Surveillance system, video quality setting method, crowd behavior analysis server, and crowd behavior analysis program

Abstract

This monitoring system (1) includes: a plurality of cameras (11-13, 21) arranged in a distributed manner within a management area; a crowd behavior analysis server (41) that analyzes, on the basis of video images acquired from the plurality of cameras (11-13, 21), the flow of people in each of individual monitoring areas respectively imaged by the plurality of cameras (11-13, 21) and that calculates a predicted people count value for predicting a change in the flow of people in each of the individual monitoring areas; and a video quality adjustment device (42) that sets the video image quality for a camera (21) corresponding to a relevant individual monitoring area such that the greater the predicted people count value, the higher the quality.

Description

[Technical Field]

[0001] The present invention relates to a surveillance system, a video quality setting method, a crowd behavior analysis server, and a crowd behavior analysis program, and in particular to a surveillance system, a video quality setting method, a crowd behavior analysis server, and a crowd behavior analysis program that use multiple cameras to analyze the flow of people in a controlled area that is set over a wide area. [Background technology]

[0002] In places where people gather or where there is a large flow of people, security guards and guides are deployed to control the flow of people to avoid confusion. However, unless the congestion situation and changes in the flow of people are understood, it is impossible to optimize the flow of people and the deployment of guides. Deploying personnel to monitor such congestion situations and changes in the flow of people not only requires additional personnel, but also makes it difficult to accurately grasp the situation. Therefore, Patent Document 1 discloses a congestion estimation system in which multiple cameras are deployed in a controlled area to grasp the congestion situation.

[0003] In the surveillance system described in Patent Document 1, the analysis server analyzes low-quality surveillance video transmitted from a surveillance camera to detect an abnormality, and when it receives a quality change request to change the quality of the surveillance video to high quality, it sends a bandwidth change request to the bandwidth management device to change the bandwidth available for transmitting the surveillance video to a wider bandwidth, and also sends a quality change request to the surveillance camera to transmit high-quality surveillance video. This makes it possible to flexibly change the quality of the surveillance video transmitted by the surveillance camera as needed without wasting bandwidth. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6595287 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the monitoring system described in Patent Document 1 has a problem in that the video quality cannot be adjusted to follow sudden changes in the flow of people and the number of people, and therefore cannot perform appropriate monitoring in managed areas where the flow of people and the number of people change significantly. [Means for solving the problem]

[0006] One aspect of the surveillance system of the present invention comprises a plurality of cameras dispersedly positioned within a management area, a crowd behavior analysis server that analyzes the flow of people in each individual surveillance area captured by each of the plurality of cameras based on the images acquired from the plurality of cameras and calculates a predicted number of people value that predicts changes in the number of people and flow of people in each individual surveillance area, and a video quality adjustment device that sets the video quality of the camera corresponding to the individual surveillance area higher the larger the predicted number of people value.

[0007] One aspect of the video quality setting method for a surveillance system according to the present invention is a video quality setting method for a surveillance system that measures the flow of people within a management area using a plurality of cameras dispersedly placed within the area, and analyzes the number of people and the flow of people in each individual monitoring area captured by each of the plurality of cameras based on the images acquired from the plurality of cameras, calculates a predicted number of people value that predicts changes in the flow of people in each individual monitoring area, and sets the video quality of the camera corresponding to the individual monitoring area higher the larger the predicted number of people value.

[0008] One aspect of the crowd behavior analysis server of the present invention comprises an image acquisition unit that acquires images of individual monitoring areas captured by each of a plurality of cameras that are distributed within a management area; a people flow analysis unit that analyzes people flow indicating the entry and exit of people and their direction of movement for each individual monitoring area based on the acquired images; a crowd analysis unit that analyzes the number of people for each individual monitoring area based on the acquired images; and a number prediction unit that calculates a number of people predicted value that is a value that predicts changes in people flow for each individual monitoring area and is used to switch the image quality of the cameras, and the number of people prediction unit calculates the number of people predicted value for each individual monitoring area by adding the number of people entering from adjacent individual monitoring areas to the number of people within the area and subtracting the number of people leaving to the adjacent individual monitoring area.

