Monitoring device, monitoring method, and program

Abstract

To detect a situation in which a criminal act can occur against a pedestrian or a vehicle.SOLUTION: A monitoring device (100) comprises a detection unit (102) which processes a captured image of road surroundings and detects that the relative distances to persons and vehicles included in the image are in a state of being at or below a reference value, and an output unit (104) which uses attributes of a person detected as being in the aforementioned state to select a type of information to be output and outputs the selected type of information.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a monitoring system, a monitoring device, a monitoring method, and a program. [Background technology]

[0002] In recent years, surveillance cameras have been installed in cities and are being used for crime prevention. Patent Document 1 describes a video surveillance system that analyzes security camera footage to detect acts such as trespassing into parking lots, and immediately issues a warning or transmits the resulting video to a display device in a surveillance room where a security guard is present, as well as to mobile phones of security guards and related parties. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2007-195130 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above document does not disclose any technology for detecting criminal acts against pedestrians or vehicles, such as kidnapping or car break-ins.

[0005] The present invention has been made in consideration of the above circumstances, and an object of the present invention is to provide a technology for detecting a situation in which a criminal act against a pedestrian or a vehicle may occur. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems, each aspect of the present invention employs the following configuration.

[0007] The program in this disclosure is A process of acquiring video from a surveillance camera; A process of acquiring a distance between a vehicle and a person based on the image; If the distance between the vehicle and the person is equal to or less than a threshold, acquiring information for determining whether the person is a person who may commit a vehicle break-in; and a process of issuing a notification when information for determining whether the person is a person likely to commit a car break-in satisfies a predetermined condition.

[0008] The monitoring method in the present disclosure includes: One or more computers Obtaining footage from security cameras Obtaining the distance between the vehicle and the person based on the image; If the distance between the vehicle and the person is equal to or less than a threshold, information is obtained for determining whether the person is a person who may commit a vehicle break-in; A notification is given when information for determining whether the person is a person who is likely to commit a car break-in satisfies a predetermined condition.

[0009] The monitoring device in the present disclosure comprises: An image acquisition means for acquiring an image from a surveillance camera; a distance acquisition means for acquiring a distance between a vehicle and a person based on the image; an information acquisition means for acquiring information for determining whether the person is a person who may commit a car break-in if the distance between the vehicle and the person is equal to or less than a threshold; and a notification means for issuing a notification when information for determining whether the person is a person likely to commit a car break-in satisfies a predetermined condition.

[0010] Another aspect of the present invention may be a program for causing at least one computer to execute the above method, or a computer-readable recording medium having such a program recorded thereon. The recording medium includes a non-transitory tangible medium. The computer program comprises computer program code which, when executed by a computer, causes the computer to perform the monitoring method on a monitoring device.

[0011] Any combination of the above components, and any transformation of the present invention into a method, device, system, recording medium, computer program, etc., are also effective as aspects of the present invention.

[0012] Furthermore, the various components of the present invention do not necessarily have to be independent entities, but may be formed as a single member by multiple components, one component may be formed from multiple components, one component may be a part of another component, or part of one component may overlap with part of another component, etc.

[0013] In addition, although the method and computer program of the present invention describe a number of steps in a sequential order, the order does not limit the order in which the steps are executed. Therefore, when implementing the method and computer program of the present invention, the order of the steps can be changed as long as it does not affect the content.

[0014] Furthermore, the steps of the method and computer program of the present invention are not limited to being executed at different timings, and therefore a step may occur while another step is being executed, or the execution timing of a step may overlap partially or entirely with the execution timing of another step, etc. Effect of the Invention

[0015] According to each of the above aspects, it is possible to provide a technology for detecting a situation in which a criminal act against a pedestrian may occur. [Brief description of the drawings]

[0016] [Figure 1] 1 is a diagram illustrating an overview of a monitoring system according to an embodiment. [Diagram 2] 2 is a functional block diagram showing an example of a logical configuration of the monitoring device of FIG. 1. [Diagram 3]2 is a block diagram illustrating an example of a hardware configuration of a computer that realizes each of a monitoring device and an image processing device in the monitoring system shown in FIG. 1. [Figure 4] 4 is a flowchart showing an example of the operation of the monitoring device of the present embodiment. [Diagram 5] FIG. 2 is a functional block diagram showing an example of a logical configuration of a monitoring system. [Figure 6] 10 is a flowchart showing an example of an operation of the monitoring system. [Figure 7] 10 is a flowchart showing an example of an operation of the monitoring system. [Figure 8] FIG. 2 is a functional block diagram showing an example of a logical configuration of a monitoring system. [Figure 9] 10 is a flowchart showing an example of an operation of the monitoring system. [Figure 10] 10 is a flowchart showing an example of an operation of the monitoring system. [Figure 11] FIG. 2 is a functional block diagram showing an example of a logical configuration of a monitoring system. [Figure 12] 4 is a flowchart showing an example of an operation of the monitoring device. [Figure 13] 10 is a flowchart showing an example of an operation of the monitoring system. [Figure 14] 10 is a flowchart showing an example of an operation of the monitoring system. [Figure 15] FIG. 2 is a functional block diagram showing an example of a logical configuration of a monitoring system. [Figure 16] 10 is a flowchart showing an example of an operation of the monitoring system. [Figure 17] 10 is a flowchart showing an example of an operation of the monitoring system. [Figure 18] FIG. 1 is a diagram for explaining the relative positions of a vehicle and a person in the case of kidnapping. [Figure 19] 10 is a flowchart showing an example of an operation of the monitoring system. [Figure 20] FIG. 1 is a diagram for explaining the relative positions of a car and a person in the case of a car break-in. [Figure 21]10 is a flowchart showing an example of an operation of the monitoring system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, the same components are given the same reference numerals and the description will be omitted as appropriate.

[0018] In the embodiment, "acquisition" includes at least one of the following: a device goes to retrieve data or information stored in another device or storage medium (active acquisition), and inputs 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 mean selecting and acquiring data or information from received data or information, or selecting and receiving distributed data or information.

[0019] (First embodiment) <System Overview> 1 is a diagram showing a schematic overview of a surveillance system 1 according to an embodiment. In the surveillance system 1, an image processing device 200 processes images captured by a surveillance camera 5 installed around town to recognize cars 10 and people 20, and a surveillance device 100 uses the processing results of the image processing device 200 to detect criminal acts such as kidnapping and car break-ins.

[0020] The surveillance system 1 includes a surveillance device 100, an image processing device 200, and at least one surveillance camera 5. The surveillance camera 5 may be one specialized for the surveillance system 1, or may be, for example, a camera that has been installed previously.

[0021] The surveillance camera 5 captures an image of a place to be monitored and generates an image. The surveillance camera 5 includes an imaging element such as a lens and a CCD (Charge Coupled Device) image sensor. The surveillance camera 5 may include a mechanism for controlling the orientation of the camera body and lens, zoom control, focusing, etc., by tracking the movement of a person who enters the field of view.

[0022] The surveillance camera 5 captures an area including at least roads on which the car 10 can pass. For example, the surveillance camera 5 captures an area including roads whose width is wider than the car 10. The surveillance camera 5 may also capture an area including roads consisting of sidewalks on which people 20 pass and roadways on which the car 10 passes. However, the surveillance camera 5 is not limited to roads, and may also capture places where the car 10 and the person 20 can enter, such as parking lots. The surveillance camera 5 may capture a person 20 who is moving, or a person 20 who is stationary. The surveillance camera 5 may capture a car 10 who is moving, or a car 10 who is stationary.

[0023] The surveillance camera 5 may capture images of areas including locations where crimes are likely to occur, such as locations in the shadow of structures such as shrubbery, fences, and buildings, locations with little foot traffic, and locations where crimes have occurred repeatedly in the past.

[0024] Images generated by the surveillance camera 5 are preferably transmitted to the surveillance device 100 in real time. However, the images transmitted to the surveillance device 100 do not have to be transmitted immediately from the surveillance camera 5, and may be images delayed by a predetermined time. Images generated by the surveillance camera 5 may be temporarily stored in another storage device, and the surveillance device 100 may read them out from the storage device sequentially or at predetermined intervals. Furthermore, the images transmitted to the surveillance device 100 are preferably moving images, but may be frame images at predetermined intervals or still images.

