Program, monitoring support system, and monitoring support method

Abstract

To provide a technology that suppresses notification of noise information to persons performing on-site monitoring operations.SOLUTION: A monitoring support system includes a monitoring range estimation unit, a blind spot area determination unit, and a notification unit. The monitoring range estimation unit estimates a monitoring range covered by one or more monitors performing monitoring operations in an area to be monitored. The blind spot area determination unit determines a blind spot area in the area to be monitored based on the estimated result within the monitoring range by each monitor. The notification unit identifies a specified area to be monitored in the blind spot area based on the information regarding the blind spot area and the information regarding the protected target located in the area to be monitored. Then, the notification unit notifies the monitors of an instruction requesting to monitor the specified area.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a program, a monitoring support system, and a monitoring support method for supporting a monitoring task. [Background technology]

[0002] The following Patent Document 1 discloses a monitoring device having a function of indicating an area that is not monitored (blind spot area). The monitoring device described in the following Patent Document 1 executes, for example, the following processes (1) to (3). (1) By analyzing footage captured by surveillance cameras, the system estimates a person's field of view based on their line of sight. (2) Based on the estimated field of view, blind spots within the monitoring area are determined. (3) If a person or object is detected in the determined blind spot area, information regarding the detection is reported to the security guard's wireless terminal. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2020 / 145255 Summary of the Invention [Problem to be solved by the invention]

[0004] Even if there are blind spots in the area to be monitored and a person or object is present in the blind spot, there may be a low potential risk or no potential risk. Information about such blind spots is merely noise information that interferes with the work of security guards (those performing on-site monitoring). Since such noise information may instead confuse the site, a mechanism is desired that prevents the on-site monitoring personnel from being notified of the information. [Means for solving the problem]

[0005] The program in this disclosure is One or more computers A monitoring range estimation means for estimating a monitoring range covered by one or more monitors performing monitoring work within a monitoring target area; a blind spot determination means for determining a blind spot area in the monitoring target area based on the estimation result of the monitoring range; a notification means for identifying a specific area to be monitored within the blind spot area based on information about the blind spot area and information about a protected object located within the monitored area, and notifying the monitor of an instruction requesting monitoring of the specific area; Operate as.

[0006] The monitoring support system according to the present disclosure includes: The system includes an information collection device that acquires information on one or more monitors performing monitoring tasks within a monitored area, and an information processing device that is connected to the information collection device via a network. In addition, the information collecting device A means for acquiring information on one or more monitors performing monitoring duties within a monitored area; a means for transmitting information of the one or more observers to the information processing device; The information processing device includes: A monitoring range estimation means for estimating a monitoring range covered by one or more monitors based on information of the one or more monitors; a blind spot determination means for determining a blind spot area in the monitoring target area based on the estimation result of the monitoring range; The system is equipped with a notification means for identifying a specific area to be monitored within the blind spot area based on information about the blind spot area and information about a protected object located within the monitored area, and for notifying the monitor of an instruction requesting monitoring of the specific area.

[0007] The monitoring assistance method according to the present disclosure includes: One or more computers Estimating a surveillance area covered by one or more observers performing surveillance duties within the surveillance area; determining a blind spot area within the monitored area based on the estimated monitoring range; Identifying a specific area to be monitored within the blind spot area based on information about the blind spot area and information about a protected object located within the monitored area, and notifying the monitor of an instruction requesting monitoring of the specific area; This includes: Effect of the Invention

[0008] According to the present disclosure, a program, a surveillance support system, and a surveillance support method are provided that prevent a person performing surveillance work on-site from being notified of information that becomes noise. [Brief description of the drawings]

[0009] [Figure 1] 1 is a diagram illustrating a first example of a functional configuration of a monitoring support system according to the present disclosure. [Diagram 2] 2 is a diagram illustrating an example of a hardware configuration of a computer that realizes each function of the monitoring support system according to the present disclosure. FIG. [Diagram 3] 5 is a flowchart showing a first example of the operation of the monitoring support system according to the present disclosure. [Figure 4] 11 is a diagram for explaining an example of an operation of a monitoring range estimation unit for setting a monitoring range of an observer; FIG. [Diagram 5] 11 is a diagram showing an example of a monitoring range estimated by a monitoring range estimation unit when an obstruction is present in the field of view of a monitor; FIG. [Figure 6] 10A and 10B are diagrams for explaining an example of an operation of a blind spot determination unit for determining a blind spot area; [Figure 7] FIG. 11 is a diagram illustrating an example of information notified by a notification unit. [Figure 8] FIG. 13 is a diagram illustrating a second example of a functional configuration of a monitoring support system according to the present disclosure. [Figure 9] 10 is a flowchart showing a second example of the operation of the monitoring support system according to the present disclosure. [Figure 10] FIG. 13 is a diagram illustrating another example of a functional configuration of the monitoring support system according to the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment according to the present disclosure will be described with reference to the drawings. In this disclosure, the drawings relate to one or more embodiments. In addition, in all drawings, similar components are given similar reference numerals, and descriptions are omitted as appropriate. In addition, unless otherwise specified, in each block diagram, each block represents a configuration in functional units, not a configuration in hardware units. In addition, when elements such as blocks in a diagram are linked by arrows, the direction of the arrows is merely for making the flow of information easier to understand. In this case, the direction of the arrows does not limit the direction of communication (one-way communication / two-way communication) unless otherwise specified.