[0009] One aspect of the computer-readable non-transitory recording medium on which the crowd behavior analysis program of the present invention is stored is a computer-readable non-transitory recording medium on which the crowd behavior analysis program is stored based on video of individual monitoring areas captured by each of a plurality of cameras distributed within a management area, and which performs the following steps: video acquisition processing to acquire the video from the plurality of cameras; people flow analysis processing to analyze people flow indicating the entry and exit of people and their direction of movement for each individual monitoring area based on the acquired video; crowd analysis processing to analyze the number of people for each individual monitoring area based on the acquired video; and number of people prediction processing to calculate a number of people predicted value that is a value that predicts changes in people flow for each individual monitoring area and is used to switch the video quality of the cameras, and the number of people prediction processing calculates the number of people predicted value for each individual monitoring area by adding the number of people entering from an adjacent individual monitoring area to the number of people within the area and subtracting the number of people leaving to the adjacent individual monitoring area. [Effects of the Invention]

[0010] The surveillance system, video quality setting method, crowd behavior analysis server, and crowd behavior analysis program of the present invention can reduce the amount of communication between the camera and the crowd analysis server while ensuring optimal video quality for people flow monitoring. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a schematic diagram of a monitoring system according to a first embodiment. [Figure 2] 1 is a block diagram of a monitoring system according to a first embodiment. [Figure 3] 4 is a flowchart illustrating the operation of the monitoring system according to the first embodiment. [Figure 4] 10 is a flowchart illustrating an initialization process of the monitoring system according to the first embodiment. [Figure 5] FIG. 3 is a diagram illustrating an outline of calculation of a predicted number of people in the monitoring system according to the first embodiment. [Figure 6] 10 is a flowchart illustrating a camera video quality adjustment process of the monitoring system according to the first embodiment. [Figure 7] FIG. 10 is a diagram illustrating the people flow analysis process in step S22 of the monitoring system according to the first embodiment. [Figure 8] FIG. 10 is a diagram illustrating the number of people prediction process in step S23 of the monitoring system according to the first embodiment. [Figure 9] FIG. 10 is a diagram illustrating the video quality adjustment process in step S24 of the monitoring system according to the first embodiment. [Figure 10] FIG. 10 is a diagram illustrating the number of people prediction process in step S23 of the monitoring system according to the second embodiment. [Figure 11] FIG. 11 is a diagram illustrating the video quality adjustment process in step S23 of the monitoring system according to the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] For clarity of explanation, the following description and drawings have been omitted and simplified as appropriate. Furthermore, each element shown in the drawings as a functional block performing various processes can be configured in hardware with a CPU (Central Processing Unit), memory, and other circuits, and in software with a program loaded into memory, etc. Therefore, those skilled in the art will understand that these functional blocks can be realized in various forms using only hardware, only software, or a combination thereof, and are not limited to any one of these. In addition, the same elements are designated by the same reference numerals in each drawing, and redundant explanations are omitted as necessary.

[0013] The above-described program can be stored in and supplied to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible recording media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). The program can also be supplied to a computer by various types of temporary computer-readable media. Examples of temporary computer-readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable media can be supplied to a computer via a wired communication path such as an electric wire or optical fiber, or via a wireless communication path.

[0014] Embodiment 1 Fig. 1 shows a schematic diagram of a monitoring system according to the first embodiment. Fig. 1 shows an example in which monitoring system 1 is placed in a predetermined management area. As shown in Fig. 1, monitoring system 1 according to the first embodiment includes cameras 11 to 13, 21, a public network 31, a crowd behavior analysis server 41, and a video quality adjustment device 42.

[0015] In the example shown in FIG. 1, cameras 11, 12, and 13 are placed at the entrances and exits of the managed area. Also, in the example shown in FIG. 1, camera 21 is placed at a branching point of a passageway within the managed area. In the monitoring system 1, at least cameras are placed at the entrances and exits of the managed area and at the branching points of passageways within the managed area. By arranging the cameras in this manner, the accuracy of the number of people predicted in the monitoring system 1 can be improved. Furthermore, the number of cameras to be placed in the monitoring system 1 can be appropriately determined depending on the size of the managed area. For example, if there is a space within the managed area where people may gather, it is preferable to place cameras in the area where people may gather. Furthermore, in straight sections of passageways within the managed area where people's movement speeds fall within a certain range, it is preferable to increase the spacing between cameras to match the people's movement speeds. In this way, by arranging the cameras in accordance with people's movement patterns, the number of installed cameras can be reduced, i.e., the number of images and the amount of data transmitted to the crowd behavior analysis server 41 can be reduced, while improving the accuracy of the number of people predicted.

