JP2010044561A - Monitoring device to be mounted on vehicle - Google Patents

Abstract

There is provided a vehicle mounting monitoring device capable of appropriately notifying an occupant of the presence, position, and outer shape of a cautionary object without alerting an occupant other than the cautionary object to be aware of a collision.
A vehicle mounting monitoring apparatus 1000 according to the present invention includes a camera 10 that captures an image of the periphery of the vehicle as a subject and generates an image signal, and an occupant collides among objects reflected in the image captured by the camera 10. A cautionary object detection unit 20 that detects a cautionary object to be aware of based on a mode of approach of the object to the vehicle, and when the cautionary object detection unit 20 detects the cautionary object, an area other than the area corresponding to the cautionary object is detected. The image processing unit 30 performs image processing that makes the image inconspicuous compared with the region corresponding to the attention object, and the monitor 40 displays the image that has been subjected to image processing by the image processing unit 30.
[Selection] Figure 1

Description

  The present invention relates to a vehicle mounting monitoring device that is mounted on a vehicle and monitors the periphery of the vehicle.

  Conventionally, as a monitoring device mounted on a vehicle, a plurality of cameras are attached to the periphery of the vehicle, and the captured images of these cameras are displayed on a monitor in the vehicle interior, so that the driver can confirm the safety of the vehicle surroundings. Something that encourages is known. Here, for example, when another vehicle approaches from the side of the host vehicle, it is difficult for the driver to check the other vehicle with the rearview mirror. However, according to this monitoring device, other vehicles approaching from the side of the vehicle of the own vehicle are displayed on the monitor in the passenger compartment, so that the driver can check the other vehicles on the monitor. As a result, for example, a collision with another vehicle at the time of lane change can be avoided.

  In addition, taking into account that the driver may overlook the display on the monitor, the captured image of the camera attached to the periphery of the vehicle is displayed on the monitor, and the presence of an approaching object is detected in the captured image. There has been proposed a monitoring device that generates a buzzer sound when an approaching object is present to alert the driver.

Further, Patent Document 1 detects that there is an approaching vehicle in the captured image of the camera, generates a buzzer sound to alert the driver, and superimposes on the captured image of the camera. There is disclosed a monitoring device that forms a square frame mark on an approaching vehicle image and displays it on a display device. According to the monitoring device described in Patent Literature 1, the driver can identify the approaching vehicle by the mark on the image displayed on the display device.
Japanese Patent Laid-Open No. 11-32494

  However, in the monitoring device described in Patent Document 1, since the vehicle other than the detected approaching vehicle and the background are also displayed on the image, the driver is not required to pay attention to changes in the image other than the approaching vehicle. You may pay. As a result, there is a problem in that unnecessary attention is originally drawn to the driver who drives while looking mainly at the front of the host vehicle, and the concentration of driving is hindered. Moreover, in the monitoring apparatus described in Patent Document 1, since a mark is added on the image of the approaching vehicle, it may be difficult to confirm the shape of the approaching vehicle.

  The present invention has been made to solve the above-described conventional problems, and the presence, position, and outer shape of the cautionary object can be determined without calling the occupant unnecessary attention other than the cautionary object to be aware of the collision. It is an object of the present invention to provide a vehicle-mounted monitoring device that can appropriately notify.

  A vehicle mounting monitoring device according to the present invention is a vehicle mounting monitoring device that is mounted on a vehicle and monitors the periphery of the vehicle, and an imaging unit that images the periphery of the vehicle as a subject and generates an image signal; A cautionary object detection unit that detects a cautionary object to which a passenger should be aware of a collision among objects reflected in an image captured by the imaging unit based on a manner in which the object approaches the vehicle; and the cautionary object An image processing unit that performs image processing to make a region other than the region corresponding to the attention object inconspicuous when the detection unit detects the attention object; and the image processing unit And a display unit that displays an image on which the image processing has been performed.

