JP2010087676A - Video camera system having feature determination function - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To photograph and record only an object image, having a prescribed feature or an object image which does not have the prescribed feature in a simple system configuration. <P>SOLUTION: The video camera system having a feature determination function includes an imaging means for imaging the object image subjected to image formation by an optical system; a storage means wherein the face image data of a photographing object person is registered beforehand; a feature determination means for determining the feature of the object by authenticating the face image of the object imaged by the imaging means through comparison with the face image registered beforehand in the storage means; and an image recording means for recording the imaged object image. While the object image is photographed by the imaging means, if the photographed facial image of the object and the facial image which is registered beforehand match through facial authentication, the image recording means starts the image recording of the object image. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a video camera system having a feature determination function, and in particular, a feature determination function when a subject image obtained by actually photographing a subject matches a subject image having a predetermined feature registered in advance. The present invention relates to a video camera system having a feature determination function in which a determination made by the above is used as a trigger for starting a predetermined operation such as the start of recording.

  Conventionally, in order to observe wild animals, etc., a surveillance camera system is installed in a place where the wild animals are likely to appear, and if it detects that a moving object has entered the field of view, it will automatically The one that is supposed to take a picture is known.

  For example, in order to prevent a car accident caused by an animal jumping out on a road in a mountainous area or the like, a notification system that detects an animal that appears on the road and notifies the driver is known.

  Alternatively, a monitoring system is known that detects a suspicious person who has illegally entered by installing a camera at the entrance of a building.

  In these systems, for example, an infrared camera, infrared sensor, or infrared radar detects an object that moves within the field of view, or measures the distance to an object in the monitoring range, and this measurement distance has changed. Thus, it is detected that the object is a moving object.

  In addition, for example, images are captured in time series, a plurality of background images are stored from the captured images, and the minimum absolute value (difference) for each pixel between the newly captured image and the stored background image is stored. There is known a monitoring device that determines the presence or absence of an intruding object based on the degree and records the newly captured image when it is determined that there is an intruding object (for example, Patent Document 1) reference).

In recent years, a crime prevention system in which an image database in which face images are registered, a host computer that performs image processing, and surveillance cameras installed at a plurality of locations are connected via a network has been considered.
JP 2001-186511 A

  However, since the conventional monitoring system described above only detects a moving object that has entered the monitoring range, even if a moving object is detected, it is unknown whether it is an animal or a human being. There wasn't. Further, even if an intruder is detected and the image is taken, there is a problem that it is difficult to obtain an image that is clear enough to determine who the person is. Moreover, in a large-scale crime prevention system using an image database in which face images are registered, it is difficult to install the system, and there is a problem that enormous costs are required.

  The present invention has been made in view of such circumstances, and only a subject image having a predetermined feature or a subject image having no predetermined feature is photographed at a desired angle and size with a simple system configuration. It is an object of the present invention to provide a video camera system having a feature determination function capable of recording or not recording.

  In order to achieve the object, the invention described in claim 1 includes an imaging unit that captures a subject image formed by an optical system, a storage unit in which face image data of a subject to be captured is registered, and Feature determination means for determining the feature of the subject by performing face authentication on the face image of the subject imaged by the imaging means and the face image registered in advance in the storage means, and recording for recording the imaged subject image And when the face image of the photographed subject matches the pre-registered face image by the face authentication during the photographing of the subject image by the imaging means, the recording means Provided is a video camera system having a feature determination function characterized by starting recording of a subject image.

  Accordingly, a face image of a subject that matches a face image registered in advance can be recorded with a simple system configuration as a subject image having predetermined characteristics.

  According to a second aspect of the present invention, there is provided a video camera system having the feature determination function according to the first aspect, wherein the image is captured by the face authentication while the subject image is captured by the imaging unit. When the face image of the subject and the face image registered in advance match, the pan / tilt and zoom are automatically linked in place of or together with the recording of the subject image by the recording means. Then, the size of the authenticated face image is set to an appropriate size.

  Thereby, the face image of the subject that matches the face image registered in advance can be photographed and recorded at a desired angle and size.

