 11101.
- a light source device 11203 is connected to the endoscope 11100, and the light generated by the light source device 11203 is guided to the tip of the lens barrel by a light guide extending inside the lens barrel 11101 to be an objective. It is irradiated toward the observation target in the body cavity of the patient 11132 through the lens.
- the endoscope 11100 may be a direct endoscope, a perspective mirror, or a side endoscope.
- An optical system and an image sensor are provided inside the camera head 11102, and the reflected light (observation light) from the observation target is focused on the image sensor by the optical system.
- the observation light is photoelectrically converted by the image sensor, and an electric signal corresponding to the observation light, that is, an image signal corresponding to the observation image is generated.
- the image signal is transmitted to the CCU (camera control unit) 11201 as RAW data.
- the CCU11201 is composed of a CPU, a GPU, and the like, and comprehensively controls the operations of the endoscope 11100 and the display device 11202. Further, the CCU 11201 receives an image signal from the camera head 11102, and performs various image processing on the image signal for displaying an image based on the image signal, such as development processing (demosaic processing).
- the display device 11202 displays an image based on the image signal processed by the CCU 11201 under the control of the CCU 11201.
- the light source device 11203 is composed of, for example, a light source such as an LED (Light Emitting Diode), and supplies irradiation light for photographing an operating part or the like to the endoscope 11100.
- a light source such as an LED (Light Emitting Diode)
- LED Light Emitting Diode
- the input device 11204 is an input interface for the endoscopic surgery system 11000.
- the user can input various information and input instructions to the endoscopic surgery system 11000 via the input device 11204.
- the user inputs an instruction to change the imaging conditions (type of irradiation light, magnification, focal length, etc.) by the endoscope 11100.
- the treatment tool control device 11205 controls the drive of the energy treatment tool 11112 for cauterizing, incising, sealing a blood vessel, or the like of a tissue.
- the pneumoperitoneum device 11206 uses a gas in the pneumoperitoneum tube 11111 to inflate the body cavity of the patient 11132 for the purpose of securing the field of view by the endoscope 11100 and securing the operator's work space.
- Recorder 11207 is a device capable of recording various information related to surgery.
- the printer 11208 is a device capable of printing various information related to surgery in various formats such as text, images, and graphs.
- the light source device 11203 that supplies the irradiation light to the endoscope 11100 when photographing the surgical site can be composed of, for example, an LED, a laser light source, or a white light source composed of a combination thereof.
- a white light source is configured by combining RGB laser light sources, the output intensity and output timing of each color (each wavelength) can be controlled with high accuracy. Therefore, the light source device 11203 adjusts the white balance of the captured image. It can be carried out.
- the laser light from each of the RGB laser light sources is irradiated to the observation target in a time-division manner, and the drive of the image sensor of the camera head 11102 is controlled in synchronization with the irradiation timing to correspond to each of RGB. It is also possible to capture the image in a time-division manner. According to this method, a color image can be obtained without providing a color filter on the image sensor.
- the drive of the light source device 11203 may be controlled so as to change the intensity of the output light at predetermined time intervals.
- the drive of the image sensor of the camera head 11102 in synchronization with the timing of the change in the light intensity to acquire images in a time-divided manner and synthesizing the images, so-called high dynamic without blackout and overexposure Range images can be generated.
- the light source device 11203 may be configured to be able to supply light in a predetermined wavelength band corresponding to special light observation.
- special light observation for example, by utilizing the wavelength dependence of light absorption in body tissue to irradiate light in a narrow band as compared with the irradiation light (that is, white light) in normal observation, the surface layer of the mucous membrane. So-called narrow band imaging, in which a predetermined tissue such as a blood vessel is photographed with high contrast, is performed.
- fluorescence observation may be performed in which an image is obtained by fluorescence generated by irradiating with excitation light.
- the body tissue is irradiated with excitation light to observe the fluorescence from the body tissue (autofluorescence observation), or a reagent such as indocyanine green (ICG) is locally injected into the body tissue and the body tissue is injected. It is possible to obtain a fluorescence image by irradiating excitation light corresponding to the fluorescence wavelength of the reagent.
- the light source device 11203 may be configured to be capable of supplying narrow band light and / or excitation light corresponding to such special light observation.
- FIG. 33 is a block diagram showing an example of the functional configuration of the camera head 11102 and CCU11201 shown in FIG. 32.
- the camera head 11102 includes a lens unit 11401, an imaging unit 11402, a driving unit 11403, a communication unit 11404, and a camera head control unit 11405.
- CCU11201 includes a communication unit 11411, an image processing unit 11412, and a control unit 11413.
- the camera head 11102 and CCU11201 are communicatively connected to each other by a transmission cable 11400.
- the lens unit 11401 is an optical system provided at a connection portion with the lens barrel 11101.
- the observation light taken in from the tip of the lens barrel 11101 is guided to the camera head 11102 and incident on the lens unit 11401.
- the lens unit 11401 is configured by combining a plurality of lenses including a zoom lens and a focus lens.
- the image pickup unit 11402 is composed of an image pickup element.
- the image sensor constituting the image pickup unit 11402 may be one (so-called single plate type) or a plurality (so-called multi-plate type).
- each image pickup element may generate an image signal corresponding to each of RGB, and a color image may be obtained by synthesizing them.