[0016] In the surveillance system 1, cameras installed within the managed area capture video and transmit the captured data to the crowd behavior analysis server 41 via the public network 31. Therefore, reducing the amount of communication data leads to stable communication and reduced operating costs. In this case, in the surveillance system 1 according to the first embodiment, the crowd behavior analysis server 41 calculates a predicted number of people for each individual monitoring area monitored by each camera, and improves the video quality according to the future number of people for each individual monitoring area, thereby reducing the amount of communication data and improving the accuracy of people flow analysis. Therefore, the surveillance system 1 including the crowd behavior analysis server 41 and the video quality adjustment device 42 will be described in detail below.

[0017] FIG. 2 shows a block diagram of the monitoring system according to the first embodiment. Among the components described in FIG. 1, FIG. 2 illustrates in detail the crowd behavior analysis server 41. Cameras 11 to 13 are installed at the entrances and exits of the managed area. Camera 21 is installed at a branching point of a passage within the managed area. Cameras 11 to 13 and 21 each capture video of an individual monitoring area set within the managed area. This video is data compressed based on a predetermined standard, such as H.264. In the monitoring system 1, a video quality adjustment device 42 adjusts the quality of the image captured by camera 21 based on the predicted number of people generated by the crowd behavior analysis server 41. The higher the resolution of the captured video, the higher the quality. As will be described in detail later, in the monitoring system 1, the video quality of cameras 11 to 13 installed at the entrances and exits of the managed area is fixed at the highest level. This is to respond to unexpected environmental changes, since the flow and number of people at the entrances and exits are affected by the environment outside the managed area.

[0018] The crowd behavior analysis server 41 analyzes the flow of people in each individual monitoring area captured by each of the multiple cameras (e.g., cameras 11-13, 21) based on images acquired from the multiple cameras, and calculates a predicted number of people value that predicts changes in the flow of people in each individual monitoring area. As will be described in detail below, the crowd behavior analysis server 41 calculates the predicted number of people value for each individual monitoring area by adding the number of people entering from an adjacent individual monitoring area to the number of people within the area and subtracting the number of people leaving the adjacent individual monitoring area. In other words, the crowd behavior analysis server 41 predicts the number of people in each individual monitoring area in the near future (e.g., the next video acquisition cycle) based on the number of people entering and leaving each individual monitoring area measured up to the present time. The video quality adjustment device 42 then sets a higher video quality for the camera corresponding to the individual monitoring area as the predicted number of people value increases.

[0019] Here, the crowd behavior analysis server 41 can be realized as dedicated hardware that performs the video acquisition processing, people flow analysis processing, and number of people prediction processing described below, but it can also be realized by running programs that perform these processing on the calculation unit of a computer. The example shown in Figure 2 shows the crowd behavior analysis server 41 that runs a crowd behavior analysis program that performs these processing on a computer.

[0020] As shown in FIG. 2, the crowd behavior analysis server 41 includes a calculation unit 51, a memory 52, and a communication interface 53. The calculation unit 51 executes a crowd behavior analysis program to implement a video acquisition unit 61, a people flow analysis unit 62, a crowd analysis unit 63, and a number of people prediction unit 64. The memory 52 is, for example, a storage unit using volatile memory and nonvolatile memory, and the crowd behavior analysis program is stored in the nonvolatile memory portion. The volatile memory portion of the memory 52 stores video data and calculation data used in the calculations performed by the calculation unit 51. The communication interface 53 performs communication processing to enable the crowd behavior analysis server 41 to communicate with the cameras 11-13, 21 and the video quality adjustment device 42. Note that in the example shown in FIG. 2, the video quality adjustment device 42 is a separate device from the crowd behavior analysis server 41, but the video quality adjustment device 42 may be incorporated as one of the functions of the crowd behavior analysis server 41.

[0021] The image acquisition unit 61 performs image acquisition processing. In this image acquisition processing, images of individual monitoring areas captured by multiple cameras distributed within the management area are acquired. The people flow analysis unit 62 performs people flow analysis processing.

[0022] The people flow analysis process analyzes the people flow in each individual monitoring area based on the acquired video. More specifically, the people flow analysis process counts the number of people who leave and enter the individual monitoring area by crossing the set boundary line that surrounds the area, and analyzes the direction of movement of people based on the position of the boundary line that people crossed.

[0023] The crowd analysis unit 63 performs crowd analysis processing. In the crowd analysis processing, the number of people present in each individual monitoring area is counted based on the acquired video. More specifically, in the crowd analysis processing, the number of people present in each individual monitoring area during the first predetermined period of the video is counted, and the counted value is used as the number of people.