[0011] In the following description, "acquisition" includes at least one of the following: a device going to retrieve data or information stored in another device or storage medium (active acquisition), and inputting data or information output from another device to the device (passive acquisition). Examples of active acquisition include making a request or inquiry to another device and receiving a reply, and accessing and reading information from another device or storage medium. Examples of passive acquisition include receiving information that is distributed (or transmitted, push notification, etc.). Furthermore, "acquisition" may also mean selecting and acquiring data or information from received data or information, or selecting and receiving distributed data or information.

[0012] First embodiment <Example of functional configuration> 1 is a diagram showing a first example of a functional configuration of a monitoring support system according to the present disclosure. The monitoring support system 1 shown in the diagram includes a monitoring range estimation unit 110, a blind spot area determination unit 120, and a notification unit .

[0013] The monitoring range estimation unit 110 estimates a monitoring range covered by one or more monitors working in an area subject to monitoring work (hereinafter also referred to as a "monitored area"). The blind spot area determination unit 120 estimates a blind spot area in the monitored area based on the estimation result of the monitoring range of each monitor. In this disclosure, a "blind spot area" can also be called an "area estimated to be not monitored by one or more monitors (a partial area in the monitored area)". The notification unit 130 identifies an area to be monitored in the blind spot area (hereinafter also referred to as a "specific area") based on information on the blind spot area and information on a protection target in the monitored area. In this disclosure, a "protection target" includes one or more people (e.g., important people or celebrities) or one or more objects (e.g., art exhibits or high-value goods) to be protected under the surveillance of one or more monitors. When a specific area is identified from the blind spot area, the notification unit 130 notifies the monitor of an instruction requesting surveillance of the specific area.

[0014] <Hardware configuration example> FIG. 2 is a diagram illustrating an example of a hardware configuration of a computer that realizes each function of the monitoring support system 1 according to the present disclosure.

[0015] The computer 1000 illustrated in this figure includes a bus 1010 , a processor 1020 , a memory 1030 , a storage device 1040 , an input / output interface 1050 , and a network interface 1060 .

[0016] The bus 1010 is a data transmission path for transmitting and receiving data among the processor 1020, memory 1030, storage device 1040, input / output interface 1050, and network interface 1060. However, the method of connecting the processor 1020 and the like to each other is not limited to a bus connection.

[0017] The processor 1020 may be a Central Processing Unit (CPU) or a Graphics Processing Unit (GPU).

[0018] The memory 1030 is a main storage device realized by a random access memory (RAM) or the like.

[0019] The storage device 1040 is an auxiliary storage device realized by a hard disk drive (HDD), a solid state drive (SSD), a memory card, a read only memory (ROM), etc. The storage device 1040 stores at least a program module that realizes the functions of the monitoring support system 1 described above (the monitoring range estimation unit 110, the blind spot area determination unit 120, and the notification unit 130).

[0020] The processor 1020 loads a program module read from the storage device 1040 onto the memory 1030 and executes the program module, thereby realizing a function corresponding to the program module. For example, the processor 1020 reads a program module corresponding to the monitoring range estimation unit 110 onto the memory 1030 and executes the program module, thereby realizing the function of the monitoring range estimation unit 110 described in the present disclosure. Similarly, the processor 1020 reads a program module corresponding to the blind spot area determination unit 120 onto the memory 1030 and executes the program module, thereby realizing the function of the blind spot area determination unit 120 described in the present disclosure. Similarly, the processor 1020 reads a program module corresponding to the notification unit 130 onto the memory 1030 and executes the program module, thereby realizing the function of the notification unit 130 described in the present disclosure. The operation of the processor 1020 is common to each embodiment included in the present disclosure.

[0021] The above-described program modules may be recorded in a recording medium other than the storage device 1040. The recording medium on which the program modules are recorded includes any non-transitory tangible medium usable by the computer 1000. The recording medium on which the program modules are recorded may have embedded therein a program code readable by the computer 1000 (processor 1020).

[0022] The input / output interface 1050 is an interface for connecting the computer 1000 to various input / output devices.

[0023] The network interface 1060 is an interface for connecting the computer 1000 to a network. This network includes, for example, a Local Area Network (LAN), a Wide Area Network (WAN), etc. The network interface 1060 connects the computer 1000 to various networks wirelessly or via a wired connection.

[0024] The computer 1000 can also be connected to various devices (not shown) via the input / output interface 1050 or the network interface 1060. The "various devices" referred to here are not particularly limited, but include, for example, input devices such as operation buttons, a keyboard, a touch panel, a mouse, and a microphone, and output devices such as a display, a speaker, and a printer.

[0025] 2 illustrates a hardware configuration using one computer, but the hardware configuration of the monitoring support system 1 is not limited to this. For example, at least some of the functions of the monitoring range estimation unit 110, the blind spot area determination unit 120, and the notification unit 130 may be realized by one computer, and the remaining functions may be realized by another computer.

[0026] <Example of operation> A first example of the operation of the monitoring support system according to the present disclosure will be described below with reference to Fig. 3. Fig. 3 is a flowchart showing the first example of the operation of the monitoring support system according to the present disclosure.

[0027] First, the monitoring area estimation unit 110 acquires images of the monitoring area from one or more cameras (not shown) arranged so as to capture the entire monitoring area (step S102).