- the image pickup unit 11402 may be configured to have a pair of image pickup elements for acquiring image signals for the right eye and the left eye corresponding to 3D (Dimensional) display, respectively.
- the 3D display enables the operator 11131 to more accurately grasp the depth of the biological tissue in the surgical site.
- a plurality of lens units 11401 may be provided corresponding to each image pickup element.
- the imaging unit 11402 does not necessarily have to be provided on the camera head 11102.
- the imaging unit 11402 may be provided inside the lens barrel 11101 immediately after the objective lens.
- the drive unit 11403 is composed of an actuator, and the zoom lens and focus lens of the lens unit 11401 are moved by a predetermined distance along the optical axis under the control of the camera head control unit 11405. As a result, the magnification and focus of the image captured by the imaging unit 11402 can be adjusted as appropriate.
- the communication unit 11404 is composed of a communication device for transmitting and receiving various information to and from the CCU11201.
- the communication unit 11404 transmits the image signal obtained from the image pickup unit 11402 as RAW data to the CCU 11201 via the transmission cable 11400.
- the communication unit 11404 receives a control signal for controlling the drive of the camera head 11102 from the CCU 11201 and supplies the control signal to the camera head control unit 11405.
- the control signal includes, for example, information to specify the frame rate of the captured image, information to specify the exposure value at the time of imaging, and / or information to specify the magnification and focus of the captured image, and the like. Contains information about the condition.
- the above-mentioned imaging conditions such as frame rate, exposure value, magnification, and focus may be appropriately specified by the user, or may be automatically set by the control unit 11413 of CCU11201 based on the acquired image signal. Good.
- the so-called AE (Auto Exposure) function, AF (Auto Focus) function, and AWB (Auto White Balance) function are mounted on the endoscope 11100.
- the camera head control unit 11405 controls the drive of the camera head 11102 based on the control signal from the CCU 11201 received via the communication unit 11404.
- the communication unit 11411 is composed of a communication device for transmitting and receiving various information to and from the camera head 11102.
- the communication unit 11411 receives an image signal transmitted from the camera head 11102 via the transmission cable 11400.
- the communication unit 11411 transmits a control signal for controlling the drive of the camera head 11102 to the camera head 11102.
- Image signals and control signals can be transmitted by telecommunications, optical communication, or the like.
- the image processing unit 11412 performs various image processing on the image signal which is the RAW data transmitted from the camera head 11102.
- the control unit 11413 performs various controls related to the imaging of the surgical site and the like by the endoscope 11100 and the display of the captured image obtained by the imaging of the surgical site and the like. For example, the control unit 11413 generates a control signal for controlling the drive of the camera head 11102.
- control unit 11413 causes the display device 11202 to display an image captured by the surgical unit or the like based on the image signal processed by the image processing unit 11412.
- the control unit 11413 may recognize various objects in the captured image by using various image recognition techniques. For example, the control unit 11413 detects the shape, color, and the like of the edge of an object included in the captured image to remove surgical tools such as forceps, a specific biological part, bleeding, and mist when using the energy treatment tool 11112. Can be recognized.
- the control unit 11413 may superimpose and display various surgical support information on the image of the surgical unit by using the recognition result. By superimposing and displaying the surgical support information and presenting it to the surgeon 11131, it is possible to reduce the burden on the surgeon 11131 and to allow the surgeon 11131 to proceed with the surgery reliably.
- the transmission cable 11400 that connects the camera head 11102 and CCU11201 is an electric signal cable that supports electric signal communication, an optical fiber that supports optical communication, or a composite cable thereof.
- the communication is performed by wire using the transmission cable 11400, but the communication between the camera head 11102 and the CCU11201 may be performed wirelessly.
- the above is an example of an endoscopic surgery system to which the technology according to the present disclosure can be applied.
- the technique according to the present disclosure can be applied to, for example, CCU11201 among the configurations described above.
- the control units 220, 220B, and 220C described above can be applied to the image processing unit 11412.
- the technique according to the present disclosure to the image processing unit 11412, the surface shape inside the body can be measured from the body image captured by the endoscope 11100.
- the technique according to the present disclosure may be applied to other, for example, a microscopic surgery system.
- each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of them may be functionally or physically distributed / physically in arbitrary units according to various loads and usage conditions. Can be integrated and configured.
- the following configurations also belong to the technical scope of the present disclosure.
- the captured image is an image obtained from reflected light of light radiated to the target from a plurality of light sources arranged at different positions.
- a flat region is extracted from the captured image based on the brightness value of the captured image.
- a control unit that calculates shape information regarding the shape of the surface of the target based on the information about the sensor and the flat region of the captured image.
- Information processing device equipped with (2)
- the control unit The captured image obtained from the reflected light of the light that is simultaneously applied to the target from the plurality of light sources is acquired.
- the information processing device according to (1).
- the control unit A region in which the brightness value of the captured image is equal to or higher than a predetermined threshold value is defined as the flat region.
- the control unit The captured image obtained from the reflected light of the light applied to the target from one of the plurality of light sources is acquired for each light source. A region in which the change in the luminance value between the plurality of captured images acquired for each light source is less than a predetermined threshold value is extracted as the flat region.
- the control unit A smoothing process is performed on the captured image to generate a smoothing image. Based on the smoothing image, the flat region is extracted from the captured image.
- the information processing device according to any one of (1) to (4).
