Monitoring system, monitoring method, and monitoring program

Abstract

To highly accurately detect abnormality in the inside of a railway vehicle.SOLUTION: An on-vehicle device 10 is provided in each of vehicles 20 included in a train 2. An imaging device 30 is provided in each of the vehicles 20 to image the inside of the vehicle 20. The on-vehicle device 10 collects images photographed by the imaging device. Further, the on-vehicle device 10 detects abnormality from the image. The on-vehicle device 10 notifies a server or a terminal device used by a crew of a detection result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Recently, crimes occurring on trains have become a social problem, and crimes such as arson, assault, molestation, and the abandonment of dangerous objects can occur on trains.

[0003] As a technology for detecting the occurrence of such crimes, a monitoring system using a camera installed in a vehicle has been proposed (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2012-69022 Summary of the Invention [Problem to be solved by the invention]

[0005] However, conventional techniques have the problem that they may not be able to accurately detect abnormalities inside railway vehicles.

[0006] Here, the monitoring system detects various events that occur in association with criminal acts on railroad vehicles as abnormalities.

[0007] For example, Patent Document 1 describes a method of storing patterns of when a person has collapsed in a surveillance camera. However, there are many different types of events that occur in criminal acts, and it is difficult to store all patterns in a surveillance camera and detect abnormalities.

[0008] For example, there are many variations in the image patterns of a person lying down, such as a pattern in which the person is lying face down, a pattern in which the person is lying sideways, and a pattern in which the person is lying on their back. [Means for solving the problem]

[0009] In order to solve the above-mentioned problems and achieve the objectives, the monitoring system comprises an on-board device provided in each vehicle included in a train, and an imaging device provided in each of the vehicles for photographing the interior of the vehicle, and the on-board device comprises a collection unit that collects images photographed by the imaging device, a detection unit that detects abnormalities from the images, and a notification unit that notifies the results of detection by the detection unit. [Effects of the Invention]

[0010] According to the present invention, abnormalities inside a railway vehicle can be detected with high accuracy. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of a monitoring system. [Figure 2] FIG. 2 is a diagram showing an example of the arrangement of the imaging devices. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of an in-vehicle device. [Figure 4] FIG. 4 is a diagram showing an example of an image when the door is closed. [Figure 5] FIG. 5 is a diagram showing an example of an image when the door is open. [Figure 6] FIG. 6 is a diagram showing an example of an image list screen. [Figure 7] FIG. 7 is a diagram showing an example of an abnormal image display screen. [Figure 8] FIG. 8 is a diagram illustrating an example of the configuration of a monitoring system. [Figure 9] FIG. 9 is a flowchart showing the flow of processing performed by the in-vehicle device. [Figure 10]FIG. 10 is a flowchart showing the flow of an abnormality detection process relating to a person's state and movement. [Figure 11] FIG. 11 is a flowchart showing the flow of an anomaly detection process related to human movement. [Figure 12] FIG. 12 is a diagram illustrating an example of a computer that executes a monitoring program. DETAILED DESCRIPTION OF THE INVENTION

[0012] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A monitoring system, a monitoring method, and a monitoring program according to the present invention will be described in detail below with reference to the accompanying drawings. However, the present invention is not limited to the following embodiments.

[0013] [Configuration of the first embodiment] First, the configuration of a monitoring system according to the first embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of the configuration of a monitoring system.

[0014] 1, the train 2 includes an on-board device 10, an imaging device 30, a terminal device 40, and a server 50. The on-board device 10 and the imaging device 30 are provided in each of the cars 20 of the train 2. The on-board device 10 is an example of a monitoring device.

[0015] The vehicle 20 is a railway vehicle that constitutes the train 2. Furthermore, for example, the train 2 is a train that runs on a railway.

[0016] 1, the on-board device 10 is connected by wire or wirelessly to an image capturing device 30 in the same vehicle 20. For example, the on-board device 10 and the image capturing device 30 are connected to a local area network (LAN) provided in the train 2 via Wi-Fi.

[0017] This allows the in-vehicle device 10 to receive data from the image capturing device 30.