[0025] The connection between the surveillance camera 5 and the monitoring device 100 may be wireless or wired. In the case of a wireless connection, it is assumed that the surveillance camera 5 and the monitoring device 100 each have a wireless communication function. The surveillance camera 5 may be a network camera such as an IP (Internet Protocol) camera.

[0026] <Example of functional configuration> Fig. 2 is a functional block diagram showing an example of a logical configuration of the monitoring device 100 of Fig. 1. The monitoring device 100 includes a detection unit 102 and an output unit 104. The detection unit 102 detects a state in which the relative distance between the person 20 and the car 10 included in the image is equal to or less than a reference value (hereinafter also referred to as a close state). The output unit 104 outputs the type of information to be output, which is selected using the attributes of the person 20 detected as being in a close state.

[0027] The state where the relative distance between the person 20 and the car 10 is equal to or less than the reference value means that the distance between the person 20 and the car 10 is equal to or less than the reference value. The state where the relative distance between the person 20 and the car 10 is equal to or less than the reference value means that at least one of the person 20 and the car 10 moves and the relative distance between them gradually shortens to equal to or less than the reference value, that is, the person 20 and the car 10 approach each other over time. The detection unit 102 may detect a state where the person 20 is moving and approaching the car 10, or may detect a state where the car 10 is moving and approaching the person 20. The detection unit 102 may detect a state where both the person 20 and the car 10 are moving and the car 10 is approaching the person 20 from behind. The detection unit 102 may detect a state where the car 10 is approaching the person 20 from the front.

[0028] For example, the image processing device 200 detects the positions of characteristic parts of the person 20 and the car 10 identified in the images in a plurality of images in a time series with respect to changes in the relative distance between the person 20 and the car 10, and can estimate the moving direction of the person 20 and the car 10 and the relative distance between the person 20 and the car 10 from changes in the positions and relative positional relationship of the person 20 and the car 10. Based on the processing result of the image processing device 200, the detection unit 102 detects a state in which the relative distance between the person 20 and the car 10 included in the image is equal to or less than a reference value.

[0029] The attributes of the person 20 are determined based on at least one of the attributes extracted from the image, such as gender, age, facial features, height, possessions, clothing, and situation.

[0030] The type of information to be output is, for example, information about the type of crime, such as the possibility of kidnapping, the possibility of car break-in, etc. The output destination and output method may differ depending on the type of information to be output.

[0031] There are various possible output destinations, and for example, the output destination may be a monitor screen of a display device at a monitoring center, a terminal (not shown) carried by a security guard, or a monitor screen of a display device at a police station (not shown). The output method includes at least one of displaying on a monitor screen, sending an e-mail, and outputting a voice or alarm sound from a speaker (not shown). At least one of the destinations of an e-mail address, an IP address of a mobile terminal, and a mobile phone number to which the e-mail is to be sent may be registered in advance.

[0032] The output contents may include the video of the surveillance camera 5 that is the subject of the notification, together with information indicating the type of selected information. In the case of a monitoring center, the video of the surveillance camera 5 that is the subject of the notification may be highlighted in a state where the videos of multiple surveillance cameras 5 are multi-displayed. For example, only the video of the surveillance camera 5 that is the subject of the notification may be displayed in a single screen or enlarged from the multi-display. Alternatively, the frame of the relevant screen in the multi-display may be highlighted, or the highlighted image may be superimposed.

[0033] In addition to the video of the surveillance camera 5, still images of images captured by the surveillance camera 5, images (icons, animations, etc.) indicating the type of output information, text information indicating the type of output information, and information reporting the occurrence of a crime may be displayed. Alternatively, an alarm sound according to the type of output information or a voice indicating the type of output information may be output from a speaker in the surveillance center.

[0034] <Hardware configuration example> FIG. 3 is a block diagram illustrating an example of a hardware configuration of a computer 1000 that realizes each of the monitoring device 100 and the image processing device 200 of the monitoring system 1 shown in FIG.

[0035] The computer 1000 has a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input / output interface 1050, and a network interface 1060.

[0036] 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.

[0037] The processor 1020 is implemented by a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or the like.

[0038] The memory 1030 is a main storage device realized by a RAM (Random Access Memory) or the like.

[0039] 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), or the like. The storage device 1040 stores program modules that realize each function of the monitoring device 100 of the monitoring system 1 (e.g., the detection unit 102, the output unit 104, etc.). The processor 1020 loads each of these program modules onto the memory 1030 and executes them, thereby realizing each function corresponding to the program module. The storage device 1040 also functions as a storage unit that stores various information used by the monitoring device 100.

[0040] The program module may be recorded in a recording medium. The recording medium for recording the program module may include a non-transitory tangible medium usable by the computer 1000, and the program code readable by the computer 1000 (processor 1020) may be embedded in the medium.

[0041] The input / output interface 1050 is an interface for connecting the computer 1000 to various input / output devices.

[0042] The network interface 1060 is an interface for connecting the computer 1000 to a communication network 3. This communication network 3 is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network). The method for connecting the network interface 1060 to the communication network 3 may be a wireless connection or a wired connection. However, the network interface 1060 may not be used.

[0043] The computer 1000 is then connected to necessary devices (eg, a surveillance camera 5, a display (not shown), a speaker (not shown), etc.) via the input / output interface 1050 or the network interface 1060.

[0044] The monitoring system 1 is realized by a combination of a monitoring device 100 and an image processing device 200, and therefore by a plurality of computers 1000 constituting each of them. The monitoring device 100 is, for example, a server computer. The image processing device 200 may be a device separate from the monitoring device 100, may be a device included inside the monitoring device 100, or may be a combination of these.

[0045] Each component of the monitoring device 100 of this embodiment shown in Fig. 2 is realized by any combination of hardware and software of the computer 1000 shown in Fig. 3. Those skilled in the art will understand that there are various variations in the realization method and device. The functional block diagram showing the monitoring device 100 of each embodiment shows blocks of logical function units, rather than a configuration in hardware units.

[0046] <Example of operation> 4 is a flowchart showing an example of the operation of the monitoring device 100 of this embodiment. Based on the processing result of an image captured around the road, the detection unit 102 detects that the relative distance between the person 20 and the car 10 included in the image is equal to or less than a reference value (step S103), and the output unit 104 outputs the type of information selected using the person's attributes (step S107).

[0047] According to this embodiment, the detection unit 102 detects a person 20 and a vehicle 10 that are approaching each other, and the output unit 104 outputs information selected based on the attributes of the person 20. This makes it possible to detect situations in which a crime against a pedestrian or a vehicle, such as kidnapping or car break-in, may occur, using images from the surveillance camera 5 capturing images of the road and surrounding areas.

[0048] Second embodiment <Example of functional configuration> Fig. 5 is a functional block diagram showing an example of a logical configuration of the monitoring system of Fig. 1. In the first embodiment, the image processing device 200 is provided separately from the monitoring device 100, but in this embodiment, the monitoring device 100 will be described as having the functions of the image processing device 200. It goes without saying that the monitoring device 100 and the image processing device 200 may be separate or the same in terms of hardware.

[0049] The surveillance system 1 includes a surveillance device 100, a storage device 300, and a surveillance camera 5. The monitoring device 100 outputs information used for monitoring based on the image generated by the monitoring camera 5. The storage device 300 stores data necessary for performing image processing, such as information on features for identifying the car 10 or the person 20, and information on features used to distinguish the attributes of a person. The monitoring device 100 includes an acquisition unit 120 , an object identification unit 122 , a position identification unit 124 , an attribute identification unit 126 , a detection unit 102 , a selection unit 128 , and an output unit 104 .

[0050] The acquisition unit 120 acquires the images generated by the surveillance camera 5 . The object identification unit 122 identifies an object by performing image processing on the image acquired by the acquisition unit 120. The object identification unit 122 recognizes and identifies the person 20 and the vehicle 10. The position identifying section 124 identifies the positions of the person 20 and the vehicle 10 identified by the object identifying section 122 through image processing. The attribute identifying section 126 uses image processing to identify the attribute of the person 20 identified by the object identifying section 122. The attribute identifying section 126 identifies whether the person 20 has a first attribute or a second attribute.

