Video surveillance device, program, and method for setting up the surveillance area

Abstract

A video monitoring device (120) comprises: a marker detection unit (123) that extends in the length direction and that, by moving a continuous body provided with a marker, detects the marker from a video obtained by imaging the movement of the marker; and a setting unit (124) that sets a monitoring area in a portion of the video in which area monitoring is performed, so that a trajectory along which the marker moves is included. The setting unit (124) proportionately increases the monitoring area at a position where the marker is captured as the size of the marker in the video increases.

Description

[Technical Field]

[0001] This disclosure relates to a video surveillance device, a program, and a method for setting up a surveillance area. [Background technology]

[0002] In recent years, surveillance cameras have been installed in all kinds of places, including public spaces such as roads and construction sites. Systems have been developed that use the images captured by these surveillance cameras to automatically monitor areas using image anomaly detection algorithms.

[0003] When applying anomaly detection algorithms to video footage, it is common practice to reduce wasted computational resources and false positives by narrowing down the area to be monitored. In the case of permanently installed surveillance cameras, the monitoring area is defined by a person using points or regions on the image. In this case, once the monitoring area is defined during the initial setup, no further configuration is required, so the proportion of operational costs in the overall operation of the video surveillance system is small and does not pose a major problem.

[0004] However, algorithms that do not require long periods of training have been developed in recent years, and there is an increasing trend towards video surveillance systems where cameras are installed on-site and operated only for short periods while the task being monitored is completed. In such cases, the effort required to set up the surveillance area accounts for a large portion of the overall operation, so there is a need to be able to set up the surveillance area as automatically as possible.

[0005] As a technology for automatically setting the monitoring area, the system described in Patent Document 1 utilizes the fact that three markers are placed at equal intervals on the horizontal plane of the object to be monitored, performs camera parameter calculations, and uses a monitoring area setting device that sets the area enclosed by a straight line connecting the three markers and a straight line parallel to it at a constant interval as the monitoring area. [Prior art documents] [Patent Documents]

[0006] [Patent Document 1] Japanese Patent Publication No. 2001-145095 [Overview of the Initiative] [Problems that the invention aims to solve]

[0007] However, conventional technology requires placing multiple markers at equal intervals for each camera, which limits its applicability. Furthermore, conventional technology can only define a monitoring area within a horizontal plane and enclosed by straight lines. Therefore, conventional technology cannot be applied when it is necessary to define a monitoring area on a curved surface in real space, such as when monitoring a factory line or cables during cable laying work. Furthermore, when dealing with continuous structures such as cables, there was the problem that it was difficult to confirm from the video whether the object was moving in the direction of continuity.

[0008] Therefore, according to one or more aspects of this disclosure, the aim is to reduce the effort required to install multiple markers and to enable the creation of a monitoring area on an image that is freely shaped and takes depth into consideration. [Means for solving the problem]

[0009] A video monitoring device according to one aspect of the present disclosure includes a marker detection unit that detects a marker from video footage of the movement of a continuous body extending in the longitudinal direction and equipped with a marker, and a setting unit that sets a monitoring area, which is an area to be monitored in a part of the video, such that the trajectory of the movement of the marker is included, wherein the setting unit makes the monitoring area at the position where the marker is captured larger the larger the size of the marker in the video.

[0010] A program according to an aspect of the present disclosure causes a computer to function as a marker detection unit that detects a marker from an image capturing the movement of the marker by moving a continuum that extends in a length direction and includes the marker, and a setting unit that sets a monitoring area that is an area for performing monitoring in a part of the image so as to include a trajectory along which the marker moves, and the setting unit enlarges the monitoring area at a position where the marker is imaged as the size of the marker in the image becomes larger.

[0011] A monitoring area setting method according to an aspect of the present disclosure is a monitoring area setting method that detects a marker from an image capturing the movement of the marker by moving a continuum that extends in a length direction and includes the marker, and sets a monitoring area that is an area for performing monitoring in a part of the image so as to include a trajectory along which the marker moves, and the monitoring area at a position where the marker is imaged is enlarged as the size of the marker in the image becomes larger.