  Similarly, in order to achieve the above object, the invention according to claim 3 is an image pickup means for picking up a subject image formed by an optical system, and a memory in which face image data of a person to be picked up is registered in advance. Means for determining the characteristics of the subject by performing face authentication of the face image of the subject imaged by the imaging means and the face image registered in advance in the storage means, and the captured subject image And when the face image of the photographed subject matches the pre-registered face image by the face authentication during the photographing of the subject image by the imaging means, Provided is a video camera system having a feature determination function, wherein the recording means does not start recording the subject image.

  As a result, it is possible to perform only necessary recording without recording a subject image having predetermined characteristics.

  According to a fourth aspect of the present invention, there is provided an imaging unit that captures a subject image formed by an optical system, a storage unit in which feature data of a shooting target is registered in advance, and a moving subject that is captured by the imaging unit. And a feature determination unit that determines whether the feature matches a feature registered in advance in the storage unit, and a recording unit that records the captured subject image, and the subject image obtained by the imaging unit The feature determination is characterized in that the recording means starts recording the subject image when the feature determination causes the feature of the captured subject to coincide with the pre-registered feature. A video camera system having functions is provided.

  As a result, a subject image having a predetermined feature can be recorded with a simple system configuration.

  According to a fifth aspect of the present invention, there is provided a video camera system having the feature determination function according to the fourth aspect, wherein the image is captured by the feature determination while the subject image is being captured by the imaging unit. When the feature of the subject that has been matched with the pre-registered feature, the feature determination is performed so that the size of the subject image determined by automatically panning / tilting and zooming becomes appropriate. The recording unit starts recording the subject image after confirming with improved accuracy.

  Thereby, when only the subject image having a predetermined characteristic is recorded, the determination accuracy can be improved.

  According to a sixth aspect of the present invention, an image pickup means for picking up a subject image formed by the optical system, a storage means in which feature data of the photographing object is registered in advance, and a moving subject picked up by the image pickup means And a feature determination unit that determines whether the feature matches a feature registered in advance in the storage unit, and a recording unit that records the captured subject image, and the subject image obtained by the imaging unit When the feature determination does not match the pre-registered feature with the feature determination, the recording unit starts recording the subject image.

  Thus, a subject image that does not have a predetermined characteristic can be recorded with a simple system configuration.

  According to a seventh aspect of the present invention, in the video camera system having the feature determination function according to any one of the fourth to sixth aspects, the feature is a color and a shape of the subject. To do.

  As a result, it is possible to record only a desired subject with a simple configuration by defining the characteristics of the subject by color and shape.

  As described above, according to the present invention, it is possible to record a subject image having a predetermined characteristic with a simple system configuration or not.

  Hereinafter, a video camera system having a feature determination function according to the present invention will be described in detail with reference to the accompanying drawings.

  The video camera system according to the first embodiment of the present invention includes a face authentication function as a feature determination function. Then, when a subject having a face image authenticated to match the face image data registered in advance is detected in the shooting screen, the detection is triggered to start a predetermined operation thereafter. Is.

  As the predetermined operation, for example, recording of the subject is automatically started, or panning / tilting and zooming are automatically linked to display an authenticated face image in an appropriate size. Or, conversely, it may be possible not to start recording.

  FIG. 1 is a block diagram showing the overall configuration of a video camera system provided with a face authentication function as a feature determination function according to the present invention. This video camera system is, for example, an imaging system used for shooting with a broadcast television camera.

  As shown in FIG. 1, the video camera system 1 according to the present embodiment includes a television camera 10, an image processing unit 18, an operation unit 20, and the like.

  The television camera 10 includes a camera body 12 composed of an HD camera compatible with a high-definition television [HD (High Definition) TV] system, and a lens device 14 having a photographing lens (optical system) attached to a lens mount of the camera body 12. It consists of.

  The camera body 12 is supported on a pan head (electric pan head device) 22 so as to be movable in a turning direction (pan) and a vertical tilt direction (tilt).

  The camera body 12 is equipped with an image sensor (for example, a CCD), a required signal processing circuit, and the like, and an image formed by the photographing lens of the lens device 14 is subjected to signal processing after being photoelectrically converted by the image sensor. Necessary signal processing is performed by the circuit and output as an HDTV video signal (HDTV signal) from the video signal output terminal of the camera body 12 to the outside.