[0051] The first attribute is an attribute that indicates a high possibility of being a crime victim. For example, the first attribute can be "female", "male", "child (e.g., estimated age X or younger)", "elderly person (e.g., estimated age Y or older)", "girl (e.g., female estimated age X or younger)", "boy (e.g., male estimated age X or younger), "tourist (e.g., person carrying a suitcase)", "acting alone (no one within a specified distance, etc.)". The first attribute is determined based on features extracted from the image, such as gender, age, facial features, height, belongings, clothing, and situation (where X and Y are integers).

[0052] The second attribute is an attribute that is different from the first attribute. The second attribute is an attribute that has the characteristics of a perpetrator of a criminal act, or an attribute other than the first attribute, that is, an attribute other than the attribute that makes a person more likely to be a victim of a criminal act.

[0053] For example, the second attribute may be a person who is carrying a dangerous object (e.g., carrying a long metal rod) or a person who is covering their face (e.g., wearing a mask, etc.) Similarly to the first attribute, the second attribute is also determined based on features extracted from the image, such as gender, age, facial features, height, belongings, clothing, and situation.

[0054] In addition, since the first attribute only needs to be an attribute that is likely to make a person a victim of a crime, it can be set according to the crime situation in the area. For example, in an area where "men" are more likely to be victims of crime, the first attribute may be "male," and in an area where "women" are more likely to be victims of crime, the first attribute may be "female."

[0055] The detection unit 102 acquires attributes related to the person 20 identified by the object identification unit 122 and the positions of the person 20 and the vehicle 10 . The detection unit 102 determines, for each pair of person 20 and vehicle 10 included in the image, based on the positions, whether or not the relative distance is equal to or less than a reference value, that is, whether or not they are in a close proximity state. When the detection unit 102 detects a person 20 and a vehicle 10 in an approaching state, the selection unit 128 acquires attributes of the person 20 in the approaching state. The selection unit 128 uses the attributes of the detected person 20 to select the type of information to be output. The output unit 104 outputs the type of information selected by the selection unit 128 .

[0056] <Example of operation> FIG. 6 is a flowchart showing an operation example of the monitoring system 1 of this embodiment. The monitoring device 100 acquires an image captured by the monitoring camera 5 and performs image processing (step S101). Specifically, the object identification unit 122 recognizes and identifies the person 20 and the car 10 from the acquired image. Then, the position identification unit 124 identifies the positions of the person 20 and the car 10 identified by the object identification unit 122. Next, the detection unit 102 detects whether the relative distance between the person 20 and the vehicle 10 included in the image is equal to or less than a reference value (step S103).

[0057] If the relative distance between the person 20 included in the image and the vehicle 10 is equal to or less than the reference value (YES in step S103), the attribute identification unit 126 identifies the attribute of the person 20 identified by the object identification unit 122 (step S104). The attribute identification unit 126 processes the person 20 included in the image and identifies whether the person has a first attribute or a second attribute. However, the timing for identifying the attributes of the person 20 may be before the detection unit 102 detects the approaching state of the person 20 and the vehicle 10. Then, the selection unit 128 selects the type of information to be output based on the attributes of the person 20 (step S105). Then, the output unit 104 outputs the selected type of information (step S107). The output unit 104 may also output an image and sound when the detection unit 102 detects the approaching state, as well as video before and after the detection unit 102 detects the approaching state.

[0058] As long as the detection unit 102 does not detect the person 20 and the vehicle 10 approaching each other, the process returns to step S101 and is repeated.

[0059] Fig. 7 is a flowchart showing an example of a detailed process procedure of step S105 in Fig. 6. The attribute specification unit 126 determines the attribute of the person 20 detected by the detection unit 102 (step S111). In step S111, when the attribute identification unit 126 determines that the person 20 is a person having the first attribute, the selection unit 128 selects a type of information indicating that the person 20 may be a victim of a crime. For example, the selection unit 128 selects information indicating that the person 20 may be kidnapped (step S115).

[0060] On the other hand, if the attribute identification unit 126 determines in step S111 that the detected person 20 is a person having the second attribute, the selection unit 128 selects a type of information indicating that the person 20 is likely to commit a crime against the car 10. For example, the selection unit 128 selects information indicating that the person 20 is likely to commit a car break-in (step S117). In other words, it can be said that the selection unit 128 selects whether the person 20 is likely to be victimized or the car 10 is likely to be victimized. After steps S115 and S117, the process returns to step S107 in FIG.

[0061] Returning to Fig. 6, the output unit 104 outputs the selected type of information to a predetermined output destination (step S107). For example, the output unit 104 outputs the selected type of information to the server 220 of the monitoring center, and the server 220 of the monitoring center may output information indicating that there is a possibility that abduction has occurred on a monitor screen of a display device of the monitoring center. Furthermore, an image in which the approach state is detected may be displayed.

[0062] In the above, the information output was exemplified as being displayed on a monitor screen, but other methods may be used as long as they can notify the user of the possibility of a crime occurring. For example, the selected information output by the output unit 104 may be output in various ways, such as voice output, alarm sound output, sending an e-mail to a terminal, notification, etc. Furthermore, the voice or alarm sound, the contents of the e-mail, or the notification contents may be changed according to the information selected by the output unit 104.

[0063] According to this embodiment, the detection unit 102 detects the person 20 and the car 10 that are approaching each other, the selection unit 128 selects the type of crime based on the attributes of the person 20, and the output unit 104 outputs the selected information. In this way, using images from the surveillance camera 5 capturing images of the road and surrounding areas, it is possible to detect situations in which a criminal act against a pedestrian or a car, such as kidnapping or car break-in, may occur, and therefore it is possible to detect the occurrence of a criminal act. Furthermore, if it is widely known that surveillance is being conducted by the surveillance camera 5, it is expected to have a deterrent effect on crime.

[0064] Furthermore, when the detection unit 102 detects an approaching state between the car 10 and the person 20, the output unit 104 can output information selected based on the attributes of the person 20. This makes it possible to notify the person 20 of the possibility of a car break-in before he or she enters the car 10, even if there is a possibility that the car 10 may be damaged by a car break-in or the like. For example, the output unit 104 can output a warning message or an alarm sound from a speaker or the like in the vicinity of the location. This can improve the crime prevention effect.

[0065] Third embodiment <Example of functional configuration> Fig. 8 is a functional block diagram showing an example of a logical configuration of the monitoring system of Fig. 1. The monitoring system 1 of this embodiment is similar to the above embodiment except that the moving speed of the vehicle 10 is used to determine the type of information to be output instead of the attribute of the person 20. The monitoring device 100 of this embodiment includes a moving speed estimation unit 130 instead of the attribute identification unit 126 of Fig. 5. The configuration of this embodiment may be combined with at least one of the configurations of the other embodiments to the extent that no contradiction occurs.

[0066] The monitoring device 100 includes an acquisition unit 120 , an object identification unit 122 , a position identification unit 124 , a moving speed estimation unit 130 , a detection unit 102 , a selection unit 128 , and an output unit 104 . The acquisition unit 120 acquires the images generated by the surveillance camera 5 . The object identification unit 122 identifies an object by performing image processing on the image acquired by the acquisition unit 120. The object identification unit 122 recognizes and identifies the person 20 and the vehicle 10. The position identifying section 124 identifies the positions of the person 20 and the vehicle 10 identified by the object identifying section 122 through image processing.

[0067] The moving speed estimation unit 130 detects the positions of the characteristic parts of the car 10 identified by the position identification unit 124 within multiple images in a time series, and estimates the moving speed from the change in the position of the car 10. The moving speed estimation unit 130 may also detect the positions of the characteristic parts of the person 20 and the car 10 identified within the images within multiple images in a time series, and estimate the change in the speed of the car 10 relative to the person 20 from the change in the relative positional relationship between the person 20 and the car 10. Furthermore, the moving speed estimation unit 130 can also estimate the moving directions of the person 20 and the car 10 in a similar manner.

[0068] For example, the travel speed estimation unit 130 can estimate the speed and the direction from which the car 10 is approaching the person 20, or the speed and the direction in which the car 10 is moving away from the person 20.