  With this configuration, for example, an object that approaches a vehicle at a certain approach speed or an object that approaches a vehicle within a certain distance, such as an object that approaches the vehicle, a cautionary object that the occupant should be aware of for collision Is detected from among objects reflected in the image captured by the imaging unit. In addition, when an attention object is detected, image processing is performed to make the region other than the region corresponding to the attention object inconspicuous compared to the region corresponding to the attention object. An image in which the attention object is conspicuous can be obtained. In addition, the image generated at this time has a clear boundary between the region of the attention object and the region other than the attention object, and is an image that accurately indicates the position and outline of the attention object. Since the image processed in this way is displayed on the display unit, the occupant can watch the object other than the cautionary object and the background image by looking at the image after the image processing. Therefore, the presence / absence, position, and outer shape of the attention object can be appropriately known. As a result, it is possible to appropriately notify the occupant of the presence, position, and outer shape of the cautionary object without alerting the occupant other than the cautionary object that should be careful of the collision.

  In the vehicle mounting monitoring apparatus according to the present invention, the image processing unit has a configuration in which a region other than the region corresponding to the attention object is a solid or achromatic image. As a result, an object other than the attention object or an image of the background can be a plain or achromatic image, and an image in which the attention object is more conspicuous can be obtained. As a result, it is possible to prevent the occupant's attention from being aroused other than the attention object.

  Further, in the vehicle mounting monitoring device according to the present invention, the image processing unit has a configuration in which the luminance of a region other than the region corresponding to the attention object is lower than the luminance of the region corresponding to the attention object. ing. As a result, it is possible to obtain an image in which the attention object is brighter than the object other than the attention object and the background. As a result, it is possible to prevent the occupant's attention from being aroused other than the attention object.

  In the vehicle mounting monitoring device according to the present invention, the caution object detection unit may cause the imaging unit to detect a moving object that moves relative to the vehicle based on a change between frames of the image signal. A moving object detection unit that detects from a captured image; and a motion vector calculation unit that obtains a motion vector indicating a motion between frames of the moving object detected by the moving object detection unit. Based on the motion vector calculated by the calculation unit, an approach speed of the moving object to the vehicle is obtained, and the attention object is detected from the moving object based on the approach speed.

  With this configuration, when detecting an attention object, first, the moving object is detected, the motion between frames of the moving object is calculated as a motion vector, and the approaching speed of the moving object to the vehicle is obtained based on the motion vector. Since the caution object is detected, an object approaching the vehicle at an approach speed of a certain level or more can be easily detected as the caution object.

  Further, in the vehicle mounting monitoring device according to the present invention, the imaging unit is configured by a stereo camera including a plurality of cameras, and the attention object detection unit is based on a change between frames of the image signal. Based on the moving object detection unit that detects the moving object that moves relative to the vehicle from the images captured by the imaging unit, and the image that is captured by the stereo camera, the moving object and the A distance calculation unit that calculates a distance to the vehicle, and detects the attention object from among the moving objects based on the distance calculated by the distance calculation unit.

  With this configuration, when detecting an attention object, first, the moving object is detected, the distance between the moving object and the vehicle is calculated using a stereo camera, and the attention object is detected based on this distance. An object approaching within the distance can be easily detected as an attention object.

  In addition, the vehicle mounting monitoring device according to the present invention includes a white line detection unit that detects whether or not a white line on a road on which the vehicle travels exists in the image captured by the imaging unit, When the attention object detection unit detects the attention object and the white line detection unit detects the white line, the image processing unit detects an area other than the attention object and an area corresponding to the white line as the attention object and It has a configuration for performing image processing that makes it inconspicuous compared with the region corresponding to the white line.

  With this configuration, it is possible to obtain an image in which the attention object and the white line on the road are conspicuous. Therefore, it is possible to alert the passenger to the white line on the road in addition to the attention object.

  The present invention detects a cautionary object to which the occupant should be careful of a collision among objects reflected in an image captured by the imaging unit based on the approaching state of the object to the vehicle. Image processing that makes the area other than the area corresponding to the object inconspicuous compared with the area corresponding to the attention object is displayed, and the image that has been subjected to this image processing is displayed. The presence, position, and outer shape of the caution object can be appropriately notified without calling unnecessary attention other than the caution object.

(First embodiment)
Hereinafter, a vehicle-mounted monitoring device according to a first embodiment of the present invention will be described with reference to the drawings.
FIG. 1 is a block diagram showing the configuration of the vehicle-mounted monitoring device according to the first embodiment of the present invention.
In FIG. 1, the vehicle-mounted monitoring device 1000 includes a camera 10, a cautionary object detection unit 20, an image processing unit 30, and a monitor 40. The vehicle mounting monitoring device 1000 here is a device for monitoring the surroundings of the vehicle, and is mounted on the vehicle.

