JP2012124773A - Monitoring system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To solve the problem that a monitoring system for monitoring an object entering a target monitoring region by using a photographing apparatus is often installed at a place where it is usually rare for people to enter, especially such as an off-limits area; however, it is necessary to periodically confirm an operating status of the system, and a large labor is needed to actually confirm the operating status.SOLUTION: A synthetic image in which an object is virtually recognizable as entering an input image is created by synthesizing a virtual object image created by a test image creating device into an input image photographed by a photographing apparatus. During test, the synthetic image is inputted to an object detection device, instead of the image obtained by the photographing apparatus, and coordinate information of a position at which the virtual object of the synthetic image is synthesized, and coordinate information of a position detected by the object detection device are compared with each other. From the result thereof, a monitoring system automatically determines whether or not the operation of the object detection device is normal.

Description

  The present invention relates to a monitoring system for monitoring an area to be monitored, and relates to a monitoring system capable of confirming the operating state of the monitoring system.

  In recent years, the development of intruder detection technology by image processing has been remarkable. When a monitoring system that detects intruders by image processing is installed in a prohibited area such as an important facility, an intruding object in the prohibited area is automatically detected by the set monitoring system, and monitoring personnel and system management are detected. Information about the detected intruding object can be immediately transmitted to the person. In particular, an excellent monitoring system can detect only an intruding object accurately with few false detections such as environmental noises being mistaken for an intruding object.

JP 2001-175860 A

In the conventional monitoring system described above, people do not always enter frequently depending on the installation environment of the monitoring system, such as a prohibited area of an important facility. Even if the monitoring system is normal, there may be no reports for a long time. For this reason, it is necessary to periodically check whether the monitoring system is operating normally or whether the operation is abnormal for some reason (a state in which an event to be monitored is not issued). However, the confirmation test to be carried out is a very complicated task, and the restricted entry areas where the monitoring system is installed are often remote areas or dangerous areas, making it difficult to carry out the confirmation test itself. It can be.
The present invention provides a means for automatically confirming the operating state of the monitoring system, automating the confirmation test and reducing the burden on the system administrator and monitoring personnel, thereby enabling more efficient system operation. It aims to be.

  In order to achieve the above object, a monitoring imaging device that images a monitoring area and outputs a monitoring image, and processes the monitoring image, extracts an intruding object from the monitoring image, and detects an intruding object in the monitoring area And a test video generation device that records a predetermined pseudo object image and a condition for an operation check test of the object detection device and outputs the condition to the object detection device. The detection device, when the pseudo object image and the operation check test conditions are input from the test video generation device, synthesizes the input pseudo object image with the monitoring video input from the monitoring imaging device. Then, the synthesized video is image-processed to detect an intruding object in the monitoring area from the video, and the detected information is output to the test video generation device, Body detector, the detected information to determine whether or not the pseudo object, if the pseudo object monitoring system is intended to ensure that in normal operation.

  In the monitoring system of the above invention, the pseudo image includes instruction means for a system administrator to set detection information such as a moving speed, an intrusion route, a color, a contrast, an appearance position, and an exit position of the pseudo image. According to the means, the test video generation device generates a composite video and automatically performs an operation check test of the monitoring system.

  According to the present invention, according to the conditions of the system operation check test predetermined by the system administrator or the supervisor, a composite image in which a pseudo intruding object appears automatically is generated, and the generated composite image A confirmation test of the operation of the monitoring system and the object detection device can be easily realized. For this reason, it is possible to greatly reduce the maintenance and inspection loads on the system administrator and the monitoring staff of the monitoring system, and it is possible to operate the system more efficiently.