- the control unit The captured image is divided into a plurality of divided regions, and the captured image is divided into a plurality of divided regions.
- the flat region is extracted for each of the plurality of divided regions, and shape information is calculated.
- the information processing device according to any one of (1) to (5).
- the control unit The normal information of the flat region in the captured image is calculated, and the normal information is calculated.
- the normal information is input to the model generated by machine learning to obtain the shape information.
- the information processing device according to any one of (1) to (6).
- the model is It is generated by updating the weight based on the comparison result between multiple correct candidate images and the output data of the model.
- the plurality of correct answer candidate images are generated by shifting the correct answer images by a different number of pixels.
- the information processing device according to (7).
- the model is Calculate the least squares error between the plurality of correct candidate images and the output data, respectively. Generated by updating the weights based on the minimum values of the plurality of least squares errors.
- the control unit The flat region is extracted based on the contrast value calculated from the brightness value of the captured image.
- the control unit The captured image is divided into a plurality of divided regions, and the captured image is divided into a plurality of divided regions.
- the contrast value is calculated for each of the plurality of divided regions, and the contrast value is calculated.
- the flat region is extracted by determining whether or not the divided region is flat according to the contrast value.
- the control unit A plurality of captured images having different depths of field planes of the sensor are acquired, and the images are captured.
- the flat region is extracted from each of the plurality of captured images.
- the information processing device according to (10) or (11).
- (13) Acquires the captured image captured by the sensor of the target,
- the captured image is an image obtained from reflected light of light radiated to the target from a plurality of light sources arranged at different positions.
- a flat region is extracted from the captured image based on the brightness value of the captured image. Based on the information about the sensor and the flat region of the captured image, shape information about the shape of the surface of the object is calculated. Information processing method.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Mathematical Physics (AREA)
- Chemical & Material Sciences (AREA)
- Biophysics (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
Description
1.背景
1.1.表面形状の算出方法
1.2.算出方法の課題
2.第1実施形態
2.1.第1実施形態の概要
2.2.システム構成例
2.3.マイクロスコープの構成例
2.4.情報処理装置の構成例
2.5.深度算出処理
3.第2実施形態
4.第3実施形態
5.第4実施形態
6.第5実施形態
7.第6実施形態
8.第7実施形態
9.第8実施形態
10.第9実施形態
11.第10実施形態
12.その他の実施形態
13.適応例
14.補足
<1.1.表面形状の算出方法>
まず、本開示の実施形態の詳細を説明する前に、本発明者らが本開示の実施形態を創作するに至った背景について説明する。