[0018] The in-vehicle device 10, the terminal device 40, and the server 50 are connected to a network N. For example, the network N is the Internet.

[0019] This allows the in-vehicle device 10, the terminal device 40, and the server 50 to transmit and receive data to and from each other via the network N.

[0020] Here, the in-vehicle device 10 is equipped with a module for executing image recognition processing, and functions as an edge computer for the image capturing device 30. For example, the module equipped in the in-vehicle device 10 is provided with a GPU (Graphics Processing Unit).

[0021] The in-vehicle device 10 can use the GPU to execute image recognition processing using a neural network.

[0022] The on-vehicle device 10 may also be installed in an inspection space provided behind a wall inside a vehicle or at a connecting portion between vehicles.

[0023] The photographing device 30 is a device in which a lighting device and a camera are integrated (Reference: Hamai Light Bulb Industrial Co., Ltd., "LED Lighting with Camera (RLioT-Camera)" (URL: http: / / www.hamai.co.jp / dk / website / products / ) (however, "RLioT" is a registered trademark)). Note that the photographing device 30 may also be a camera that is not integrated with a lighting device.

[0024] The image capturing device 30 captures images of the inside of the vehicle 20 constantly or at predetermined timings. The image capturing device 30 also transmits the images of the inside of the vehicle 20 to the in-vehicle device 10 in the same vehicle 20.

[0025] The image capturing device 30 may capture still images at regular intervals (for example, every second), or may constantly capture moving images.

[0026] The image capturing device 30 is arranged as shown in Fig. 2. Fig. 2 is a diagram showing an example of the arrangement of the image capturing device. Fig. 2 is a diagram of the vehicle 20 viewed vertically downward from above.

[0027] For example, by replacing an existing lighting device arranged as shown in FIG. 2 with the photographing device 30, the photographing device 30 can be easily installed.

[0028] Furthermore, by disposing the image capturing devices 30 at dispersed locations as shown in FIG. 2, blind spots are less likely to occur when capturing an image of the interior of the vehicle 20.

[0029] The terminal device 40 is used by crew members (for example, the conductor and the driver) of the train 2. The terminal device 40 is a personal computer, a smartphone, a tablet terminal, or the like.

[0030] The processing flow of the monitoring system 1 will be described with reference to Fig. 1. First, as shown in Fig. 1, the vehicle-mounted device 10 collects images of the inside of the vehicle 20 captured by the image capturing device 30 (step S11).

[0031] The in-vehicle device 10 detects anomalies from the collected images (step S12). The in-vehicle device 10 performs anomaly detection based on the output result obtained by inputting the feature amounts extracted from the images into a trained neural network.

[0032] Next, the in-vehicle device 10 transmits the detection results to the server 50 (step S13). The in-vehicle device 10 may transmit all of the detection results to the server 50, or may transmit only the detection results when an abnormality is detected to the server 50.

[0033] Furthermore, the vehicle-mounted device 10 may transmit the images collected from the image capturing device 30 to the server 50 together with the detection results.

[0034] Here, the server 50 generates monitoring information based on the detection result (step S14). The monitoring information is information that allows the crew of the train 2 to check the detection result.

[0035] For example, the server 50 generates, as monitoring information, a web page that is designed with visibility in mind and that contains information indicating the anomaly detection result.

[0036] The server 50 transmits the generated monitoring information to the terminal device 40 (step S15). The terminal device 40 provides the monitoring information to the crew member who is to provide it.

[0037] The monitoring information may be transmitted to the administrator of the monitoring system 1 or to another system that cooperates with the monitoring system 1.

[0038] The processing by the in-vehicle device 10 described here is performed by a plurality of in-vehicle devices 10 shown in FIG.

[0039] That is, the multiple in-vehicle devices 10 collect images from the image capturing devices 30 provided in the same vehicle 20. The multiple in-vehicle devices 10 then transmit the detection results to the server 50.

[0040] The configuration of the in-vehicle device 10 will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the configuration of the in-vehicle device.