It is a block diagram which shows the structure of one Example of the monitoring system of this invention. It is a figure which shows an example of the input image | video in one Example of the monitoring system of this invention. It is a figure which shows an example of the monitoring area | region setting in one Example of the monitoring system of this invention. It is a figure which shows an example of the output image in one Example of the monitoring system of this invention. It is a figure which shows an example of the list of the test items implemented in one Example of the monitoring system of this invention. It is a figure which shows an example of the pseudo | simulation object image used in one Example of the monitoring system of this invention. It is a figure which shows an example of the setting in one Example of the monitoring system of this invention. It is a figure of an example of the synthetic | combination image | video of the input image | video and the pseudo object image in one Example of the monitoring system of this invention. It is a figure for demonstrating an example of the synthetic | combination video generation method in one Example of the monitoring system of this invention.

  The monitoring system of the present invention extracts an object in the monitoring area by processing an image captured by the imaging apparatus and an image captured by the imaging apparatus, and determines whether or not the extracted object is a target to be detected. An object detection device for detecting an object in the monitoring region, a test video generation device for confirming the operation of the object detection device, a setting device for adjusting parameters of the object detection device and the test video generation device, and an object detection device A test system that includes a display device that displays an output image based on the detection result of the image, and the test video generation device automatically generates a video image captured by the imaging device and a predetermined pseudo intruder image. Combining means for combining, output means for outputting the combined video to the object detecting device, and object detection results when the combined video is input to the object detecting device and information for confirming the operation of the monitoring system Those having a recording output means for recording and outputs Te.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In addition, the following description is for describing one embodiment of the present invention, and does not limit the scope of the present invention. Accordingly, those skilled in the art can employ embodiments in which these elements or all of the elements are replaced with equivalent ones, and these embodiments are also included in the scope of the present invention.
In the description of each figure, components having the same functions are denoted by the same reference numerals, and description thereof is omitted as much as possible to avoid duplication.

The configuration of an embodiment of the monitoring system of the present invention will be described with reference to FIG. FIG. 1 is a block diagram showing the configuration of an embodiment of the monitoring system of the present invention. Reference numeral 100 denotes a monitoring system of the present invention, 101 denotes an imaging device, 112 denotes an object detection device, 130 denotes a test video generation device, 109 denotes an instruction device, 110 denotes an alarm output device, and 111 denotes a display output device. In the object detection device 122, 102 is a video input circuit, 103 is an image processor, 104 is a program memory, 105 is a work memory, 106 is an external IF (Interface) circuit, 107 is a video output circuit, and 108 is a data bus. . In the test video generation apparatus 130, 132 is a video input circuit, 133 is an image processor, 134 is a program memory, 135 is a work memory, 136 is an external IF circuit, 137 is a video output circuit, and 138 is a data bus.
The test video generation device 130 does not necessarily have the same configuration as that of the object detection device 112. For example, the test video generation device 130 may be included in each component of the object detection device 112 as one function.

  In the monitoring system 100 of FIG. 1, the imaging apparatus 101 captures an area to be monitored (monitoring area), and the captured video 201 (see FIG. 2 described later) is transferred to the work memory via the video input circuit 102. 105. The image processor 103 processes the input video recorded in the work memory 105 according to the program recorded in the program memory 104, and outputs the processing result to the display device 111 via the video output circuit 107 for display. It is displayed on the device 111. The image processor 103 outputs an alarm signal to the alarm output device 110 via the external IF circuit 106 when the image processor 103 determines that the alarm should be issued as a result of the image processing. Issues an alarm based on the alarm signal.

  Also, the image processor 103 processes the input video while changing or correcting the parameters of the program based on an instruction input via the external IF circuit 106. The video input circuit 102, the image processor 103, the program memory 104, the work memory 105, the external IF circuit 106, and the video output circuit 107 are connected to the data bus 108. The instruction input via the external IF circuit 106 is operated by an operator (user or administrator) using an instruction device 109 such as a mouse or a keyboard.

  The basic operation and image processing algorithm of the object detection apparatus 112 having the above-described device configuration can be realized by using a well-known technique (see, for example, Japanese Patent Application Laid-Open Nos. 2008-176768 and 2006-212696). ).

