Retention detection system

Abstract

To efficiently and low-costly detect objects that remain in railway facilities for long periods of time.SOLUTION: A retention detection system includes a camera mounted on a train, an image processing device that analyzes images captured by the camera, and a server that detects retained objects using the analysis results by the image processing device, and the image processing device detects objects from the images captured by the camera and transmits detection results including at least the coordinates where the object has been detected and the detection time to the server, and the server compares the current detection results by the image processing device with past detection results to detect objects that have been present for a predetermined period of time or more.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a congestion detection system that detects people or objects staying in a railway facility. [Background technology]

[0002] There are dangerous areas in railway facilities such as stations, and people who remain in railway facilities for a long time may later engage in dangerous behavior, so it is necessary to detect people who remain in railway facilities for a long time. For this reason, it is necessary to install surveillance cameras in each monitoring area and check the images captured by the cameras.

[0003] The following prior art is included as background technology in this technical field. Patent Document 1 (JP Patent Publication 2010-205191A) describes a safety management device that includes a person detection means for processing an image captured by an imaging device capturing an image of a station platform and detecting a person captured in the image, a determination train association means for associating, for each person detected by the person detection means, a plurality of trains departing from the station platform after the timing of detection of the person as a determination train, a determination means for determining that the behavior of the person is peculiar when the person detection means detects a person whose associated determination train departs from the station platform, and an output means for outputting a notice to that effect when the determination means determines that the behavior of a certain person is peculiar. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2010-205191 A Summary of the Invention [Problem to be solved by the invention]

[0005] The technology described in the above-mentioned Patent Document 1 detects people from images captured by cameras installed on the platform, and detects people who have stayed until the arrival of a judgment train by associating the person's features with a judgment train that judges that the person's behavior is peculiar. However, the cost of installing a surveillance camera for each surveillance area increases.

[0006] In addition, although cameras are installed on the train to monitor the outside of the train, the background art described above does not take into consideration the detection of stranded persons using cameras mounted on the train.

[0007] The present invention aims to detect objects that remain in railway facilities for long periods of time efficiently and at low cost. [Means for solving the problem]

[0008] A representative example of the invention disclosed in this application is as follows: A congestion detection system includes a camera mounted on a train, an image processing device that analyzes video captured by the camera, and a server that detects a lingering object using the analysis result by the image processing device, the image processing device detects an object from the video captured by the camera and transmits a detection result including at least the coordinates and detection time at which the object was detected to the server, and the server compares the current detection result and past detection results by the image processing device to detect an object that has been present for a predetermined time or more (at the same place). Effect of the Invention

[0009] According to one aspect of the present invention, a person or object remaining in a railway facility can be detected at low cost by using a camera mounted on a train. Problems, configurations, and effects other than those described above will become apparent from the following description of the embodiment. [Brief description of the drawings]

[0010] [Figure 1] 1 is a diagram illustrating a configuration of a monitoring system according to an embodiment of the present invention. [Figure 2A]FIG. 1 is a diagram showing a vehicle-side camera according to an embodiment of the present invention. [Figure 2B] 1 is a diagram showing a video display device according to an embodiment of the present invention; [Diagram 3] FIG. 4 is a sequence diagram of a process executed by the monitoring system according to the embodiment of the present invention. [Figure 4] FIG. 2 is a conceptual diagram of a process executed by the monitoring system according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0012] FIG. 1 is a diagram showing a configuration of a monitoring system according to an embodiment of the present invention.

[0013] The congestion detection system of this embodiment is a monitoring system that uses images captured by cameras mounted on trains, and has an image processing device 10, an image display device 11, a control device 12, a front camera 14, a vehicle-side camera 15, and an image recording device 16 in the train, and a center-side server 20 and a wireless communication device 21 in the traffic control center on the ground. The devices in the train are connected by a network device 13 to form a network.

[0014] The image processing device 10 is configured by a computer having an arithmetic unit and a storage device, and analyzes images captured by the front camera 14 and the vehicle-side camera 15. For example, the image processing device 10 has a machine learning model that has learned from images of objects (people, objects), analyzes the images captured by the front camera 14 and the vehicle-side camera 15, acquires the location of the object (coordinates at which the object is detected in the image), the type of the detected object (people, objects, etc.), the number of detected objects, the time at which the object was detected, the certainty of the detected object, the features of the object, etc., and generates detection data including this information.