  In addition, the camera body 12 includes a recording device 13, and is recorded with an HDTV video signal at a predetermined timing.

  The lens device 14 includes a photographing lens (zoom lens) 24 that is attached to the lens mount of the camera body 12. The subject 16 is imaged on the imaging surface of the imaging element of the camera body 12 by the photographing lens 24. Although not shown, the photographic lens 24 is provided with movable parts for adjusting photographing conditions such as a focus lens group, a zoom lens group, and a diaphragm as constituent parts thereof. Servo mechanism) is electrically driven. For example, the focus lens group and the zoom lens group move in the optical axis direction, the focus (subject distance) adjustment is performed by moving the focus lens group, and the focal length (zoom magnification) is adjusted by moving the zoom lens group. Adjustments are made.

  In the system related to autofocus, it is sufficient that at least the focus lens group can be driven electrically, and other movable parts may be driven only manually. Further, when the predetermined movable portion is electrically driven according to the operation of the operator, it is based on a control signal output according to the operation of the operator from an operation means (not shown) such as an operation means of a controller connected to the lens device 14. Thus, the operation of the movable part is controlled, but details are omitted.

  The lens device 14 includes an AF unit 26 and a lens CPU (not shown). The lens CPU controls the entire lens device 14. Although not shown, the AF unit 26 includes an AF processing unit, an AF imaging circuit, and the like. The AF image pickup circuit is disposed in the lens device 14 to acquire an image signal for AF processing. An image pickup device such as an image pickup device CCD (referred to as an image pickup device for AF) or an output signal of the AF image pickup device is used in a predetermined format. And a processing circuit for outputting as a video signal. The video signal output from the AF imaging circuit is a luminance signal.

  On the image pickup surface of the AF image pickup device, subject light branched from the subject light incident on the image pickup device of the camera main body 12 is imaged by a half mirror or the like disposed on the optical path of the taking lens 24. . The shooting range and subject distance (distance of the subject in focus) with respect to the imaging area of the AF imaging element are configured to match the shooting range and subject distance with respect to the imaging area of the imaging element of the camera body 12. The subject image captured by the image sensor matches the subject image captured by the image sensor of the camera body 12. It should be noted that the shooting ranges of the two do not have to coincide completely, and for example, the shooting range of the AF image sensor may be a larger range including the shooting range of the image sensor of the camera body 12.

  The AF processing unit acquires a video signal from the AF imaging circuit, and calculates a focus evaluation value indicating the level of contrast of the subject image based on the video signal. For example, after extracting a high-frequency component signal of a video signal obtained from an AF image sensor with a high-pass filter, a signal in a range corresponding to the AF area targeted for AF is extracted from the high-frequency component signal. Accumulate one screen (one frame) at a time. The integrated value obtained for each screen in this way indicates the level of contrast of the subject image, and is given to the lens CPU as a focus evaluation value.

  The lens CPU acquires AF frame information (AF frame information) indicating the range (contour) of the AF area from the operation unit 20 through the image processing unit 18 as described later, and is designated by the AF frame information. The range within the AF frame is designated as an AF area to the AF processing unit. Then, the focus evaluation value obtained from the image (video signal) in the AF area is acquired from the AF processing unit.

  In this way, every time a video signal for one screen is acquired from the AF imaging circuit (each time the focus evaluation value is obtained by the AF processing unit), the focus evaluation value is acquired from the AF processing unit, and the acquired focus is obtained. The focus lens group is controlled so that the evaluation value is maximum (maximum), that is, the contrast of the subject image in the AF area is maximum. For example, a hill-climbing method is generally known as a control method for a focus lens group based on a focus evaluation value, and the focus evaluation value starts to decrease by moving the focus lens group in a direction in which the focus evaluation value increases. Is detected, the focus lens group is set at that position. Thereby, the subject in the AF frame is automatically focused.

  Note that the camera body 12 and the lens device 14 are provided with tally lamps 12a and 14a informing that the TV camera 10 is in a shooting operation (ON AIR) at a location that is easy to see from the subject side.