  The camera 10 is installed indoors or outdoors of the host vehicle, images a predetermined range around the host vehicle as a subject, and generates an image signal. A plurality of cameras 10 may be provided in the own vehicle. The camera 10 is an imaging unit of the present invention.

  The caution object detection unit 20 detects an caution object that an occupant should be aware of in a collision from among objects reflected in an image captured by the camera 10. Here, the caution object detection unit 20 detects an object that approaches the host vehicle at a certain approach speed as a caution object. The attention object detection unit 20 includes a moving object detection unit 21, a motion vector calculation unit 22, and a attention object determination unit 23.

  The moving object detection unit 21 detects a moving object from the captured image of the camera 10 based on the change between frames of the image signal generated by the camera 10. The moving object here is an object that moves relative to the host vehicle. That is, regardless of whether the host vehicle is stopped or moving, the moving object detection unit 21 detects only an object moving with the host vehicle as a reference. Further, in the moving object detection process, a moving object is detected by separating a background region and a moving object (a tangible object such as a person, an animal, or an object) from a captured image of the camera 10. . Specifically, the moving object detection unit 21 analyzes the image signal by calculating the difference of the image signal between the previous frame and the current frame, and determines the changed area as the area of the moving object. Is detected for each frame.

  The motion vector calculation unit 22 obtains a motion vector indicating the motion between frames of the moving object detected by the moving object detection unit 21 using the optical flow. The optical flow here is a vector representing the motion of a moving object in temporally continuous images.

  The caution object determination unit 23 obtains the approaching speed of the moving object to the host vehicle based on the motion vector calculated by the motion vector calculation unit 22, and determines whether the moving object is equal to or greater than a certain value. Is determined to be an attention object.

  When the attention object detection unit 20 detects the attention object, the image processing unit 30 compares a region other than the region corresponding to the attention object in the image captured by the camera 10 with the region corresponding to the attention object. Image processing to make it inconspicuous.

  The monitor 40 displays an image that has been subjected to image processing by the image processing unit 30. The monitor 40 is attached, for example, in the vicinity of the driver's seat in the passenger compartment of the host vehicle so that the passenger can visually recognize the image on the monitor 40. The monitor 40 is a display unit of the present invention.

  Next, the operation of the vehicle-mounted monitoring device 1000 according to the first embodiment of the present invention will be described with reference to the drawings.

  First, the camera 10 captures an image around the subject vehicle as a subject. FIG. 2 is a diagram illustrating an example of an image captured by the camera 10. In the example of FIG. 2, the image which imaged the back of the own vehicle as a to-be-photographed is shown. As shown in FIG. 2, the captured image 100 of the camera 10 includes another vehicle 101 running on the road, an obstacle 102 such as a signboard fixed on the road end, and a pedestrian 103 walking on the sidewalk on the road end. The white line 104 provided on the road for regulating the lane is included.

  Next, the caution object detection unit 20 detects the caution object that the occupant should be careful of in the collision from the objects shown in the captured image 100 of the camera 10. Here, the caution object detection unit 20 detects an object that approaches the host vehicle at a certain approach speed as a caution object. This will be specifically described below with reference to FIGS.

  FIG. 3 is a diagram illustrating an example of the detection result of the moving object. The moving object detection unit 21 detects a moving object from the captured image 100 of the camera 10. Specifically, the moving object detection unit 21 analyzes the image signal by calculating a difference in the image signal between the previous frame and the current frame, and determines the changed area as the moving object area. Is detected for each frame. As shown in FIG. 3, as a detection result of the moving object detection unit 21, the other vehicle 101, the obstacle 102 and the pedestrian 103 are detected as moving objects. Note that the moving object here is an object that moves relative to the host vehicle as described above.

  FIG. 4 is a diagram illustrating an example of the detection result of the approaching object. As will be described in detail later, the caution object determination unit 23 calculates the approach speed of the moving object detected by the moving object detection unit 21 based on the motion vector calculated by the motion vector calculation unit 22 and calculates It is determined whether or not the moving object is a caution object based on whether or not the approach speed is a certain level or more. As shown in FIG. 4, only the other vehicle 101 is determined as the caution object as the determination result of the caution object determination unit 23.