[0015] The image display device 11 performs processing such as trimming and inversion on live images captured by the front camera 14 and the vehicle-side camera 15, images recorded in the image recording device 16, or images of objects detected by the image processing device 10 according to instructions from the control device 12, and then displays multiple images side by side. The recorded images are mainly used for analysis when accidents or crimes occur.

[0016] As shown in Fig. 2B, it is recommended to install two image display devices 11 side by side in the driver's cab so that the crew can view them simultaneously. The image display device 11 has a display area divided into three parts, left and right, for a total of six parts. Therefore, one image display device 11 can simultaneously display camera images of a three-car train. Also, if the display screen is divided into six parts, two image display devices 11 can be used to simultaneously display camera images of a maximum six-car train.

[0017] By viewing the image from the vehicle-side camera 15 displayed on the image display device 11, the crew can check passengers getting on and off, passengers approaching or coming into contact with the vehicle, the congestion situation on the platform, passengers rushing to the vehicle, passengers running alongside the vehicle, and people stranded on the platform, and can assist passengers getting on and off.

[0018] The control device 12 is composed of a computer having an arithmetic unit and a storage device, and executes image display control such as switching images captured by the vehicle-side camera 15 and displaying them on the image display device 11. External signals (e.g., door-open signals, speed signals) are input to the control device 12 from the traffic management device, and the control device 12 switches the images to be displayed according to the running state of the train determined by the input external signals.

[0019] The front camera 14 is installed on the front of the vehicle and monitors the area ahead of the vehicle, and the vehicle-side camera 15 is installed on the side of the vehicle and monitors passengers getting on and off.

[0020] The front camera 14 and the vehicle-side camera 15 automatically capture video within a predetermined field of view at a predetermined frame rate, convert the captured live video into a format such as H.264, MPEG4, or JPEG, and transmit it via the network device 13 to the image processing device 10, the video display device 11, and the video recording device 16. In addition, the front camera 14 and the vehicle-side camera 15 transmit the captured video to the video display device 11 and the video recording device 16 in response to a transmission request transmitted from the video display device 11. Whether the front camera 14 and the vehicle-side camera 15 transmit video automatically or in response to a transmission request is set at the start of system operation, and can be switched by the driver operating the control device 12.

[0021] As shown in Fig. 2A, the vehicle-side camera 15 is usually mounted above the vehicle and is mounted at an angle downward so that it can capture images of passengers getting on and off the vehicle through the doors from above. Also, a vehicle-side camera 15 that captures the rear from the front and a vehicle-side camera 15 that captures the front from the rear are installed on one side of a vehicle, and a vehicle-side camera 15 that captures the rear from the front and a vehicle-side camera 15 that captures the front from the rear are installed on the other side. Note that in Fig. 2A, the vehicle-side camera 15 is depicted deformed and larger than its actual size.

[0022] The video recording device 16 records the images captured by the front camera 14 and the vehicle-side camera 15 in association with the identification information of the camera that captured the image and the capture time.

[0023] The network device 13 is a switching hub that connects the devices that make up the monitoring system.

[0024] The wireless communication device 17 is mounted on a train and wirelessly communicates with a wireless communication device 21 in a traffic control center. The communication between the wireless communication device 17 and the wireless communication device 21 may use either a public network (e.g., a mobile phone network) or a dedicated line (e.g., a train radio system).

[0025] The wireless communication device 21 is installed in a traffic control center and wirelessly communicates with the wireless communication device 17 installed in the train. The communication between the wireless communication device 17 and the wireless communication device 21 may use either a public network (e.g., a mobile phone network) or a dedicated line (e.g., a train radio system).

[0026] The center-side server 20 is installed in the operation management center and is a computer system consisting of a computer having a processor (CPU), memory, auxiliary storage device, communication interface, input interface, and output interface, and detects people remaining on the platform from the images most recently captured by the front camera 14 and the vehicle-side camera 15.

[0027] The processor is a computing device that executes programs stored in the memory. The processor executes various programs to realize the functions of each processing unit of the center-side server 20. Note that some of the processes performed by the processor by executing the programs may be executed by other computing devices (e.g., hardware such as ASIC and FPGA).

