Abnormality detection system, vehicle system, and abnormality detection method

Abstract

This abnormality detection system (4) comprises: a communication unit (41) that acquires vehicle information including operation information about a vehicle in a train; an image acquisition unit (43) that acquires an image of the inside of the vehicle; a timing specification unit (42) that, on the basis of the vehicle information, specifies a passenger arrangement pattern acquisition timing for acquiring, with the image acquisition unit (43), an image of a passenger arrangement pattern inside the vehicle in a situation in which an abnormality to be compared in an abnormality detection has not occurred, and specifies an abnormality detection start timing at which the abnormality detection is to be started; and an abnormal state determination unit (44) that determines whether an abnormality has occurred inside the vehicle using the vehicle information and a comparison result obtained by comparing, on the basis of the abnormality detection start timing, the image of the passenger arrangement pattern with the image acquired by the image acquisition unit (43).

Description

Anomaly detection system, vehicle system, and anomaly detection method

[0001] The present disclosure relates to an abnormality detection system, a vehicle system, and an abnormality detection method for use in a train vehicle.

[0002] Conventionally, abnormal conditions have been detected from images captured by a surveillance camera or the like. For example, Patent Literature 1 discloses a technology in which an image processing device detects a change in the state of a target person based on an input image, and determines that an abnormal condition has been detected when the change in state of the target occurs in multiple people. The image processing device described in Patent Literature 1 detects an abnormal condition when multiple people make similar movements.

[0003] International Publication No. 2015 / 198767

[0004] In recent years, surveillance cameras and the like have been installed in each train car to prevent crimes on board. It is conceivable to apply the technology described in Patent Literature 1 to images acquired by the surveillance cameras in each car. However, when a train brakes suddenly or passes through a switch, the entire car shakes, and passengers in the car may also shake at the same time, i.e., may move in the same way. Therefore, even if the technology described in Patent Literature 1 is applied to images acquired by the surveillance cameras installed in the train cars, there is a problem in that it is not possible to accurately detect abnormal conditions. Abnormal conditions can be detected by performing high-level image recognition on images acquired by the surveillance cameras installed in the train cars, so as to detect abnormal behavior itself. However, building a similar system for all train formations would be extremely expensive.

[0005] The present disclosure has been made in consideration of the above, and aims to provide an abnormality detection system that can detect abnormal conditions occurring in train cars while suppressing increases in costs.

[0006] In order to solve the above-mentioned problems and achieve the objectives, the abnormality detection system disclosed herein is characterized by comprising: a communication unit that acquires vehicle information including operation information of train vehicles; an image acquisition unit that acquires images of the interior of the vehicle; a timing identification unit that identifies, based on the vehicle information, the passenger arrangement pattern acquisition timing for acquiring an image of the passenger arrangement pattern inside the vehicle in a situation where no abnormality has occurred in the image acquisition unit to be compared for abnormality detection, and that identifies the abnormality detection start timing for starting abnormality detection; and an abnormality condition determination unit that determines whether an abnormality has occurred inside the vehicle using the comparison result obtained by comparing the image of the passenger arrangement pattern with the image acquired by the image acquisition unit based on the abnormality detection start timing, and the vehicle information.

[0007] The abnormality detection system disclosed herein has the advantage of being able to detect abnormal conditions occurring in train cars while suppressing increases in costs.

[0008] FIG. 1 shows an example of the configuration of a vehicle system according to embodiment 1. FIG. 1 shows an example of the configuration of an abnormality detection system according to embodiment 1. FIG. 2 shows an example of a situation in which passenger placement is not fixed in a vehicle equipped with the abnormality detection system according to embodiment 1. FIG. 3 shows an example of a situation in which passenger placement is fixed in a vehicle equipped with the abnormality detection system according to embodiment 1. FIG. 4 shows an example of passenger movement when an abnormality occurs in a vehicle equipped with the abnormality detection system according to embodiment 1. Flowchart showing the operation of the abnormality detection system according to embodiment 1. FIG. 5 shows an example of the configuration of a processing circuit in the case where the processing circuit of the abnormality detection system according to embodiment 1 is realized by a processor and a memory. FIG. 6 shows an example of the configuration of a processing circuit in the case where the processing circuit of the abnormality detection system according to embodiment 1 is realized by dedicated hardware. FIG. 7 shows an example of the configuration of an abnormality detection system according to embodiment 2.