  The camera body 12 and the lens device 14 transmit and receive various kinds of information via serial communication interfaces (SCI) 12b and 14b provided respectively. Further, the AF unit 26 of the lens device 14 and the main board 30 of the image processing unit 18 to be described later transmit and receive various information to and from the serial communication interfaces 26a and 30a provided respectively. Yes.

  The HDTV signal output from the camera body 12 is converted (down-converted) into a standard television [NTSC (National Television System Committee)] video signal (SDTV signal) by the down converter 28 and input to the image processing unit 18. It has come to be.

  The image processing unit 18 performs face authentication on the subject person in the captured subject image, and when it matches the face image data registered in advance, sends a signal from the serial communication interface 30b to the electric pan head device 22, The subject person is tracked, the AF unit 26 is driven via the serial communication interfaces 30a and 26a to perform autofocus control, and the recording of the subject person image is started by the recording device 13. is there.

  In order to perform face authentication in this way and determine whether or not the subject 16 matches a face registered in the memory in advance, it is not necessary to be a high-definition image using an HDTV signal, and a standard television video signal Since an image of (SDTV signal) is sufficient, the HDTV signal output from the camera body 12 is converted into an SDTV signal by the down converter 28.

  The image processing unit 18 includes blocks for performing each process on separate boards, and includes a main board 30, an authentication processing calculation board 32, and a face authentication data card 34.

  The main board 30 includes a decoder (A / D converter) 36, a CPU 38, a RAM 40, and a superimposer 42. The main board 30 has serial communication interfaces 30a and 30b. The serial communication interface 30a performs data communication with the serial communication interface 26a of the AF unit 26 of the lens device 14 as described above. In addition, the serial communication interface 30 b sends a control signal to the electric head device 22.

  As described above, the HDTV signal output from the camera body 12 is converted into the SDTV signal by the down converter 28 and input to the image processing unit 18. The decoder (A / D converter) 36 converts the SDTV signal into the SDTV signal. The converted video signal of analog data is converted into digital data for face authentication processing in the image processing unit 18.

  The CPU 38 controls the entire image processing unit 18. In addition, the CPU 38 calls face image data and information accompanying the face image data, which have been registered in the memory (storage device) in advance, from the memory so as to be used at the time of shooting, and expands them in the memory RAM 40 in the system.

  The superimposer 42 is used to display information accompanying the registered face image data on an image displayed on the display screen of the operation unit 20 to be described later.

  The authentication processing calculation board 32 includes a CPU 32a that executes authentication processing and a VRAM 32b that holds a display image.

  The operation unit 20 includes an LCD (liquid crystal display screen) with a touch panel, and data displayed on the LCD display screen is an NTSC / PAL (composite) signal.

  An operator (photographer) selects a mode on the touch panel display screen of the operation unit 20. The modes include a mode for recalling registered face image data, and a mode for performing face authentication of a photographing target and tracking a matching target face.

  Face authentication in the authentication processing calculation board 32 is performed by a known face authentication technique. For example, feature points are extracted from the imaged subject according to a predetermined algorithm. The extracted feature points include the contours of human eyes, pupils, eyebrows, nose, mouth, ears, their orientation, position, size, and the like, and the presence of hairstyles, wrinkles, and glasses. By comparing these with registered data, it is authenticated whether or not they are the same person.

  FIG. 2 shows a display example of a display screen configured by an LCD with a touch panel of the operation unit 20.

  FIG. 2 shows a display for the operator to select a mode. Here, the face tracking mode is selected.

  In the tracking mode, a target to be tracked is selected from the registered face image data on the LCD with a touch panel of the operation unit 20. Then, face authentication is performed on the face of the subject image on the shooting screen and the selected face image data.

  When the face of a certain subject image coincides with the selected face image data to be tracked, recording of the photographed image of the subject 16 by the recording device 13 is started. At this time, the tally lamp 12a or 14a installed in the camera body 12 or the lens device 14 is lit or blinked for a predetermined time. At this time, the lighting time, the brightness at the time of lighting, and the like may be characterized.

  Next, the operation of this embodiment will be described.