[0028] Memory includes ROM, which is a non-volatile storage element, and RAM, which is a volatile storage element. ROM stores unchanging programs (e.g., BIOS), etc. RAM is a high-speed, volatile storage element such as DRAM (Dynamic Random Access Memory), and temporarily stores programs executed by a processor and data used when executing the programs.

[0029] The auxiliary storage device is, for example, a large-capacity, non-volatile storage device such as a magnetic storage device (HDD) or a flash memory (SSD). The auxiliary storage device also stores data used by the processor when executing a program, and the program executed by the processor. That is, the program is read from the auxiliary storage device, loaded into the memory, and executed by the processor to realize each function of the center-side server 20.

[0030] The communication interface is a network interface device that controls communications with other devices according to a predetermined protocol.

[0031] An input interface is an interface that receives input from a user, such as a keyboard or a mouse. An output interface is an interface that outputs the results of program execution in a format that is visible to the user, such as a display device or a printer. For example, the output interface outputs the results of program execution. The output interface may also be a data output port that outputs the results of program execution in a format that is visible to the user. A terminal connected to the computer via a network may provide the input interface and the output interface.

[0032] The programs executed by the processor are provided to the computer via removable media (CD-ROM, flash memory, etc.) or a network, and are stored in a non-volatile auxiliary storage device, which is a non-transient storage medium. For this reason, the center-side server 20 should have an interface for reading data from removable media.

[0033] The center-side server 20 is a computer system configured on one physical computer, or on multiple logically or physically configured computers, and may operate on a virtual computer constructed on multiple physical computer resources. For example, each functional unit may operate on a separate physical or logical computer, or multiple functional units may be combined to operate on a single physical or logical computer.

[0034] FIG. 3 is a sequence diagram of the processing executed by the monitoring system of this embodiment, and FIG. 4 is a conceptual diagram of the processing executed by the monitoring system of this embodiment.

[0035] The vehicle-side camera 15 transmits the captured live video via the network device 13 to the image processing device 10 , the video recording device 16 , and the center-side server 20 .

[0036] The video recording device 16 records the video received from the vehicle-side camera 15. In addition, the center-side server 20 displays the video received from the vehicle-side camera 15. The center-side server 20 may store the video received from the vehicle-side camera 15.

[0037] The image processing device 10 analyzes the video received from the vehicle-side camera 15, acquires the location where the object exists (the coordinates where the object is detected in the image), the type of the detected object (person, object, etc.), the number of detected objects, the time when the object was detected, the certainty of the detected object, etc., and generates detection data including this information. The coordinates where the object is detected in the image may be converted into absolute coordinates using the absolute position of the camera to obtain data on the location where the object exists. The image processing device 10 transmits the generated detection data to the video recording device 16 and the center-side server 20.

[0038] The video recording device 16 uses the detection time of the detection data received from the image processing device 10 to associate it with the video received from the vehicle-side camera 15 and records it. In addition, the video recording device 16 uses the detection time of the detection data received from the image processing device 10 to extract a snapshot image at the time of detection from the video received from the vehicle-side camera 15 and transmits it to the center-side server 20.

[0039] The center-side server 20 displays the alarm information included in the detection data received from the image processing device 10 and stores the detection data as a log. The center-side server 20 also stores a snapshot image at the time of detection received from the video recording device 16 as a log.

[0040] The center-side server 20 detects the same person in the same area by comparing the detection data of the image captured most recently by the front camera 14 and the vehicle-side camera 15 with the features of the object in the detection data collected from multiple trains and recorded as a log. As a method of determining whether or not it is the same area, there is a method of comparing GNSS (Global Navigation Satellite System) and kilometer information and judging whether or not the person was captured in the same position. More specifically, as a method of comparing whether or not it is the same area (for example, the front or rear of the train), there is a method of comparing the identification information of the camera that detected the object and judging whether or not it is the camera installed in the same position (the camera with the same subject). More specifically, as a method of comparing whether or not it is the same area (for example, the edge of the station), there is a method of judging whether or not the coordinates (area) where the object was detected are nearby. Note that it is also possible to set in advance the area in which the object is to be detected within the angle of view of each camera, and compare in which area it was detected. In this way, even if the object moves slightly, it can be determined that the object was detected in the same area. If the center-side server 20 detects the same person in the same area, it determines that the person is a person staying on the platform. The center-side server 20 may calculate the staying time by the difference between the time when the staying person was first detected and the current time, and may determine the level of the alert for the staying person. For example, the level may be set to a warning alert if the staying time is 10 minutes or more, and a danger alert if the staying time is 1 hour or more. The information indicating the staying person displayed on the video display device 11 may be different depending on the level of the alert.