[0009] An abnormality detection system, a vehicle system, and an abnormality detection method according to embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0010] Embodiment 1. FIG. 1 is a diagram showing an example of the configuration of a vehicle system 1 according to Embodiment 1. The vehicle system 1 includes a vehicle monitoring device 2, a media terminal device 3, and an abnormality detection system 4. The vehicle system 1 is a system mounted on a train vehicle (not shown). The vehicle monitoring device 2 is mounted in a driver's seat (not shown) or the like of the train vehicle, and displays the status of the vehicle and on-board equipment mounted on the vehicle, and monitors and controls the vehicle and on-board equipment. The media terminal device 3 stores information such as the vehicle's destination, the vehicle's stops, and advertising content, which is displayed on an in-vehicle display device or the like. The abnormality detection system 4 detects an abnormality occurring inside the vehicle. If the abnormality detection system 4 detects an abnormality occurring inside the vehicle, it notifies a control center or the like of a wayside system (not shown) that manages the operation of the train vehicles of the abnormality via the media terminal device 3 and the vehicle monitoring device 2. Note that communication between the vehicle monitoring device 2 and the wayside system may use a dedicated network or a public network. The train on which the vehicle system 1 is mounted may be composed of a single vehicle as well as a plurality of vehicles.

[0011] The following describes the configuration and operation of the abnormality detection system 4. Fig. 2 is a diagram showing an example configuration of the abnormality detection system 4 according to embodiment 1. The abnormality detection system 4 includes a communication unit 41, a timing identification unit 42, an image acquisition unit 43, and an abnormal state determination unit 44.

[0012] The communication unit 41 is connected to the media terminal device 3 and communicates with the media terminal device 3. The communication unit 41 acquires vehicle information, including operation information of the train cars, from the media terminal device 3. The vehicle information includes, for example, information on whether the vehicle doors are open or closed, location information such as the vehicle's distance in kilometers, the vehicle's traveling speed, the vehicle's stop stations, the total weight of the vehicle interior, and the distance between stations on the route on which the vehicle travels, but may also include other information. The information on the route on which the vehicle travels may include information on the positions of curves, points on the track, and the like. The communication unit 41 outputs the acquired vehicle information to the timing identification unit 42 and the abnormal state determination unit 44. Furthermore, when the abnormal state determination unit 44 determines that an abnormality has occurred inside the vehicle, as will be described later, the communication unit 41 notifies a control center or the like of the track system of the occurrence of the abnormality via the media terminal device 3 and the vehicle monitor device 2.

[0013] The timing identification unit 42 acquires vehicle information from the communication unit 41. Based on the acquired vehicle information, the timing identification unit 42 identifies a passenger arrangement pattern acquisition timing for capturing, i.e., acquiring, an image of a passenger arrangement pattern inside the vehicle in a situation where no abnormality has occurred and which is the target of comparison for anomaly detection by the image acquisition unit 43. Typically, when a vehicle stops at a station, passengers get on and off, so many passengers are moving around inside the vehicle. In this embodiment, since it is difficult to detect an abnormality occurring inside the vehicle in such a situation, the abnormality detection system 4 does not perform processing to detect an abnormality occurring inside the vehicle. Furthermore, even after passengers board the vehicle, they may move around inside the vehicle depending on the relationship between the location of the ticket gate or stairs at the boarding station and the location of the ticket gate or stairs at the disembarking station. Therefore, it is considered that passenger movement will not stop inside the vehicle for some time after the vehicle departs from the station. Therefore, the timing identification unit 42 identifies the timing at which passenger movement stops inside the vehicle after the vehicle departs from the station as the passenger arrangement pattern acquisition timing. The timing specifying unit 42 specifies the passenger arrangement pattern acquisition timing using, for example, at least one of the following: the vehicle door has closed, the vehicle has reached a specified speed, and the vehicle is at a position where it has traveled a specified distance. The timing specifying unit 42 may specify the passenger arrangement pattern acquisition timing using other conditions, such as the vehicle having traveled a specified period of time since leaving a station. The timing specifying unit 42 notifies the image acquiring unit 43 of the specified passenger arrangement pattern acquisition timing.