  FIG. 2 shows an example of the input video 201 captured by the imaging device 101. It is a figure which shows an example of the input image | video in one Example of the monitoring system of this invention. FIG. 3 shows an example of the monitoring area 301 input by the administrator of the monitoring system using the pointing device. FIG. 3 is a diagram showing an example of monitoring area setting in an embodiment of the monitoring system of the present invention. FIG. 4 is a diagram showing an example of an output image in one embodiment of the monitoring system of the present invention. 201 is an input image, 301 is a monitoring area, 401 is an intruder, 402 is a rectangle, and 403 is a trajectory.

For example, as shown in FIG. 4, when an intruder 401 enters the monitoring area 301, the intruder 401 is detected by the monitoring system of the present invention, a rectangle 402 and a trajectory 403 are displayed, and an alarm is issued. .
In the test video generation device 130, the work memory 135 stores the conditions of the operation check test of the image processing system 100 or the object detection device 112 set in advance through the instruction device 109 by the system administrator (or a supervisor), and the test video parameters. 139 has means for receiving and recording through the external IF circuit 136. In addition, the work memory 135 uses a program recorded in the image processor 133 and the program memory 134 in a video input from the imaging apparatus 101 via the video input circuit 132 in accordance with the recorded test video parameter 139 according to a program. Means for automatically synthesizing. The work memory 135 has means for outputting the generated composite video to the object detection device 112 via the video output circuit 137. Furthermore, the work memory 135 has means for receiving presence / absence of object detection in the object detection device 112 and coordinate information of the detected object via the external IF circuit 136.

FIG. 5 is a diagram showing an example of a list of test items implemented in an embodiment of the monitoring system of the present invention. FIG. 6 is a diagram showing an example of a pseudo object image used in an embodiment of the monitoring system of the present invention. FIG. 7 is a diagram showing an example of settings in an embodiment of the monitoring system of the present invention.
Here, for example, for an operation confirmation test of the object detection device 112 of the monitoring system 100, an administrator enters the monitoring area from an intrusion route according to a predetermined test item list 501 from 9:00 am every Tuesday. Confirm that the monitoring system is operating normally by detecting the object correctly. That is, if an intruding object from the intrusion routes 701, 702, 703 to the monitoring area 301 shown in FIG. 7 can be correctly detected according to the test item list 501 shown in FIG. 5, the normal operation of the monitoring system can be confirmed.
In this case, first, the administrator inputs the conditions related to the test as the test video parameters 139 to the test video generation device 130 by the instruction device 109. The test video parameters 139 are at least the moving speed of the intruding object, the intrusion route, the number of trials, and the behavior under the conditions shown in the test item list 501.

  In the test video generation device 130, image information to be combined with the input video as a pseudo intruding object is recorded in advance. FIG. 6 shows an example of the pseudo object image 601. The pseudo object image 601 may be a still image or a moving image. In addition, the administrator can input a condition related to the image 601 (feature of the pseudo object image 601) as the test video parameter 139 to the test video generation device 130 using the instruction device 109. For example, the height, clothes (color), intrusion route, appearance position, exit position, movement speed, movement direction, and the like may be freely set for the pseudo object image 601. Further, the pseudo object image is not necessarily an upright person like the pseudo object image 601, and may be, for example, a person moving forward, a bicycle, a car, or the like according to a predetermined test item.

FIG. 8 shows an example of a composite video 801 of an input video and a pseudo object image. FIG. 8 is a diagram showing an example of a composite video of an input video and a pseudo object image in an embodiment of the monitoring system of the present invention. The composite image 801 here is an example when the pseudo object image 601 enters through walking through the intrusion route 702.
FIG. 9 shows an example of a method for generating the composite video 801. FIG. 9 is a diagram for explaining an example of a composite video generation method in an embodiment of the monitoring system of the present invention.
The image processor 133 in the test video generation device 130 includes, as the test video parameters 139, the size of the pseudo object image input in advance, the velocity vector, the intrusion route (start point, end point), camera parameters 902, and test video start. Based on the elapsed time 903, coordinate information 904 of the size and the position of the pseudo object image 601 in the pixel unit at the current time (current frame) is calculated.