[0024] The number of people prediction unit 64 performs a number of people prediction process. In the number of people prediction process, a predicted number of people value is calculated, which is a value that predicts changes in the number of people in each individual monitoring area and is used to switch the camera's video quality. Specifically, in the number of people prediction process, the predicted number of people value is calculated by adding the number of people entering from an adjacent individual monitoring area to the number of people in the area and subtracting the number of people leaving the adjacent individual monitoring area. Note that the number of people prediction method used by the people flow analysis unit 62 does not simply rely on addition and subtraction, but can also utilize prediction processing using artificial intelligence, for example.

[0025] Next, the operation of the monitoring system 1 according to the first embodiment will be described. Therefore, Fig. 3 shows a flowchart illustrating the operation of the monitoring system according to the first embodiment. As shown in Fig. 3, the monitoring system 1 according to the first embodiment performs an initialization process (step S1) to initialize camera settings, and then performs a people flow monitoring process including a camera image quality adjustment process (step S2). Note that Fig. 3 only shows the camera image quality adjustment process out of the people flow monitoring process. Also, as shown in Fig. 3, the monitoring system 1 according to the first embodiment repeatedly executes the camera image quality adjustment process at a preset periodic cycle (for example, a cycle with a set periodic time of 1 minute).

[0026] The initialization process will now be described in detail. Fig. 4 shows a flowchart illustrating the initialization process of the monitoring system 1 according to the first embodiment. As shown in Fig. 4, in the initialization process, first, the video quality adjustment device 42 sets the video quality of the cameras (for example, cameras 11 to 13) installed at the entrances and exits of the managed area to the highest quality (step S11). Note that the cameras whose video quality has been set in step S11 will maintain that setting thereafter.

[0027] Next, the image quality adjustment device 42 sets the image quality of cameras (e.g., camera 21) installed other than at the entrances and exits of the controlled area to the lowest quality (step S12). The initialization process is preferably performed, for example, when there is no or extremely little intrusion of people into the controlled area. This is because, under such conditions, it is easy to lower the image quality of cameras installed other than at the entrances and exits of the controlled area to the lowest level.

[0028] Next, the camera image quality adjustment process in the monitoring system 1 according to the first embodiment will be described in detail. One of the features of this camera image quality adjustment process is that it calculates a predicted number of people. Therefore, Fig. 5 is a diagram illustrating an outline of the calculation of the predicted number of people in the monitoring system 1 according to the first embodiment.

[0029] As shown in FIG. 5, in the monitoring system 1 according to the first embodiment, each of the cameras 11 to 13 and 21 captures an image of an individual monitoring area and generates a video. Also, in FIG. 5, the people who were in the individual monitoring area at the start of a certain imaging cycle are indicated by a solid line, and the people who entered and left the individual monitoring area at the end of the imaging cycle are indicated by a dashed line. That is, the number of people indicated by the solid line is the number of people calculated by the crowd analysis process, and the people indicated by the dashed line are the people and their movement direction analyzed by the people flow analysis process. Then, in the monitoring system 1 according to the first embodiment, the number and movement direction of people who left the individual monitoring area during the imaging cycle are analyzed based on the people who were in the individual monitoring area at the beginning of the imaging cycle. Then, based on the results of this analysis, a predicted number of people who are predicted to be present in each individual monitoring area in the near future (for example, in the next imaging cycle) is calculated as a predicted number of people value.

[0030] In the example shown in Figure 5, the individual management area of camera 21 is the subject of the predicted number of people value, the number of people in the current shooting cycle is 5, the number of people leaving the area is 4, and the number of people entering the area is 3, so the predicted number of people is 4.

[0031] Next, a detailed description will be given of the camera image quality adjustment process in the monitoring system 1 according to the first embodiment. Fig. 6 shows a flowchart illustrating the camera image quality adjustment process in the monitoring system according to the first embodiment.