[0069] For example, in the case of kidnapping, the car 10 approaches the person 20 from behind at a low speed, puts the person 20 in the car 10, and drives away from the scene. Therefore, if the movement speed estimation unit 130 estimates that the movement speed of the car 10 is low and that the car 10 is moving in a direction approaching the person 20, it can determine that there is a risk of kidnapping. Also, in the case of car break-in, the person 20 approaches the stationary car 10 and then the person 20 leaves. Therefore, if the movement speed estimation unit 130 estimates that the car 10 is stationary, it can determine that there is a risk of car break-in. Note that if the movement speed of the car 10 is a normal driving speed, it can be determined that normal traffic is occurring.

[0070] The detection unit 102 determines, for each pair of person 20 and vehicle 10 included in the image, based on the positions, whether or not the relative distance is equal to or less than a reference value, that is, whether or not they are in a close proximity state. The selection unit 128 uses the moving speed of the car 10 estimated by the moving speed estimation unit 130 to select the type of information to be output. The output unit 104 outputs the type of information selected by the selection unit 128 .

[0071] <Example of operation> Fig. 9 is a flowchart showing an example of the operation of the monitoring system 1. The flowchart in Fig. 9 includes steps S101, S103, and S107 of the flowchart in Fig. 6, and further includes steps S204 and S205 instead of steps S104 and S105 of Fig. 6.

[0072] The monitoring device 100 acquires an image captured by the monitoring camera 5 and performs image processing (step S101). Specifically, the object identification unit 122 recognizes and identifies the person 20 and the car 10 from the acquired image. Then, the position identification unit 124 identifies the positions of the person 20 and the car 10 identified by the object identification unit 122. Next, the detection unit 102 detects whether the relative distance between the person 20 and the vehicle 10 included in the image is equal to or less than a reference value (step S103).

[0073] When the relative distance between the person 20 and the car 10 included in the image is equal to or less than the reference value (YES in step S103), the moving speed estimation unit 130 estimates the moving speed of the car 10 (step S204). Then, the selection unit 128 selects the type of information to be output based on the moving speed of the car 10 (step S205). Then, the output unit 104 outputs the selected type of information (step S107).

[0074] FIG. 10 is a flowchart showing an example of a detailed processing procedure of step S205 in FIG. 9. The moving speed estimation unit 130 determines the moving speed of the car 10 (step S211). If the moving speed estimation unit 130 determines in step S211 that the car 10 is approaching the person 20 at a low speed, the selection unit 128 determines that the person 20 may be a victim of a crime, and selects, as the type of information to be output, information of a type indicating that the person 20 may be a victim. For example, the selection unit 128 selects information indicating that the person 20 may be kidnapped (step S115). On the other hand, if the moving speed estimation unit 130 determines in step S211 that the car 10 is stationary, the selection unit 128 determines that there is a possibility that the person 20 will commit a crime, and selects, as the type of information to be output, information of a type indicating that the person 20 may commit a crime. For example, the selection unit 128 selects information indicating that there is a possibility that the person 20 will commit a car break-in (step S117). After steps S115 and S117, the process returns to step S107 in FIG.

[0075] 9. If the moving speed estimation unit 130 determines in step S211 that the moving speed of the car 10 is low and that the car 10 is neither approaching nor stationary, it can be determined that the car 10 is simply passing by, and the process returns to step S107 in FIG.

[0076] 9, the output unit 104 outputs the selected type of information (step S107). As long as the person 20 and the vehicle 10 that are approaching each other are not detected (NO in step S103), the process returns to step S101 and is repeated.

[0077] According to this embodiment, the detection unit 102 detects the person 20 and the car 10 that are approaching each other, and the selection unit 128 uses the moving speed of the car 10 to determine whether the person 20 is likely to become a victim of a crime or to commit a crime, and selects information based on the determination result. The output unit 104 then outputs the selected information. In this way, the type of criminal act, such as kidnapping or car break-in, can be detected using the images from the surveillance camera 5 capturing images of the road and surrounding area. In addition, if it is widely known that surveillance is being performed by the surveillance camera 5, a crime deterrent effect can be expected.

[0078] (Fourth embodiment) <Example of functional configuration> Fig. 11 is a functional block diagram showing an example of a logical configuration of the monitoring system of Fig. 1. The monitoring system 1 of this embodiment is similar to any of the above embodiments except that the monitoring device 100 has both the functions of the second embodiment and the functions of the third embodiment. The monitoring device 100 of this embodiment may be combined with at least one of the configurations of the other embodiments to the extent that no contradiction occurs.

[0079] The monitoring device 100 includes an acquisition unit 120 , an object identification unit 122 , a position identification unit 124 , an attribute identification unit 126 , a travel speed estimation unit 130 , a detection unit 102 , a selection unit 128 , and an output unit 104 .

[0080] The acquisition unit 120 acquires the images generated by the surveillance camera 5 . The object identification unit 122 identifies an object by performing image processing on the image acquired by the acquisition unit 120. The object identification unit 122 recognizes and identifies the person 20 and the vehicle 10. The position identifying section 124 identifies the positions of the person 20 and the vehicle 10 identified by the object identifying section 122 through image processing.

[0081] The attribute specifying unit 126 uses image processing to specify the attribute of the person 20. The attribute specifying unit 126 specifies whether the person 20 has a first attribute or a second attribute. The moving speed estimation unit 130 detects the positions of the characteristic parts of the car 10 identified by the position identification unit 124 within a plurality of images in a time series, and estimates the moving speed of the car 10 from the change in position of the car 10 . The detection unit 102 determines, for each pair of person 20 and vehicle 10 included in the image, based on the positions, whether or not the relative distance is equal to or less than a reference value, that is, whether or not they are in a close proximity state. The selection unit 128 uses the travel speed of the car 10 estimated by the travel speed estimation unit 130 and the attribute identified by the attribute identification unit 126 to select the type of information to be output. The output unit 104 outputs the type of information selected by the selection unit 128 .

[0082] <Example of operation> Fig. 12 is a flowchart showing an example of the operation of the monitoring system 1. The flowchart in Fig. 12 includes steps S101, S103, S104, and S107 of the flowchart in Fig. 6 and step S204 of Fig. 9, and further includes step S305 instead of step S105 of Fig. 6 or step S205 of Fig. 9.

[0083] The monitoring device 100 acquires an image captured by the monitoring camera 5 and performs image processing (step S101). Specifically, the object identification unit 122 recognizes and identifies the person 20 and the car 10 from the acquired image. Then, the position identification unit 124 identifies the positions of the person 20 and the car 10 identified by the object identification unit 122. Next, the detection unit 102 detects whether the relative distance between the person 20 and the vehicle 10 included in the image is equal to or less than a reference value (step S103).

[0084] If the relative distance between the person 20 and the car 10 included in the image is equal to or less than the reference value (YES in step S103), the attribute identification unit 126 identifies the attribute of the person 20 identified by the object identification unit 122 (step S104). Furthermore, the movement speed estimation unit 130 detects the positions of the characteristic parts of the car 10 identified by the position identification unit 124 within multiple images in time series, and estimates the movement speed of the car 10 from the change in the position of the car 10 (step S204). Then, the selection unit 128 selects the type of information to be output based on the attributes of the person 20 and the moving speed of the car 10 (step S305). Then, the output unit 104 outputs the selected type of information (step S107).

[0085] Fig. 13 is a flowchart showing an example of a detailed processing procedure of step S305 in Fig. 12. The attribute identification unit 126 determines the attribute of the person 20 identified by the object identification unit 122 (step S111). In step S111, the attribute identification unit 126 determines whether the person 20 is a person having a first attribute, and if it is determined that the person 20 is a person having the first attribute, the process proceeds to step S121. On the other hand, if it is determined that the person 20 is a person having a second attribute in step S111, the process proceeds to step S123.

[0086] In step S121, if the moving speed estimation unit 130 determines that the car 10 is approaching the person 20 at a low speed (YES in step S121), the selection unit 128 determines that the person 20 may be a victim of a crime, and selects, as the type of information to be output, information of a type indicating that the person 20 may be a victim. For example, the selection unit 128 selects information indicating that the person 20 may be kidnapped (step S115). If the moving speed estimation unit 130 determines that the car 10 is not approaching the person 20 at a low speed (NO in step S121), it can be determined that the car 10 is simply passing by, and the process returns to step S107 in FIG. 12.