[0014] Furthermore, the timing identification unit 42 identifies, based on the vehicle information, the abnormality detection start timing at which the abnormal state determination unit 44 starts abnormality detection. As described above, when a vehicle is stopped at a station, passengers are getting on and off inside the vehicle, making it difficult to detect an abnormality that has occurred inside the vehicle. Therefore, while the vehicle is stopped at a station, the abnormal state determination unit 44 does not determine whether an abnormality has occurred inside the vehicle. Therefore, the timing identification unit 42 identifies the timing at which the abnormal state determination unit 44 resumes the operation of determining whether an abnormality has occurred inside the vehicle. The timing identification unit 42 may identify the abnormality detection start timing at which the abnormal state determination unit 44 starts abnormality detection under the same conditions as when identifying the passenger placement pattern acquisition timing, or may identify the abnormality detection start timing at which the abnormal state determination unit 44 starts abnormality detection under different conditions. However, because the abnormal state determination unit 44 cannot perform abnormality detection without an image of the passenger placement pattern, the abnormality detection start timing at which the abnormal state determination unit 44 starts abnormality detection is set to be the same timing as the passenger placement pattern acquisition timing or later than the passenger placement pattern acquisition timing. The timing specifying unit 42 may determine the timing after a specified period has elapsed from the passenger placement pattern acquisition timing as the abnormality detection start timing at which the abnormal state determination unit 44 starts abnormality detection. The timing specifying unit 42 notifies the abnormal state determination unit 44 of the specified abnormality detection start timing. Note that the timing specifying unit 42 may notify the image acquisition unit 43 of the specified abnormality detection start timing.

[0015] The image acquisition unit 43 acquires images of the interior of the vehicle. The image acquisition unit 43 has a built-in imaging device such as a camera, and acquires images of the interior of the vehicle by capturing images of the interior of the vehicle. The images captured, i.e., acquired, by the image acquisition unit 43 may be moving images or still images captured at a specified imaging period. As described above, while the vehicle is stopped at a station, the abnormal state determination unit 44 does not determine whether an abnormality has occurred inside the vehicle. Therefore, the image acquisition unit 43 stops acquiring images of the interior of the vehicle when the vehicle stops at a station. The image acquisition unit 43 does not acquire images of the interior of the vehicle from the time the vehicle stops at a station until the timing determination unit 42 determines the timing for acquiring a passenger placement pattern. The timing determination unit 42 can determine that the vehicle has stopped at a station from the vehicle information, and therefore notifies the image acquisition unit 43 when the vehicle has stopped at a station. This allows the image acquisition unit 43 to determine that the vehicle has stopped at a station and to stop capturing images of the interior of the vehicle. When the image acquisition unit 43 is notified of the passenger arrangement pattern acquisition timing from the timing identification unit 42, it starts acquiring images of the interior of the vehicle and outputs the acquired images as passenger arrangement pattern images to the abnormal condition determination unit 44. Whether the images captured, i.e., acquired by the image acquisition unit 43 are moving images or still images, the passenger arrangement pattern images are still images. The image acquisition unit 43 continues capturing, i.e., acquiring images while the vehicle is traveling, and outputs the acquired images to the abnormal condition determination unit 44. Note that when the image acquisition unit 43 is notified of the abnormality detection start timing from the timing identification unit 42, it may be configured to output images captured and acquired after the abnormality detection start timing to the abnormal condition determination unit 44.