[0041] As shown in FIG. 3, the in-vehicle device 10 includes a communication unit 11, a storage unit 12, and a control unit 13.

[0042] The communication unit 11 is an interface for the in-vehicle device 10 to transmit and receive data to and from other devices.

[0043] For example, the communication unit 11 includes a Wi-Fi module, which allows the on-board device 10 to connect to a LAN in the train 2 and transmit and receive data to and from the image capturing device 30.

[0044] Furthermore, for example, the communication unit 11 includes a communication module for mobile data communication (for example, LTE (Long Term Evolution) or 5G). This allows the in-vehicle device 10 to connect to the network N and transmit and receive data to and from the server 50.

[0045] The storage unit 12 is a storage device such as a hard disk drive (HDD), a solid state drive (SSD), an optical disk, etc. The storage unit 12 may be a data-rewritable semiconductor memory such as a random access memory (RAM), a flash memory, or a non-volatile static random access memory (NVSRAM). The storage unit 12 stores an operating system (OS) and various programs executed by the in-vehicle device 10.

[0046] The storage unit 12 stores model information 121. The model information 121 is information about a model for image recognition. For example, the model information 121 is parameters of a neural network that performs image recognition.

[0047] The control unit 13 controls the entire in-vehicle device 10. The control unit 13 is, for example, an electronic circuit such as a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or a GPU, and an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 13 also includes a GPU for executing image recognition processing.

[0048] The control unit 13 has an internal memory for storing programs that define various processing procedures and control data, and executes each process using the internal memory. The control unit 13 also functions as various processing units by running various programs. For example, the control unit 13 has a collection unit 131, a detection unit 132, and a notification unit 133.

[0049] The collection unit 131 collects images captured by the image capturing devices. The collection unit 131 collects images from all or some of the image capturing devices 30 provided in the same vehicle 20 as the in-vehicle device 10.

[0050] The collecting unit 131 may collect an image by connecting images collected from each of the multiple image capturing devices 30 .

[0051] The detection unit 132 detects an abnormality from the images collected by the collection unit 131. The detection unit 132 detects an abnormality by performing image recognition using a model constructed from the model information 121.

[0052] For example, the model performs image recognition using YOLO, where the model outputs a score based on the probability that a bounding box placed at a given location in the image contains a particular object.

[0053] The model is pre-trained to recognize objects related to criminal activities that are expected to occur on trains, such as fighting, assault, molestation, arson, etc.

[0054] Furthermore, if there is an object whose score output by the model is equal to or greater than a threshold, the detection unit 132 detects the object. Then, if the detection unit 132 detects the object, it detects an abnormality.

[0055] For example, when the detection unit 132 detects a "flame," which is an object related to arson, it detects an abnormality.

[0056] Furthermore, the detection unit 132 detects an abnormality when an object related to assault, such as "a person committing an assault," "a person carrying a weapon," or "a person brandishing an object," is detected.

[0057] The object "person committing assault" corresponds to a person who actually commits direct acts of assault, such as punching or kicking.

[0058] The object "person carrying a deadly weapon" corresponds to a person holding a tool such as a knife or a gun that could be used for assault.

[0059] The object "person brandishing an object" corresponds to a person brandishing a knife, stick, or the like and making an action that may lead to assault.

[0060] In this way, multiple objects may be associated with one type of criminal act, namely assault.

[0061] Each object may also be assigned a priority. For example, the priority may be highest for a "person committing an assault," followed by a "person carrying a weapon," and then a "person brandishing an object."

[0062] At this time, if the detection unit 132 does not detect a "person committing an assault" from the model output, it further checks whether it can detect a "person carrying a weapon" from the model output. Then, if the detection unit 132 does not detect a "person carrying a weapon" from the model output, it further checks whether it can detect a "person brandishing an object" from the model output.

[0063] In this way, by assigning a priority to each object, the detection unit 132 can efficiently perform detection processing.

[0064] Furthermore, the detection unit 132 can detect an abnormality based on the movement directions of multiple people detected from the image.

[0065] When the door of the vehicle 20 is open, the detection unit 132 does not detect an abnormality based on the direction of movement of a person.