[0087] In step S123, if the travel speed estimation unit 130 determines that the car 10 is stationary (YES in step S123), the selection unit 128 determines that the car 10 is stationary, determines that there is a possibility that the person 20 will commit a crime, and selects, as the type of information to be output, information of a type indicating that there is a possibility that the person 20 will commit a crime. For example, the selection unit 128 selects information indicating that there is a possibility that the person 20 will commit a car break-in (step S117). If the travel speed estimation unit 130 determines that the car 10 is not stationary (NO in step S123), it can be determined that the car 10 is simply passing by, and the process returns to step S107 in FIG. 12. After steps S115 and S117, the process returns to step S107 in FIG.

[0088] Fig. 14 is a flowchart showing another example of the detailed processing procedure of step S305 in Fig. 12. The processing procedure shown in Fig. 14 is the same as that in Fig. 13 except that discrimination is first performed using the moving speed of the car 10 (step S211), and then discrimination is performed using the attributes of the person 20 (steps S131 and S133).

[0089] The selection unit 128 makes a determination based on the moving speed of the car 10 estimated by the moving speed estimation unit 130 (step S211). If the moving speed estimation unit 130 determines in step S211 that the car 10 is approaching the person 20 at a low speed, the process proceeds to step S131. If the moving speed estimation unit 130 determines in step S211 that the car 10 is stationary, the process proceeds to step S133. Also, if the moving speed estimation unit 130 determines in step S211 that the moving speed of the car 10 is low and is neither approaching nor stationary, the process returns to step S107 in FIG. 12 since it can be determined that the car 10 is simply passing by.

[0090] In step S131, when the attribute identification unit 126 determines that the person 20 is a person having the first attribute (YES in step S131), the selection unit 128 selects, as the type of information to be output, information of a type indicating that the person 20 may be harmed. For example, the output unit 104 selects information indicating that the person 20 may be kidnapped (step S115). When the person 20 is determined not to be a person having the first attribute (NO in step S131), the process returns to step S107 in FIG. 12.

[0091] In step S133, if the attribute identification unit 126 determines that the person 20 is a person having the second attribute (YES in step S133), the selection unit 128 determines that there is a possibility that the person 20 will commit a crime, and selects, as the type of information to be output, information of a type indicating that the person 20 is likely to commit a crime. For example, the selection unit 128 selects information indicating that the person 20 is likely to commit a car break-in (step S117). If the attribute identification unit 126 determines that the person 20 is not a person having the second attribute (NO in step S133), the process returns to step S107 in FIG. 12. After steps S115 and S117, the process returns to step S107 in FIG.

[0092] In step S107 of Fig. 12, if it is determined that the vehicle 10 is simply passing or stopping in step S121, step S123, or step S211, step S131, or step S133 of the flowchart in Fig. 13 or Fig. 14, the type of information to be output is not selected, so the output unit 104 performs processing without outputting information. However, if it is determined that the vehicle 10 is simply passing or stopping in step S121, step S123, or step S211, step S131, or step S133 of the flowchart in Fig. 13 or Fig. 14, the type of information to be output may be selected to indicate that the vehicle 10 is passing or stopping, respectively. In that case, in step S107 of Fig. 12, the output unit 104 may select and output information indicating that the vehicle 10 is passing or stopping, respectively.

[0093] According to this embodiment, the same effects as those of the above embodiment can be achieved, and further, the type of information to be output can be selected using both the moving speed of the car 10 and the attributes of the person 20, thereby increasing the possibility of detecting criminal acts with greater accuracy.

[0094] Fifth embodiment <Example of functional configuration> Fig. 15 is a functional block diagram showing an example of the logical configuration of the monitoring system of Fig. 1. The monitoring system 1 of this embodiment is the same as that of the second embodiment, except that the type of information to be output is selected depending on whether the person 20 is acting alone or not. The monitoring device 100 of this embodiment further has a number of people identification unit 132 in addition to the configuration of the second embodiment of Fig. 5. However, the monitoring device 100 of this embodiment may be combined with at least one of the configurations of the other embodiments to the extent that no contradiction occurs.

[0095] The monitoring device 100 includes an acquisition unit 120 , an object identification unit 122 , a position identification unit 124 , an attribute identification unit 126 , a number of people identification unit 132 , a detection unit 102 , a selection unit 128 , and an output unit 104 . The acquisition unit 120 acquires the images generated by the surveillance camera 5 .

[0096] The object identification unit 122 identifies an object by performing image processing on the image acquired by the acquisition unit 120. The object identification unit 122 recognizes and identifies the person 20 and the vehicle 10. The position identification unit 124 identifies the positions of the person 20 and the vehicle 10 identified by the object identification unit 122 . The attribute specifying unit 126 uses image processing to specify the attribute of the person 20. The attribute specifying unit 126 specifies whether the person 20 has a first attribute or a second attribute.

[0097] The number of people specifying unit 132 specifies the number of people 20. For example, the object specifying unit 122 determines whether multiple people 20 have been specified. When the object specifying unit 122 specifies multiple people 20, the number of people specifying unit 132 determines whether there are people 20 whose mutual distances are within a reference value. For example, the number of people specifying unit 132 determines whether there are people 20 whose mutual distances are within a reference value, based on the positions of the people 20 specified by the position specifying unit 124. Note that this reference value may be the same as the reference value for determining the relative distance between the car 10 and the people 20, or may be a different value. The number of people specifying unit 132 determines that a person is not acting alone when there is a person whose distance from the plurality of people 20 is within a reference value. The number of people specifying unit 132 determines that a person is acting alone when there is no person whose distance from the plurality of people 20 is within a reference value.

[0098] This is because kidnappings are especially likely to occur when people are alone. However, solo activities can also be carried out by a small group of people, such as 2-3 people. The detection unit 102 determines, for each pair of person 20 and vehicle 10 included in the image, based on the positions, whether or not the relative distance is equal to or less than a reference value, that is, whether or not they are in a close proximity state. The selection unit 128 selects the type of information to be output depending on whether the determination result in the number-of-persons determination unit 132 is that the person 20 is acting alone or not. The output unit 104 outputs the type of information selected by the selection unit 128 .

[0099] <Example of operation> Fig. 16 is a flowchart showing an example of the operation of the monitoring system 1. The flowchart in Fig. 16 includes step S141 instead of step S121 in the flowchart in Fig. 13. However, the flowchart in Fig. 16 may also include step S121 in Fig. 13. The order of step S121 and step S141 is not particularly limited.

[0100] The attribute identification unit 126 determines the attribute of the person 20 identified by the object identification unit 122 (step S111). If the attribute identification unit 126 determines in step S111 that the person 20 has the first attribute, the process proceeds to step S141. On the other hand, if the attribute identification unit 126 determines in step S111 that the person 20 has the second attribute, the process proceeds to step S123.

[0101] In step S141, if the number of people identification unit 132 determines that the person 20 is acting alone (YES in step S141), the selection unit 128 selects, as the type of information to be output, information of a type indicating that the person 20 may be harmed. For example, the output unit 104 selects information indicating that the person 20 may be kidnapped (step S115). If the number of people identification unit 132 determines that the person 20 is not acting alone (NO in step S141), it can be determined that the person 20 is simply passing by a car 10, and the process returns to step S107 in FIG. 12.

[0102] The process from step S123 onwards is the same as that in FIG. 13, and therefore the description will be omitted.

[0103] Fig. 17 is a flowchart showing another example of the operation of the monitoring system 1. The flowchart in Fig. 17 is the same as Fig. 16 except that the order of steps S111 and S141 in the flowchart in Fig. 16 is switched. The flowchart in Fig. 17 may include step S121 in Fig. 13. In that case, the order of steps S121 and S141 is not particularly limited.

[0104] The number of people identification unit 132 determines whether the person 20 is acting alone (step S141). If the number of people identification unit 132 determines in step S141 that the person 20 is acting alone (YES in step S141), the process proceeds to step S111. If the number of people identification unit 132 determines in step S141 that the person 20 is not acting alone (NO in step S141), the process returns to step S107 in FIG. 12 because it can be determined that the person 20 is simply passing by a car 10.

[0105] In step S111, the attribute identification unit 126 determines the attribute of the person 20 identified by the object identification unit 122. If the attribute identification unit 126 determines in step S111 that the person 20 has the first attribute, the process proceeds to step S115. On the other hand, if the attribute identification unit 126 determines in step S111 that the person 20 has the second attribute, the process proceeds to step S123. The process thereafter is the same as in FIG. 16, and therefore will not be described.