[0032] As shown in FIG. 6, in the camera image quality adjustment process, the image acquisition unit 61 first receives captured images from each camera (step S21). Next, the people flow analysis unit 62 analyzes the received images to calculate the number of people and the flow of people in each individual monitoring area, and the crowd analysis unit 63 performs a crowd analysis process to analyze the number of people in each individual monitoring area based on the acquired images (step S22). FIG. 7 illustrates the people flow analysis process in step S22 of the monitoring system according to the first embodiment. In the example shown in FIG. 7, the crowd analysis process in step S22 calculates that the initial number of people in the individual monitoring area captured by camera 11 is 30. The people flow analysis process calculates that 20 people are heading toward the individual monitoring area captured by camera 21, and 5 people are moving in a direction outside the management area. The crowd analysis process also calculates that the initial number of people in the individual monitoring area captured by camera 12 is 14. The people flow analysis process then calculates that 6 people are heading toward the individual monitoring area captured by camera 21, and 5 people are moving in a direction outside the management area. Furthermore, the crowd analysis process calculates that the initial number of people in the individual monitoring area photographed by camera 13 is nine. The people flow analysis process calculates that three people then head in the direction of the individual monitoring area photographed by camera 21, and five people move in a direction outside the management area. The crowd analysis process calculates that the initial number of people in the individual monitoring area photographed by camera 21 is ten. The people flow analysis process calculates that three people then head in the direction of the individual monitoring area photographed by camera 11, three people head in the direction of the individual monitoring area set up by camera 12, and four people moved in the direction of the individual monitoring area photographed by camera 13. In this way, the people flow analysis process in step S22 calculates the initial number of people in each individual monitoring area, the number of people who subsequently moved, and the direction of their movement.

[0033] Next, in the camera image quality adjustment process, a number of people prediction process is performed to calculate a predicted number of people value that predicts the number of people in each individual monitoring area in the next shooting cycle based on the calculation result of step S22 (step S23). Here, FIG. 8 is a diagram illustrating the number of people prediction process of step S23 in the monitoring system 1 according to the first embodiment. As shown in FIG. 8, in the number of people prediction process, the predicted number of people value is calculated by adding the number of people entering each individual monitoring area and subtracting the number of people leaving for each individual monitoring area. In this case, the monitoring system 1 according to the first embodiment does not calculate a predicted number of people value for the individual monitoring areas captured by cameras 11 to 13 located at the entrances and exits of the managed area. This is because the individual monitoring areas are significantly affected by undetectable external factors, resulting in large calculation errors, and the quality of the images captured by cameras 11 to 13 is fixed. Meanwhile, for camera 21, which is the subject of calculation of the predicted number of people value, applying the number of people entering and leaving to the initial number of people results in 29.

[0034] Next, in the camera image quality adjustment process, based on the calculation result of step S23, an image quality adjustment process is performed to adjust the image quality settings of the cameras 21 that will capture images of the individual monitoring areas set other than the entrances and exits of the management area in the next capture cycle (step S24). FIG. 9 is a diagram illustrating the image quality adjustment process of step S24 in the monitoring system 1 according to the first embodiment. As shown in FIG. 9, in the image quality adjustment process, a quality setting table that associates the number of people in the predicted number of people value with image quality settings is referenced, and it is analyzed which column in the quality setting table the predicted number of people value calculated in step S23 corresponds to. Then, the image quality setting value corresponding to the column that matches is applied to the camera 21. In the example shown in FIG. 9, the image quality of the camera 21 is changed to increase the quality from the minimum of 640 × 360 to 1920 × 1080.

[0035] As explained above, the monitoring system 1 according to the first embodiment calculates a predicted number of people value that predicts the number of people in each individual monitoring area in the near future using the number of people and people flow in adjacent individual monitoring areas among the individual monitoring areas at the current time acquired using multiple cameras.The monitoring system 1 according to the first embodiment then improves the video quality of the cameras as the predicted number of people value increases, thereby proactively improving the video quality and realizing high responsiveness to changes in the flow of people, while reducing the amount of data communication generated by transmitting the video data.

[0036] More specifically, in the monitoring system 1 according to the first embodiment, the accuracy of the number of people calculation process in the crowd analysis process can be improved by proactively improving the video quality based on the predicted number of people. Also, in the people flow analysis process, improving the video quality can improve the accuracy of determining the number of people moving and their direction of movement. On the other hand, in the monitoring system 1 according to the first embodiment, the video quality can be proactively lowered even when the number of people and the flow of people decrease, thereby reducing the amount of communication traffic.

[0037] Embodiment 2 In the second embodiment, a description will be given of another mode of the number of people prediction process according to the first embodiment. Fig. 10 shows a diagram for explaining the number of people prediction process in step S23 of the monitoring system according to the second embodiment.

[0038] As shown in Fig. 10, the number of people prediction process according to the second embodiment takes into consideration people entering the management area from outside and calculates a predicted number of people for each individual monitoring area photographed by cameras 11 to 13, which was not included in the calculations in the first embodiment. Here, the number of people entering from outside is calculated based on past statistical data such as the day of the week, time period, etc. Alternatively, the number of people entering from outside can be a value predicted by artificial intelligence.