[0066] This is because when the door of the vehicle 20 is open, passengers get on and off and move between seats or spaces, and it is considered that the direction of people's movement is not constant.

[0067] When the door of the vehicle 20 is open, this includes the door being in the middle of opening and closing.

[0068] Furthermore, when the door of the vehicle 20 is closed, the detection unit 132 detects an abnormality based on the direction of movement of the person.

[0069] When the doors of vehicle 20 are closed, it is conceivable that a single or small number of passengers may be moving to change seats, prepare to disembark, etc. On the other hand, the simultaneous movement of a large number of passengers may be the result of criminal activity.

[0070] For example, as shown in Fig. 4, when the detection unit 132 detects a closed door in an area 301a of an image 301, it detects an abnormality based on the direction of movement of a person. Fig. 4 is a diagram showing an example of an image when the door is closed.

[0071] For example, it is conceivable that many people will rush to the aid of a person who has fallen due to an assault or to the location of a molestation. It is also conceivable that many people will flee, for example, in a direction away from the location of a fire or away from a random assailant.

[0072] For example, as shown in Fig. 5, when the detection unit 132 detects an open door in an area 301a of the image 301, the detection unit 132 does not detect an abnormality based on the direction of movement of the person. Fig. 5 is a diagram showing an example of an image when the door is open.

[0073] The arrows in FIG. 5 represent the flow of movement of people (passengers) getting on and off the vehicle 20.

[0074] The detection of anomalies based on the direction of movement of people by the detection unit 132 will now be described. First, the detection unit 132 detects people from multiple images taken at different times. At this time, the detection unit 132 assigns an identifier to each of the detected people to distinguish them from each other.

[0075] The image here may be a still image or a frame image included in a moving image.

[0076] For example, the detection unit 132 assigns identifiers such as "P011," "P012," and "P013" to each of three people detected in an image captured at time t1. Then, the detection unit 132 determines whether or not the people detected in an image captured at time t2 (where t2>t1) are the same as the people to whom identifiers have already been assigned.

[0077] For example, the detection unit 132 determines the identity of the person based on whether or not the feature amounts of the images in the area in which the person is detected are similar.

[0078] Then, a vector is generated connecting the positions of people with the same identifier across the images, and the direction of the vector is considered to be the direction of movement of the person.

[0079] For example, the direction indicated by a vector pointing from the position of a person assigned with identifier "P011" at time t1 to the position of the person at time t2 is defined as the moving direction of the person assigned with identifier "P011".

[0080] Here, the detection unit 132 calculates straight lines by extending the vectors generated for each person in the direction of movement. If the number of straight lines calculated exceeds a threshold and passes through a specific point or area (hereinafter, target position), it is determined that a large number of people are approaching the target position, and an abnormality is detected.

[0081] In this way, the detection unit 132 detects an abnormality when it detects that the vehicle door is closed and that multiple people are moving toward a specific location.

[0082] The detection unit 132 also calculates lines by extending the vectors generated for each person in the direction opposite to the direction of movement. If the number of lines passing through the target position exceeds a threshold, it is determined that a large number of people are away from the target position, and an abnormality is detected.

[0083] In this way, the detection unit 132 detects an abnormality when it detects that the vehicle door is closed and that multiple people are moving away from a specific position.

[0084] The notification unit 133 notifies the result of detection by the detection unit 132. The notification unit 133 notifies the crew member using the terminal device 40 of the detection result via the server 50.

[0085] The server 50 generates an image list screen and an abnormal image display screen based on the images and detection results acquired from the in-vehicle device 10, and provides them to the terminal device 40. The terminal device 40 displays the provided image list screen and abnormal image display screen.

[0086] 6 is a diagram showing an example of an image list screen 401. As shown in FIG. 6, images captured by the image capturing device 30 are displayed on the image list screen 401.

[0087] "A03_1," "A03_2," "A03_3," and "A03_4" shown in FIG. 6 are information for identifying the train and vehicle from which the image was taken. For example, "A03" is information for identifying the train. Also, "_1" and the like are information for identifying the vehicle.

