JPH10336632A - Monitoring device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a monitoring device capable of easily recording face images important for establishing an individual. SOLUTION: This device is provided with a camera 1 for monitoring for picking up the images of the entire monitoring area and the camera 2 for close-up for picking up the image of the face part of a person in the close-up. The movement of the person is detected in a motion vector detection circuit 4 based on the images of the camera for monitoring, and corresponding to the motion vector, a control circuit 7 switches a signal switching circuit 5 and records the images from the camera 2 for the close-up in an image recording part 6.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a monitoring device suitable for being installed in a convenience store or a bank.

[0002]

2. Description of the Related Art In convenience stores and banks,
A surveillance video camera is installed for crime prevention, and images taken by the video camera are recorded on a video device and used for criminal investigation.

[0003]

However, in the conventional apparatus, since the entire surveillance area is imaged and recorded, the criminal's face recorded on the video apparatus can be sufficiently recognized in the event of a crime or the like. In some cases, it was not possible.

[0004] In addition, even when almost nobody is present, such as at night, the video is always recorded on the video device, so that the amount of video tapes and the like becomes enormous, and it takes time to perform a search later.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned conventional problems, and has as its object to provide a monitoring apparatus capable of easily recording a face image important for personal identification.

A monitoring device according to the present invention comprises:
When a surveillance camera captures an image of a monitoring area and detects movement of an object in the monitoring area, at least a moving object portion is captured.

[0006] It is preferable that the object part is imaged in close-up.

Further, the surveillance device according to the present invention includes a surveillance camera for photographing the entire surveillance area and a close-up camera for photographing a part of the surveillance area in a close-up manner. Upon detection, an image from the close-up camera is output.

According to the above-described configuration, when a movement is detected due to a movement or the like of a person in the monitoring area, the moved part is given as data, so that an object such as a person can be easily specified. In particular, when a close-up image is taken, the identification becomes easier.

[0009] It is preferable that a recording means for recording an image in the monitoring area is provided, and when a movement of an object in the monitoring area is detected, an image to be given to the recording means is switched.

[0010] By recording the close-up person or the like on the recording means, it is possible to easily specify the person or the like when searching later.

Further, it is preferable that the detection of the motion is recorded together with the image.

[0012] By recording the detection of the motion together with the image, the search can be easily performed.

[0013] Further, the recording means may be configured so that the reproduction of an image of a part having a movement from the recording means is slower than the reproduction speed of another part.

The search time can be shortened by reproducing the portion other than the portion having motion at a high speed.

Further, it is possible to provide a recording means for recording an image in the monitoring area, and to record the image on the recording means only when a movement of an object in the monitoring area is detected.

Recording by motion extraction can save recording capacity.

[0017]

Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 is a functional block diagram showing a monitoring device according to a first embodiment of the present invention. As shown in FIG. 1, a surveillance video camera 1 for imaging one or a plurality of whole areas is arranged in a surveillance area such as an entrance or a store,
The surveillance area is monitored by the surveillance video camera 1. Further, a close-up video camera 2 for taking a close-up image of the face of an individual is arranged. The close-up video camera 2 is moved up and down, left and right by a pan / tilt driving device 3 so that the close-up video camera 2 is aimed at an imaging target portion. The close-up video camera 2 has an auto-focus function, and is configured to be able to output an imaging target as clear image data.

Image data from the monitoring video camera 1 and the close-up video camera 2 are sent to a recording unit 6 such as a video device via a signal switching circuit 5.

Further, the image data from the surveillance video camera 1 is given to a motion vector detection circuit 4.

The motion vector detection circuit 2 overlaps the current image and an image after a predetermined frame (for example, one frame after) by a vector amount within the detection range, based on the image data supplied from the surveillance video camera 1. This is to detect a motion vector from a shift amount when they are overlapped in view of the condition. As a method of detecting a motion vector, an all-point matching method, a representative point matching method, or the like is used. For example, when the representative point matching method is used, attention is paid to some pixels on the screen of the surveillance area provided from the surveillance video camera 1, that is, representative points, and a motion vector is determined from these pixels. As shown in FIG. 3, the luminance level of the representative point of the current frame is written into the memory, and the luminance levels are compared with the pixels (1) to (9) within the detection range one frame later. Among them, it is determined that the representative point has moved to the position of the pixel having the closest level, and the difference between this point and the representative point is calculated as a motion vector.