[0039] In this way, by calculating the predicted number of people for individual monitoring areas set at the entrances and exits of the management area, the resolution of the cameras installed at the entrances and exits of the management area can be set appropriately low to reduce the amount of data communication.

[0040] Embodiment 3 Another mode of the video quality setting items will be described in the third embodiment. Fig. 11 shows a diagram for explaining the video quality adjustment process in step S23 of the monitoring system according to the third embodiment.

[0041] As shown in FIG. 11, in the monitoring system 1, it is also possible to set the quality setting table so that not only the resolution of the captured image but also the frame rate increases as the number of people in an individual monitoring area increases.

[0042] As the number of people increases, increasing the frame rate can improve the accuracy of people flow analysis, but increasing the frame rate also increases the amount of data transmitted. Therefore, by lowering the frame rate according to the number of people and the flow of people, it is possible to strike a balance between the accuracy of people flow analysis and the amount of data transmitted.

[0043] The present invention is not limited to the above-described embodiment, and can be modified as appropriate within the scope of the invention.

[0044] (Appendix 1) A plurality of cameras distributed within a management area; a crowd behavior analysis server that analyzes the number of people and the flow of people for each individual monitoring area captured by each of the plurality of cameras based on the images acquired from the plurality of cameras, and calculates a predicted number of people value that predicts changes in the flow of people for each of the individual monitoring areas; a video quality adjustment device that sets a higher video quality for the camera corresponding to the individual monitoring area as the predicted number of people increases; A monitoring system having: (Appendix 2) The monitoring system described in Appendix 1, wherein the crowd behavior analysis server calculates the predicted number of people by adding the number of people entering from an adjacent individual monitoring area to the number of people within each individual monitoring area and subtracting the number of people leaving to the adjacent individual monitoring area. (Appendix 3) 3. The monitoring system according to claim 1, wherein the crowd behavior analysis server does not calculate the predicted number of people for an individual monitoring area among the plurality of individual monitoring areas that is located at the entrance / exit of the management area. (Appendix 4) The monitoring system described in Appendix 1 or 2, wherein the crowd behavior analysis server calculates the predicted number of people for an individual monitoring area among the plurality of individual monitoring areas that is located at the entrance / exit of the management area by adding or subtracting a statistically calculated predicted entry / exit value to the number of people in the individual monitoring area. (Appendix 5) The surveillance system according to any one of appendices 1 to 4, wherein the video quality adjustment device sets a predetermined fixed image quality for the camera among the plurality of cameras located at the entrance / exit of the management area. (Appendix 6) A surveillance system as described in any one of appendices 1 to 4, wherein the video quality adjustment device sets the highest possible image quality for the camera located at the entrance / exit of the management area among the multiple cameras. (Appendix 7) The video quality adjustment device has a video quality table that describes the video quality corresponding to the predicted number of people value, and refers to the video quality table to improve the video quality set on the camera as the predicted number of people value increases. A surveillance system as described in any one of Appendices 1 to 6. (Appendix 8) 8. The monitoring system according to claim 1, wherein the video quality adjustment device adjusts at least one of a resolution and a frame rate of the video as the video quality. (Appendix 9) The monitoring system according to any one of appendices 1 to 8, wherein the individual monitoring areas are set at least at branch points and entrances / exits within the management area. (Appendix 10) 10. The monitoring system according to any one of claims 1 to 9, wherein the individual monitoring area is set to include an area within the management area where people tend to stay. (Appendix 11) A monitoring system as described in any one of Appendices 1 to 10, wherein the individual monitoring areas are set so that, in parts of the management area where people are moving within a certain speed range, the distance between adjacent individual monitoring areas increases as the people's moving speed increases. (Appendix 12) A method for setting video quality of a surveillance system that measures people flow within a management area using a plurality of cameras that are distributed within the management area, comprising: analyzing the flow of people in each individual monitoring area photographed by each of the plurality of cameras based on the images acquired from the plurality of cameras, and calculating a predicted number of people value that predicts changes in the number of people and the flow of people in each individual monitoring area; A video quality setting method for a surveillance system, wherein the video quality of the camera corresponding to the individual surveillance area is set higher as the predicted number of people increases. (Appendix 13) an image acquisition unit that acquires images of individual monitoring areas captured by a plurality of cameras that are distributed within the management area; a people flow analysis unit that analyzes people flow indicating the entry and exit of people and their movement directions for each individual monitoring area based on the acquired video; a crowd analysis unit that analyzes the number of people in each individual monitoring area based on the acquired video; a number of people prediction unit that calculates a predicted number of people value that is a value that predicts a change in the flow of people for each individual monitoring area and is used to switch the video quality of the camera; The number of people prediction unit is a crowd behavior analysis server that calculates the predicted number of people by adding the number of people entering from an adjacent individual monitoring area to the number of people within each individual monitoring area and subtracting the number of people leaving to the adjacent individual monitoring area. (Appendix 14) A computer-readable non-transitory recording medium storing a crowd behavior analysis program based on images of individual monitoring areas captured by a plurality of cameras dispersedly placed within a management area, an image acquisition process for acquiring the images from the plurality of cameras; a people flow analysis process for analyzing people flow indicating the entry and exit of people and their movement directions for each individual monitoring area based on the acquired video; a crowd analysis process for analyzing the number of people in each individual monitoring area based on the acquired video; a number of people prediction process for calculating a number of people predicted value that is a value that predicts a change in the flow of people for each individual monitoring area and is used to switch the video quality of the camera; The number of people prediction process is performed on a computer-readable non-transitory recording medium that stores a crowd behavior analysis program that calculates the number of people prediction value by adding the number of people entering from an adjacent individual monitoring area to the number of people within each individual monitoring area and subtracting the number of people leaving to the adjacent individual monitoring area. [Explanation of symbols]