  FIG. 3 is a flowchart showing the operation of the present embodiment.

  First, in step S100 in FIG. 3, the operator (photographer) selects a mode using the touch panel-equipped LCD of the operation unit 20. Here, the face tracking mode is selected. This is because, when the operator designates a target to be tracked from face image data registered in advance and performs shooting, the face of the subject 16 matches the selected face image data by face authentication. The 16 faces are recorded while being automatically tracked.

  Next, in step S110, the subject 16 is photographed. The captured face image of the subject 16 is output from the camera body 12, converted by the down converter 28, and input to the image processing unit 18.

  In step S120, face authentication processing is performed. The face image of the subject 16 is sent to the authentication processing calculation board 32 together with the selected face image data developed in the RAM 40 and the data of the face authentication data card 34 to be subjected to face authentication processing.

  As a result, if it is determined in step S130 that the captured face image of the subject 16 matches the selected face image data registered in advance, recording of the subject 16 starts in the next step S140. Is done. At this time, the tally lamps 12a and 14a of the camera body 12 and the lens device 14 are turned on. It is informed that recording has started as a result of face authentication.

  On the display screen of the operation unit 20, information registered in advance for the recorded subject 16 is added to the image as character information and displayed by the superimposer 42.

  In addition, when it is authenticated that the face image of the subject 16 photographed at this time matches the selected face image data registered in advance, the authentication is automatically performed by interlocking pan / tilt, focus, and zoom. The size of the face may be an appropriate size.

  If the result of face authentication does not match in step S130, the process returns to step S110 to continue photographing the subject 16.

  In this way, the subject is photographed, and when the face image matches the registered face image as a result of the face authentication, the operation of recording the subject image is repeated.

  Thereby, it is possible to monitor the behavior of the person who needs attention. In addition, when the face image matches with the registered face image as a result of face authentication, the registered face is automatically linked with pan / tilt and zoom so that the authenticated face size is appropriate. The matching accuracy can be improved.

  As described above, the video camera system 1 of the present embodiment is an imaging system used for shooting with a broadcast television camera, for example, and further includes a face authentication function. By using this face authentication function, When a subject that matches the face registered in the captured image is detected with a simple system configuration, recording of the subject can be automatically started.

  Next, another control method of the video camera system of this embodiment will be described.

  FIG. 4 shows a control flow in this case.

  First, in step S200 of FIG. 4, the operator selects a mode. Here, it is assumed that the face tracking mode is selected. However, unlike the face tracking mode in FIG. 3 described above, this face tracking mode tracks and records a subject having a face image that matches face image data selected from face image data registered in advance by the operator. Rather than recording what matches the selected face image data, it tracks what does not match.

  For example, in a security camera system in an apartment or the like, it is assumed that a person other than a registered resident or a regular visitor is recorded as a suspicious person.

  Therefore, in this case, the number of face image data selected from the registered face image data is not limited to one, and may be plural. That is, a face image that does not match any of the plurality of selected face image data is tracked.

  In step S210, the subject 16 is photographed. In the next step S220, a person is detected from the shooting screen. When a person is detected, the face of the person is extracted, and the face selected in the next step S230 is selected. Face authentication is performed with face image data to check whether there is a match. Here, detection of a person from an image and face extraction may be performed using a known technique, and the method is not particularly limited.

  If the extracted face does not match the selected face image data in step S240, recording of the extracted face is started in the next step S250, and automatic tracking and focus control are performed.

  If no person is detected on the shooting screen in step 220, the process returns to step S210 to continue shooting. If the extracted face matches the selected face image data in step S240, the face recording is not performed, and the process returns to step S210 to continue photographing the next subject 16.

  In this way, recording is not performed when the face of the photographed subject matches the registered face image data, but recording is started only when the face does not match, so that recording is not necessary. By recording only what really needs to be recorded, efficient recording becomes possible.

  Of course, also in this case, when recording a face image that does not match the registered face image data in step S250, pan / tilt and zoom are automatically linked so that the size of the recorded face image is an appropriate size. It is preferable to do so.

  Next, a second embodiment of the present invention will be described.