[0028] Then, the monitoring area estimation unit 110 estimates the monitoring area of ​​each monitor by analyzing the video of the monitored area acquired in the process of step S102 (step S104).

[0029] As an example, the monitoring range estimation unit 110 recognizes the image area of ​​each guard and the image area of ​​the face (or eyes) of each guard by analyzing the video of one or more cameras using a known image recognition algorithm. The monitoring range estimation unit 110 also identifies the direction of the face (or gaze) of each guard based on the recognition result of the image area of ​​the face of each guard. Then, as shown in FIG. 4, for example, the monitoring range estimation unit 110 arranges a region of a predetermined size and shape along the direction of the face (or gaze) identified for each guard, based on the image area recognized for each guard. The monitoring range estimation unit 110 may estimate the monitoring range of each guard by analyzing point cloud information obtained using LiDAR (Light Detection And Ranging) or Radar (Radio Detection And Ranging).

[0030] FIG. 4 is a diagram for explaining an example of the operation of the monitoring range estimation unit 110 to set the monitoring range of a monitor. In the example of FIG. 4, the monitoring range estimation unit 110 arranges a sector-shaped range defined by a predetermined angle θ in the horizontal direction and a predetermined distance d in the depth direction with respect to the position (e.g., face position) P of the monitor as a reference, along the direction of the face (or line of sight) of the monitor. In this manner, an estimation result of the monitoring range of each monitor is obtained. Note that the monitoring range estimation unit 110 may be configured to set a monitoring range of a three-dimensional shape (e.g., a cone shape or a pyramid shape) by adding information of a predetermined angle in the vertical direction to the monitoring range of a two-dimensional shape exemplified in FIG. 4. Furthermore, when an obstruction (an object that may obstruct the field of view of the monitor, such as a wall, a pillar, or a crowd) exists in the monitoring range set as exemplified in FIG. 4, the blind spot area determination unit 120 may deform the monitoring range based on the position of the obstruction. FIG. 5 is a diagram showing an example of a monitoring range estimated by the monitoring range estimation unit 110 when an obstruction exists in the field of view of the monitor. As shown in FIG. 5, the surveillance area estimation unit 110 may estimate an area (hatched area in the figure) that is out of the surveillance personnel's line of sight based on the position of an obstruction, and determine the surveillance area excluding that area.

[0031] Then, the blind spot area determination unit 120 determines the blind spot area in the monitored area based on the estimation result of the monitoring range of each monitor (step S106). For example, the blind spot area determination unit 120 can determine the blind spot area as follows. First, the blind spot area determination unit 120 specifies the area monitored by one or more monitors (hereinafter, also referred to as "area under monitoring") by combining the monitoring ranges of each monitor estimated in the process of step S104. Then, the blind spot area determination unit 120 determines the area remaining as a result of removing the monitored area from the monitored area as a blind spot area (e.g., FIG. 6).

[0032] FIG. 6 is a diagram for explaining an example of the operation of the blind spot area determination unit 120 to determine a blind spot area. In the example of FIG. 6, a plurality of cameras capture the monitored area (area surrounded by a dashed line in the figure). Images captured by the plurality of cameras are input to the monitoring support system 1. In the example of FIG. 6, three monitors are performing monitoring work within the monitored area. The monitoring range estimation unit 110 estimates the range indicated by the dotted sector in the figure as the monitoring range of each monitor by the above-mentioned process. The blind spot area determination unit 120 can specify, for example, the area indicated by the dotted circle and hatching in the figure as the blind spot area by combining the monitoring ranges of each monitor. In the example of FIG. 6, two blind spot areas are specified.

[0033] Next, the notification unit 130 determines whether or not a region to be monitored (specific region) has been identified in the blind spot region determined in the process of step S106 (step S108). The notification unit 130 can identify a region in the blind spot region that has a potential risk as a specific region by using, for example, information about the blind spot region and information about a protection target to be protected under the surveillance of a monitor. Details of this process will be described later.

[0034] If a specific area is identified in the blind spot area (S108: YES), the notification unit 130 notifies the monitor of a request to monitor the identified specific area (step S110). For example, among the two blind spot areas determined in the example shown in Fig. 6, the blind spot area located on the right side in the figure is identified as a specific area as a result of the determination process in step S108. In this case, as shown in Fig. 7, the notification unit 130 outputs information requesting monitoring of the area to the monitor corresponding to the blind spot area identified as the specific area.

[0035] FIG. 7 is a diagram showing an example of information notified by the notification unit 130. As exemplified in FIG. 7, the notification unit 130 specifies the monitor in the center and the monitor on the right side of the figure as monitors corresponding to the blind spot area on the right side of the figure identified as the specific area, among the three monitors, as targets of notification. Then, the notification unit 130 outputs a notification requesting each monitor to monitor the blind spot area identified as the specific area. For example, as exemplified in FIG. 7, the notification unit 130 notifies the monitor of message information informing the position of the specific area. The message information as exemplified in FIG. 7 is output as, for example, image information or sound information through a display or speaker of a mobile terminal held by the monitor or a head-mounted display or earphones worn by the monitor. In the example of FIG. 7, the notification unit 130 notifies the monitor in the center of the figure of message information such as "Pay attention to the area in front of the left". Also, in the example of FIG. 7, the notification unit 130 notifies the monitor on the right side of the figure of message information such as "Pay attention to the area in front of the right". As a modified example, the notification unit 130 may output a map of the area to be monitored, in which the positions of specific areas are made identifiable (for example, highlighted), on the display of a mobile terminal carried by the monitor or on a head-mounted display worn by the monitor. Monitors notified of such information can easily notice that there is an area that has a potential risk but is not being monitored by on-site monitors.