  5 and 6 are diagrams for explaining a motion vector calculation method by the motion vector calculation unit 22. Here, for convenience of explanation, a method for calculating a motion vector will be described using an image obtained by photographing a camera obliquely behind the host vehicle.

  FIG. 5A is an image obtained by imaging the left diagonal rear of the host vehicle, and FIG. 5B is an image obtained by imaging the right diagonal rear of the host vehicle. In FIG. 5A and FIG. 5B, the other vehicles 501 and 503 represent only the side surfaces of the vehicle for convenience. As shown in FIG. 5A, an image obtained by imaging the diagonally left rear of the host vehicle includes another vehicle 501 running side by side in the background 502. As shown in FIG. 5 (b), an image obtained by imaging the right rear side of the host vehicle includes another vehicle 503 running side by side in the background 504.

  Here, an example in which the motion vector calculation unit 22 calculates a motion vector (optical flow vector) using the other vehicles 501 and 503 and the backgrounds 502 and 504 shown in FIGS. 5A and 5B as moving objects. explain. The motion vector calculation unit 22 first extracts feature points of the other vehicles 501, 503 and the backgrounds 502, 504, and calculates a motion vector from the amount of variation of the extracted feature points between frames. Note that the method of calculating the motion vector is not limited to this, and the motion vector may be calculated using, for example, a gradient method.

  FIG. 6A and FIG. 6B are diagrams showing an example of the calculation result of the optical flow vector by the motion vector calculation unit 22, and show the other vehicle and the optical flow vector of the background based on the own vehicle. FIG.

  As shown in FIG. 6A, the optical flow vector 505 of the other vehicle 501 has an arrow pointing toward the front side of the host vehicle, and the optical flow vector 506 of the background 502 is pointing toward the rear side of the host vehicle. Is suitable. From this, it can be seen that the other vehicle 501 approaches the host vehicle from behind the host vehicle.

  As shown in FIG. 6B, the optical flow vector 507 of the other vehicle 503 has an arrow pointing toward the rear side of the own vehicle, and the optical flow vector 508 of the background 504 faces the rear side of the own vehicle. The arrow is pointing. From this, it can be seen that the other vehicle 503 is moving away from the own vehicle toward the rear of the own vehicle. The motion vector calculation method by the motion vector calculation unit 22 has been described above with reference to FIGS. 5 and 6.

  Next, the caution object determination unit 23 obtains the approaching speed of the moving object to the host vehicle based on the motion vector calculated by the motion vector calculation unit 22, and determines whether or not the calculated approaching speed is a certain level or more. To determine whether or not the moving object is a caution object.

  5 and 6, the attention object determination unit 23 determines whether the other vehicle 501, the other vehicle 501, the length of the optical flow vector 505, 507 or the length of the optical flow vector 505, 507, the other vehicle 501, 503. The approach speed to the own vehicle is calculated at 503. The attention object determination unit 23 determines that the other vehicles 501 and 503 are attention objects when the calculated approach speed is equal to or higher than a preset threshold value.

  In approach detection using such an optical flow, an attention object can be determined almost in real time using only a captured image of one camera. The method for determining the cautionary object by the cautionary object determination unit 23 has been described above.

  Returning to FIG. 4, when the attention object detection unit 20 detects the other vehicle 101 as an approaching object, the image processing unit 30 selects an area other than the area corresponding to the other vehicle 101 in the captured image 100 of the camera 10. Compared with the area corresponding to the other vehicle 101, image processing that makes it inconspicuous is performed.

  FIG. 7 is a diagram for explaining processing by the image processing unit 30. As illustrated in FIG. 7, the image processing unit 30 extracts only the other vehicle 101 from the captured image 100 of the original subject captured by the camera 10, and the other vehicle detected as an approaching object by the attention object detection unit 20. The other vehicle 101 is synthesized with a plain background using the contour data 101 as a synthesis key signal. As described above, the image processing unit 30 makes the region other than the region corresponding to the other vehicle 101 conspicuous by making the region other than the region corresponding to the other vehicle 101 out of the captured image 100 of the camera 10. Perform image processing to be eliminated.