[0106] According to this embodiment, the number of people determination unit 132 determines whether the person 20 is acting alone, and if so, outputs a message indicating that there is a high possibility of kidnapping. By combining this with other conditions, the accuracy of the determination can be improved and frequent notifications can be prevented.

[0107] Sixth embodiment <Example of functional configuration> The monitoring system 1 of this embodiment differs from the above-described fourth embodiment in that the vehicle 10 is stationary, the vehicle 10 detects the entry and exit of a person 20 from the stationary vehicle 10, and the result is used to select the type of information to be output. That is, the operation of the detection unit 102 and the operation of the selection unit 128 are different. The following describes the fourth embodiment using the functional block diagram of FIG. 11. However, the monitoring device 100 of this embodiment may be combined with at least one of the configurations of the other embodiments to the extent that no contradiction occurs.

[0108] The detection unit 102 determines whether or not the relative distance between each pair of person 20 and vehicle 10 included in the image is equal to or less than a reference value, that is, whether or not they are in an approaching state, based on the positions. Furthermore, when the detection unit 102 determines that the vehicle 10 that the detection unit 102 determines to be in an approaching state is in a stationary state based on the travel speed estimated by the travel speed estimation unit 130, the detection unit 102 further detects whether or not a person is entering or leaving the vehicle 10. The selection unit 128 further uses the detection result of the detection unit 102 regarding the entrance and exit of people to select the type of information to be output.

[0109] For example, as shown in FIG. 18, in the case of kidnapping, the car 10 approaches the person 20 (FIG. 18(a) to FIG. 18(b)), and from inside the car 10, the person may reach out an arm to grab the person 20 and drag him / her into the car 10, taking him / her away (FIG. 18(c)). In other words, in the case of kidnapping, the person does not come out of the stationary car 10. In the case of car break-in, it is highly likely that the driver will come out of the stationary car 10. This situation can be detected to distinguish between kidnapping and car break-in.

[0110] <Example of operation> Fig. 19 is a flowchart showing an example of the operation of the monitoring system 1. The flowchart in Fig. 19 includes step S211, step S131, step S133, step S115, and step S117 of the flowchart in Fig. 14, and further includes step S151.

[0111] In step S211, if the travel speed estimation unit 130 estimates that the car 10 is traveling at a low speed and the detection unit 102 determines that the car 10 is approaching a person 20, the process proceeds to step S131, and the attribute identification unit 126 identifies the attributes of the person 20.

[0112] Next, if the travel speed estimation unit 130 determines in step S211 that the car 10 is stationary, the process proceeds to step S151. In step S151, the detection unit 102 determines whether or not a person, i.e., the driver, has emerged from the stationary car 10. For example, the detection unit 102 can detect the entry or exit of a person by determining whether or not a person has emerged from the car within a predetermined time after the travel speed estimation unit 130 has determined that the car 10 is stationary.

[0113] If the detection unit 102 detects that no person has emerged from the vehicle 10 within a predetermined time (NO in step S151), there is a high possibility of kidnapping, so the process proceeds to step S131. Also, if the movement speed estimation unit 130 determines in step S211 that the movement speed of the vehicle 10 is slow and that the vehicle is neither approaching nor stationary, it can be determined that the vehicle 10 is simply passing by, so the process returns to step S107 in Fig. 12. The process from step S131 onwards is the same as in the above embodiment, so a description thereof will be omitted.

[0114] On the other hand, if the detection unit 102 detects that a person is emerging from the vehicle 10 (YES in step S151), the attribute identification unit 126 determines the attribute of the person 20 in the approaching state (step S133). If the attribute identification unit 126 determines that the person 20 has the second attribute (YES in step S133), the selection unit 128 selects information indicating that the person 20 may commit a vehicle break-in (step S117), as in FIG. 14.

[0115] According to this embodiment, it is possible to select the type of information to be processed by detecting whether or not a person has emerged from the stationary vehicle 10. This makes it possible to further improve the accuracy of discrimination.

[0116] Although the embodiments of the present invention have been described above with reference to the drawings, these are merely examples of the present invention, and various configurations other than those described above can also be adopted. For example, because criminal activity is detected using images from the surveillance camera 5, the images can be recorded when the criminal activity is detected, and the recordings can be used as evidence at the time the crime occurs. This can lead to the early resolution of cases, the arrest of criminals, and the rescue of victims.

[0117] Furthermore, the detection unit 102 may perform processing using images from a specific surveillance camera 5 among multiple surveillance cameras 5 capturing images of the road and surrounding areas. As described above, surveillance may be performed using images from surveillance cameras 5 installed in areas with particularly bad security, or areas where crimes such as kidnappings and car break-ins frequently occur. In addition, a priority may be assigned to specific surveillance cameras 5, and the proportion of surveillance time for the surveillance camera 5 with the higher priority may be set longer than that for the other surveillance cameras 5.

[0118] Furthermore, the detection unit 102 may obtain and store a facial image of the person 20 when the relative distance between the car 10 and the person 20 is detected to be equal to or less than a reference value. The facial image can be stored in the memory 1030 or the storage device 1040 in FIG. 3.

[0119] As shown in Fig. 20, in the case of a car break-in, the owner 30 of the car 10 first emerges from the stopped car 10 (Fig. 20(a)). The detection unit 102 detects that a person has emerged from the car 10, obtains a facial image of person A (the owner of the car 10) who emerged from the car 10, and temporarily stores the image.

[0120] Monitoring continues and the detection unit 102 detects a person 20 approaching the car 10 (Fig. 20(b)). At this time, it acquires a facial image of the person 20. The detection unit 102 may then transmit the facial image of person A acquired earlier and the facial image of person 20 acquired later to the image processing device 200 to compare whether they are the same person or not. The selection unit 128 uses the comparison result to select the type of information to be output. If they are not the same person, it is determined that there has been a car break-in (Fig. 20(c)). If they are the same person, it is determined that they are the owner.

[0121] Also, if a facial image cannot be captured, if the person 20 who approaches the car 10 in FIG. 20(b) enters the car 10 once and then comes out immediately (after a specified time), it may be determined that the person has committed a car break-in.

[0122] Furthermore, other processing procedures of an example in which the entrance and exit of a person from the stopped car 10 described in FIG. 19 of the fifth embodiment is detected and the result is used can be considered. FIG. 21 is a flowchart showing an example of the operation of the monitoring system 1. The flowchart in FIG. 21 includes step S151 instead of step S131 in the flowchart in FIG. 14. In this example, if the detection unit 102 determines in step S211 that the car 10 is approaching the person 20 at a low speed, the process proceeds to step S151 to determine whether or not a person has come out of the car 10. If the detection unit 102 cannot detect that a person has come out (NO in step S151), there is a high possibility of kidnapping, so the process proceeds to step S115. If the detection unit 102 detects that a person has come out (YES in step S151), it can be determined that the car 10 is simply stopped, so the process returns to step S107 in FIG. 12. The other processing is the same as that in FIG. 14, so a description thereof will be omitted.

[0123] Although the present invention has been described above with reference to the embodiments and examples, the present invention is not limited to the above-mentioned embodiments and examples. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. In addition, when information about users is acquired and / or used in the present invention, this shall be done lawfully.

[0124] Below, examples of reference forms are given. 1. A detection means for processing an image captured around a road and detecting whether the relative distance between a person and a vehicle included in the image is equal to or less than a reference value; and an output means for selecting a type of information to be output using an attribute of the person detected to be in the state, and outputting the selected type of information. 2. In the monitoring device according to 1., The output means further selects the type of information to be output using the moving speed of the vehicle detected as being in the state. 3. A detection means for processing an image captured around a road and detecting whether the relative distance between a person and a vehicle included in the image is equal to or less than a reference value; and an output means for selecting a type of information to be output using the moving speed of the vehicle detected as being in the said state, and outputting the selected type of information. 4. In the monitoring device according to any one of 1. to 3., The output means includes: The monitoring device further selects the type of information to be output depending on whether the person detected to be in the state is acting alone or not. 5. In the monitoring device according to any one of 1. to 4., The detection means detects that the vehicle detected to be in the above-mentioned state is stationary, and detects the entry and exit of people after the vehicle has come to a standstill, The output means further uses the detection result by the detection means to select the type of information to be output. 6. In the monitoring device according to any one of 1. to 5., A monitoring device, wherein the detection means performs the processing using an image from a specific camera among a plurality of cameras capturing images of the area around the road.