p:算出した法線のx方向
q:算出した法線のy方向
Zx:求める深度のx方向の偏微分(法線のx方向)
Zy:求める深度のy方向の偏微分(法線のy方向)
Zxx:求める深度のx方向の2回偏微分(法線のx方向のx方向への偏微分)
Zyy:求める深度のy方向の2回偏微分(法線のy方向のy方向への偏微分)
Zxy:求める深度のx、y方向の2回偏微分
上述した算出方法において、式(1)の右辺の2段目および3段目は、式(1)におけるcost項であり、2段目が法線の絶対値の総和、3段目が法線の微分の絶対値の総和を表している。
<2.1.第1実施形態の概要>
図3は、本開示の第1実施形態の概要について説明するための図である。第1実施形態に係る情報処理装置200A(図示省略)は、上述した仮定1、2を満たす領域(平坦領域)を撮像画像から抽出することで、対象の表面形状に関する形状情報(深度情報)の精度劣化を抑制し、形状計測の精度を向上させる。
図4は、本開示の第1実施形態に係る情報処理システム1の構成例を示すブロック図である。図4に示すように、情報処理システム1は、マイクロスコープ100と、情報処理装置200Aと、を有する。
図5は、本開示の第1実施形態に係るマイクロスコープ100の構成例を示す図である。マイクロスコープ100は、センサ150と、センサ150と撮像対象との間に設置される筒状の機構であるヘッドマウント部10と、を有する。また、マイクロスコープ100は、それぞれ異なる位置に配置される点光源160A、160B(図示省略)を有する。
図6は、本開示の第1実施形態に係る情報処理装置200Aの構成例を示すブロック図である。情報処理装置200Aは、制御部220と、記憶部230と、を有する。
制御部220は、情報処理装置200Aの動作を制御する。制御部220は、取得部221と、領域取得部225と、法線算出部222と、深度算出部223と、表示制御部224と、を有する。取得部221と、領域取得部225と、法線算出部222と、深度算出部223と、表示制御部224と、の各機能部は、例えば、制御部220によって、制御部220内部に記憶されたプログラムがRAM等を作業領域として実行されることにより実現される。なお、制御部220の内部構造は、図6に示した構成に限られず、後述する情報処理を行う構成であれば他の構成であってもよい。また、制御部220が有する各処理部の接続関係は、図6に示した接続関係に限られず、他の接続関係であってもよい。
取得部221は、マイクロスコープ100が撮像した撮像画像M11や、マイクロスコープ100に関する情報を取得する。マイクロスコープ100に関する情報には、例えば焦点距離fやヘッドマウント部10の長さdなど、マイクロスコープ100の構造に関する情報が含まれる。
領域取得部225は、撮像画像M11から平坦領域SABを抽出する。領域取得部225は、例えば、撮像画像M11の各画素の輝度値L(x、y)と閾値thとを比較する。図7に示すように、領域取得部225は、輝度値L(x、y)が閾値th以上の画素を含む領域を処理領域とし、輝度値L(x、y)が閾値th未満の画素を含む領域を除外領域とする。なお、図7は、撮像画像M11の輝度値の一例を示す図であり、図7では、y軸の値を所定値「β」とした場合の輝度値L(x、β)と画素(x、β)との関係を示している。
法線算出部222は、撮像画像M11の平坦領域SABに基づいて、対象Sの表面における法線情報を法線画像として算出する。法線算出部222は、例えば、CNNを用いて法線画像を生成する。法線算出部222は、CNNを利用して事前に学習された学習器を用いて法線画像を生成する。学習器300(図11参照)の入力チャネル数は、入力画像(ここでは平坦領域SAB)のRGBに相当する3チャネル、あるいは、入力画像のグレースケールの1チャネルとする。また、学習器300の出力チャネル数は、出力画像(ここでは法線画像)のRGBに相当する3チャネルとする。また、出力画像の解像度は、入力画像の解像度と等しいものとする。
深度算出部223は、法線画像の各画素値を入力として、上述した式(1)~(3)を用いた式変換を行ってセンサ150から対象Sまでの距離(深度)を算出する。具体的には、深度算出部223は、以下の通り、上述した式(3)を逆フーリエ変換してZ’を算出し、求める深度ZをZ=Z’×Pとして算出する。
P(u、v):法線のx方向のフーリエ変換
Q(u、v):法線のy方向のフーリエ変換
u、v:各画素の周波数空間中での座標
P:撮像画像xyの1pixel(1画素)あたりの長さ[μm]
ZF:求める深度のフーリエ変換
Z’:求める1pixelあたりの深度[pixel]
Z:求める深度[μm]
表示制御部224は、各種の画像を液晶ディスプレイ等の表示部(図示省略)に表示させる。図13は、表示制御部224が表示部に表示させる画像M17の一例を示す図である。図13に示すように、表示制御部224は、例えば撮像画像M17a、法線画像M17b、深度画像M17c、深度グラフを示す画像M17dおよび対象Sの3D画像M17eを含む画像M17を表示部に表示させる。
記憶部230は、制御部220の処理に用いられるプログラムや演算パラメータ等を記憶するROM(Read Only Memory)、および適宜変化するパラメータ等を一時記憶するRAM(Random Access Memory)により実現される。
図14は、本開示の第1実施形態に係る深度算出処理の一例を説明するためのフローチャートである。図14に示す深度算出処理は、情報処理装置200Aの制御部220がプログラムを実行することによって実現される。図14に示す深度算出処理は、マイクロスコープ100が撮像画像M11を撮像した後に実行される。あるいは、図14に示す深度算出処理は、ユーザからの指示に応じて実行されるようにしてもよい。
上記第1実施形態では、複数の点光源160A、160Bから同時に光IA、IBが照射される間にマイクロスコープ100が撮像した撮像画像M11に基づき、情報処理装置200Aが深度を算出する場合を示した。上記例以外にも、情報処理装置200Aは、1つの点光源から光が照射される間にマイクロスコープ100が撮像した撮像画像に基づいて深度を算出してもよい。そこで、第2実施形態では、情報処理装置200Aが、複数の点光源160A、160Bの1つから対象Sに照射された光の反射光から得られる撮像画像であって、点光源160A、160Bごとに得られる撮像画像に基づき、深度を算出する例について説明する。なお、第2実施形態に係る情報処理装置200Aは、取得部221および領域取得部225の動作を除き、第1実施形態に係る情報処理装置200Aと同じ構成および動作であるため、同一符号を付し、一部の説明を省略する。
上記第1、第2実施形態では、取得部221が取得した撮像画像から平坦領域SABを取得する場合を示した。上記例以外にも、情報処理装置200Aは、撮像画像に対してスムージング処理を行ってから平坦領域SABを取得してもよい。そこで、第3実施形態では、情報処理装置200Aが撮像画像から平坦領域SABを取得する前にスムージング処理を行う例について説明する。なお、第3実施形態に係る情報処理装置200Aは、領域取得部225の動作を除き、第1実施形態に係る情報処理装置200Aと同じ構成および動作であるため、同一符号を付し、一部の説明を省略する。