[0016] The abnormal state determination unit 44 acquires vehicle information from the communication unit 41. The abnormal state determination unit 44 also acquires an abnormality detection start timing from the timing identification unit 42. The abnormal state determination unit 44 also acquires an image of a passenger arrangement pattern and an image acquired by the image acquisition unit 43 while the vehicle is traveling from the image acquisition unit 43. The abnormal state determination unit 44 compares the image of the passenger arrangement pattern with the image acquired by the image acquisition unit 43 while the vehicle is traveling based on the abnormality detection start timing. The abnormal state determination unit 44 determines whether an abnormality has occurred inside the vehicle using a comparison result between the image of the passenger arrangement pattern and the image acquired by the image acquisition unit 43 while the vehicle is traveling, and the vehicle information. If the comparison result indicates that there is passenger movement in the image acquired by the image acquisition unit 43 compared to the image of the passenger arrangement pattern, and the passenger movement is not due to vehicle operation as determined from the vehicle information, the abnormal state determination unit 44 determines that an abnormality has occurred inside the vehicle.

[0017] For example, if a person carrying a weapon or other weapon is acting violently inside a train car, many passengers inside the train will move away from the person. In contrast, when a train passes through a curve or a point on the tracks, the entire train shakes, and it is conceivable that all passengers inside the train will be shaken in the same direction. Therefore, even if many passengers move inside the train car, the abnormal state determination unit 44 determines that no abnormality has occurred inside the train car if the passenger movements are due to the train's operation as determined from the train information. The abnormal state determination unit 44 determines that an abnormality has occurred inside the train car if many passengers move inside the train car but are not due to the train's operation as determined from the train information. The abnormal state determination unit 44 determines that an abnormality has occurred inside the train car, for example, if a large number of passengers move while the train car is moving, if passenger movements exceed those due to a specified railway-specific event while the train car is moving, or if multiple passengers make similar movements while the train car is moving.

[0018] In this way, the abnormal state determination unit 44 does not detect or identify an abnormality that has occurred in the vehicle from the images acquired by the image acquisition unit 43. Instead, by comparing the latest image with an image of the interior of the vehicle when no abnormality has occurred, the abnormal state determination unit 44 determines that an abnormality has occurred inside the vehicle when multiple passengers are moving in a situation where no passengers should be moving inside the vehicle. Since the abnormal state determination unit 44 detects an abnormality by comparing the latest image with a previous image acquired by the image acquisition unit 43, there is no need for advanced image processing to detect an abnormality from a single image, thereby suppressing an increase in processing load. Furthermore, since the abnormal state determination unit 44 does not detect or identify an abnormality from the images acquired by the image acquisition unit 43, there is no need for prior preparation, such as learning for AI (artificial intelligence) analysis. Note that, as described above, positions that cause the entire vehicle to shake, such as curves and points on the tracks, may be included in the vehicle information as information on the positions of the curves and points on the tracks, or may be included in the vehicle information as information on positions where the entire vehicle will shake.

[0019] Here, the assumed situation of passengers inside a vehicle will be described. FIG. 3 is a diagram showing an example of a situation in which the passenger arrangement is not determined in a vehicle 5 equipped with the anomaly detection system 4 according to the first embodiment. Note that, although only one vehicle 5 is shown in the example of FIG. 3, the vehicle 5 may be a single vehicle constituting a train formation. Also, in the example of FIG. 3, multiple anomaly detection systems 4 are installed inside one vehicle 5, but the number of anomaly detection systems 4 installed inside one vehicle 5 may be three or less, or five or more. The same applies hereinafter. When the vehicle 5 is stopped at a station, multiple passengers get on and off, so the passenger arrangement is not determined. In such a situation, the anomaly detection system 4 does not detect an abnormal state.

[0020] FIG. 4 is a diagram showing an example of a situation in which passenger arrangement is determined in a vehicle 5 equipped with the anomaly detection system 4 according to embodiment 1. When the vehicle 5 departs from a station and starts traveling, the passenger arrangement in the vehicle 5 is determined by passengers sitting in seats, passengers standing inside the vehicle 5, and the like. The anomaly detection system 4 acquires vehicle information as described above, and is therefore able to grasp the traveling status of the vehicle 5. Therefore, after the vehicle 5 departs from a station and starts traveling, the anomaly detection system 4 acquires an image of the passenger arrangement pattern inside the vehicle 5 in a situation in which no anomaly has occurred, which is the target for comparison with anomaly detection, based on conditions under which the passenger arrangement is expected to be stable as described above. The diagram shown in FIG. 4 can also be considered an example of the passenger arrangement pattern when the passenger arrangement pattern image is acquired.