[0041] Then, the center-side server 20 transmits the detection result of the stranded person to the image display device 11 on the train side via the wireless communication device 21 and the wireless communication device 17.

[0042] The video display device 11 generates information indicating the stranded person (for example, a figure surrounding the stranded person or text calling attention to the stranded person's presence) from the stranded person detection result transmitted from the center side server 20, and displays it superimposed on the snapshot image at the time of detection recorded in the video recorder 16. The driver can see the stranded person information displayed on the video display device 11 and call attention to the stranded person through an external announcement, or approach the stranded person to check the situation.

[0043] In addition, the control device 12 may select an automatic voice from the detection result of the stranded person transmitted from the center side server 20, and use the train's broadcasting device (not shown) to automatically broadcast a warning to people outside the train.

[0044] Furthermore, the center-side server 20 may analyze a time period when there are many stayers by performing statistical processing of the relationship between the number of stayers and time.

[0045] In this embodiment, the center-side server 20 detects stranded persons, but the image processing device 10 on the train side may also detect stranded persons.

[0046] In addition, in this embodiment, although people on the platform of a station are detected, people in other places (for example, people along the tracks using images captured by the in-car camera 15 while the train is running) can also be detected. In addition to alerting crew members and people staying behind, it is also possible to alert station staff using terminals installed in the station.

[0047] In addition, in the present embodiment, a person is detected as an example of an object, but a staying object may be detected. In this case, the image processing device 10 analyzes the images captured by the front camera 14 and the vehicle-side camera 15, and detects an object (such as a suitcase or a cart) to be detected as a staying object.

[0048] As described above, in the embodiment of the present invention, by using the images captured by the cameras mounted on commercial trains, it is possible to detect people stranded at a time period corresponding to the train schedule, and for example, it is possible to quickly find people who have been standing at the edge of a station platform for a long time, and to alert the train driver and the stranded person. In addition, since the cameras mounted on the trains are used, it is possible to detect people stranded without installing surveillance cameras in each surveillance area, and it is possible to detect people stranded even in surveillance areas on quiet lines without making capital investments.

[0049] The present invention is not limited to the above-described embodiments, and includes various modified examples and equivalent configurations within the spirit of the appended claims. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the configurations described. Furthermore, a part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Furthermore, the configuration of another embodiment may be added to the configuration of one embodiment. Furthermore, a part of the configuration of each embodiment may be added, deleted, or replaced with another configuration.

[0050] In addition, each of the above-mentioned configurations, functions, processing units, processing means, etc. may be realized in hardware, for example by designing some or all of them as an integrated circuit, or may be realized in software by a processor interpreting and executing a program that realizes each function.

[0051] Information such as programs, tables, and files that realize each function can be stored in a storage device such as a memory, a hard disk, or an SSD (Solid State Drive), or in a recording medium such as an IC card, an SD card, or a DVD.

[0052] In addition, the control lines and information lines shown are those considered necessary for the explanation, and do not necessarily show all the control lines and information lines necessary for implementation. In reality, it can be considered that almost all components are connected to each other. [Explanation of symbols]

[0053] 10 Image processing device 11 Video display devices 12 Control device 13 Network Equipment 14 Front Camera 15 Car side camera 16 Video Recording Device 17 Wireless communication devices 20 Center Server 21 Wireless communication devices

Claims

[Claim 1] A retention detection system, comprising: A camera mounted on the train an image processing device that analyzes the image captured by the camera; a server that detects a resident object using an analysis result by the image processing device; the image processing device detects an object from the image captured by the camera, and transmits a detection result including at least a coordinate where the object was detected and a detection time to the server; The server compares current detection results with past detection results by the image processing device to detect objects that have been present for a predetermined period of time or longer.

Images