  The video camera system according to the second embodiment of the present invention has a feature presentation function for discriminating a subject from features such as color and shape. When it is confirmed that the feature of the moving subject in the shooting screen matches the pre-registered feature during shooting, for example, the moving subject is automatically recorded by using the match as a trigger. It starts or automatically links pan / tilt and zoom so that the size of the subject becomes an appropriate size, or conversely, recording is not started.

  FIG. 5 is a block diagram showing an overall configuration of a video camera system having a feature determination function according to the second embodiment of the present invention.

  This video camera system is an imaging system used for shooting with a broadcast television camera, as in the first embodiment.

  As shown in FIG. 5, the video camera system 100 of the present embodiment has the same configuration as the video camera system 1 of the first embodiment described above, and includes a television camera 110, an image processing unit 118, and an operation unit 120. And so on.

  In addition, about the member similar to the video camera system 1 of 1st Embodiment, the last two digits of a code | symbol shall be made the same and detailed description shall be abbreviate | omitted.

  The image formed by the photographing lens of the lens device 114 attached to the lens mount of the camera body 112 is subjected to photoelectric conversion by the image sensor, and then subjected to necessary signal processing by a signal processing circuit to be an HDTV video signal. (HDTV signal) is output to the outside from the video signal output terminal of the camera body 112 or the like.

  The HDTV signal output from the camera body 112 is converted (down-converted) into a standard television (NTSC) video signal (SDTV signal) by the down converter 128 and input to the image processing unit 118. Yes.

  The image processing unit 118 performs feature determination on the subject in the captured subject image, and when it matches a pre-registered feature, the image processing unit 118 sends a signal from the serial communication interface 130b to the electric pan head device 122 to select the subject. In addition to tracking, the AF unit 126 is driven via the serial communication interfaces 130a and 126a to perform autofocus control, and recording of the subject image is started by the recording device 113.

  The image processing unit 118 includes blocks for performing each process on separate boards, and includes a main board 130, a feature determination processing calculation board 152, and a feature determination data card 154.

  The main board 130 includes a decoder (A / D converter) 136, a CPU 138, a RAM 140, and a superimposer 142. The main board 130 has serial communication interfaces 130a and 130b. As described above, the serial communication interface 130a performs data communication with the serial communication interface 126a of the AF unit 126 of the lens device 114. Further, the serial communication interface 130 b sends a control signal to the electric head device 122.

  As described above, the HDTV signal output from the camera body 112 is converted into the SDTV signal by the down converter 128 and input to the image processing unit 118. The decoder (A / D converter) 136 converts the SDTV signal into the SDTV signal. The converted analog data video signal is converted into digital data for feature determination processing in the image processing unit 118.

  The CPU 138 controls the entire image processing unit 118. In addition, the CPU 138 calls out the features such as the color and shape of the subject and the information associated therewith previously registered in the memory (storage device) from the memory to be used at the time of shooting, and expands them in the memory RAM 140 in the system. To do.

  In addition, the superimposer 142 is for displaying information related to registered features and the like on an image displayed on the display screen of the operation unit 120 described later.

  The feature determination processing calculation board 152 includes a CPU 152a that executes feature determination processing and a VRAM 152b that holds an image for display.

  The operation unit 120 includes an LCD (liquid crystal display screen) with a touch panel, and data displayed on the LCD display screen is an NTSC / PAL (composite) signal.

  An operator (cameraman) selects a mode on the touch panel display screen of the operation unit 120. The mode includes a mode for calling a registered feature and a mode for tracking a matched object by determining a feature of a shooting target.

  The feature determination on the feature determination processing calculation board 152 is performed by a known image processing technique. Feature determination is performed by extracting features from the imaged subject and comparing them with registered features.

  Next, the operation of this embodiment will be described.

  FIG. 6 is a flowchart showing the operation of the present embodiment.

  First, in step S300 in FIG. 6, the operator (photographer) selects a mode using the touch panel-equipped LCD of the operation unit 120. Here, it is assumed that a feature tracking mode for tracking a moving subject having a predetermined feature is selected. This is because when the operator designates a feature that should be tracked from feature data registered in advance and the user performs shooting, the feature of the moving subject 150 (see FIG. 5) is selected as feature data. Are recorded while tracking the subject 150 automatically.