Advantages of the Invention

[0012] According to one or more aspects of the present disclosure, it is possible to reduce the labor of installing a plurality of markers and set a monitoring area having a free shape and considering depth on an image.

Brief Description of the Drawings

[0013] [Figure 1] It is a block diagram schematically showing the configuration of a monitoring system according to Embodiment 1. [Figure 2] It is a block diagram schematically showing the configuration of a video monitoring device in Embodiment 1. [Figure 3] (A) to (C) are schematic diagrams for explaining the operation of the marker detection unit. [Figure 4] (A) to (C) are schematic diagrams for explaining the operation of the moving marker detection unit. [Figure 5] (A) and (B) are schematic diagrams for explaining the operation of the marker trajectory specifying unit. [Figure 6] It is a schematic diagram for explaining the operations of the marker width calculation unit and the monitoring area setting unit. [Figure 7] (A) and (B) are schematic diagrams for explaining an example of setting the monitoring area when the continuum passes through a bent location. [Figure 8] It is a block diagram schematically showing the configuration of the PC. [Figure 9] It is a block diagram schematically showing the configuration of the video monitoring device in Embodiment 2. [Figure 10] (A) to (C) are schematic diagrams for explaining the operation of the marker width calculation unit. [Figure 11] (A) and (B) are schematic diagrams for explaining the operation of the monitoring area setting unit. [Figure 12] It is a schematic diagram for explaining an example of applying an abnormality detection algorithm to one frame included in the video.

Embodiments for Carrying Out the Invention

[0014] Embodiment 1. FIG. 1 is a block diagram schematically showing the configuration of the monitoring system 100 according to Embodiment 1. The monitoring system 100 includes a camera 110 and a video monitoring device 120. The camera 110 and the video monitoring device 120 are connected to a network 101 such as the Internet or a LAN (Local Area Network).

[0015] Here, the monitoring system 100 is a system for monitoring a cable extension method in which a cable 102 as a continuum is laid along a line 103. Here, the cable 102 is usually of a large weight that cannot be held by human hands and is laid over a relatively long distance. Specifically, a cable extender 104 with two powered rollers 104a and 104b is installed at appropriate intervals, and the cable 102 can be laid by feeding out the cable 102 from the head. The cable 102 is an example of a continuum extending in the length direction.

[0016] Cable 102 is equipped with a marker 105 for monitoring its movement. The marker 105 can be applied to any continuum, and is not limited to cable 102. By moving cable 102, marker 105 can also be moved. Marker 105 may be attached to a continuum or it may be printed on.

[0017] Camera 110 is an imaging device that captures video footage to monitor the work status in cable laying construction. The captured video footage is transmitted to the video monitoring device 120 via the network 101. Here, camera 110 can be any type of camera capable of acquiring images that can identify marker 105, such as a color camera, grayscale camera, near-infrared camera, infrared camera, fisheye camera, or wide-angle camera.

[0018] Figure 2 is a block diagram schematically showing the configuration of the video surveillance device 120 in Embodiment 1. The video monitoring device 120 includes a communication unit 121, a video acquisition unit 122, a marker detection unit 123, and a setting unit 124. The setting unit 124 includes a moving marker detection unit 125, a marker trajectory identification unit 126, a marker width calculation unit 127, and a monitoring area setting unit 128.

[0019] The communication unit 121 communicates via the network 101. For example, the communication unit 121 receives video from the camera 110 via the network 101. The received video is then provided to the video acquisition unit 122.

[0020] The video acquisition unit 122 acquires video from the camera 110. Here, the video acquisition unit 122 acquires video from the camera 110 via the communication unit 121. The acquired video is then provided to the marker detection unit 123. If video footage from the camera 110 is already stored in a storage unit (not shown) or a cloud-based storage device, the video acquisition unit 122 may acquire the video footage from that storage unit or device.