The output from the motion vector detecting circuit 4 is given to a control circuit 7 composed of a microcomputer or the like. The control circuit 7 determines whether or not a person has moved into the monitoring area based on the output of the motion vector detection circuit 4, and controls the driving of the pan / tilt driving device 3, the close-up video camera 2 and the signal switching circuit 5. Is what you do.

As described above, the surveillance video camera 1 monitors the inside of the surveillance area, and when a person moves within the surveillance area, the motion vector detection circuit 4 calculates and outputs a motion vector. The control circuit 7 determines whether or not a person has moved in accordance with the motion vector from the motion vector detection circuit 4, and if it determines that a person has entered the monitoring area, closes up image data to be supplied to the recording unit 6. Switching to the image data from the video camera 2. That is, when no person moves in the monitoring area, the image data from the monitoring camera 1 is given to the recording unit 6, and an image of the entire monitoring area is recorded.

When the control circuit 7 determines that the person has moved in accordance with the motion vector from the motion vector detection circuit 4, the control circuit 7 operates the pan / tilt driving device 3 to move the close-up video camera 2 to the position where the person is. Turn to. Since the data of the entire monitoring area is given to the motion vector detection circuit 4 by the monitoring camera 1 based on this data, the control circuit 7 predicts the position of the person and performs close-up. The video camera 2 for use. Then, the close-up video camera 2 is operated to make the face of the person close-up and record the image on the recording unit 6. This close-up image may be controlled so as to be recorded for a predetermined time, or it may be controlled so that the camera 2 is moved and recorded so as to follow while the person is moving. Further, when recording image data for close-up, a flag or the like may be recorded at the same time so that the image to be recorded can be distinguished from the entire video so as to be convenient for later search.

When the output of the motion vector from the motion vector detection circuit 4 is not supplied to the control circuit 7, that is, when no person is present in the monitoring area, the control circuit 7 outputs the image data from the monitoring camera 1 for the whole observation. The signal switching circuit 5 is switched so as to be given to the recording unit 6.

As described above, the surveillance video camera 1 monitors the inside of the surveillance area. When a person moves within the surveillance area, the close-up video camera 2
Since the face portion of the individual imaged at is clearly recorded, the individual can be easily fixed.

FIG. 2 is a functional block diagram showing a monitoring device according to a second embodiment of the present invention. The embodiment shown in FIG. 2 is configured so that one video camera 1a captures an image of the entire monitoring area and a close-up of a face. Therefore, this video camera 1a
Has a zoom function.

A video camera 1a having the above-mentioned zoom function is arranged in the surveillance area, and the surveillance area is monitored by setting the zoom of the video camera 1a to a wide angle. And
The video camera 1a is provided with a pan / tilt driving device 3 for pointing the video camera 1a toward a person at the time of close-up. The pan / tilt driving device moves the video camera 1a vertically and horizontally. The video camera 1a is pointed at the imaging target portion. Further, the video camera 1a has an autofocus function, and is configured to be able to output an imaging target as clear image data.

The image data from the video camera 1a is sent to a recording unit 6 such as a video device and recorded.

Further, the image data from the video camera 1a is supplied to the motion vector detecting circuit 4 in the same manner as in the above-described embodiment.
Given to.

The motion vector detection circuit 4 shifts the current image and the image after a predetermined frame (for example, one frame after) by an amount of vector within the detection range to determine the degree of overlap with the image data supplied from the video camera 1a. A motion vector is detected based on the shift amount when the images overlap.

The output from the motion vector detecting circuit 4 is given to a control circuit 7 composed of a microcomputer or the like. The control circuit 7 determines whether or not a person has moved into the monitoring area based on the output of the motion vector detection circuit 4, and performs drive control of the pan / tilt drive circuit 3 and the zoom mechanism of the video camera 1a. .