上記第1、第2実施形態では、領域取得部225が画素の輝度値を閾値判定することで平坦領域SABを取得する場合を示した。上記例以外にも、情報処理装置200Aは、撮像画像を複数のブロックに分割することで平坦領域を取得してもよい。そこで、第4実施形態では、情報処理装置200Aが、撮像画像を複数のブロックに分割する例について説明する。なお、第4実施形態に係る情報処理装置200Aは、領域取得部225の動作を除き、第1実施形態に係る情報処理装置200Aと同じ構成および動作であるため、同一符号を付し、一部の説明を省略する。
上記第4実施形態では、領域取得部225が撮像画像をブロックに分割することで平坦領域を取得する場合を示した。上記例以外にも、情報処理装置200Aは、分割したブロックのコントラスト値に応じて平坦領域を取得してもよい。そこで、第5実施形態では、情報処理装置200Aが、分割したブロックのコントラスト値に応じて平坦領域を取得する例について説明する。なお、第5実施形態に係る情報処理装置200Aは、領域取得部225の動作を除き、第4実施形態に係る情報処理装置200Aと同じ構成および動作であるため、同一符号を付し、一部の説明を省略する。
上記第5実施形態では、領域取得部225が1枚の撮像画像を複数のブロックに分割し、分割したブロックごとのコントラスト値に応じて平坦領域を取得する場合を示した。上記例以外にも、情報処理装置200Aは、被写体深度が異なる複数の撮像画像をそれぞれ複数のブロックに分割し、分割したブロックごとのコントラスト値に応じて平坦領域を取得してもよい。そこで、第6実施形態では、情報処理装置200Aが複数の撮像画像それぞれのブロックごとのコントラスト値に応じて平坦領域を取得する例について説明する。なお、第6実施形態に係る情報処理装置200Aは、取得部221および領域取得部225の動作を除き、第5実施形態に係る情報処理装置200Aと同じ構成および動作であるため、同一符号を付し、一部の説明を省略する。
上記第1~6実施形態では、領域取得部225が撮像画像から平坦領域を取得する場合を示した。上記例以外にも、法線算出部222が算出した法線情報から高周波成分を抽出するようにしてもよい。そこで、第7実施形態では、法線情報から高周波成分を抽出して深度情報を算出する例について説明する。
上記第7実施形態では、法線情報の高周波成分から深度情報を算出する場合を示した。上記例以外にも、法線情報の高周波成分に加え、低周波成分も用いて深度情報を算出するようにしてもよい。そこで、第8実施形態では、法線情報から高周波成分および低周波成分を分離して深度情報を算出する例について説明する。
上記第1実施形態では、真値である画像M16を用いて学習器300の学習を行う場合を示した。上記例以外にも、情報処理装置200Aは、画像M16をシフトさせた画像を正解データとして学習器300の学習を行ってもよい。そこで、第9実施形態では、情報処理装置200Aが画像M16をシフトさせた画像を正解データとして学習器300の学習を行う例について図29を用いて説明する。図29は、第9実施形態に係る学習器300の学習方法について説明するための図である。なお、第9実施形態に係る情報処理装置200Aは、法線算出部222の動作を除き、第1実施形態に係る情報処理装置200Aと同じ構成および動作であるため、同一符号を付し、一部の説明を省略する。
上記第1実施形態では、撮像画像から平坦領域を取得する場合を示した。上記例以外にも、情報処理装置200Aは、撮像画像を複数の領域に分割し、分割した領域ごとに平坦領域を取得するようにしてもよい。そこで、第10実施形態では、情報処理装置200Aが撮像画像を複数の領域に分割し、分割した領域ごとに平坦領域を取得する例について図30を用いて説明する。図30は、本開示の第10実施形態に係る情報処理装置200Aの制御部220Dの構成例を示す図である。
上述した各実施形態に係る処理は、上記各実施形態以外にも種々の異なる形態にて実施されてよい。
図31を用いて、第1~第10実施形態に係る情報処理装置200A~200Cの適用例について説明する。図31は、本開示に係る技術(本技術)が適用され得る、カプセル型内視鏡を用いた患者の体内情報取得システムの概略的な構成の一例を示すブロック図である。
本開示に係る技術は、さらに、内視鏡手術システムに適用されてもよい。図32は、本開示に係る技術(本技術)が適用され得る内視鏡手術システムの概略的な構成の一例を示す図である。
以上、添付図面を参照しながら本開示の好適な実施形態について詳細に説明したが、本開示の技術的範囲はかかる例に限定されない。本開示の技術分野における通常の知識を有する者であれば、請求の範囲に記載された技術的思想の範疇内において、各種の変更例または修正例に想到し得ることは明らかであり、これらについても、当然に本開示の技術的範囲に属するものと了解される。
(1)
対象をセンサが撮像した撮像画像を取得し、
前記撮像画像は、それぞれ異なる位置に配置される複数の光源から前記対象に照射された光の反射光から得られる画像であり、
前記撮像画像の輝度値に基づき、前記撮像画像から平坦領域を抽出し、
前記センサに関する情報および前記撮像画像の前記平坦領域に基づき、前記対象の表面の形状に関する形状情報を算出する制御部、
を備える情報処理装置。
(2)
前記制御部は、
複数の前記光源から同時に前記対象に照射された前記光の前記反射光から得られる前記撮像画像を取得する、
(1)に記載の情報処理装置。
(3)
前記制御部は、
前記撮像画像の輝度値が、所定閾値以上である領域を前記平坦領域とする、
(1)または(2)に記載の情報処理装置。
(4)
前記制御部は、
複数の前記光源の1つから前記対象に照射された前記光の前記反射光から得られる前記撮像画像を、前記光源ごとに取得し、
前記光源ごとに取得した複数の前記撮像画像間における前記輝度値の変化が所定閾値未満である領域を前記平坦領域として抽出する、
(1)に記載の情報処理装置。
(5)
前記制御部は、
前記撮像画像にスムージング処理を行ってスムージング画像を生成し、
前記スムージング画像に基づき、前記撮像画像から前記平坦領域を抽出する、
(1)~(4)のいずれか1つに記載の情報処理装置。
(6)
前記制御部は、
前記撮像画像を複数の分割領域に分割し、
複数の前記分割領域ごとに前記平坦領域を抽出し、形状情報を算出する、
(1)~(5)のいずれか1つに記載の情報処理装置。
(7)
前記制御部は、
前記撮像画像における前記平坦領域の法線情報を算出し、
前記法線情報を機械学習により生成されたモデルに入力して前記形状情報を得る、
(1)~(6)のいずれか1つに記載の情報処理装置。
(8)
前記モデルは、
複数の正解候補画像と前記モデルの出力データとの比較結果に基づいて重みを更新することで生成され、
複数の前記正解候補画像は、正解画像をそれぞれ異なる画素数ずつずらして生成される、
(7)に記載の情報処理装置。
(9)
前記モデルは、