[0021] The marker detection unit 123 detects the marker from the image captured by moving the cable 102. For example, the marker detection unit 123 extracts a marker region, which is the area where the marker 105 is visible, from each frame included in the video, and generates a marker image that shows that marker region.

[0022] Figures 3(A) to 3(C) are schematic diagrams illustrating the operation of the marker detection unit 123. The marker detection unit 123 applies a specified HSV color space or RGB color space range to the frame 140A shown in Figure 3(A) and binarizes it using a specific color (for example, red) used as the color of the marker 105, thereby generating a binarized image 140B as shown in Figure 3(B).

[0023] The marker detection unit 123 then generates a marker image 140C, as shown in Figure 3(C), by retaining only the regions with a certain area or larger that can distinguish between the noise 107 and the marker 105 from the binarized image 140B. Furthermore, any method that allows the marker's outline to be recognized, such as pattern matching, is acceptable for detecting marker 105, and any known technology can be used.

[0024] Returning to Figure 2, the setting unit 124 sets a monitoring area, which is an area in the video that will be monitored, so that the trajectory of the marker's movement is included. Here, the setting unit 124 increases the monitoring area at the location where the marker is being captured, as the size of the marker in the video increases. Embodiment 1 shows a first example of setting up such a monitoring area.

[0025] The moving marker detection unit 125 sequentially identifies two frames from a plurality of frames contained in the video, and sequentially identifies the moving marker region indicating the area where the two markers have moved, based on the difference between the two markers contained in those two frames. The two frames can be identified sequentially, for example, at the same time interval.

[0026] For example, the moving marker detection unit 125 generates a moving marker image by extracting only the portion of the marker that has moved from the marker image.

[0027] Figures 4(A) to 4(C) are schematic diagrams illustrating the operation of the moving marker detection unit 125. The moving marker detection unit 125 acquires a marker image 141A as shown in Figure 4(A). The marker image 141A is generated from a frame at a certain point in time, and the marker image 141A shows the marker region 141a, which is the area of ​​the marker.

[0028] As shown in Figure 4(B), the moving marker detection unit 125 generates a moving marker image 142, as shown in Figure 4(C), by taking the difference between the marker image 141B, which was generated from a frame later than the marker image 141A in Figure 4(A), and the marker image 141A in Figure 4(A). The generated moving marker image 142 is provided to the marker trajectory identification unit 126.

[0029] Returning to Figure 2, the marker trajectory identification unit 126 identifies a reference point within the moving marker area, and then connects the multiple reference points identified according to multiple frames to identify a reference line. Furthermore, the marker trajectory identification unit 126 identifies a trajectory region by combining multiple movement marker regions identified according to multiple frames.

[0030] For example, the marker trajectory identification unit 126 uses the moving marker image to create a marker trajectory image that shows the trajectory region, which is the area of ​​the marker's movement.

[0031] Figures 5(A) and (B) are schematic diagrams illustrating the operation of the marker trajectory identification unit 126. First, as shown in Figure 5(A), the marker trajectory identification unit 126 identifies reference points Pa and Pb within the moving marker regions 142Aa and 142Ab indicated by the moving marker image 142A. Here, the reference points Pa and Pb are assumed to be the centroids of the moving marker regions 142Aa and 142Ab. Then, by connecting the reference points of multiple moving marker images generated from multiple frames contained in the video, the reference line RL is identified as shown in Figure 5(B). When determining the reference line RL by connecting the reference points, you may use either reference point Pa or reference point Pb, or you may use both reference point Pa and reference point Pb to ensure stable operation.

[0032] Furthermore, the marker trajectory identification unit 126 identifies the trajectory region TR of the moving marker by performing a logical OR operation in the time axis direction on multiple moving marker images generated from multiple frames included in the video, as shown in Figure 5(B).