At this time, the coordinate information 904 of the position is calculated by converting from the meter unit to the pixel unit.
In this case, a parameter (region parameter) indicating in which region of the monitoring video to be captured the position of the pseudo object image 601 is set, and the position of the object (for example, the installation position) is in that region. Determine whether or not. In addition, the range (size parameter) of the size of the object to be detected is designated. In order to set the pseudo object image 601, for example, an input image is displayed on the display output device 110, and a polygon vertex is set on the display screen using the pointing device 109 such as a mouse. Specify the area.
Then, the image processor 133 scales and scales the pseudo object image 601 according to the coordinate information 904 of the position in units of pixels. Next, the scaled pseudo object image 905 is synthesized with a position 901 according to the coordinate information 904 of the current input video 301 to obtain a synthesized video 801. That is, the pseudo object image 601 calculates the position and size in units of pixels according to the distance from the imaging device 101 based on the camera parameters input in advance, converts the size of the pseudo object image 601, A scaled pseudo object image 905 is obtained and synthesized.
As a result, the size in meters can be made unchanged according to the distance from the imaging device 101.

  The position, size, and speed of the pseudo object image 905 in units of pixels are updated every frame. Note that the size and speed of the pseudo object image 905 may have a variable width in order to approximate the movement of the real object. For example, information on the size and speed corresponding to the elapsed time 903 is stored in the test video parameter 139. In addition, every frame may be changed.

The video input circuit 102 of the object detection circuit 112 is connected to the imaging device 101 and the video output circuit 137 of the test video generation device 130. However, when the test video generation device 130 generates the composite video 801, the composite video 801 from the test video generation device 130 has priority over the direct input video from the imaging device 101 and is input to the object detection device 112.
In addition, when the composite video 801 is not generated, the video input circuit 102 of the object detection device 112 is given priority to the input video 201 from the imaging device 101 and is input to the object detection device 112.
These determinations may be performed by either the object detection device 112 or the test video generation device 130.

Further, in the system operation check test in the monitoring system of the present invention, coordinate information 904 relating to the size and position obtained by combining the pseudo object 601 in the input video by the test video generation device 130 is recorded in the work memory 135.
More preferably, when the composite image 801 is input to the object detection device 112, if the object detection device 112 detects any object, the coordinate information of the detected object is passed through the external IF circuit 106 to the test video generation device 130. Automatically output. The test video generation device 130 compares the coordinate information 904 when the pseudo object image 905 is synthesized with the coordinate information of the detected object output from the object detection device 112, and the coordinate information when the pseudo object image 905 is synthesized. On the other hand, when the coordinate information of the detected object exists within the predetermined area range, the notification by the object detection device 112 is determined to be the pseudo object image 905. If not, the test video generation device 130 determines that the notification by the object detection device 112 is from a true intruder or a pseudo object image 905.
The test video generation device 130 records an image obtained by previously synthesizing the pseudo object 601 generated by the test video generation device 130 with the video captured by the imaging device 101. In the system operation check test, the composite video 801 is input. The synthesized video 801 synthesized in advance may be recorded in the work memory 135.

In the test video generation device 130, for example, the coordinates of the pseudo object image 601 are (320, 220) to (350, 300), and the coordinate information of the detected object is (330, 210) to (350, 295). In this case, since the overlapping rate of the rectangles described by the coordinates exceeds 80%, for example, it is determined that the notification by the object detection device 112 is due to a pseudo object, and a test using a composite image is performed in the work memory 135. Record success. That is, the test video generation device 130 determines that the object detection operation is normal as a result of the operation check test of the object detection device 112.
In addition, when the composite image of the pseudo object is input to the object detection device 112, it cannot be determined that the object detection device has detected the pseudo object (the overlapping rate of the rectangles described by each coordinate is 80%, for example) For example, when no object is detected, it is recorded in the work memory 135 that the test using the synthesized video has failed.