複数の正解候補画像と前記出力データとの最小二乗誤差をそれぞれ算出し、
複数の前記最小二乗誤差の最小値に基づいて前記重みを更新することで生成される、
(8)に記載の情報処理装置。
(10)
前記制御部は、
前記撮像画像の輝度値から算出されるコントラスト値に基づき、前記平坦領域を抽出する、
(1)に記載の情報処理装置。
(11)
前記制御部は、
前記撮像画像を複数の分割領域に分割し、
複数の前記分割領域ごとに前記コントラスト値を算出し、
前記コントラスト値に応じて前記分割領域が平坦であるか否かを判定することで、前記平坦領域を抽出する、
(1)に記載の情報処理装置。
(12)
前記制御部は、
前記センサの被写界深度面がそれぞれ異なる複数の前記撮像画像を取得し、
複数の前記撮像画像からそれぞれ前記平坦領域を抽出する、
(10)または(11)に記載の情報処理装置。
(13)
対象をセンサが撮像した撮像画像を取得し、
前記撮像画像は、それぞれ異なる位置に配置される複数の光源から前記対象に照射された光の反射光から得られる画像であり、
前記撮像画像の輝度値に基づき、前記撮像画像から平坦領域を抽出し、
前記センサに関する情報および前記撮像画像の前記平坦領域に基づき、前記対象の表面の形状に関する形状情報を算出する、
情報処理方法。
100 マイクロスコープ
150 センサ
160 点光源
200 情報処理装置
220 制御部
221 取得部
222 法線算出部
223 深度算出部
224 表示制御部
225 領域取得部
226 法線周波数分離部
227 深度合成部
230 記憶部
Claims (13)
- 対象をセンサが撮像した撮像画像を取得し、
前記撮像画像は、それぞれ異なる位置に配置される複数の光源から前記対象に照射された光の反射光から得られる画像であり、
前記撮像画像の輝度値に基づき、前記撮像画像から平坦領域を抽出し、
前記センサに関する情報および前記撮像画像の前記平坦領域に基づき、前記対象の表面の形状に関する形状情報を算出する制御部、
を備える情報処理装置。 - 前記制御部は、
複数の前記光源から同時に前記対象に照射された前記光の前記反射光から得られる前記撮像画像を取得する、
請求項1に記載の情報処理装置。 - 前記制御部は、
前記撮像画像の輝度値が、所定閾値以上である領域を前記平坦領域とする、
請求項2に記載の情報処理装置。 - 前記制御部は、
複数の前記光源の1つから前記対象に照射された前記光の前記反射光から得られる前記撮像画像を、前記光源ごとに取得し、
前記光源ごとに取得した複数の前記撮像画像間における前記輝度値の変化が所定閾値未満である領域を前記平坦領域として抽出する、
請求項1に記載の情報処理装置。 - 前記制御部は、
前記撮像画像にスムージング処理を行ってスムージング画像を生成し、
前記スムージング画像に基づき、前記撮像画像から前記平坦領域を抽出する、
請求項2に記載の情報処理装置。 - 前記制御部は、
前記撮像画像を複数の分割領域に分割し、
複数の前記分割領域ごとに前記平坦領域を抽出し、形状情報を算出する、
請求項5に記載の情報処理装置。 - 前記制御部は、
前記撮像画像における前記平坦領域の法線情報を算出し、
前記法線情報を機械学習により生成されたモデルに入力して前記形状情報を得る、
請求項6に記載の情報処理装置。 - 前記モデルは、
複数の正解候補画像と前記モデルの出力データとの比較結果に基づいて重みを更新することで生成され、
複数の前記正解候補画像は、正解画像をそれぞれ異なる画素数ずつずらして生成される、
請求項7に記載の情報処理装置。 - 前記モデルは、
複数の正解候補画像と前記出力データとの最小二乗誤差をそれぞれ算出し、
複数の前記最小二乗誤差の最小値に基づいて前記重みを更新することで生成される、
請求項8に記載の情報処理装置。 - 前記制御部は、
前記撮像画像の輝度値から算出されるコントラスト値に基づき、前記平坦領域を抽出する、
請求項1に記載の情報処理装置。 - 前記制御部は、
前記撮像画像を複数の分割領域に分割し、
複数の前記分割領域ごとに前記コントラスト値を算出し、
前記コントラスト値に応じて前記分割領域が平坦であるか否かを判定することで、前記平坦領域を抽出する、
請求項10に記載の情報処理装置。 - 前記制御部は、
前記センサの被写界深度面がそれぞれ異なる複数の前記撮像画像を取得し、
複数の前記撮像画像からそれぞれ前記平坦領域を抽出する、
請求項10に記載の情報処理装置。 - 対象をセンサが撮像した撮像画像を取得し、
前記撮像画像は、それぞれ異なる位置に配置される複数の光源から前記対象に照射された光の反射光から得られる画像であり、
前記撮像画像の輝度値に基づき、前記撮像画像から平坦領域を抽出し、
前記センサに関する情報および前記撮像画像の前記平坦領域に基づき、前記対象の表面の形状に関する形状情報を算出する、
情報処理方法。
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US17/755,725 US12361573B2 (en) | 2019-11-15 | 2020-11-09 | Information processing apparatus and information processing method for shape measurement of target |
| CN202080077511.7A CN114667431B (zh) | 2019-11-15 | 2020-11-09 | 信息处理装置和信息处理方法 |
| JP2021556079A JP7609075B2 (ja) | 2019-11-15 | 2020-11-09 | 情報処理装置および情報処理方法 |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2019207103 | 2019-11-15 | ||
| JP2019-207103 | 2019-11-15 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2021095672A1 true WO2021095672A1 (ja) | 2021-05-20 |
Family
ID=75912071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2020/041676 Ceased WO2021095672A1 (ja) | 2019-11-15 | 2020-11-09 | 情報処理装置および情報処理方法 |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US12361573B2 (ja) |
| JP (1) | JP7609075B2 (ja) |
| CN (1) | CN114667431B (ja) |
| WO (1) | WO2021095672A1 (ja) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2022012897A (ja) * | 2020-07-02 | 2022-01-17 | キヤノン株式会社 | 画像処理装置、画像処理方法及びプログラム |