[0036] The notification unit 130 may be configured to change the message to be output based on the distance from the monitor to the object to be protected and the distance from the monitor to the blind area identified as the specific area. For example, it is assumed that the second distance from a certain monitor to the blind area identified as the specific area is longer than the first distance from the certain monitor to the object to be protected. In this case, the notification unit 130 outputs a notification to the certain monitor to prompt the certain monitor to take an action to protect the object to be protected, rather than prompting the certain monitor to move toward the blind area. On the other hand, it is assumed that the second distance from the certain monitor to the blind area identified as the specific area is shorter than the first distance from the certain monitor to the object to be protected. In this case, the notification unit 130 outputs a notification to the certain monitor to prompt the certain monitor to move toward the blind area, rather than taking an action to protect the object to be protected. In this way, by changing the notification according to the distance between the monitor and the object to be protected and the distance between the monitor and the specific area, it is expected to have an effect of reducing the possibility of damage to the object to be protected. In addition, when a notification is sent to multiple observers, the notification unit 130 may be configured to change the notification sent to each observer according to the distance between each observer and the object to be protected and the distance between each observer and the specific area. For example, the notification unit 130 notifies an observer who is closer to a blind spot area identified as a specific area compared to other observers, encouraging the observer to pay attention to the blind spot area or to move toward the blind spot area. On the other hand, the notification unit 130 outputs a notification to an observer who is closer to the object to be protected compared to other observers, encouraging the observer to turn his / her eyes to the object to be protected or to take action to protect the object to be protected. By changing the notification according to the position of the observer in this way, the object to be protected can be protected more firmly.

[0037] The notification unit 130 may also display information on a monitor who has a terminal to be notified on a terminal of a monitoring center (not shown). In this case, a person who is resident at the monitoring center checks the information displayed on the display, and then operates the terminal of the monitoring center to notify the target monitor (the terminal held by the monitor). The notification unit 130 may also be configured to further display on the terminal of the monitoring center any information indicating the relationship between the blind spot area identified as the specific area (the blind spot area to which attention should be paid), the monitor related to the blind spot area, and the object to be protected. For example, the "any information" is not particularly limited, and is at least one of the information listed below. Note that the "distance" in the following description may be the distance from a reference point (e.g., a center point) of the area, or the shortest distance connecting the edge position of the area and the position of the monitor. -Blind spot area and distance to the observer - Distance between the guard and the object being protected - Distance between blind spots and objects to be protected

[0038] On the other hand, if a specific area is not identified in the blind spot area (S108: NO), the process using the image acquired in the process of step S102 ends. In this case, the above-mentioned process is repeatedly executed using images newly acquired from one or more cameras.

[0039] In a first example of the monitoring support system in the present disclosure, it is determined whether or not there is an area that poses a potential risk within a blind spot area that is not monitored by one or more monitors. If such an area is found within the blind spot area, the area is identified as an area to be monitored (specific area). A request to monitor the specific area is then notified to the monitor. According to the first example of the monitoring support system in the present disclosure, information regarding a specific area that poses a potential risk within the blind spot area is notified to the monitor. In other words, the monitor (the person performing the monitoring work on-site) is prevented from being notified of information that becomes noise in the monitoring work.

[0040] <Modification> As one variation, the monitoring range estimation unit 110 may estimate the monitoring range of each observer using information obtained from a monitoring camera carried or worn by each observer. The monitoring range estimation unit 110 acquires, for example, position information of the camera of each observer (e.g., GPS (Global Positioning System) information, etc.) and information indicating the orientation (shooting direction) of the camera of each observer. Then, the monitoring range estimation unit 110 can treat the range obtained based on information about the monitoring camera carried or worn by each observer as the monitoring range of the observer.

[0041] One or more cameras arranged to capture the entire monitored area, surveillance cameras carried or worn by each monitor, and devices such as LiDAR (Light Detection and Ranging) and Radar (Radio Detection and Ranging) can be categorized as "information collection devices." The information collection device in this disclosure can also be called a device that acquires information about one or more monitors performing monitoring work in the monitored area. The monitoring support system 1 according to the present disclosure can also be interpreted as a system including such an information collection device and an information processing device (information processing device 10) connected to the information collection device via a network.

[0042] In this case, the configuration of the monitoring support system 1 is shown, for example, as shown in FIG. 10. FIG. 10 is a diagram showing another example of the functional configuration of the monitoring support system according to the present disclosure. The monitoring support system 1 exemplified in FIG. 10 is configured to include an information processing device 10 and an information collection device 50. The information processing device 10 in this figure has a configuration similar to that exemplified in FIG. 1. The information collection device 50 includes an observer information acquisition unit 510 and a transmission unit 520. The observer information acquisition unit 510 is a processing unit that acquires information on one or more observers performing monitoring work in a monitored area (a processing unit that acquires information using one or more devices such as the above-mentioned cameras, surveillance cameras, LiDAR, and Radar). The transmission unit 520 is a processing unit that transmits information on the one or more observers to the information processing device 10. The information processing device 10 executes the above-mentioned processing using the information on the one or more observers received from the information collection device 50. The information processing device 10 executes the above-mentioned processing using the information on the one or more observers received from the information collection device 50. The information processing device 10 and the information collection device 50 are connected to each other via any network such as a LAN or a WAN.