  Next, another example of image processing of the image processing unit 30 will be described with reference to FIG. The image processing unit 30 does not display all but the other vehicle 101 as in the example of FIG. 7 and does not display a plain image, but also displays an image other than the other vehicle 101 as shown in FIG. An area other than the area corresponding to the other vehicle 101 may be achromatic.

  Next, the image subjected to the image processing by the image processing unit 30 is input to the monitor 40. The monitor 40 displays the image processed by the image processing unit 30.

  According to the vehicle mounting monitoring apparatus 1000 of the first embodiment of the present invention, the camera 10 captures a cautionary object to which the occupant should be careful of collision according to the manner in which the object approaches the host vehicle. Detection is performed from among objects reflected in the image 100. Further, when the caution object detection unit 20 detects the other vehicle 101 as the caution object, for example, a region other than the region corresponding to the other vehicle 101 in the captured image 100 of the camera 10 is compared with the region corresponding to the other vehicle 101. Then, since the image processing to make it inconspicuous is performed, it is possible to obtain an image in which the attention object is more conspicuous than the object other than the attention object and the background. In addition, the image generated at this time has a clear boundary between the region of the attention object and the region other than the attention object, and is an image that accurately indicates the position and outline of the attention object. Since the image processed in this way is displayed on the monitor 40, the occupant can watch the object other than the cautionary object and the background image by looking at the image after the image processing. Therefore, the presence / absence, position, and outer shape of the attention object can be appropriately known. As a result, it is possible to appropriately notify the occupant of the presence, position, and outer shape of the cautionary object without calling unnecessary attention other than the cautionary object to be aware of the collision.

  In addition, according to the vehicle mounting monitoring apparatus 1000 of the first embodiment of the present invention, the image processing unit 30 displays a region other than the region corresponding to the other vehicle 101 that is the attention object, as a plain or achromatic image. The configuration is as follows. As a result, an object other than the caution object or an image of the background can be a plain or achromatic image, and an image in which the caution object is more conspicuous can be obtained. As a result, it is possible to prevent the occupant's attention from being aroused other than the attention object.

  In addition, according to the vehicle mounting monitoring apparatus 1000 of the first embodiment of the present invention, when detecting an attention object, first, the moving object is detected, and the motion between frames of the moving object is calculated using a motion vector. Since the approaching speed of the moving object to the host vehicle is determined based on the motion vector and the attention object is detected, an object approaching the host vehicle at a certain approach speed or more can be easily detected as the attention object. it can.

(Second Embodiment)
Hereinafter, a vehicle-mounted monitoring device according to a second embodiment of the present invention will be described with reference to the drawings.
FIG. 9 is a block diagram showing a configuration of a vehicle-mounted monitoring device 1001 according to the second embodiment of the present invention.
In FIG. 9, the vehicle-mounted monitoring device 1001 includes a camera 10 </ b> A, a cautionary object detection unit 20 </ b> A, an image processing unit 30, and a monitor 40.

  When FIG. 1 and FIG. 9 are compared, in the on-vehicle monitoring apparatus 1000 according to the first embodiment of the present invention, the camera 10 is a single camera, whereas the second embodiment of the present invention. In the vehicle-mounted monitoring apparatus 1001 of the embodiment, the camera 10A is different in that it constitutes a stereo camera composed of two cameras.

  As shown in FIG. 1, the caution object detection unit 20 of the vehicle-mounted monitoring apparatus 1000 according to the first embodiment of the present invention includes a moving object detection unit 21, a motion vector calculation unit 22, and a caution object determination unit. 23. On the other hand, as shown in FIG. 9, the caution object detection unit 20A of the vehicle-mounted monitoring device 1001 according to the second embodiment of the present invention includes a moving object detection unit 21, a distance calculation unit 24, and a caution object. It is comprised by the determination part 23A.

  The camera 10A includes a reference camera 11 and a reference camera 12, and constitutes a stereo camera including these cameras. The camera 10 </ b> A is installed indoors or outdoors of the host vehicle, images a predetermined range around the host vehicle as a subject, and generates an image signal. The reference camera 11 and the reference camera 12 are arranged at a predetermined interval, and are configured so that a subject can be imaged simultaneously. The camera 10A corresponds to the imaging unit of the present invention.