[0088] 7 is a diagram showing an example of an abnormal image display screen. The abnormal image display screen 302 is a screen that displays an image (still image or moving image) when an abnormality is detected.

[0089] The image displayed in the image display area 302a may be an image selected from the image list 302b. For each image, the image list 302b displays information identifying the train and vehicle, the date and time when the abnormality was detected, and an explanation of the detected abnormality.

[0090] The abnormality image display screen 302 allows the crew to check the details of the criminal act even if they are in a location far from where the criminal act occurred.

[0091] Here, the monitoring system 1 may be configured without using the network N. Fig. 8 is a diagram showing an example of the configuration of a monitoring system.

[0092] As shown in FIG. 8, the on-board device 10 may transmit the detection result to the terminal device 40 via a LAN in the train 2, instead of the Internet.

[0093] In the example of FIG. 8, first, the vehicle-mounted device 10 collects images of the interior of the vehicle 20 captured by the image capturing device 30 (step S21).

[0094] Next, the vehicle-mounted device 10 detects an abnormality from the collected images (step S22), and then transmits the detection result to the terminal device 40 (step S23).

[0095] For example, the in-vehicle device 10 generates an image list screen 401 and an abnormal image display screen 302 and provides them to the terminal device 40.

[0096] [Processing of the first embodiment] The flow of processing in the in-vehicle device 10 will be described with reference to Fig. 9. Fig. 9 is a flowchart showing the flow of processing in the in-vehicle device.

[0097] 9, the in-vehicle device 10 collects images from the camera (step S101). The camera is the image capturing device 30.

[0098] Next, the vehicle-mounted device 10 detects an abnormality regarding the state and movement of the person (step S102). For example, the vehicle-mounted device 10 detects an abnormality when it detects the occurrence of an assault.

[0099] Then, the vehicle-mounted device 10 performs abnormality detection related to a fire (step S103). For example, the vehicle-mounted device 10 detects an abnormality when it detects flames and smoke.

[0100] The in-vehicle device 10 detects an abnormality related to the movement of people (step S104). For example, the in-vehicle device 10 detects an abnormality when detecting that a large number of people are approaching a target position or that a large number of people are leaving a target position.

[0101] The vehicle-mounted device 10 transmits the detection result together with the image (step S105). The vehicle-mounted device 10 transmits the detection result to the server 50 or the terminal device 40.

[0102] The flow of the process of detecting an abnormality regarding a person's state and movement (corresponding to step S102 in FIG. 9) will be described with reference to FIG. 10. FIG. 10 is a flowchart showing the flow of the process of detecting an abnormality regarding a person's state and movement. Here, it is assumed that the in-vehicle device 10 detects an abnormality when it detects the occurrence of an assault.

[0103] As shown in FIG. 10, first, the in-vehicle device 10 checks whether or not an act of violence has occurred based on the result of image recognition (step S201).

[0104] If the in-vehicle device 10 can confirm that an act of violence has occurred (Yes in step S201), it determines that an abnormality has occurred (detects an abnormality) (step S205).

[0105] If the in-vehicle device 10 is unable to confirm that an act of violence has occurred (step S201, No), it checks whether or not there is a person carrying a weapon based on the result of image recognition (step S202).

[0106] If the in-vehicle device 10 can confirm that there is a person carrying a weapon (Yes in step S202), it determines that there is an abnormality (detects an abnormality) (step S205).

[0107] If the in-vehicle device 10 is unable to confirm that there is a person carrying a weapon (step S202, No), it checks from the result of image recognition whether there is a person brandishing an object (step S203).

[0108] If it is confirmed that there is a person waving an object around (Yes in step S203), the in-vehicle device 10 determines that there is an abnormality (detects an abnormality) (step S205).

[0109] If the in-vehicle device 10 cannot confirm that there is a person carrying a weapon (step S203, No), it determines that there is no abnormality (step S204).

[0110] The flow of the process of detecting an abnormality related to the state and movement of a person (corresponding to step S104 in FIG. 9) will be described with reference to FIG. 11. FIG. 11 is a flowchart showing the flow of the process of detecting an abnormality related to the movement of a person.