[0021] FIG. 5 is a diagram illustrating an example of passenger behavior when an abnormality occurs in a vehicle 5 equipped with the anomaly detection system 4 according to the first embodiment. FIG. 5 illustrates a specific example of an abnormality, in which an abnormal person behaves abnormally. When an abnormal person behaves abnormally inside a moving vehicle 5, a significant change in passenger placement is expected. In the anomaly detection system 4, the abnormal state determination unit 44 compares an image of the passenger placement pattern in the situation shown in FIG. 4 with an image acquired by the image acquisition unit 43 in the situation shown in FIG. 5. In the example of FIG. 5, the abnormal state determination unit 44 determines that a significant movement has occurred, such as passengers inside the vehicle 5 moving away from the abnormal person near the center of the vehicle 5 and escaping into an adjacent vehicle 5. Using the vehicle information, the abnormal state determination unit 44 determines that the change in passenger placement is not due to the movement of the vehicle 5, and determines that an abnormality has occurred inside the vehicle 5. The abnormal state determination unit 44 notifies a control center or the like of the track system of the occurrence of an abnormality inside the vehicle 5 from the communication unit 41 via the media terminal device 3 and the vehicle monitoring device 2.

[0022] 3 to 5 , one anomaly detection system 4 may be configured to include multiple image acquisition units 43, taking into consideration the case where multiple anomaly detection systems 4 are installed in one vehicle 5. In this case, the load on the abnormal state determination unit 44 increases, but the configuration can be simplified because one vehicle 5 can have one communication unit 41 and one timing identification unit 42.

[0023] 6 is a flowchart showing the operation of the abnormality detection system 4 according to the first embodiment. In the abnormality detection system 4, the communication unit 41 acquires vehicle information from the media terminal device 3 (step S101). If, based on the vehicle information, the passenger arrangement inside the vehicle is not stable (step S102: No), the timing identification unit 42 waits. If, based on the vehicle information, the passenger arrangement inside the vehicle is stable (step S102: Yes), the timing identification unit 42 identifies a passenger arrangement pattern acquisition timing for acquiring an image of the passenger arrangement pattern inside the vehicle in a state where no abnormality has occurred and which is to be used for comparison with the abnormality detection by the image acquisition unit 43 (step S103). The image acquisition unit 43 acquires an image of the passenger arrangement pattern based on the passenger arrangement pattern acquisition timing (step S104). Based on the vehicle information, the timing identification unit 42 identifies an abnormality detection start timing for the abnormal state determination unit 44 to start abnormality detection (step S105).

[0024] The image acquisition unit 43 acquires an image of the interior of the vehicle (step S106). The abnormal state determination unit 44 compares the image of the passenger arrangement pattern with the image acquired by the image acquisition unit 43 based on the abnormality detection start timing (step S107). If the abnormal state determination unit 44 determines that an abnormality has occurred inside the vehicle using the comparison result and the vehicle information (step S108: Yes), it notifies the control center of the track system or the like from the communication unit 41 via the media terminal device 3 and the vehicle monitor device 2 (step S109). If the abnormal state determination unit 44 determines that no abnormality has occurred inside the vehicle using the comparison result and the vehicle information (step S108: No), it determines whether the vehicle has stopped at a station (step S110). If the vehicle has not stopped at a station (step S110: No), the abnormality detection system 4 returns to step S106 and repeats the above-described operations. If the vehicle has stopped at a station (step S110: Yes), the abnormality detection system 4 ends its operation.