[0033] The marker trajectory identification unit 126 generates a reference image 143 showing the identified reference line RL and trajectory area TR, and provides the reference image 143 to the marker width calculation unit 127 and the monitoring area setting unit 128. Alternatively, instead of generating the reference image 143, the marker trajectory identification unit 126 may notify the marker width calculation unit 127 and the monitoring area setting unit 128 of the positions of the identified baseline RL and trajectory region TR within the image. In this case, the marker width calculation unit 127 and the monitoring area setting unit 128 may generate the reference image 143, or only the trajectory region TR may be drawn. Furthermore, the marker trajectory identification unit 126 may apply noise reduction processing to eliminate noise, leaving only regions with an area greater than a certain size. Furthermore, the marker trajectory identification unit 126 does not need to use all frames included in the video, and may skip frames as long as it does not affect the processing result.

[0034] Returning to Figure 2, the marker width calculation unit 127 calculates the marker width as the distance from the sample point on the reference line to the boundary of the trajectory region in a direction intersecting the direction in which the marker moves. Note that when the moving marker image moves from the foreground to the background in the composition of the image, the marker width gradually narrows.

[0035] For example, the marker width calculation unit 127 samples multiple points on the reference line identified by the marker trajectory identification unit 126 and calculates the marker width at each point.

[0036] Figure 6 is a schematic diagram illustrating the operation of the marker width calculation unit 127 and the monitoring area setting unit 128. As shown in Figure 6, the marker width calculation unit 127 calculates the distance l from the boundary of the trajectory region TR in a direction perpendicular to the reference line RL at the sample point p(x,y). (x、y) The marker width is calculated as l. (x、y) This information is sent to the monitoring area setting unit 128.

[0037] The marker width calculation unit 127 may calculate the width of the monitoring area separately for the left and right sides with respect to the direction of movement of the continuum. This allows the monitoring area to be set according to the object being monitored, for example, if work on the continuum is performed only from one side (left or right). Also, if the reference line is separated to the left and right from the boundary of the trajectory image, the monitoring area setting unit 128 can eliminate this separation and set the monitoring area by selecting the marker width separately for the left and right sides.

[0038] Returning to Figure 2, the monitoring area setting unit 128 sets the monitoring area to include the trajectory region. Here, the monitoring area setting unit 128 sets the width of the monitoring area in the direction that intersects the reference line at the position of the sample point so that it increases as the marker width at that sample point increases. The monitoring area setting unit 128 sets the width of the monitoring area in the direction that intersects the reference line at the position of the sample point by multiplying the marker width at the position of the sample point by a predetermined value.

[0039] For example, the monitoring area setting unit 128 calculates a monitoring area that includes a reference line and is such that the distance from the sample point to the boundary of the monitoring area increases as the marker width at the sample point increases.

[0040] As shown in FIG. 6, the monitoring area setting unit 128 sets, as the monitoring area AR, an area expanded by a constant n-fold (n > 0) of the marker width l in a direction orthogonal to the reference line RL. (x,y)

[0041] As shown in FIG. 6, the width L of the monitoring area at the point p(x, y) is expressed by the following equation (1). Thereby, the expansion width is adjusted by an arbitrary constant n. (x,y)

[0042] L (x,y) = nl (x,y) (1)

[0043] Here, the case where the size of the marker width l is the same on both sides of the reference line RL is described as an example. However, as described above, the size of the marker width l may be different on both sides of the reference line RL, and the width L of the monitoring area (x,y) may also be different on both sides of the reference line RL. For example, as expressed by the following equations (2) and (3), by having separate expansion width adjustment constants for the left, n (x,y) and for the right, n L R as shown, the widths L L(x,y) and L R(x,y) of the left and right monitoring areas can be adjusted respectively. L(x,y)

[0044] L L = n (x,y) l R(x,y) (2) L R = n (x,y) l (x,y) (3)

[0045] As described above, the monitoring area setting unit 128 can estimate the scale of the monitoring area on the image from the known actual marker width, using the marker trajectory image generated by the marker trajectory identification unit 126 and the marker width calculated by the marker width calculation unit 127, and then set the enlarged area as the monitoring area using that scale. For example, the monitoring area setting unit 128 is set to the scale l (x,y) The larger the size, the wider the monitoring area L. (x,y) You may enlarge it, scale l (x,y) The smaller L (x,y) You can make it smaller.