[0125] 7. Multiple cameras that capture images of the road and its surroundings; A monitoring device for monitoring images captured by the plurality of cameras, The monitoring device includes: a detection means for processing an image captured around a road and detecting whether a relative distance between a person and a vehicle included in the image is equal to or less than a reference value; and an output means for selecting a type of information to be output using an attribute of the person detected to be in the state, and outputting the selected type of information. 8. In the monitoring system according to 7., A monitoring system in which the output means of the monitoring device further selects the type of information to be output using the moving speed of the vehicle detected to be in the state. 9. Multiple cameras that capture images of the road and surrounding areas; A monitoring device for monitoring images captured by the plurality of cameras, The monitoring device includes: a detection means for processing an image captured around a road and detecting whether a relative distance between a person and a vehicle included in the image is equal to or less than a reference value; and an output means for selecting a type of information to be output using the moving speed of the vehicle detected as being in the said state, and outputting the selected type of information. 10. In the monitoring system according to any one of 7. to 9., The output means of the monitoring device The monitoring system further selects the type of information to be output depending on whether the person detected to be in the state is acting alone. 11. In the monitoring system according to any one of 7. to 10., The detection means of the monitoring device detects that the vehicle is in the above-mentioned state and is stationary, and detects the entry and exit of people from the vehicle after the vehicle has stopped; A monitoring system, wherein the output means of the monitoring device further uses a detection result by the detection means to select the type of information to be output. 12 In the monitoring system according to any one of 7. to 11., A surveillance system in which the detection means of the surveillance device performs the processing using an image from a specific camera among a plurality of cameras capturing images of the area around the road.

[0126] 13. Surveillance equipment: Processing an image of the road surroundings and detecting whether the relative distance between a person and a vehicle included in the image is equal to or less than a reference value; A monitoring method comprising: selecting a type of information to be output using an attribute of the person detected to be in the state; and outputting the selected type of information. 14. In the monitoring method according to 13., The monitoring method further comprises the step of selecting the type of information to be output using a moving speed of the vehicle detected as being in the state. 15. Surveillance equipment: Processing an image of the road surroundings and detecting whether the relative distance between a person and a vehicle included in the image is equal to or less than a reference value; A monitoring method comprising: selecting a type of information to be output using the moving speed of the vehicle detected as being in the state; and outputting the selected type of information. 16. In the monitoring method according to any one of 13. to 15., The monitoring device, The monitoring method further comprises selecting the type of information to be output depending on whether the person detected to be in the state is acting alone. 17. In the monitoring method according to any one of 13. to 16., The monitoring device, The vehicle detected as being in the above-mentioned state is stationary, and detecting people entering or exiting the vehicle after the vehicle has come to a standstill; A monitoring method further comprising: selecting the type of information to be output using a result of the detection. 18. In the monitoring method according to any one of 13. to 17., The monitoring device, A surveillance method in which the processing is performed using an image from a specific camera among a plurality of cameras capturing images of the road and its surroundings.

[0127] 19. To the computer: A step of processing an image captured around a road and detecting whether a relative distance between a person and a vehicle included in the image is equal to or less than a reference value; A program for executing a procedure of selecting a type of information to be output using attributes of the person detected to be in the state, and outputting the selected type of information. 20. In the program according to paragraph 19, Further, the program causes the computer to execute a procedure of selecting the type of information to be output using the moving speed of the vehicle detected to be in the above-mentioned state. 21. To the computer: A step of processing an image captured around a road and detecting whether a relative distance between a person and a vehicle included in the image is equal to or less than a reference value; A program for executing a procedure of selecting a type of information to be output using the moving speed of the vehicle detected to be in the said state, and outputting the selected type of information. 22. In the program according to any one of 19. to 21., Further, the program causes a computer to execute a procedure for selecting the type of information to be output depending on whether the person detected to be in the state is acting alone or not. 23. In the program according to any one of 19. to 22., the vehicle detected to be in the said state is in a stationary state, and a step of detecting entry or exit of a person after the vehicle has come to a stationary state; A program for causing a computer to execute a procedure for selecting a type of information to be output by further using a detection result from the detection procedure. 24. In the program according to any one of 19. to 23., A program for causing a computer to execute a procedure for performing the above-mentioned processing using images from a specific camera among a plurality of cameras capturing images of the road and its surroundings.

[0128] Further reference examples are given below. 25. A detection means for processing an image captured around a road and detecting whether the relative distance between a person and a vehicle included in the image is equal to or less than a reference value; and an output means for outputting a type of information to be output selected using an attribute of the person detected as being in the state. 26. In the monitoring device according to 25., An acquisition means for acquiring the image of the road surroundings captured by a camera; an object identification means for identifying and recognizing people and vehicles by performing image processing on the image acquired by the acquisition means; a position identification means for identifying a position of the person and the vehicle identified by the object identification means by performing the image processing; an attribute specifying means for specifying an attribute of the person specified by the position specifying means by performing the image processing; a selection means for selecting the type of information to be output for the detected person by using the identified attribute when the detection means detects a person and a vehicle in the state, The output means outputs the type of information selected by the selection means. 27. In the monitoring device according to 25. or 26., An acquisition means for acquiring the image of the road surroundings captured by a camera; an object identification means for identifying and recognizing people and vehicles by performing image processing on the image acquired by the acquisition means; a position identification means for identifying a position of the person and the vehicle identified by the object identification means by performing the image processing; a moving speed estimating means for estimating a moving speed of the vehicle identified by the position identifying means from a change in the position of the vehicle; a selection means for selecting the type of information to be output by using the travel speed of the vehicle estimated by the travel speed estimation means, The output means outputs the type of information selected by the selection means. 28. In the monitoring device according to any one of 25. to 27., An acquisition means for acquiring the image of the road surroundings captured by a camera; an object identification means for identifying and recognizing people and vehicles by performing image processing on the image acquired by the acquisition means; a position identification means for identifying a position of the person and the vehicle identified by the object identification means by performing the image processing; a number-of-people specifying means for specifying the number of people specified by the object specifying means and determining whether the specified people are acting alone; a selection means for selecting the type of information to be output in accordance with the determination result of the number of people specification means, The output means outputs the type of information selected by the selection means.

[0129] 31. A plurality of cameras for capturing images of the road and surroundings; A monitoring device for monitoring images captured by the plurality of cameras, The monitoring device includes: a detection means for processing an image captured around a road and detecting whether a relative distance between a person and a vehicle included in the image is equal to or less than a reference value; and an output means for outputting a type of information to be output selected using an attribute of the person detected as being in the state. 32. In the monitoring system according to 31., The monitoring device includes: An acquisition means for acquiring the image of the road surroundings captured by a camera; an object identification means for identifying and recognizing people and vehicles by performing image processing on the image acquired by the acquisition means; a position identification means for identifying a position of the person and the vehicle identified by the object identification means by performing the image processing; an attribute specifying means for specifying an attribute of the person specified by the position specifying means by performing the image processing; a selection means for selecting the type of information to be output for the detected person by using the identified attribute when the detection means detects a person and a vehicle in the state, A monitoring system, wherein the output means of the monitoring device outputs the type of information selected by the selection means. 33. In the monitoring system according to 31. or 32., The monitoring device includes: An acquisition means for acquiring the image of the road surroundings captured by a camera; an object identification means for identifying and recognizing people and vehicles by performing image processing on the image acquired by the acquisition means; a position identification means for identifying a position of the person and the vehicle identified by the object identification means by performing the image processing; a moving speed estimating means for estimating a moving speed of the vehicle identified by the position identifying means from a change in the position of the vehicle; a selection means for selecting the type of information to be output by using the travel speed of the vehicle estimated by the travel speed estimation means, A monitoring system, wherein the output means of the monitoring device outputs the type of information selected by the selection means. 34. In the monitoring system according to any one of 31. to 33., The monitoring device includes: An acquisition means for acquiring the image of the road surroundings captured by a camera; an object identification means for identifying and recognizing people and vehicles by performing image processing on the image acquired by the acquisition means; a position identification means for identifying a position of the person and the vehicle identified by the object identification means by performing the image processing; a number-of-people specifying means for specifying the number of people specified by the object specifying means and determining whether the specified people are acting alone; a selection means for selecting the type of information to be output in accordance with the determination result of the number of people specification means, A monitoring system, wherein the output means of the monitoring device outputs the type of information selected by the selection means. 35. In the monitoring system according to 33. or 34. which quotes 33., When the detection means of the monitoring device determines that the vehicle detected as being in the above-mentioned state is in a stationary state based on the moving speed estimated by the moving speed estimation means, the detection means further detects whether a person is entering or exiting the vehicle; the selection means of the monitoring device further uses the detection result of the entry and exit of the person by the detection means to select the type of the information to be output; A monitoring system, wherein the output means of the monitoring device outputs the type of information selected by the selection means. 36. In the monitoring system according to any one of 31. to 35., A surveillance system in which the detection means of the surveillance device performs the processing using an image from a specific camera among a plurality of cameras capturing images of the area around the road.