  As described above, the caution object detection unit 20A includes the moving object detection unit 21, the distance calculation unit 24, and the caution object determination unit 23A. The attention object detection unit 20 </ b> A detects an attention object from which an occupant should be careful of a collision among objects reflected in a captured image of the camera 10. Here, unlike the first embodiment, the caution object detection unit 20A detects an object that approaches a certain distance from the host vehicle as a caution object.

  The moving object detection unit 21 has the same function as that of the first embodiment. The distance calculation unit 24 is based on the two images simultaneously captured by the reference camera 11 and the reference camera 12 constituting the stereo camera, and the distance between the moving object detected by the moving object detection unit 21 and the host vehicle. Calculate the distance.

  The attention object determination unit 23A determines whether the moving object is the attention object based on the distance calculated by the distance calculation unit 24. Specifically, the attention object determination unit 23A determines whether or not the distance between the moving object calculated by the distance calculation unit 24 and the host vehicle is equal to or less than a preset threshold value, and is equal to or less than the threshold value. The moving object is determined to be an attention object.

  Next, the operation of the vehicle-mounted monitoring device 1001 according to the second embodiment of the present invention will be described with reference to the drawings. In the following description, processing different from that of the first embodiment will be mainly described.

  First, the camera 10A takes an image of the vicinity of the host vehicle as a subject. At this time, the base camera 11 and the reference camera 12 simultaneously image the subject. Next, the caution object detection unit 20 </ b> A detects a caution object that the occupant should be aware of in a collision from among the objects shown in the captured image of the camera 10. Here, the caution object detection unit 20A detects an object approaching within a certain distance from the host vehicle as the caution object.

  At this time, the moving object detection unit 21 detects a moving object from the captured image of the camera 10A, as described with reference to FIG. 3 in the first embodiment. Further, the distance calculation unit 24 calculates the distance between the moving object detected by the moving object detection unit 21 and the vehicle based on the two images simultaneously captured by the base camera 11 and the reference camera 12. .

  The attention object determination unit 23A determines whether or not the moving object is the attention object based on the distance calculated by the distance calculation unit 24. Specifically, the attention object determination unit 23A determines whether or not the distance between the moving object calculated by the distance calculation unit 24 and the host vehicle is equal to or less than a preset threshold value, and is equal to or less than the threshold value. The moving object is determined to be an attention object.

  Next, as described with reference to FIG. 7 in the first embodiment, the image processing unit 30 converts the region other than the region corresponding to the other vehicle 101 that is the attention object into a plain image, Image processing that makes the region other than the region corresponding to the vehicle 101 inconspicuous in comparison with the region corresponding to the other vehicle 101 is performed. Note that the image processing unit 30 may set a region other than the region corresponding to the attention object to an achromatic color, as described with reference to FIG.

  Next, the image of the subject that has been subjected to image processing by the image processing unit 30 is input to the monitor 40. The monitor 40 displays the image processed by the image processing unit 30.

  According to the on-vehicle monitoring apparatus 1001 according to the second embodiment of the present invention, when detecting an attention object, first, the moving object detection unit 21 detects the moving object and moves using the stereo camera. Since the distance between the object and the vehicle is calculated and the attention object is detected based on this distance, an object approaching within a certain distance from the host vehicle can be easily detected as the attention object.

(Third embodiment)
Hereinafter, a vehicle-mounted monitoring device according to a third embodiment of the present invention will be described with reference to the drawings.
FIG. 10 is a block diagram showing a configuration of a vehicle-mounted monitoring device 1002 according to the third embodiment of the present invention. In FIG. 10, the vehicle-mounted monitoring device 1002 includes a camera 10, a cautionary object detection unit 20, an image processing unit 30 </ b> A, a monitor 40, and a white line detection unit 50.

  When FIG. 1 is compared with FIG. 10, a white line detection unit 50 is newly provided in the vehicle-mounted monitoring device 1002 according to the third embodiment.