[0046] As described above, by utilizing the fact that moving markers appear larger when close and smaller as they move further away, it is possible to set a monitoring area of ​​any shape that takes depth into account, based on the position of the marker obtained by the marker trajectory identification unit 126 and the marker width calculation unit 127, as well as the change in size.

[0047] The width of the expansion, or in other words, the constant n, can be different on the left and right sides with respect to the direction of movement of the continuum. Furthermore, the marker's trajectory does not necessarily have to be a straight line. As shown in Figure 7, it may pass through a curved section of the continuum.

[0048] By using a monitoring system 100 with this configuration, the effort required to install multiple markers is reduced, and a monitoring area can be set on the image with a free shape and taking depth into consideration.

[0049] The video surveillance device 120 described above can be implemented, for example, by a computer such as the PC 10 shown in Figure 8. The PC10 includes storage 11 such as an HDD (Hard Disk Drive) and an SSD (Solid State Drive), memory 12, a processor 13 such as a CPU (Central Processing Unit), and a communication I / F (Interface) 14 such as a NIC (Network Interface Card). Furthermore, the PC10 may be equipped with an input interface 15 such as a keyboard and mouse, and a display 16.

[0050] For example, the video acquisition unit 122, marker detection unit 123, moving marker detection unit 125, and setting unit 124 can be realized by the processor 13 executing a program. The communication unit 121 can be implemented using the communication interface 14.

[0051] The program may be downloaded to storage 11 via a reader / writer (not shown) from a recording medium (not shown), or via a communication interface 14 from network 101, and then loaded into memory 12 and executed by processor 13. Alternatively, it may be loaded directly into memory 12 via a reader / writer from a recording medium, or via a communication interface 14 from network 101, and then executed by processor 13. In other words, the program may be provided by a computer program product such as a recording medium.

[0052] Embodiment 2. As shown in Figure 1, the surveillance system 200 according to Embodiment 2 includes a camera 110 and a video surveillance device 220.

[0053] Figure 9 is a block diagram schematically showing the configuration of the video surveillance device 220 in Embodiment 2. The video monitoring device 220 includes a communication unit 121, a video acquisition unit 122, a marker detection unit 123, and a setting unit 224. The setting unit 224 includes a moving marker detection unit 125, a monitoring area setting unit 228, and an area size calculation unit 229.

[0054] The communication unit 121, video acquisition unit 122, marker detection unit 123, and moving marker detection unit 125 of the video monitoring device 220 in Embodiment 2 are the same as those of the communication unit 121, video acquisition unit 122, marker detection unit 123, and moving marker detection unit 125 of the video monitoring device 220 in Embodiment 2. However, in Embodiment 2, the moving marker detection unit 125 provides the moving marker image to the area size calculation unit 229 and the monitoring area setting unit 228.

[0055] The setting unit 224 sets a monitoring area, which is an area to be monitored within a portion of the video, so that the trajectory of the marker's movement is included. Here, the setting unit 224 increases the monitoring area at the location where the marker is being captured in the video, as the size of the marker in the video increases. Embodiment 2 shows a second example of setting up such a monitoring area.

[0056] The region size calculation unit 229 identifies a reference point included within the moving marker region shown in the moving marker image. Here, the reference point is assumed to be the centroid of the moving marker region. The region size calculation unit 229 then calculates the region size as the distance from the reference point to the furthest point within the moving marker region. The calculated region size is notified to the monitoring area setting unit 228.

[0057] Furthermore, the moving marker region is thought to increase as the size of the marker in the video increases. Therefore, it can be assumed that the marker size is also larger as the region size increases.

[0058] Figures 10(A) to (C) are schematic diagrams illustrating the operation of the region size calculation unit 229. When a moving marker image 244, as shown in Figure 10(A), is acquired, the region size calculation unit 229 identifies the centroid Pc as a reference point, as shown in Figure 10(B), and identifies the distance l1 between the centroid Pc and the point furthest away as the region size.