  Next, in step S310, the moving subject 150 (see FIG. 5) is photographed. The photographed image of the subject 150 is output from the camera body 112, converted by the down converter 128, and input to the image processing unit 118.

  In step S320, feature determination processing is performed. The image of the subject 150 is sent to the feature determination processing calculation board 152 together with the selected feature data developed in the RAM 140 and the data of the feature determination data card 154 to be subjected to feature determination processing.

  As a result, if it is determined in step S330 that the feature of the photographed subject 150 matches the selected data indicating the pre-registered feature, the subject 150 is recorded in the next step S340. Be started. At this time, the camera body 112 and the tally lamps 112a and 114a of the lens device 114 are turned on. Thereby, it is notified that the result of the feature determination is coincident and the recording is started.

  On the display screen of the operation unit 120, information or the like registered in advance for the recorded subject 150 is added to the image as character information by the superimposer 142 and displayed.

  If it is determined that the feature of the subject 150 photographed at this time matches the selected data indicating the pre-registered feature, the matched subject is linked with pan / tilt, focus, and zoom. Recording may be started after confirming the matching accuracy in the feature determination by increasing the size of 150 so as to be an appropriate size.

  In step S330, if they do not match as a result of the feature determination, the process returns to step S310 to continue shooting the subject 150.

  In this way, when the moving subject is photographed and the feature determination is performed, if the feature matches the registered feature, the operation of recording the subject image is repeated.

  Here, for example, by specifying the color yellow and the shape of the butterfly, only the yellow butterfly can be photographed and recorded. In addition, among the yellow butterflies, if the features of the crested yellow butterfly are specified, only the crested yellow butterfly can be photographed and recorded.

  Next, another example of control in the present embodiment will be described.

  FIG. 7 shows a control flow in this case.

  First, in step S400 of FIG. 7, the operator selects a mode. Here, as before, it is assumed that the feature tracking mode for tracking a moving subject having a predetermined feature is selected. However, the tracking mode in this case is different from the feature tracking mode in FIG. 6 described above, and does not track and record a subject having a feature that matches the feature selected from the feature data registered in advance by the operator. Those that match the selected feature are not recorded, but instead those that do not match the selected feature are tracked.

  This is the case, for example, where a butterfly other than yellow is photographed and recorded by designating features with a yellow color and a butterfly shape.

  In step S410, the moving subject 150 is photographed. In the next step S420, features are extracted from the subject 150 in the shooting screen, and feature determination processing is performed. As a result, if it is determined in step S430 that the feature of the photographed subject 150 does not match the selected data indicating the pre-registered feature, recording of the subject 150 is performed in the next step S440. Is started. At this time, the camera body 112 and the tally lamps 112a and 114a of the lens device 114 are turned on. Thereby, it is notified that the recording is started without the result of the feature determination being coincident.

  If the feature of the photographed subject 150 matches the selected feature in step S430, recording is not performed and the procedure returns to step S410 to continue photographing.

  In this way, recording is not performed when the feature of the photographed subject matches the registered feature, but recording is started only when the feature does not match, thereby avoiding recording of a subject having a certain feature. In addition, efficient recording is possible by recording only what really needs to be recorded.

  Of course, in this case as well, when recording a subject having a feature that does not match the feature registered in step S440, the size of the subject to be recorded becomes an appropriate size by automatically interlocking pan / tilt and zoom. It is preferable to do so.

  In each of the embodiments described above, the accuracy of face authentication or feature determination is improved by automatically linking pan / tilt and zoom so that the size of the subject becomes an appropriate size. Instead of these, or together with these methods, the frame rate may be checked at a high speed or the high pixel mode may be checked.

  As described above, in any of the embodiments, a conventional video camera system having a feature determination function (or particularly a face authentication function) as an imaging system used for shooting with a broadcast television camera can be configured in a compact manner. Without taking a large-scale configuration via a network such as a security system, only a subject image having a predetermined feature or a subject image having a predetermined feature is photographed at a desired angle and size with a simple configuration. Or record.