[0025] It should be noted that the order of the operations in each step of the flowchart shown in FIG. 6 may be reversed, or some operations may be performed simultaneously. Here, the passenger allocation pattern needs to be updated every time the passenger allocation changes. In this embodiment, it is assumed that the passenger allocation changes as the train stops at a station and passengers get on and off. Therefore, the abnormality detection system 4 performs the operations of the flowchart shown in FIG. 6 every time the train departs after stopping at a station.

[0026] Next, the hardware configuration of the anomaly detection system 4 according to the first embodiment will be described. In the anomaly detection system 4, the communication unit 41 is a communication interface capable of communicating with the media terminal device 3. The image acquisition unit 43 is a camera capable of capturing at least one of moving images and still images. In addition to the camera, the image acquisition unit 43 may also include circuits and mechanical components capable of adjusting the camera's imaging direction, imaging range, etc. The timing identification unit 42 and the abnormal state determination unit 44 are realized by a processing circuit. The processing circuit may be a memory that stores a program and a processor that executes the program stored in the memory, or may be dedicated hardware. The processing circuit is also called a control circuit.

[0027] FIG. 7 is a diagram illustrating an example of the configuration of a processing circuit 90 when the processing circuit of the anomaly detection system 4 according to the first embodiment is realized by a processor 91 and a memory 92. The processing circuit 90 illustrated in FIG. 7 is a control circuit and includes a processor 91 and a memory 92. When the processing circuit 90 is configured with the processor 91 and the memory 92, each function of the processing circuit 90 is realized by software, firmware, or a combination of software and firmware. The software or firmware is written as a program and stored in the memory 92. The processing circuit 90 realizes each function by having the processor 91 read and execute the program stored in the memory 92. That is, the processing circuit 90 includes the memory 92 for storing a program that results in the processing of the anomaly detection system 4 being executed. This program can also be said to be a program that causes the anomaly detection system 4 to execute each function realized by the processing circuit 90. This program may be provided by a storage medium on which the program is stored, or by other means such as a communication medium.

[0028] The above program can also be said to be a program that causes the abnormality detection system 4 to execute the following steps: a communication step in which the communication unit 41 acquires vehicle information including operation information of the train vehicles; an image acquisition step in which the image acquisition unit 43 acquires images of the interior of the vehicle; a timing identification step in which the timing identification unit 42 identifies, based on the vehicle information, the passenger arrangement pattern acquisition timing in which the image acquisition unit 43 acquires an image of the passenger arrangement pattern inside the vehicle in a situation where no abnormality has occurred to be compared for abnormality detection, and identifies the abnormality detection start timing to start abnormality detection; and an abnormality state determination step in which the abnormality state determination unit 44 uses the comparison result of comparing the image of the passenger arrangement pattern with the image acquired by the image acquisition unit 43 based on the abnormality detection start timing, and the vehicle information, to determine whether or not an abnormality has occurred inside the vehicle.

[0029] Here, the processor 91 is, for example, a CPU (Central Processing Unit), a processing device, an arithmetic unit, a microprocessor, a microcomputer, or a DSP (Digital Signal Processor), etc. The memory 92 is, for example, a non-volatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable ROM), or an EEPROM (Electrically EPROM), a magnetic disk, a flexible disk, an optical disk, a compact disk, a minidisk, or a DVD (Digital Versatile Disc).

[0030] FIG. 8 is a diagram illustrating an example of the configuration of the processing circuit 93 in the anomaly detection system 4 according to the first embodiment, when the processing circuit is implemented by dedicated hardware. The processing circuit 93 illustrated in FIG. 8 corresponds to, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof. The processing circuit 93 may be partially implemented by dedicated hardware and partially implemented by software or firmware. In this way, the processing circuit 93 can realize each of the above-described functions by dedicated hardware, software, firmware, or a combination thereof.