  The white line detection unit 50 detects whether or not there is a white line on the road on which the host vehicle travels in the image captured by the camera 10. Specifically, white line detection processing by the white line detection unit 50 is performed by an image processing program that detects a white line on a road surface from an image captured by a camera, as disclosed in, for example, Japanese Patent Application Laid-Open No. 2006-134232. In this white line detection process, first, the captured image is binarized by luminance, and pixels that are considered to correspond to white lines on the road surface in the binarized image (hereinafter referred to as white line candidate points) are selected. If the white line candidate points are linearly arranged, it is determined that the selected white line candidate point is a white line on the road surface. Here, for example, a means such as a Hough transform is used to determine that the lines are arranged in a straight line.

  When the attention object detection unit 20 detects the attention object and the white line detection unit 50 detects the white line, the image processing unit 30A detects an area other than the area corresponding to the attention object and the white line in the captured image of the camera 10. Compared with the region corresponding to the attention object and the white line, image processing that makes it inconspicuous is performed.

  Next, the operation of the vehicle-mounted monitoring device 1002 according to the third embodiment of the present invention will be described with reference to the drawings. In the following description, processing different from that of the first embodiment will be mainly described.

  The caution object detection unit 20 detects the caution object from the objects shown in the captured image of the camera 10. Further, the white line detection unit 50 detects whether or not a white line on the road on which the host vehicle travels is present in the image captured by the camera 10. As described above, the white line detection processing by the white line detection unit 50 is performed by an image processing program that detects a white line on the road surface from an image captured by the camera 10.

  Next, when the attention object detection unit 20 detects an approaching object and the white line detection unit 50 detects a white line, the image processing unit 30A includes a region other than the region corresponding to the attention object and the white line in the captured image of the camera 10. Is compared with the region corresponding to the attention object and the white line, and image processing is performed to make the region inconspicuous.

  FIG. 11 is a diagram for explaining image processing by the image processing unit 30A. Here, similarly to the description in FIG. 7, it is assumed that the caution object detection unit 20 detects the other vehicle 101 as the caution object. As shown in FIG. 11, the image processing unit 30 </ b> A sets a region other than the region corresponding to the other vehicle 101 and the white line 104, which are objects of attention, in the captured image 100 of the camera 10 as a plain image. Image processing that makes the region other than the region corresponding to the other vehicle 101 and the white line 104 inconspicuous in comparison with the region corresponding to the other vehicle 101 and the white line 104 is performed. In this embodiment as well, as described with reference to FIG. 8, the image processing unit 30 </ b> A does not display all but the other vehicle 101 and the white line 104, as in the first embodiment. Instead of displaying the image other than the other vehicle 101 and the white line 104, an area other than the area corresponding to the other vehicle 101 and the white line 104 may be achromatic.

  Next, the image subjected to the image processing by the image processing unit 30A is input to the monitor 40. The monitor 40 displays the image processed by the image processing unit 30A.

  According to the on-vehicle monitoring apparatus 1002 of the third embodiment of the present invention, whether there is a white line on the road on which the host vehicle travels by the white line detection unit 50 in the captured image of the camera 10. When the caution object detection unit 20 detects the caution object and the white line detection unit 50 detects the white line, the image processing unit 30A handles the caution object and the white line in the captured image of the camera 10. An area other than the area to be compared is compared with the area corresponding to the attention object and the white line, and image processing is performed to make the area less noticeable. As a result, an image in which the attention object and the white line on the road are conspicuous can be obtained, so that the occupant's attention can be given to the white line on the road in addition to the attention object.

  The embodiments of the present invention have been described above by way of example, but the scope of the present invention is not limited to these embodiments, and can be changed or modified in accordance with the purpose within the scope of the claims. is there.

  In the above embodiment, the image processing units 30 and 30A convert a region other than the region corresponding to the other vehicle 101 that is the attention object to a plain or achromatic image, and correspond to the region other than the region corresponding to the attention object to the attention object. It has been described that the image processing is made inconspicuous compared with the area to be performed. On the other hand, the image processing units 30 and 30A may perform image processing in which the luminance of the region other than the region corresponding to the attention object is lower than the luminance of the region corresponding to the attention object. As a result, it is possible to obtain an image in which the attention object is brighter than the object other than the attention object and the background. As a result, it is possible to prevent the occupant's attention from being aroused other than the attention object.

  In addition, the image processing units 30 and 30A make a region other than the region corresponding to the attention object a solid or achromatic image, and the luminance of the region other than the region corresponding to the attention object is set to the luminance of the region corresponding to the attention object. You may perform the image process made lower than a brightness | luminance. Thereby, it is possible to obtain an image in which the attention object is brighter and more conspicuous than the object other than the attention object and the background. As a result, it is possible to prevent the occupant's attention from being aroused other than the attention object.