[0043] The function of the monitoring range estimation unit 110 of the information processing device 10 may be provided on the information collection device 50 side. That is, the information collection device 50 may be configured to acquire information using one or more of the above-mentioned devices such as a camera, a surveillance camera, a LiDAR, and a Radar, and then estimate the monitoring range of each observer by analyzing the information. In this case, for example, the information collection device 50 includes information indicating the estimated result of the range of each observer in metadata or the like and transmits it to the information processing device 10. Then, the information processing device 10 executes the remaining processes other than the process of estimating the monitoring range.

[0044] Hereinafter, a detailed example of the monitoring support system 1 according to the present disclosure (a detailed example of the process of identifying a specific area by the notification unit 130) will be described.

[0045] <Detailed example of specific area identification processing> The process of step S108 (the process of identifying a specific area from among blind spots) executed by the notification unit 130 will be described below with some specific examples.

[0046] As a first example, the notification unit 130 can identify a specific area based on the relationship between the blind spot area and the position of the protection target. For example, a partial area close to the position of the protection target when compared among the blind spot areas can be said to be an area with a high potential risk in the event of an unexpected event (for example, the approach of a suspicious person or a suspicious object). Therefore, the notification unit 130 identifies a partial area located within a predetermined distance from the position of the protection target as a specific area to be monitored preferentially. The process of "identifying a specific area" includes, for example, processes such as "determining or identifying the position coordinates of an area corresponding to a specific area from among the blind spot areas existing in the monitoring target area" and "assigning information indicating that the blind spot area is a specific area (classifying it into a class indicating a specific area)." With this configuration, information indicating a potential high risk area (information that is unlikely to become noise in the monitoring work) can be conveyed to the monitor.

[0047] As another example, when the protection target is a person, the notification unit 130 may further use information about the person to be protected to identify the specific area. For example, as a second example, the notification unit 130 can identify the specific area as follows. First, the notification unit 130 recognizes the area of ​​the person to be protected from the image of the monitoring target area. Then, the notification unit 130 estimates the direction of the line of sight of the person to be protected by analyzing the area of ​​the person to be protected. Then, the notification unit 130 identifies an area with a potential risk from the blind spot area based on the direction of the line of sight of the person to be protected relative to the blind spot area. For example, when an unexpected event occurs in an area that does not overlap with the line of sight (field of vision) of the person to be protected, the person to be protected himself / herself may not be able to see the unexpected event, and avoidance action may be delayed. Such an area can be said to be an area with a potential risk. Therefore, the notification unit 130 identifies an area in the field of vision that does not overlap with the line of sight (field of vision) of the person to be protected as a specific area. With such a configuration, information indicating an area with a high potential risk (information that is unlikely to become noise in the monitoring work) can be conveyed to the monitor.

[0048] Also, in the case where the protection target is a person, as a third example, the notification unit 130 may identify the specific area as follows. First, the notification unit 130 recognizes the area of ​​the person to be protected from the image of the monitored area. Then, the notification unit 130 estimates the direction of the line of sight of the person to be protected by analyzing the area of ​​the person to be protected. Then, the notification unit 130 identifies at least one of an object and another person that exists in an area located in the opposite direction to the line of sight of the person to be protected. Then, the notification unit 130 determines whether or not an area located in the opposite direction to the line of sight of the person to be protected corresponds to a specific area based on information on at least one of the identified object and the other person. For example, suppose that an object (such as a building, wall, barricade, or rope) that obstructs movement is installed in an area located in the opposite direction to the line of sight of the person to be protected. In this case, in order for another person or some object to approach the person to be protected, it has to approach from the front where the person to be protected can be seen, not from behind where the person to be protected cannot be seen. In other words, such an area can be said to have a low potential risk. On the other hand, if an area located in the opposite direction to the line of sight of the person to be protected is a particularly empty space, other people or objects may easily approach the person to be protected. In other words, such an area is a high potential risk and can be said to correspond to a specific area. Then, the notification unit 130 notifies the monitor of a request to monitor the area determined to correspond to the specific area. With this configuration, it is possible to convey information indicating areas with high potential risk (information that is unlikely to become noise in the monitoring work) to the monitor.

[0049] As a fourth example, the notification unit 130 can identify a specific area from a blind area based on the presence or absence of an obstacle present in an area that can be a movement route between the blind area and the position of the person to be protected. First, the notification unit 130 judges whether or not a movement route from the blind area to the position of the person to be protected can be set. For example, when two blind areas are identified as shown in FIG. 6, the notification unit 130 calculates a movement route from each of the two blind areas to the position of the person to be protected. At this time, it is assumed that there is an obstacle (such as a barricade or rope installed in an area that can be a movement route, or a crowd present in an area that can be a movement route) between a certain blind area and the position of the person to be protected, and it is in a situation where a movement route from the blind area to the position of the person to be protected cannot be set. In this case, when the notification unit 130 detects an obstacle present in an area that can be a movement route when a certain blind area is used as a starting point, it does not identify the blind area as a specific area. On the other hand, it is assumed that there is no particular obstacle between a certain blind area and the position of the person to be protected, and it is in a situation where a movement route to the position of the person to be protected can be set. In this case, the notification unit 130 identifies the blind spot area as a specific area that has a potential risk and should be monitored. With this configuration, it is possible to convey information indicating areas with high potential risk (information that is unlikely to become noise in the monitoring work) to the monitoring personnel.