| CN114359063A (zh) * | 2021-12-03 | 2022-04-15 | 上海微创医疗机器人(集团)股份有限公司 | 目标亮度确定方法、光源控制方法和系统、设备和介质 |
| WO2025110014A1 (ja) * | 2023-11-22 | 2025-05-30 | 株式会社Ihi | 生成装置および生成方法 |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7693585B2 (ja) * | 2022-03-03 | 2025-06-17 | 株式会社日立製作所 | 撮影装置および認証装置 |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007139067A1 (ja) * | 2006-05-29 | 2007-12-06 | Panasonic Corporation | 画像高解像度化装置、画像高解像度化方法、画像高解像度化プログラムおよび画像高解像度化システム |
| WO2018159738A1 (ja) * | 2017-03-03 | 2018-09-07 | ソニーセミコンダクタソリューションズ株式会社 | 固体撮像装置および電子機器 |
| JP2019139694A (ja) * | 2018-02-15 | 2019-08-22 | キヤノン株式会社 | 画像処理方法、画像処理装置、撮像装置、画像処理プログラム、および、記憶媒体 |
Family Cites Families (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10307011A (ja) * | 1995-12-05 | 1998-11-17 | New Kurieishiyon:Kk | 表面検査方法および表面検査装置 |
| JP3980722B2 (ja) | 1997-04-03 | 2007-09-26 | 株式会社モリテックス | Ccdマイクロスコープ |
| JP3738291B2 (ja) * | 2003-06-09 | 2006-01-25 | 住友大阪セメント株式会社 | 三次元形状測定装置 |
| JP2008253498A (ja) | 2007-04-04 | 2008-10-23 | Shiseido Co Ltd | マイクロスコープの先端ドーム |
| JP5152077B2 (ja) * | 2009-04-01 | 2013-02-27 | ソニー株式会社 | 生体像提示装置、生体像提示方法及びプログラム並びに生体像提示システム |
| JP5908668B2 (ja) * | 2010-04-12 | 2016-04-26 | 富士フイルム株式会社 | 可搬型放射線撮影装置 |
| KR101087180B1 (ko) * | 2011-06-22 | 2011-11-28 | 동국대학교 경주캠퍼스 산학협력단 | 신뢰성 있는 금속 표면 3차원 형상 추출 기법 및 시스템 |
| KR101087172B1 (ko) * | 2011-07-13 | 2011-11-28 | 동국대학교 경주캠퍼스 산학협력단 | 고온 금속 표면 3차원 형상 추출 시스템 및 방법 |
| JP6063315B2 (ja) * | 2013-03-26 | 2017-01-18 | 富士フイルム株式会社 | 真贋判定システム,特徴点登録装置およびその動作制御方法,ならびに照合判定装置およびその動作制御方法 |
| US9903710B2 (en) | 2015-06-05 | 2018-02-27 | Nippon Steel & Sumitomo Metal Corporation | Shape inspection apparatus for metallic body and shape inspection method for metallic body |
| JP2017146938A (ja) * | 2016-02-19 | 2017-08-24 | 富士通株式会社 | 書籍検出装置、書籍検出方法及び書籍検出用コンピュータプログラム |
| WO2017194276A1 (en) * | 2016-05-13 | 2017-11-16 | Basf Se | System and method for detecting plant diseases |
| JPWO2018079255A1 (ja) * | 2016-10-24 | 2019-09-12 | パナソニックIpマネジメント株式会社 | 画像処理装置、画像処理方法、および画像処理プログラム |
| JP6820515B2 (ja) * | 2017-03-06 | 2021-01-27 | 株式会社東京精密 | 表面形状測定装置及び表面形状測定方法 |
| WO2019139694A1 (en) | 2018-01-11 | 2019-07-18 | Exxonmobil Chemical Patents Inc. | Polyethylene compositions and articles manufactured therefrom |
| JP7163049B2 (ja) * | 2018-04-03 | 2022-10-31 | キヤノン株式会社 | 情報処理装置、情報処理方法及びプログラム |
| CN109272459B (zh) * | 2018-08-20 | 2020-12-01 | Oppo广东移动通信有限公司 | 图像处理方法、装置、存储介质及电子设备 |
| JP6585793B2 (ja) * | 2018-09-18 | 2019-10-02 | 株式会社キーエンス | 検査装置、検査方法およびプログラム |
| KR102644946B1 (ko) * | 2019-05-02 | 2024-03-08 | 삼성전자주식회사 | 영상 처리 방법 및 장치 |
| US11651505B2 (en) * | 2020-01-27 | 2023-05-16 | Cognex Corporation | Systems and method for vision inspection with multiple types of light |
-
2020
- 2020-11-09 WO PCT/JP2020/041676 patent/WO2021095672A1/ja not_active Ceased
- 2020-11-09 US US17/755,725 patent/US12361573B2/en active Active
- 2020-11-09 JP JP2021556079A patent/JP7609075B2/ja active Active