[0031] As described above, according to the present embodiment, in the anomaly detection system 4, the timing identification unit 42, based on the vehicle information, identifies a passenger arrangement pattern acquisition timing for acquiring an image of a passenger arrangement pattern inside the vehicle in a state where no abnormality has occurred to be compared by the image acquisition unit 43 for anomaly detection, and also identifies an abnormality detection start timing for the abnormal state determination unit 44 to start abnormality detection. The image acquisition unit 43 acquires images of the vehicle interior from after the passenger arrangement pattern acquisition timing until the vehicle stops at the next station. The abnormal state determination unit 44 detects an abnormality occurring inside the vehicle by comparing the passenger arrangement pattern image with the image acquired by the image acquisition unit 43 from after the abnormality detection start timing until the vehicle stops at the next station. This allows the anomaly detection system 4 to detect an abnormality occurring inside the vehicle while taking into account circumstances specific to railways, without performing advanced image processing or the like. The anomaly detection system 4 can detect an abnormal state occurring in a train vehicle while suppressing increases in costs.

[0032] Second Embodiment In a second embodiment, a case where the abnormality detection system includes a display unit will be described.

[0033] FIG. 9 is a diagram showing an example of the configuration of an abnormality detection system 4a according to the second embodiment. The abnormality detection system 4a includes a communication unit 41, a timing identification unit 42, a camera-equipped display device 46, and an abnormal state determination unit 44. The camera-equipped display device 46 includes an image acquisition unit 43 and a display unit 45. When the communication unit 41 acquires vehicle information from the media terminal device 3, it also outputs the vehicle information to the display unit 45. The display unit 45 is installed inside the vehicle, for example, above the door, and displays vehicle running information included in the vehicle information to passengers inside the vehicle based on the vehicle information acquired from the communication unit 41. The running information includes, for example, the stations where the vehicle will stop. The camera-equipped display device 46 is configured such that the image acquisition unit 43 and the display unit 45 are integrated into one unit.

[0034] Many recent train vehicles are equipped with display devices for passengers, such as above the doors. Because the anomaly detection system 4a can be installed in the same space where such display devices are installed, there is no need to build a new network for the anomaly detection system 4a; the network used for the existing display devices can be utilized. The anomaly detection system 4a can be used, for example, as a display device for train vision. The operation of the anomaly detection system 4a to detect an abnormality occurring inside the vehicle is the same as the operation of the anomaly detection system 4 in the first embodiment to detect an abnormality occurring inside the vehicle. Therefore, a description of the operation of the anomaly detection system 4a will be omitted. Although not shown, the vehicle system in the second embodiment is the same as the vehicle system 1 shown in FIG. 1 , except that the anomaly detection system 4 is replaced with the anomaly detection system 4a.

[0035] As described above, according to this embodiment, the anomaly detection system 4a has an integrated configuration of the image acquisition unit 43 and the display unit 45. Because the installation space and network for the display device above the vehicle door can be used, a vehicle equipped with the anomaly detection system 4a does not need to provide a new installation space for the anomaly detection system 4a, nor does it need to create a new network for the anomaly detection system 4a.

[0036] The configurations shown in the above embodiments are merely examples, and may be combined with other known technologies, or different embodiments may be combined with each other. It is also possible to omit or modify parts of the configurations as long as they do not deviate from the gist of the invention.

[0037] REFERENCE SIGNS LIST 1 vehicle system, 2 vehicle monitor device, 3 media terminal device, 4, 4a abnormality detection system, 5 vehicle, 41 communication unit, 42 timing identification unit, 43 image acquisition unit, 44 abnormal state determination unit, 45 display unit, 46 camera-equipped display device, 90, 93 processing circuit, 91 processor, 92 memory.

Claims

1. An abnormality detection system comprising: a communications unit that acquires vehicle information including operation information of train vehicles; an image acquisition unit that acquires images of the interior of the vehicle; a timing identification unit that identifies, based on the vehicle information, a passenger arrangement pattern acquisition timing for acquiring an image of a passenger arrangement pattern inside the vehicle in a situation where no abnormality has occurred that is to be compared in the image acquisition unit for abnormality detection, and that identifies an abnormality detection start timing for starting the abnormality detection; and an abnormality condition determination unit that determines whether or not an abnormality has occurred inside the vehicle, using a comparison result obtained by comparing the image of the passenger arrangement pattern with the image acquired by the image acquisition unit based on the abnormality detection start timing, and the vehicle information.