[0059] Note that the marker does not need to be rectangular in shape. For example, even if the marker area is a moving marker area as shown in Figure 10(C), the area size calculation unit 229 identifies the centroid Pd as a reference point and determines the area size as the distance l2 between the centroid Pd and the point furthest from it.

[0060] Returning to Figure 9, the monitoring area setting unit 228 identifies multiple expanded moving marker regions from multiple frames by expanding the moving marker regions so that they become larger as the region size (the size of the moving marker region) increases. Then, the monitoring area setting unit 228 sets the monitoring area by combining these multiple expanded moving marker regions.

[0061] For example, the monitoring area setting unit 228 identifies an expanded moving marker region by expanding the moving marker region shown in the moving marker image, and identifies an expanded marker trajectory region by taking a logical OR operation in the time axis direction of the expanded moving marker region corresponding to multiple frames included in the video.

[0062] For the expansion process, the commonly used morphological processing is applied. Specifically, the monitoring area setting unit 228 slides across the image using a specific kernel and sets the new value of each pixel to the maximum value of its neighbors. The kernel used at this time is generally a Rectangular Kernel, Elliptical Kernel, or Cross-shaped Kernel, but any of them can be used. Here, the iteration parameter, which specifies how many times the expansion process should be applied, is determined by multiplying a constant by the region sizes l1 and l2.

[0063] The monitoring area setting unit 228 then sets the expanding marker trajectory region as the monitoring area.

[0064] Figures 11(A) and (B) are schematic diagrams illustrating the operation of the monitoring area setting unit 228. First, the monitoring area setting unit 228 identifies the expanded moving marker regions 244c and 244d by expanding the moving marker regions 244a and 244b indicated by the moving marker image 244, as shown in Figure 11(A). Then, as shown in Figure 11(B), the monitoring area setting unit 228 performs an inflation process on multiple moving marker images generated from multiple frames included in the video, and by taking the logical OR of the inflated moving marker images, it identifies the inflated marker movement region 245a, which is the area where the inflated marker has moved, and sets that inflated marker movement region 245a as the monitoring area. The monitoring area setting unit 228 may skip frames to the extent that it does not affect the processing results.

[0065] As described above, the monitoring system 200 according to Embodiment 2 also reduces the effort required to install multiple markers and allows for the creation of a monitoring area of ​​any shape, taking depth into consideration.

[0066] Embodiment 3. The video monitoring devices 120 and 220 in the embodiments 1 or 2 described above may be provided with a monitoring unit (not shown) that applies a known anomaly detection algorithm to partial video footage, which is a portion of the video footage acquired by the video acquisition unit 122 that falls within the monitoring area set by the monitoring area setting units 128 and 228, in order to detect anomalies.

[0067] By providing the monitoring unit described above, it is possible to determine whether the worker is functioning normally or abnormally from the video footage, thereby eliminating external disturbances from the perspective of an anomaly detection algorithm, such as worker movement.

[0068] Figure 12 is a schematic diagram illustrating an example of applying an anomaly detection algorithm to a single frame included in captured video footage. As shown in Figure 12, the video monitoring devices 120 and 220 can automatically set the monitoring area AR1 and the non-monitoring areas AR2 and AR3, so that monitoring by the monitoring unit can be limited to the monitoring area AR1 only. This reduces the monitoring load on the monitoring unit.

[0069] As described above, in conventional technology, when setting up a monitoring area, it was necessary to install multiple markers at equal intervals along a straight line of the monitoring area. However, according to embodiments 1 to 3, by providing a single marker on a moving continuum, the effort required to install multiple markers at the monitoring location can be reduced.

[0070] Furthermore, conventional technology, in order to set a monitoring area that takes into account the actual depth, calculated camera parameters by utilizing the fact that markers are placed at equal intervals on a straight line, and could only set the monitoring area to an area on a horizontal plane demarcated by a straight line including the markers. In contrast, according to embodiments 1 to 3, by utilizing the trajectory of markers provided on a continuum and the size change of the markers in the video, it is possible to set a monitoring area of ​​any shape, including a three-dimensional area.