- 2020-11-09 CN CN202080077511.7A patent/CN114667431B/zh active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007139067A1 (ja) * | 2006-05-29 | 2007-12-06 | Panasonic Corporation | 画像高解像度化装置、画像高解像度化方法、画像高解像度化プログラムおよび画像高解像度化システム |
| WO2018159738A1 (ja) * | 2017-03-03 | 2018-09-07 | ソニーセミコンダクタソリューションズ株式会社 | 固体撮像装置および電子機器 |
| JP2019139694A (ja) * | 2018-02-15 | 2019-08-22 | キヤノン株式会社 | 画像処理方法、画像処理装置、撮像装置、画像処理プログラム、および、記憶媒体 |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2022012897A (ja) * | 2020-07-02 | 2022-01-17 | キヤノン株式会社 | 画像処理装置、画像処理方法及びプログラム |
| JP7799375B2 (ja) | 2020-07-02 | 2026-01-15 | キヤノン株式会社 | 画像処理装置、画像処理方法及びプログラム |
| CN114359063A (zh) * | 2021-12-03 | 2022-04-15 | 上海微创医疗机器人(集团)股份有限公司 | 目标亮度确定方法、光源控制方法和系统、设备和介质 |
| WO2025110014A1 (ja) * | 2023-11-22 | 2025-05-30 | 株式会社Ihi | 生成装置および生成方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| JP7609075B2 (ja) | 2025-01-07 |
| CN114667431B (zh) | 2025-10-28 |
| US12361573B2 (en) | 2025-07-15 |
| US20230044097A1 (en) | 2023-02-09 |
| CN114667431A (zh) | 2022-06-24 |
| JPWO2021095672A1 (ja) | 2021-05-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7609075B2 (ja) | 情報処理装置および情報処理方法 | |
| JP7074065B2 (ja) | 医療用画像処理装置、医療用画像処理方法、プログラム | |
| US11503201B2 (en) | Focus detection device and method | |
| US20190083180A1 (en) | Medical image processing apparatus, medical image processing method, and program | |
| CA2627611A1 (en) | Imaging system and method to improve depth perception | |
| WO2018123613A1 (ja) | 医療用画像処理装置、医療用画像処理方法、プログラム | |
| CN212326346U (zh) | 一种内窥镜成像系统 | |
| US11699215B2 (en) | Imaging device, method and program for producing images of a scene having an extended depth of field with good contrast | |
| JPWO2018221041A1 (ja) | 医療用観察システム及び医療用観察装置 | |
| JP2023164610A (ja) | 画像処理装置、画像処理方法および画像処理システム | |
| US12364386B2 (en) | Medical image generation apparatus, medical image generation method, and medical image generation program | |
| US12182974B2 (en) | Endoscopic surgery system, image processing apparatus, and image processing method | |
| WO2022019057A1 (ja) | 医療用アーム制御システム、医療用アーム制御方法及びプログラム | |
| US11464393B2 (en) | Endoscope apparatus and method of operating endoscope apparatus | |
| JP5422180B2 (ja) | 内視鏡装置およびその作動方法 | |
| JP7456385B2 (ja) | 画像処理装置、および画像処理方法、並びにプログラム | |
| JP2021145859A (ja) | 医療用画像処理装置及び医療用観察システム | |
| WO2020116067A1 (ja) | 医療システム、情報処理装置及び情報処理方法 | |
| JP7063321B2 (ja) | 撮像装置、映像信号処理装置および映像信号処理方法 | |
| CN106455948B (zh) | 摄像系统 | |
| WO2022172733A1 (ja) | 医療用観察装置、観察装置、観察方法及びアダプタ | |
| JP7140113B2 (ja) | 内視鏡 | |
| WO2022249572A1 (ja) | 画像処理装置、画像処理方法及び記録媒体 | |
| JPWO2020050187A1 (ja) | 医療システム、情報処理装置及び情報処理方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20887892 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2021556079 Country of ref document: JP Kind code of ref document: A |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 20887892 Country of ref document: EP Kind code of ref document: A1 |
|
| WWG | Wipo information: grant in national office |
Ref document number: 17755725 Country of ref document: US |
|
| WWG | Wipo information: grant in national office |
Ref document number: 202080077511.7 Country of ref document: CN |