For example, when all the test item lists shown in FIG. 5 are executed, the total number of trials of the operation check test using the composite video is 60 times, and the success / failure information for 60 times is recorded in the work memory 135. Here, for example, when the judgment condition for determining that the object detection device is operating normally in the test using the composite video is 55 times out of 60 times, when the success number is less than 55 times, Warning that there is an abnormality in the monitoring system.
The information on the success or failure of the test is recorded as a log so that the administrator can view and download it.
Note that if it is confirmed that the notification by the object detection device 112 is due to the pseudo object 601, the alarm output device 110 may not issue the alarm notifying that the intruding object has been found because it is redundant. .
Also, a schedule for executing the confirmation test may be recorded in advance in the test video generation device, and the automatically designated confirmation test may be executed when the date or time corresponding to the schedule is reached.

  According to the above embodiment, in the monitoring system, it is possible to automatically determine whether the operation of the object detection device is normal, and it is possible to regularly check the system operation state. In some cases or in remote areas, the operating state can be easily confirmed without stopping the system. It is especially suitable for surveillance systems installed in places where people are not likely to enter, such as restricted areas.

Also, the video output by the test video generation device 130 is not necessarily limited to the composite video of the input video and the pseudo object. For example, when the object detection device has a function of determining an abnormality of the input video for detecting a failure of the imaging device 101, an abnormal video such as a color bar image or a white noise image is intentionally synthesized. May be input to the object detection device 112.
Furthermore, the test of the monitoring system by the test video generation device 130 does not necessarily require the setting of the test method by the administrator through the instruction device 109, that is, the test video parameter 139. A function for randomly determining the test video parameters 139 such as the speed, size, and intrusion path of the object is recorded in the program memory 134 by the test video generation device 130 so that the test can be performed irregularly and fully automatically. May be.

  DESCRIPTION OF SYMBOLS 100: Surveillance system 101: Imaging device 112: Object detection device 130: Test image generation device 109: Instruction device 110: Alarm output device 111: Display output device 102: Image input circuit 103: Image processing Processor: 104: Program memory, 105: Work memory, 106: External IF circuit, 107: Video output circuit, 108: Data bus, 132: Video input circuit, 133: Image processor, 134: Program memory, 135: Work memory 136: External IF circuit, 137: Video output circuit, 138: Data bus, 201: Input video, 301: Monitoring area, 401: Intruder, 402: Rectangular, 403: Trajectory, 501: Test item list, 601: Pseudo Object image, 701: entry path, 702: Intrusion path, 703: Intrusion path, 801: Composite video, 901: Position, 902: Camera parameter, 903: Elapsed time, 904: Coordinate information, 905: Pseudo object image after scaling.

Claims (2)

A monitoring imaging device that images a monitoring region and outputs a monitoring image, and an object detection device that performs image processing on the monitoring image, extracts an intruding object from the monitoring image, and detects an intruding object in the monitoring region. The monitoring system further includes a test image generation device that records a predetermined pseudo object image and conditions for the operation check test of the object detection device and outputs the conditions to the object detection device,
When the pseudo object image and the condition of the operation check test are input from the test video generation device, the object detection device includes the pseudo object image input to the monitoring video input from the monitoring imaging device, and , Image processing is performed on the synthesized video, an intruding object in the monitoring area is detected from the video, and the detected information is output to the test video generation device, and the object detection device detects the detected information. Is a pseudo object, and if it is the pseudo object, it is confirmed that the monitoring system is operating normally.   The monitoring system according to claim 1, further comprising: instruction means for a system administrator to set detection information such as a moving speed, an intrusion route, a color, a contrast, an appearance position, and an exit position of the pseudo image with respect to the pseudo image. The monitoring system characterized in that the test video generation device generates a composite video by the setting means and automatically performs an operation check test of the monitoring system.

Images