[0045] 1. Surveillance System 11 Camera 12 Camera 13 Camera 21 Camera 31 Public Networks 41 Crowd behavior analysis server 42 Video quality adjustment device 51 Arithmetic section 52 memory 53 Communication Interface 61 Video acquisition unit 62 People flow analysis department 63 Crowd Analysis Department 64 Number Prediction Department

Claims

1. A plurality of cameras distributed within a management area; a crowd behavior analysis server that analyzes the number of people and the flow of people for each individual monitoring area captured by each of the plurality of cameras based on the images acquired from the plurality of cameras, and calculates a predicted number of people value that predicts changes in the flow of people for each of the individual monitoring areas; a video quality adjustment device that sets a higher video quality for the camera corresponding to the individual monitoring area as the predicted number of people increases, A monitoring system in which the crowd behavior analysis server does not calculate the predicted number of people for an individual monitoring area, among the plurality of individual monitoring areas, that is located at an entrance / exit of the management area.

2. A plurality of cameras distributed within a management area; a crowd behavior analysis server that analyzes the number of people and the flow of people for each individual monitoring area captured by each of the plurality of cameras based on the images acquired from the plurality of cameras, and calculates a predicted number of people value that predicts changes in the flow of people for each of the individual monitoring areas; a video quality adjustment device that sets a higher video quality for the camera corresponding to the individual monitoring area as the predicted number of people increases, The crowd behavior analysis server is a monitoring system that calculates the predicted number of people for an individual monitoring area located at the entrance or exit of the management area among the multiple individual monitoring areas by adding or subtracting a statistically calculated predicted entry / exit value to the number of people in the individual monitoring area.

3. 3. The monitoring system according to claim 1, wherein the crowd behavior analysis server calculates the predicted number of people by adding the number of people entering from an adjacent individual monitoring area to the number of people within each individual monitoring area and subtracting the number of people leaving to the adjacent individual monitoring area.

4. 4. The surveillance system according to claim 1, wherein the video quality adjustment device sets a preset fixed image quality for a camera located at an entrance / exit of the controlled area among the plurality of cameras.

5. 4. The surveillance system according to claim 1, wherein the image quality adjustment device adjusts the image quality of a camera located at an entrance to the controlled area, among the plurality of cameras, to the highest image quality that can be set.

6. The video quality adjustment device has a video quality table that stores video quality corresponding to the predicted number of people value, and refers to the video quality table to improve the video quality set on the camera as the predicted number of people value increases.

7. A method for setting video quality of a surveillance system that measures people flow within a management area using a plurality of cameras that are distributed within the management area, comprising: analyzing the flow of people in each individual monitoring area photographed by each of the plurality of cameras based on the images acquired from the plurality of cameras, and calculating a predicted number of people value that predicts changes in the number of people and the flow of people in each individual monitoring area; The larger the predicted number of people value, the higher the image quality of the camera corresponding to the individual monitoring area is set; A video quality setting method for a surveillance system, in which, when calculating the predicted number of people, the predicted number of people is not calculated for an individual surveillance area located at the entrance / exit of the management area among the multiple individual surveillance areas.