[0071] Furthermore, while conventional technology required the installation of a marker for each surveillance camera, according to embodiments 1 to 3, the surveillance area can be automatically set by moving a continuous body equipped with markers, thus eliminating the need to install a marker for each individual camera. [Explanation of Symbols]

[0072] 100,200 Surveillance system, 110 Camera, 120,220 Video surveillance device, 121 Communication unit, 122 Video acquisition unit, 123 Marker detection unit, 124,224 Setting unit, 125 Moving marker detection unit, 126 Marker trajectory identification unit, 127 Marker width calculation unit, 128,228 Surveillance area setting unit, 229 Area size calculation unit.

Claims

1. A marker detection unit detects the marker from an image captured of the movement of a continuous body that extends in the longitudinal direction and is equipped with a marker, The system includes a setting unit that sets a monitoring area, which is an area to be monitored in a part of the video, such that the trajectory of the moving marker is included, The setting unit makes the monitoring area at the location where the marker is being captured larger the larger the size of the marker in the video. A video surveillance device characterized by the following.

2. The setting unit is, A moving marker detection unit sequentially identifies two frames from a plurality of frames contained in the aforementioned video, and sequentially identifies a moving marker region indicating the area where the two markers have moved based on the difference between two markers contained in the two frames. A marker trajectory identification unit identifies a reference point within the moving marker region, connects the multiple reference points identified according to the multiple frames to identify a reference line, and combines the multiple moving marker regions identified according to the multiple frames to identify a trajectory region. A marker width calculation unit calculates the distance from a sample point on the reference line to the boundary of the trajectory region in a direction intersecting the direction in which the marker moves, as the marker width. The system includes a monitoring area setting unit that sets the monitoring area to include the trajectory region, and sets the width of the monitoring area in the direction that intersects the reference line at the position of the sample point to be larger as the width of the marker at the sample point increases. The video surveillance device according to claim 1, characterized by the following:

3. The monitoring area setting unit sets the width of the monitoring area in the direction intersecting the reference line at the location of the sample point by multiplying the marker width at the location of the sample point by a predetermined value. The video surveillance device according to claim 2, characterized by the following:

4. The setting unit is, A moving marker detection unit sequentially identifies two frames from a plurality of frames contained in the aforementioned video, and sequentially identifies a moving marker region indicating the area where the two markers have moved based on the difference between two markers contained in the two frames. The system includes a monitoring area setting unit that expands the moving marker area so that it becomes larger as the area size, which is the size of the moving marker area, increases, thereby identifying multiple expanded moving marker areas from the multiple frames, and then combines the multiple expanded moving marker areas to set the monitoring area. The video surveillance device according to claim 1, characterized by the following:

5. The monitoring area setting unit determines the area size as the distance from the center of gravity of the moving marker area to the point furthest from the center of gravity of the moving marker area within the boundary of the moving marker area. The video surveillance device according to claim 4, characterized by the following:

6. The monitoring area is further provided with a monitoring unit that detects abnormalities. A video surveillance device according to any one of claims 1 to 5, characterized by the following:

7. Computers, A marker detection unit detects the marker from an image captured of the movement of a continuous body extending in the longitudinal direction and equipped with a marker, and The setting unit functions as a setting unit that sets a monitoring area, which is an area to be monitored in a part of the video, so that the trajectory of the marker's movement is included. The setting unit makes the monitoring area at the location where the marker is being captured larger the larger the size of the marker in the video. A program characterized by the following.

8. By moving a continuous body that extends in the longitudinal direction and has a marker, the movement of the marker is captured in the image and the marker is detected. A method for setting a monitoring area, which is an area to be monitored in a part of the video, such that the trajectory of the moving marker is included, The larger the size of the marker in the video, the larger the monitoring area at the location where the marker is being captured. A monitoring area configuration method characterized by the following.

Images