[0111] As shown in FIG. 11, first, the in-vehicle device 10 checks whether the vehicle door is open or closed (step S301).

[0112] If the vehicle door is open (step S301, open), the in-vehicle device 10 determines that there is no abnormality (step S304).

[0113] When the vehicle door is closed (step S301, closed), the in-vehicle device 10 checks whether a plurality of people are moving to one location (target position) (step S302).

[0114] If it is confirmed that a plurality of people are moving to one location (target position) (step S302, Yes), the vehicle-mounted device 10 determines that there is an abnormality (detects an abnormality) (step S305).

[0115] If the in-vehicle device 10 is unable to confirm that multiple people are moving to one location (target location) (step S302, No), it checks whether multiple people are moving from one location (target location) (step S303).

[0116] If it is confirmed that a plurality of people are moving from one point (target position) (step S303, Yes), the in-vehicle device 10 determines that there is an abnormality (detects an abnormality) (step S305).

[0117] If the vehicle-mounted device 10 cannot confirm that multiple people are moving from one point (target position) (step S303, No), it determines that there is no abnormality (step S304).

[0118] [Advantages of the first embodiment] As explained above, an on-board device 10 is provided in each of the vehicles 20 included in the train 2. An imaging device 30 is provided in each of the vehicles 20 and captures images of the interior of the vehicle 20. A collection unit 131 of the on-board device 10 collects images captured by the imaging devices. A detection unit 132 detects abnormalities from the images. A notification unit 133 notifies the detection result by the detection unit 132.

[0119] In this way, the on-board device 10 provided in each vehicle 20 performs abnormality detection, so that abnormalities inside the railway vehicle can be detected with high accuracy.

[0120] Furthermore, when the detection unit 132 detects from the image by image recognition a person committing an assault, a person carrying a weapon, or a person brandishing an object, it detects that an abnormality has occurred.

[0121] In this way, by associating a plurality of objects to be detected with a criminal act such as assault, it becomes possible to perform detection more reliably.

[0122] Furthermore, the detection unit 132 detects an abnormality based on the movement directions of multiple people detected from the image.

[0123] For example, the detection unit 132 detects an abnormality when it detects that a vehicle door is closed and that multiple people are moving toward a specific location. Also, for example, the detection unit 132 detects an abnormality when it detects that a vehicle door is closed and that multiple people are moving away from a specific location.

[0124] In this way, by focusing on the movements of multiple people, it becomes possible to detect abnormalities that would be difficult to detect based on the state and movements of just one person.

[0125] [Other embodiments] The in-vehicle device 10 may be provided with a function for measuring its position. For example, the in-vehicle device 10 measures its own position using a GPS (Global Positioning System) receiver.

[0126] The on-board device 10 notifies the train of the detection result together with the location information. This allows, for example, a train crew member who sees the detection result to know at which station the train is stopped or in which section the train is traveling.

[0127] The location information may be estimated from information identifying the vehicle and train in which the on-board device 10 is installed and timetable information indicating the operation schedule of each train. For example, the timetable information includes the stations where the train stops or the sections where the train runs in each time period.

[0128] The on-board device 10 may also cooperate with a system that controls trains. In this case, for example, when an abnormality is detected, the on-board device 10 can issue an instruction to stop the train 2 and open the doors of each car.

[0129] [System configuration, etc.] Furthermore, the components of each device shown in the figure are functional concepts and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown, and all or part of the devices can be functionally or physically distributed or integrated in any unit depending on various loads, usage conditions, etc. Furthermore, all or any part of the processing functions performed by each device can be realized by a CPU (Central Processing Unit) and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic. Note that the program may be executed not only by the CPU but also by other processors such as a GPU.

[0130] Furthermore, among the processes described in this embodiment, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using a known method.In addition, the information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified.