[0130] 37. Surveillance equipment: Processing an image of the road surroundings and detecting whether the relative distance between a person and a vehicle included in the image is equal to or less than a reference value; A monitoring method that outputs a type of information to be output selected using an attribute of the person detected to be in the state. 38. In the monitoring method according to 37., The monitoring device, Acquiring the image of the road surroundings generated by a camera; The acquired image is subjected to image processing to recognize and identify people and vehicles; performing the image processing on the identified person and vehicle to identify their positions; Identifying attributes of the identified person by performing the image processing; When a person and a vehicle in the state are detected, selecting the type of information to be output for the detected person using the identified attribute; and outputting said selected type of information. 39. In the monitoring method according to 37. or 38., The monitoring device, Acquiring the image of the road surroundings generated by a camera; The acquired image is subjected to image processing to recognize and identify people and vehicles; The position of the identified person and vehicle is identified by performing the image processing; Estimating a moving speed of the identified vehicle from a change in position of the vehicle; selecting the type of information to be output using the estimated travel speed of the vehicle; outputting said selected type of information. 40. In the monitoring method according to any one of 37. to 39., The monitoring device, Acquiring the image of the road surroundings generated by a camera; The acquired image is subjected to image processing to recognize and identify people and vehicles; The position of the identified person and vehicle is identified by performing the image processing; Identifying the number of the identified people, and determining whether the identified people are acting alone; Selecting the type of information to be output according to the result of the determination; A monitoring method that outputs selected types of information. 41. In the monitoring method according to 39. and 40. which refers to 39., The monitoring device, When it is determined that the vehicle detected to be in the above-mentioned state is stationary based on the estimated moving speed, it is further determined whether a person is entering or exiting the vehicle; further using the result of the detection of the entry and exit of the person to select the type of the information to be output; A monitoring method that outputs selected types of information. 42. In the monitoring method according to any one of 37. to 41., The monitoring device, A surveillance method in which the processing is performed using an image from a specific camera among a plurality of cameras capturing images of the road and its surroundings.

[0131] 43. To the computer: A step of processing an image captured around a road and detecting whether a relative distance between a person and a vehicle included in the image is equal to or less than a reference value; A program for executing a procedure for outputting a type of information to be output selected using an attribute of the person detected to be in the state. 44. In the program according to 43., acquiring the image of the road surroundings generated by a camera; a step of performing image processing on the image acquired in the acquiring step to recognize and identify people and vehicles; a step of performing the image processing on the person and the vehicle identified in the step of identifying the person and the vehicle to identify their positions; A step of identifying attributes of the person identified in the step of identifying the position by performing the image processing; a step of selecting the type of information to be output for the detected person using the identified attribute when a person and a vehicle in the state are detected in the detection step; A program for causing a computer to execute a procedure for outputting the type of information selected in the selection procedure. 45. In the program according to 43. or 44., acquiring the image of the road surroundings generated by a camera; a step of performing image processing on the image acquired in the acquiring step to recognize and identify people and vehicles; a step of identifying positions of the person and the vehicle by performing the image processing on the person and the vehicle identified in the step of identifying the person and the vehicle; a step of estimating a moving speed of the vehicle identified in the step of identifying the position based on a change in the position of the vehicle; selecting the type of information to be output using the travel speed of the vehicle estimated in the step of estimating the travel speed; A program for causing a computer to execute a procedure for outputting the type of information selected in the selection procedure. 46. ​​In the program according to any one of 43. to 45., acquiring the image of the road surroundings generated by a camera; a step of performing image processing on the image acquired in the acquiring step to recognize and identify people and vehicles; a step of identifying positions of the person and the vehicle by performing the image processing on the person and the vehicle identified in the step of identifying the person and the vehicle; a step of identifying the number of people identified in the step of identifying people and vehicles, and determining whether the identified people are acting alone; selecting the type of information to be output according to the result of the determination; A program for causing a computer to execute a procedure for outputting the type of information selected in the selection procedure. 47. In the program described in 45. or 46. which references 45., a step of detecting whether or not a person is entering or leaving the vehicle when it is determined that the vehicle detected to be in the above-mentioned state is stationary based on the moving speed estimated in the step of estimating the moving speed; a step of selecting the type of information to be output using the result of the detection of the entry and exit of people; The output means outputs the type of information selected by the selection means. 48. In the program according to any one of claims 43 to 47, A program for causing a computer to execute a procedure for performing the above-mentioned processing using images from a specific camera among a plurality of cameras capturing images of the road and its surroundings.

[0132] This application claims priority to International Application No. PCT / JP2020 / 001760, filed on January 20, 2020, the disclosure of which is incorporated herein in its entirety. [Explanation of symbols]

[0133] 1. Surveillance System 3. Communication Network 5. Surveillance Cameras 10 cars 20 people 30 owners 100 Monitoring equipment 102 Detection unit 104 Output section 120 Acquisition Department 122 Object identification part 124 Location identification part 126 Attribute identification part 128 Selection 130 Movement speed estimation section 132 Number of people identification department 200 Image processing device 220 Server 300 storage device 1000 Computers 1010 Bus 1020 Processor 1030 Memory 1040 Storage Device 1050 Input / Output Interface 1060 Network Interface

Claims

1. A process of acquiring video from a surveillance camera; A process of acquiring a distance between a vehicle and a person based on the image; If the distance between the vehicle and the person is equal to or less than a threshold, acquiring information for determining whether the person is a person who may commit a vehicle break-in; and executing a process of notifying the user when the information for determining whether the user is a person who may commit a car break-in satisfies a predetermined condition. The information for determining whether the person is a person who may commit a car break-in includes information regarding the movement of the car, The program, wherein the case where the predetermined condition is satisfied includes a case where the information regarding the movement of the vehicle indicates that the vehicle is stationary.

2. The program according to claim 1, The program, in which information for determining whether the person is likely to commit a car break-in includes attributes of the person.

3. The program according to claim 2, The program, wherein the case where the specified condition is satisfied includes a case where the attributes of the person include attributes that have characteristics that make them the perpetrator of a predetermined crime.

4. One or more computers Obtaining footage from security cameras Obtaining the distance between the vehicle and the person based on the image; If the distance between the vehicle and the person is equal to or less than a threshold, information is obtained for determining whether the person is a person who may commit a vehicle break-in; If the information for determining whether the person is a person who may commit a car break-in satisfies a predetermined condition, a notification is given; The information for determining whether the person is a person who may commit a car break-in includes information regarding the movement of the car, The monitoring method, wherein the case where the predetermined condition is satisfied includes a case where the information relating to the movement of the vehicle indicates that the vehicle is stationary.

5. An image acquisition means for acquiring an image from a surveillance camera; a distance acquisition means for acquiring a distance between a vehicle and a person based on the image; an information acquisition means for acquiring information for determining whether the person is a person who may commit a car break-in if the distance between the vehicle and the person is equal to or less than a threshold; a notification means for notifying the user when information for determining whether the user is a person who may commit a car break-in satisfies a predetermined condition, The information for determining whether the person is a person who may commit a car break-in includes information regarding the movement of the car, A monitoring device, wherein the case where the predetermined condition is satisfied includes a case where the information regarding the movement of the vehicle indicates that the vehicle is stationary.

Images