2. The anomaly detection system described in claim 1, characterized in that the image acquisition unit does not acquire images of the interior of the vehicle from the time the vehicle stops at the station until the timing identification unit identifies the timing for acquiring the passenger placement pattern.

3. The anomaly detection system of claim 1 or 2, characterized in that the timing identification unit identifies the passenger placement pattern acquisition timing using at least one of the following: the vehicle door has closed, the vehicle has reached a specified constant speed, and the vehicle is at a position where it has traveled a specified distance.

4. The abnormality detection system of any one of claims 1 to 3, characterized in that the abnormality condition determination unit determines that an abnormality has occurred inside the vehicle when the comparison result is that there is passenger movement in the image acquired by the image acquisition unit compared to the image of the passenger arrangement pattern, and the passenger movement is not caused by the operation of the vehicle as determined from the vehicle information.

5. The abnormality detection system of any one of claims 1 to 4, characterized in that the abnormality condition determination unit determines that an abnormality has occurred inside the vehicle when at least one of the following occurs: when a large number of passengers move while the vehicle is moving; when a passenger exhibits movement greater than or equal to the passenger movement caused by a specified railway-specific event while the vehicle is moving; and when a plurality of passengers exhibit similar movement while the vehicle is moving.

6. An abnormality detection system as described in any one of claims 1 to 5, characterized in that it is further equipped with a display unit that displays driving information of the vehicle contained in the vehicle information to passengers inside the vehicle, and the image acquisition unit and the display unit are of an integrated configuration.

7. A vehicle system comprising: an abnormality detection system according to any one of claims 1 to 6; a vehicle monitor device for monitoring and controlling the vehicle and on-board equipment; and a media terminal device for holding information to be displayed on a display device inside the vehicle.

8. An abnormality detection method comprising: a communication step in which a communication unit acquires vehicle information including operation information of train vehicles; an image acquisition step in which an image acquisition unit acquires an image of the interior of the vehicle; a timing identification step in which a timing determination unit identifies, based on the vehicle information, a passenger arrangement pattern acquisition timing for acquiring an image of a passenger arrangement pattern inside the vehicle in a situation where no abnormality has occurred that is to be compared in the image acquisition unit for abnormality detection, and identifies an abnormality detection start timing for starting the abnormality detection; and an abnormality condition determination step in which an abnormality condition determination unit determines whether or not an abnormality has occurred inside the vehicle, using a comparison result obtained by comparing the image of the passenger arrangement pattern with the image acquired by the image acquisition unit based on the abnormality detection start timing, and the vehicle information.

9. The abnormality detection method described in claim 8, characterized in that in the image acquisition step, the image acquisition unit does not acquire images of the interior of the vehicle from the time the vehicle stops at the station until the timing identification unit identifies the passenger placement pattern acquisition timing.

10. The abnormality detection method described in claim 8 or 9, characterized in that in the timing identification step, the timing identification unit identifies the passenger placement pattern acquisition timing using at least one of the following: the vehicle door has closed, the vehicle has reached a specified constant speed, and the vehicle is at a position where it has traveled a specified distance.

11. An abnormality detection method as described in any one of claims 8 to 10, characterized in that in the abnormality condition determination step, the abnormality condition determination unit determines that an abnormality has occurred inside the vehicle if the comparison result is that there is movement of passengers in the image acquired by the image acquisition unit compared to the image of the passenger arrangement pattern, and the movement of the passengers is not caused by the operation of the vehicle as determined from the vehicle information.

12. The abnormality detection method described in any one of claims 8 to 11, characterized in that in the abnormality condition determination step, the abnormality condition determination unit determines that an abnormality has occurred inside the vehicle when at least one of the following occurs: a large number of passengers move while the vehicle is traveling, a passenger exhibits movement greater than or equal to the passenger movement caused by a specified railway-specific event while the vehicle is traveling, and a plurality of passengers exhibit similar movement while the vehicle is traveling.

Images