[0131] [program] In one embodiment, the in-vehicle device 10 can be implemented by installing a monitoring program that executes the above-described monitoring process as package software or online software on a desired computer. For example, by executing the above-described monitoring program on an information processing device, the information processing device can function as the in-vehicle device 10. The information processing device referred to here includes desktop and notebook personal computers. In addition, the information processing device also includes mobile communication terminals such as smartphones, mobile phones, and PHS (Personal Handyphone Systems), as well as slate terminals such as PDAs (Personal Digital Assistants).

[0132] 12 is a diagram showing an example of a computer that executes a monitoring program. The computer 1000 includes, for example, a memory 1010 and a CPU 1020. The computer 1000 also includes a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0133] The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM (Random Access Memory) 1012. The ROM 1011 stores a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to a hard disk drive 1090. The disk drive interface 1040 is connected to a disk drive 1100. A removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to a mouse 1110 and a keyboard 1120, for example. The video adapter 1060 is connected to a display 1130, for example.

[0134] The hard disk drive 1090 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. That is, a program that defines each process of the in-vehicle device 10 is implemented as a program module 1093 in which computer-executable code is written. The program module 1093 is stored, for example, in the hard disk drive 1090. For example, a program module 1093 for executing the same process as the functional configuration of the in-vehicle device 10 is stored in the hard disk drive 1090. The hard disk drive 1090 may be replaced with an SSD (Solid State Drive).

[0135] Furthermore, setting data used in the processing of the above-described embodiment is stored as program data 1094, for example, in the memory 1010 or the hard disk drive 1090. Then, the CPU 1020 reads the program module 1093 or the program data 1094 stored in the memory 1010 or the hard disk drive 1090 into the RAM 1012 as necessary, and executes the processing of the above-described embodiment.

[0136] The program module 1093 and program data 1094 are not limited to being stored in the hard disk drive 1090, but may also be stored in, for example, a removable storage medium and read by the CPU 1020 via the disk drive 1100 or the like. Alternatively, the program module 1093 and program data 1094 may be stored in another computer connected via a network (such as a LAN or a WAN (Wide Area Network)). The program module 1093 and program data 1094 may then be read by the CPU 1020 from the other computer via the network interface 1070. [Explanation of symbols]

[0137] N Network 1. Surveillance System 2 trains 10 Onboard equipment 11 Communications Department 12 Storage section 13 Control Unit 20 vehicles 30 Imaging equipment 40 Terminal Equipment 50 servers 121 Model Information 131 Collection Department 132 Detection unit 133 Notification Department

Claims

1. an on-board device provided in each of the cars included in the train; an imaging device provided in each of the vehicles for imaging the interior of the vehicle; and The in-vehicle device an acquisition unit that acquires images captured by the imaging device; a detection unit that detects an abnormality when a specific object with a priority level is detected from the image; a notification unit that notifies a result of detection by the detection unit; A monitoring system comprising:

2. The monitoring system according to claim 1, wherein the detection unit detects an abnormality when, through image recognition, a person committing an assault, a person carrying a weapon, or a person brandishing an object is detected from the image.

3. 2. The monitoring system according to claim 1, wherein the detection unit detects an abnormality based on the movement directions of a plurality of people detected from the image.

4. 4. The monitoring system according to claim 3, wherein the detection unit detects an abnormality when it detects that the door of the vehicle is closed and that multiple people are moving toward one location.

5. 5. The monitoring system according to claim 3, wherein the detection unit detects an abnormality when it detects that the door of the vehicle is closed and that multiple people are moving away from a single point.

6. A monitoring method performed by an on-board device provided in a vehicle included in a train, comprising: a collection step of collecting images captured by an imaging device provided in the vehicle and configured to capture images of the interior of the vehicle; a detection step of detecting an abnormality when a specific object with a priority is detected from the image; a notification step of notifying a result of the detection step; A monitoring method comprising:

7. On-board equipment installed in cars included in the train a collecting step of collecting images captured by an imaging device provided in the vehicle and configured to capture images of the interior of the vehicle; a detection step of detecting an abnormality when a specific object with a priority is detected from the image; a notification step of notifying a result of the detection step; A monitoring program characterized by executing the above.

Images