As described above, the monitoring area is monitored by the video camera 1a, and when a person moves within the monitoring area, the motion vector detection circuit 4 calculates and outputs a motion vector. The control circuit 7 determines whether or not a person has moved in accordance with the motion vector from the motion vector detection circuit 4, and if it determines that a person has entered the monitoring area, operates the pan / tilt driving device 3 to perform video The user turns the camera 1a to the position where the person is, closes up the face of the person by the zoom function, and records the image on the recording unit 6 for a predetermined time. Further, when recording the close-up image data for convenient later search, a flag or the like may be recorded at the same time so that the recorded image can be distinguished from the entire image.

When the output of the motion vector from the motion vector detection circuit 4 is no longer given to the control circuit 7, that is, when there are no more people in the monitoring area, the control circuit 7 controls the video camera 1a to record a video signal for the entire observation. Then, the zoom mechanism and the pan / tilt driving device 3 are operated so as to be supplied to the control unit 6.

As described above, one video camera 1a
When a person in the monitoring area moves and the person moves in the monitoring area, a close-up of the face of the individual taken and imaged by the zoom mechanism is clearly recorded on the recording unit 6.
Individuals can be easily fixed.

In both of the above-described embodiments, the image of the entire monitoring area and the close-up image are switched and recorded by the recording unit 6. , That is, only the video when the motion vector is output from the motion detection circuit 4 may be recorded.

The output of the image from the recording unit 7 includes a flag so that a close-up image, that is, an image when there is a motion, can be identified as in the above embodiment. When recording, if the flag is not detected, the reproduction is performed at high speed, and if the flag is detected, the reproduction is performed at standard or low speed, so that the search can be performed very easily.

When no flag or the like is recorded, a motion detecting circuit is provided in the recording / reproducing apparatus. When the motion detecting circuit does not output a motion vector, the motion vector is reproduced at a high speed. When output, it may be configured to reproduce at standard or low speed. In addition, in the case of such a configuration, the first frame in which a motion has occurred cannot be played back at standard or low speed, but
Since a frame is 1/60 second, there is no problem even if one frame cannot be reproduced by standard or the like.

[0039]

As described above, according to the present invention, when there is a movement of a person or the like, the portion can be recorded in close-up, so that the individual can be easily fixed.

[Brief description of the drawings]

FIG. 1 is a functional block diagram showing a monitoring device according to a first embodiment of the present invention.

FIG. 2 is a functional block diagram illustrating a monitoring device according to a second embodiment of the present invention.

FIG. 3 is a schematic diagram illustrating the concept of a motion vector detection device.

[Explanation of symbols]

 REFERENCE SIGNS LIST 1 surveillance video camera 2 close-up video camera 3 pan / tilt driving device 4 motion vector detection circuit 5 signal switching circuit 6 recording unit 7 control circuit

Claims (7)

[Claims] An image of a surveillance area is taken by a surveillance camera,
A monitoring apparatus characterized in that, when a movement of an object in the monitoring area is detected, at least an image of a moving object portion is taken. 2. The monitoring apparatus according to claim 1, wherein the object is magnified and imaged. 3. A monitoring camera for capturing an image of the entire monitoring area, and a close-up camera for capturing a portion of the monitoring area in a close-up manner. A monitoring device that outputs an image of the subject. 4. The image processing apparatus according to claim 1, further comprising recording means for recording an image in the surveillance area, wherein when a movement of an object in the surveillance area is detected, an image to be supplied to the recording means is switched. The monitoring device as described. 5. The monitoring device according to claim 4, wherein the detection of the movement is recorded together with the image. 6. The monitoring apparatus according to claim 4, wherein said recording means makes the reproduction of an image of a part having a movement from the recording means slower than a reproduction speed of another part. 7. The recording device according to claim 1, further comprising a recording unit that records an image in the monitoring area, wherein the recording unit records the image only when a movement of an object in the monitoring area is detected. A monitoring device according to any one of the above.