  The video camera system having the feature determination function of the present invention has been described in detail above. However, the present invention is not limited to the above examples, and various improvements and modifications can be made without departing from the gist of the present invention. Of course you can go.

It is the block diagram which showed the whole structure of the video camera system provided with the face authentication function as a feature determination function based on this invention. It is explanatory drawing which shows the example of a display of the display screen comprised with LCD with a touch panel of an operation part. It is a flowchart which shows the effect | action of 1st Embodiment. It is a flowchart which shows the flow of other control of 1st Embodiment. It is the block diagram which showed the whole structure of the video camera system provided with the characteristic determination function which concerns on the 2nd Embodiment of this invention. It is a flowchart which shows the effect | action of 2nd Embodiment. It is a flowchart which shows the flow of other control of 2nd Embodiment.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 ... Video camera system of 1st Embodiment, 10 ... Television camera, 12 ... Camera body, 14 ... Lens apparatus, 16 ... Subject, 18 ... Image processing unit, 20 ... Operation part, 22 ... Pan head, 23 ... (cloud Damper, 24 ... Shooting lens, 26 ... AF unit, 30 ... Main board, 32 ... Authentication processing calculation board, 34 ... Face authentication data card, 36 ... Decoder, 38 ... CPU, 40 ... RAM, 42 ... Super-in Poza

Claims (7)

Imaging means for imaging a subject image formed by an optical system;
Storage means in which face image data of the person to be photographed is registered in advance;
Feature determination means for performing feature determination of the subject by performing face authentication of a face image of the subject imaged by the imaging means and a face image registered in advance in the storage means;
Recording means for recording the imaged subject image,
When the face image of the photographed subject matches the pre-registered face image by the face authentication during the photographing of the subject image by the imaging means, the recording means starts recording the subject image. A video camera system having a feature determination function.   The video camera system having the feature determination function according to claim 1, wherein the face image of the imaged subject is registered in advance by the face authentication during imaging of the subject image by the imaging unit. When the face image matches the recorded face image, instead of recording the subject image by the recording means or together with the recording, the pan / tilt and zoom are automatically linked so that the size of the authenticated face image is appropriate. A video camera system equipped with a feature determination function characterized by having a large size. Imaging means for imaging a subject image formed by an optical system;
Storage means in which face image data of the person to be photographed is registered in advance;
Feature determination means for performing feature determination of the subject by performing face authentication of a face image of the subject imaged by the imaging means and a face image registered in advance in the storage means;
Recording means for recording the imaged subject image,
If the face image of the photographed subject matches the pre-registered face image by the face authentication while the subject image is being captured by the image capturing unit, the recording unit records the subject image. A video camera system having a feature determination function characterized by not starting. Imaging means for imaging a subject image formed by an optical system;
Storage means in which feature data of the object to be photographed is registered in advance;
A feature determination unit that determines whether or not the feature of the moving subject imaged by the imaging unit matches the feature registered in advance in the storage unit;
Recording means for recording the imaged subject image,
During imaging of a subject image by the imaging means, the recording means starts recording of the subject image when the characteristics of the captured subject coincide with the pre-registered characteristics by the feature determination. A video camera system with a feature determination function.   5. The video camera system having the feature determination function according to claim 4, further comprising: registering the feature of the imaged subject and the pre-registered by the feature determination during imaging of the subject image by the imaging unit. When the feature matches, the panning / tilting and zooming are automatically linked so that the size of the subject image subjected to the feature determination becomes an appropriate size and the accuracy of the feature determination is improved and confirmed. A video camera system having a feature determination function, wherein recording of the subject image is started by the recording means. Imaging means for imaging a subject image formed by an optical system;
Storage means in which feature data of the object to be photographed is registered in advance;
A feature determination unit that determines whether or not the feature of the moving subject imaged by the imaging unit matches the feature registered in advance in the storage unit;
Recording means for recording the imaged subject image,
During imaging of a subject image by the imaging unit, the recording unit starts recording the subject image when the feature determination does not match the pre-registered feature with the feature determination. A video camera system with a feature determination function.   7. A video camera system having a feature determination function according to claim 4, wherein the feature is a color and shape of the subject. .

Images