  As described above, the present invention is capable of appropriately notifying an occupant of the presence, position, and outer shape of a caution object without calling unnecessary caution other than the caution object that should be careful of the collision. For example, it is useful for a vehicle monitoring device that is mounted on a vehicle and monitors the periphery of the vehicle.

The block diagram which shows the structure of the monitoring apparatus for vehicle mounting of the 1st Embodiment of this invention The figure which shows an example of the image imaged with the camera A figure showing an example of the detection result of a moving object Diagram showing an example of the detection result of a caution object (A) The figure for demonstrating the calculation method of the motion vector by a motion vector calculation part (b) The figure for demonstrating the calculation method of the motion vector by a motion vector calculation part (A) The figure for demonstrating the calculation method of the motion vector by a motion vector calculation part (b) The figure for demonstrating the calculation method of the motion vector by a motion vector calculation part The figure for demonstrating the image processing by the image process part in the 1st Embodiment of this invention The figure for demonstrating another example of the image processing by the image processing part in the 1st Embodiment of this invention The block diagram which shows the structure of the monitoring apparatus for vehicle mounting of the 2nd Embodiment of this invention. The block diagram which shows the structure of the monitoring apparatus for vehicle mounting of the 3rd Embodiment of this invention. The figure for demonstrating the image processing by the image process part in the 3rd Embodiment of this invention

Explanation of symbols

10, 10A camera 11 reference camera 12 reference camera 20, 20A attention object detection unit 21 moving object detection unit 22 motion vector calculation unit 23, 23A attention object determination unit 24 distance calculation unit 30, 30A image processing unit 40 monitor 50 white line detection 1000, 1001, 1002 Vehicle-mounted monitoring device

Claims (6)

A vehicle mounting monitoring device mounted on a vehicle for monitoring the periphery of the vehicle,
An imaging unit that images the periphery of the vehicle as a subject and generates an image signal;
A cautionary object detection unit that detects a cautionary object to which a occupant should be careful of a collision among objects reflected in an image captured by the imaging unit, based on a manner in which the object approaches the vehicle;
An image processing unit that performs image processing to make a region other than the region corresponding to the caution object inconspicuous when the caution object detection unit detects the caution object;
A display unit that displays the image subjected to the image processing by the image processing unit;
A vehicle mounting monitoring device characterized by comprising:   The vehicle mounting monitoring apparatus according to claim 1, wherein the image processing unit sets a region other than the region corresponding to the attention object as a plain or achromatic image.   3. The vehicle mounting monitor according to claim 1, wherein the image processing unit makes the brightness of an area other than the area corresponding to the attention object lower than the brightness of the area corresponding to the attention object. apparatus. The attention object detection unit is
A moving object detection unit that detects a moving object that moves relative to the vehicle based on a change between frames of the image signal from an image captured by the imaging unit;
A motion vector calculation unit for obtaining a motion vector indicating a motion between frames of the moving object detected by the moving object detection unit,
An approach speed of the moving object to the vehicle is obtained based on the motion vector calculated by the motion vector calculation unit, and the attention object is detected from the moving object based on the approach speed. The vehicle mounting monitoring device according to any one of claims 1 to 3. The imaging unit is composed of a stereo camera composed of a plurality of cameras,
The attention object detection unit is
A moving object detection unit that detects a moving object that moves relative to the vehicle based on a change between frames of the image signal from an image captured by the imaging unit;
A distance calculation unit that calculates a distance between the moving object and the vehicle based on an image captured by the stereo camera;
The vehicle mounting monitoring apparatus according to claim 1, wherein the attention object is detected from the moving objects based on the distance calculated by the distance calculation unit. A white line detection unit for detecting whether or not a white line on a road on which the vehicle travels exists in the image captured by the imaging unit;
The image processing unit detects an area other than the area corresponding to the attention object and the white line when the attention object detection section detects the attention object and the white line detection section detects the white line. 6. The vehicle mounting monitoring apparatus according to claim 1, wherein image processing is performed to make the image inconspicuous in comparison with an area corresponding to the white line.

Images