[0050] As a fifth example, the notification unit 130 may be configured to identify the specific area using a machine learning model that is trained to input a video including a person or an object, identify one or more movement paths, and output the reachability to the destination for each movement path. The machine learning model is trained using multiple learning data, for example, to predict the future position of each person from the past movement (movement trajectory) of the person, and identify the movement path to the destination (the location of the protected object) based on the predicted future location of each person. In addition, the machine learning model is trained to calculate the possibility that a person will reach the destination if he / she moves along the movement path based on additional information of each movement path, such as the width and movement distance (travel time to the destination) of the identified movement path. The machine learning model trained in this way is stored in a storage area accessible to the notification unit 130, such as the memory 1030 or the storage device 1040. The notification unit 130 evaluates the potential risk of each blind spot area based on the output result of the machine learning model (the reachability from each blind spot area to the location of the protected object) and identifies the specific area. For example, the notification unit 130 can identify a blind spot area where the reachability to the location of the protected object is a predetermined value (e.g., 50%) or more as a specific area. With such a configuration, it is possible to convey information indicating areas with high potential risk (information that is unlikely to become noise in the monitoring work) to the monitoring personnel.

[0051] Second embodiment <Example of functional configuration> 8 is a diagram illustrating a second example of the functional configuration of the monitoring support system according to the present disclosure. In the monitoring support system illustrated in this figure, the notification unit 130 further includes an attribute information generation unit 132.

[0052] The attribute information generating unit 132 generates attribute information indicating attributes of at least one of one or more people and one or more objects present in the blind spot area. The attribute information generating unit 132 is configured to generate information indicating attributes of people and objects in the video by using, for example, a known image processing technique. The notification unit 130 in the example of this figure is configured to further use the acquired attribute information to identify a specific area.

[0053] <Example of operation> 9 is a flowchart showing a second example of the operation of the monitoring support system according to the present disclosure. The process shown in the flowchart in this figure is executed as part of the process of step S108 in the flowchart in FIG.

[0054] First, the attribute information generating unit 132 analyzes the video of the monitored area and identifies one or more people or one or more objects located in the area determined to be a blind spot area (step S202).The attribute information generating unit 132 then analyzes the image area corresponding to each of the identified one or more people or one or more objects.As a result, the attribute information generating unit 132 generates attribute information indicating attributes related to at least one of the one or more people and one or more objects present in the blind spot area (step S204).

[0055] Here, the attribute information generating unit 132 can generate, for example, the following information as attribute information indicating the attributes of a person. Whether or not a person has any personal belongings (luggage or bags) Age of the person Person's gender · Whether or not you are traveling with someone

[0056] Furthermore, the attribute information generating unit 132 can generate, for example, the following information as information indicating the attributes of an object. Color of the object - Object shape

[0057] The notification unit 130 further uses the attribute information regarding at least one of one or more people and one or more objects present in the blind spot area generated by the attribute information generation unit 132 to identify a specific area to be monitored within the blind spot area (step S206).

[0058] As an example, it is assumed that attribute information is generated for a person present in a certain blind spot area, indicating that the person is carrying luggage, a bag, or the like. In this case, it is possible that the person carrying luggage, a bag, or the like is hiding an object that may cause damage to the protected object. Therefore, when attribute information is acquired for a person present in a certain blind spot area, indicating that the person is carrying luggage, a bag, or the like, the notification unit 130 identifies the blind spot area as a specific area. In addition, when multiple blind spot areas are identified, the notification unit 130 may be configured to determine the priority of each blind spot area based on the attribute information. For example, the notification unit 130 may set the priority of a blind spot area for which attribute information is acquired for a person, indicating that the person is carrying luggage, a bag, or the like, higher than the other blind spot areas. As a result, a request for monitoring the corresponding blind spot area (a blind spot area with a high potential risk) is more likely to be notified to a monitor at the site.

[0059] As another example, suppose that attribute information is generated for a person present in a certain blind spot area, indicating an age (for example, 65 years or older) that is deemed to be elderly. In this case, it is generally considered that an elderly person has a lower risk of causing damage to a protected object than a younger person who is generally physically superior. Therefore, when attribute information is generated for a person present in a certain blind spot area that indicates that the person is elderly, the notification unit 130 does not identify the blind spot area as a specific area. In addition, when multiple blind spot areas are identified, the notification unit 130 may be configured to determine the priority of each blind spot area based on the attribute information. For example, the notification unit 130 may lower the degree of risk of the corresponding blind spot area. As a result, a request for monitoring the corresponding blind spot area (a blind spot area with a low potential risk) is less likely to be notified to a monitor at the site.