8. A method for setting image quality in a surveillance system that measures people flow within a controlled area using a plurality of cameras that are distributed within the controlled area, comprising: analyzing the flow of people in each individual monitoring area photographed by each of the plurality of cameras based on the images acquired from the plurality of cameras, and calculating a predicted number of people value that predicts changes in the number of people and the flow of people in each individual monitoring area; The larger the predicted number of people value, the higher the image quality of the camera corresponding to the individual monitoring area is set; A method for setting video quality in a surveillance system, in which, in calculating the predicted number of people, for an individual monitoring area among the multiple individual monitoring areas that is located at the entrance / exit of the management area, the predicted number of people is calculated by adding or subtracting a statistically calculated predicted entry / exit value to the number of people in the individual monitoring area.

9. an image acquisition unit that acquires images of individual monitoring areas captured by a plurality of cameras that are distributed within the management area; a people flow analysis unit that analyzes people flow indicating the entry and exit of people and their movement directions for each individual monitoring area based on the acquired video; a crowd analysis unit that analyzes the number of people in each individual monitoring area based on the acquired video; a number of people prediction unit that calculates a predicted number of people value that is a value that predicts a change in the flow of people for each individual monitoring area and is used to switch the video quality of the camera; the number-of-people prediction unit calculates the predicted number-of-people value by adding the number of people entering from the adjacent individual monitoring area to the number of people within the area for each individual monitoring area and subtracting the number of people leaving to the adjacent individual monitoring area; The crowd behavior analysis server does not calculate the predicted number of people for an individual monitoring area located at an entrance / exit of the management area among the plurality of individual monitoring areas.

10. An image acquisition unit that acquires images of individual monitoring areas captured by each of a plurality of cameras that are distributed within a management area; a people flow analysis unit that analyzes people flow indicating the entry and exit of people and their movement directions for each individual monitoring area based on the acquired video; a crowd analysis unit that analyzes the number of people in each individual monitoring area based on the acquired video; a number of people prediction unit that calculates a predicted number of people value that is a value that predicts a change in the flow of people for each individual monitoring area and is used to switch the video quality of the camera; the number-of-people prediction unit calculates the predicted number-of-people value by adding the number of people entering from the adjacent individual monitoring area to the number of people within the area for each individual monitoring area and subtracting the number of people leaving to the adjacent individual monitoring area; A crowd behavior analysis server that calculates the predicted number of people for an individual monitoring area located at the entrance or exit of the management area among the multiple individual monitoring areas by adding or subtracting a statistically calculated predicted entry / exit value to the number of people in the individual monitoring area.

11. A crowd behavior analysis program that causes a computer to execute a process of measuring the flow of people within a management area based on images of individual monitoring areas captured by each of a plurality of cameras that are distributed within the management area, an image acquisition process for acquiring the images from the plurality of cameras; a people flow analysis process for analyzing people flow indicating the entry and exit of people and their movement directions for each individual monitoring area based on the acquired video; a crowd analysis process for analyzing the number of people in each individual monitoring area based on the acquired video; a number of people prediction process for calculating a number of people predicted value that is a value that predicts a change in the flow of people for each individual monitoring area and is used to switch the video quality of the camera; A crowd behavior analysis program in which the number of people prediction process does not calculate the number of people prediction value for an individual monitoring area located at an entrance / exit of the management area among the multiple individual monitoring areas.

12. A crowd behavior analysis program that causes a computer to execute a process of measuring the flow of people within a controlled area based on images of individual monitoring areas captured by each of a plurality of cameras that are dispersedly placed within the controlled area, an image acquisition process for acquiring the images from the plurality of cameras; a people flow analysis process for analyzing people flow indicating the entry and exit of people and their movement directions for each individual monitoring area based on the acquired video; a crowd analysis process for analyzing the number of people in each individual monitoring area based on the acquired video; a number of people prediction process for calculating a number of people predicted value that is a value that predicts a change in the flow of people for each individual monitoring area and is used to switch the video quality of the camera; The number of people prediction process is a crowd behavior analysis program that calculates the number of people prediction value for an individual monitoring area located at the entrance / exit of the management area among the multiple individual monitoring areas by adding or subtracting a statistically calculated entry / exit prediction value to the number of people in the individual monitoring area.

Images