[0060] As another example, it is assumed that attribute information indicating that a plurality of persons existing in a certain blind spot area are accompanying persons is generated. In this case, the notification unit 130 refers to the attribute information of each accompanying person and identifies the difference in the attributes of the accompanying persons (for example, the difference in age and / or the difference in height). Here, if the difference in the attributes of the accompanying persons, specifically the difference in age and / or the difference in height, is equal to or greater than a certain level, it can be estimated that the plurality of persons are a family with children. As an example, it is assumed that the person to be protected is an important person or a famous person. In this case, it is considered that the risk of harming the person to be protected is low for a family with children. Therefore, when the difference in the attributes of the plurality of persons existing in a certain blind spot area satisfies a predetermined criterion (for example, they are identified as a family with children), the notification unit 130 may not identify the corresponding blind spot area as a specific area. In addition, when a plurality of blind spot areas are identified, the notification unit 130 may be configured to determine the priority of each blind spot area based on the attribute information. For example, the notification unit 130 may lower the degree of risk of the corresponding blind spot area. As a result, a request for monitoring the corresponding blind spot area (a blind spot area with a low potential risk) is less likely to be notified to the on-site monitor. As another example, assume that the object of protection is an art exhibit or a high-value item. In this case, it is considered that a family with children (especially children) is at high risk of causing damage to the object of protection. Therefore, the notification unit 130 may identify the corresponding blind spot area as a specific area when a difference in the attributes of multiple people present in a certain blind spot area satisfies a predetermined standard (for example, the person is identified as a family with children). In addition, when multiple blind spot areas are identified, the notification unit 130 may be configured to determine the priority of each blind spot area based on the attribute information. For example, the notification unit 130 may increase the degree of risk of the corresponding blind spot area. As a result, a request for monitoring the corresponding blind spot area (a blind spot area with a high potential risk) is more likely to be notified to the on-site monitor.

[0061] As another example, suppose that attribute information indicating a color or shape of an object present in a blind spot that is likely to be a weapon is acquired. In this case, the potential risk of the blind spot is extremely high. Therefore, when attribute information indicating a color or shape of an object present in a certain blind spot that is likely to be a weapon is acquired, the notification unit 130 immediately identifies the corresponding blind spot as a specific area. In addition, when multiple blind spot areas are identified, the notification unit 130 may raise the degree of risk of the corresponding blind spot to the highest level. As a result, a request for monitoring the corresponding blind spot (a blind spot with an extremely high potential risk) is more likely to be notified to a monitor at the site.

[0062] As described above, the second example of the monitoring support system in the present disclosure has at least the same functional configuration as the first example. Therefore, the second example of the monitoring support system in the present disclosure also provides the effects described above. Furthermore, in the second example of the monitoring support system in the present disclosure, attribute information indicating at least one attribute of one or more people and one or more objects present in each blind spot area is used as additional information for identifying a specific area to be monitored in the blind spot area. The area to be monitored (specific area) in the blind spot area is identified by further using information indicating at least one attribute of one or more people and one or more objects present in each blind spot area. This allows information regarding blind spot areas with potential risks to be conveyed to the monitor with higher accuracy.

[0063] 10, the information collecting device 50 may have the function of the attribute information generating unit 132 described above. In that case, for example, the information collecting device 50 includes the attribute information acquired for each person in metadata or the like and transmits the metadata to the information processing device 10. Then, the information processing device 10 executes the above-mentioned process using the attribute information of each person.

[0064] Although the present disclosure has been described above with reference to a number of embodiments, the present disclosure is not limited to the above-described number of embodiments. Various modifications that can be understood by a person skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Each embodiment can be appropriately combined with other embodiments.

[0065] In addition, in the flowcharts used in the above description, the steps (processes) are described in order, but the order of the steps executed in each embodiment is not limited to the order described. In each embodiment, the order of the steps shown in the drawings can be changed as long as it does not affect the content.

[0066] A part or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes. 1. One or more computers A monitoring range estimation means for estimating a monitoring range covered by one or more monitors performing monitoring work within a monitoring target area; a blind spot determination means for determining a blind spot area in the monitoring target area based on the estimation result of the monitoring range; a notification means for identifying a specific area to be monitored within the blind spot area based on information about the blind spot area and information about a protected object located within the monitored area, and notifying the monitor of an instruction requesting monitoring of the specific area; A program to operate as. 2. The notification means includes: identifying the specific area based on a relationship between the blind spot area and a position of the protected object; 1. The program described in. 3. The notification means includes: If the protection target is a person, analyzing an image of the protection target to estimate a gaze direction of the protection target; Identifying the specific area based on a line of sight direction of the protected object relative to the blind spot area. 1. The program described in. 4. The notification means includes: If the protection target is a person, analyzing an image of the protection target to estimate a gaze direction of the protection target; determining whether or not a blind spot area corresponds to the specific area based on information about at least one of an object and another person present in an area of ​​the blind spot area that is located in a direction opposite to the line of sight of the protection target; 1. The program described in. 5. The notification means includes: identifying the specific area from within the blind spot area based on a position of an obstacle present in an area that may be a movement path between the blind spot area and the location of the protected object; 1. The program described in. 6. the notification means detects, as the obstacle, an object installed in an area that may be the movement route and a crowd of people present in the area that may be the movement route; 5. The program described in. 7. The notification means includes: Identifying the specific area using a machine learning model that has been trained to identify one or more movement paths using an input of a video including a person or object and to output a reachability to a destination for each movement path; 1. The program described in. 8. The notification means includes: Identifying the specific area using attribute information indicating attributes of at least one of one or more people and one or more objects present in the blind spot area. 8. The program according to any one of 1. to 7. 9. The notification means includes: When a plurality of pieces of attribute information are acquired, the specific region is identified based on a difference in attributes indicated by each piece of attribute information. 8. The program described in. 10. A monitoring support system including an information collection device that acquires information on one or more monitors performing monitoring work in a monitored area, and an information processing device that is connected to the information collection device via a network, The information collecting device includes: A means for acquiring information on one or more monitors performing monitoring duties within a monitored area; a means for transmitting information of the one or more observers to the information processing device; The information processing device includes: A monitoring range estimation means for estimating a monitoring range covered by one or more monitors based on information of the one or more monitors; a blind spot determination means for determining a blind spot area in the monitoring target area based on the estimation result of the monitoring range; a notification means for identifying a specific area to be monitored within the blind spot area based on information about the blind spot area and information about a protected object located within the monitored area, and for notifying the monitor of an instruction requesting monitoring of the specific area, Surveillance support system. 11. One or more computers Estimating a surveillance area covered by one or more observers performing surveillance duties within the surveillance area; determining a blind spot area within the monitored area based on the estimated monitoring range; Identifying a specific area to be monitored within the blind spot area based on information about the blind spot area and information about a protected object located within the monitored area, and notifying the monitor of an instruction requesting monitoring of the specific area; A monitoring support method comprising:

[0067] In addition, some or all of the configurations described in Supplementary Notes 2 to 9 that are dependent on Supplementary Note 1 (program) described above may also be dependent on Supplementary Note 10 (monitoring support system) and Supplementary Note 11 (monitoring support method) in the same dependent relationship as Supplementary Note 2 to Supplementary Note 9. Furthermore, not limited to Supplementary Note 1, Supplementary Note 10, and Supplementary Note 11, various hardware, software, various recording means for recording software, or systems may also be dependent on some or all of the configurations described as supplementary notes, within the scope of each of the above-mentioned embodiments. [Explanation of symbols]

[0068] 1. Surveillance support system 110 Monitoring range estimation unit 120 Blind spot area determination unit 130 Notification Department 132 Attribute information generation section 1000 Computers 1010 Bus 1020 Processor 1030 Memory 1040 Storage Device 1050 Input / Output Interface 1060 Network Interface

Claims

1. One or more computers, A monitoring range estimation means for estimating a monitoring range covered by one or more monitors performing monitoring work within a monitoring target area; a blind spot determination means for determining a blind spot area in the monitoring target area based on the estimation result of the monitoring range; a notification means for identifying a specific area to be monitored within the blind spot area based on information about the blind spot area and information about a protected object located within the monitored area, and notifying the monitor of an instruction requesting monitoring of the specific area; A program to operate as.

2. The notification means includes: identifying the specific area based on a relationship between the blind spot area and a position of the protected object; The program according to claim 1.

3. The notification means includes: If the protection target is a person, analyzing an image of the protection target to estimate a gaze direction of the protection target; Identifying the specific area based on a line of sight direction of the protected object relative to the blind spot area. The program according to claim 1.

4. The notification means includes: If the protection target is a person, analyzing an image of the protection target to estimate a gaze direction of the protection target; determining whether or not a blind spot area corresponds to the specific area based on information about at least one of an object and another person present in an area of ​​the blind spot area that is located in a direction opposite to the line of sight of the protection target; The program according to claim 1.

5. The notification means includes: identifying the specific area from within the blind spot area based on a position of an obstacle present in an area that may be a movement path between the blind spot area and the location of the protected object; The program according to claim 1.

6. the notification means detects, as the obstacle, an object installed in an area that may be the movement route and a crowd of people present in the area that may be the movement route; The program according to claim 5.

7. The notification means includes: Identifying the specific area using a machine learning model that has been trained to identify one or more movement paths using an input of a video including a person or object and to output a reachability to a destination for each movement path; The program according to claim 1.

8. The notification means includes: identifying the specific area using attribute information indicating attributes of at least one of one or more persons and one or more objects present in the blind spot area; The program according to any one of claims 1 to 7.

9. The notification means includes: When a plurality of pieces of attribute information are acquired, the specific region is identified based on a difference in attributes indicated by each piece of attribute information. The program according to claim 8.

10. A monitoring support system including an information collection device that acquires information on one or more monitors performing monitoring work in a monitored area, and an information processing device that is connected to the information collection device via a network, The information collecting device includes: A means for acquiring information on one or more monitors performing monitoring duties within a monitored area; a means for transmitting information of the one or more observers to the information processing device; The information processing device includes: a monitoring range estimating means for estimating a monitoring range covered by one or more observers based on information of the one or more observers; a blind spot determination means for determining a blind spot area in the monitoring target area based on the estimation result of the monitoring range; a notification means for identifying a specific area to be monitored within the blind spot area based on information about the blind spot area and information about a protection target located within the monitored area, and for notifying the monitor of an instruction requesting monitoring of the specific area, Surveillance support system.

11. One or more computers Estimating a monitoring range covered by one or more monitors performing monitoring tasks within a monitored area; determining a blind spot area within the monitored area based on the estimated monitoring range; Identifying a specific area to be monitored within the blind spot area based on information about the blind spot area and information about a protected object located within the monitored area, and notifying the monitor of an instruction requesting monitoring of the specific area; A monitoring support method comprising:

Images