Information processing method

Abstract

To provide an information processing method capable of inhibiting time from being taken to grasp a stop factor of a train.SOLUTION: An information processing method is a method to be executed by an information processing system 1 including a vehicle 10 provided with an imaging unit 11, and a communication unit, and a server device 20. The information processing method includes: requesting the server device 20 to provide a peripheral image to the vehicle 10 located within an information collection area including a stop position of the train when the train moving on a track stops between stations; and making the communication unit of the vehicle 10 located within the information collection area transmit to the server device 20 a stop factor image being a peripheral image including at least one of the train stopping at the stop position or the track around the train.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an information processing method. [Background technology]

[0002] In the railway business, a control center grasps the operating status of trains in the section under its control and monitors the track environment. When an event that interferes with the operation of a train occurs, the train driver or conductor stops the train and transmits details of the event to the control center. For example, Patent Document 1 discloses that a transmission is made to the drivers or conductors of other trains located in the section under the control of the control center that an event that interferes with the operation of a train has occurred. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2010-176612 A Summary of the Invention [Problem to be solved by the invention]

[0004] Incidentally, when a train stops between stations, the driver or conductor is required to know the cause of the train stopping. However, since the driver or conductor is required to communicate with the control center and to provide information to passengers through the train's internal broadcasting system, it may be difficult for them to immediately know the cause of the train stopping. In addition, the technology disclosed in Patent Document 1 could inform the driver or conductor of another train that an event that interferes with the train's operation has occurred, but it was not possible for the driver or conductor to know the cause of the train stopping. [Means for solving the problem]

[0005] An information processing method for solving the above problem is an information processing method executed in an information processing system comprising a vehicle having an imaging unit that generates a surrounding image by imaging the surrounding situation and a communication unit that communicates with the outside, and a server device installed outside the vehicle, and configured so that the surrounding image is transmitted from the communication unit of the vehicle to the server device via a communication network, the information processing method including the steps of: when a train traveling on a track stops between stations, the server device requests the vehicle located within an information collection area including the stopping position of the train to provide the surrounding image; and the communication unit of the vehicle located within the information collection area transmits to the server device a stop cause image, which is the surrounding image that shows at least one of the train stopped at the stopping position and the track near the train. Effect of the Invention

[0006] According to the above configuration, it is possible to reduce the time required to identify the cause of a train stopping. [Brief description of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram used to explain an information processing system. [Diagram 2] FIG. 2 is a diagram illustrating an example of the configuration of the server device, the control device, and the railroad crossing control device. [Diagram 3] FIG. 3 is a flowchart illustrating an example of a process executed in the server device. [Figure 4] FIG. 4 is a flowchart illustrating an example of a process executed in the server device. [Diagram 5] FIG. 5 is a flowchart illustrating an example of a process executed in the control device. [Figure 6] FIG. 6 is a flowchart illustrating an example of a process executed in the server device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] <Embodiment> Hereinafter, one embodiment of the information processing method will be described with reference to FIGS. <Overall configuration of information processing system 1> As shown in Fig. 1, an information processing system 1 that realizes the information processing method includes, for example, one or more vehicles 10, a server device 20, and one or more railroad crossing control devices 60. The vehicle 10 includes, for example, an imaging unit 11, a position information acquisition unit 12, and a control device 30. The railroad crossing control devices 60 are installed in railroad crossing equipment boxes 50 provided in the vicinity of different railroad crossings 40. The control device 30, the server device 20, and the railroad crossing control device 60 are connected to each other via a communication network 70 so as to be able to transmit and receive information. The communication network 70 includes, for example, the Internet, a Wide Area Network (WAN), a Local Area Network (LAN), a provider terminal, a wireless communication network, a wireless base station, a dedicated line, and the like.

[0009] The imaging unit 11 is, for example, a digital camera using a solid-state imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). One example of the imaging unit 11 is a digital camera constituting a drive recorder. The imaging unit 11 captures images of the surroundings of the vehicle 10. Depending on the installation position of the imaging unit 11 on the vehicle 10, the imaging unit 11 can capture images of the front, rear, and sides of the vehicle 10. The imaging unit 11 generates a surrounding image by capturing images of the surroundings of the vehicle 10. When the vehicle 10 travels near a railroad crossing 40 or a railroad track 101, the surrounding image generated by the imaging unit 11 may include the train 100 or the railroad track 101.

[0010] The position information acquisition unit 12 is, for example, a Global Navigation Satellite System (GNSS) receiver. The position information acquisition unit 12 identifies the position of the vehicle 10 based on a signal received from a GNSS satellite, and acquires position information indicating the position of the vehicle 10.

[0011] The control device 30 transmits position information to the server device 20 at predetermined time intervals, thereby enabling the server device 20 to identify the position of the vehicle 10. Furthermore, the control device 30 transmits a stop cause image to the server device 20 when requested by the server device 20. The stop cause image is a peripheral image that shows at least one of the train 100 stopped between stations and the track 101 near the train 100, among the peripheral images. In other words, the stop cause image is an image that is highly likely to show the cause of the train 100 stopping.

[0012] The server device 20 is, for example, a device that aggregates information used for operation control of the trains 100 traveling on the managed track. The server device 20 is provided, for example, in a control center. A commander at the control center refers to the information aggregated in the server device 20 and performs operation control of the trains 100 traveling on the managed track.

[0013] The crossing control device 60 controls the crossing 40 that is the target of control. Specifically, when the crossing controller of the crossing 40 detects the approach of a train 100, the crossing control device 60 sounds the warning device of the crossing 40, lowers the barrier, and flashes the warning light. In addition, when the crossing controller of the crossing 40 detects the passage of a train 100, the crossing control device 60 stops the warning device of the crossing 40, raises the barrier, and turns off the warning light.

[0014] Further, an emergency stop button 61 and an obstacle detection device 62 are connected to the crossing control device 60. The emergency stop button 61 is operated by a pedestrian passing through the crossing 40 or a driver of a vehicle 10 passing through the crossing 40. When the emergency stop button 61 is operated, the crossing control device 60 turns on a special signal light provided in front of the crossing 40 and transmits a stop signal to a train 100 present near the crossing 40. The obstacle detection device 62 detects an obstacle present within the crossing 40. The obstacle detection device 62 detects an obstacle by a detection method such as an optical sensor type, a loop coil type, or a three-dimensional laser radar type. When an obstacle is detected by the obstacle detection device 62, the crossing control device 60 turns on a special signal light or transmits a stop signal. When the driver of the train 100 approaching the railroad crossing 40 sees the special signal light on or receives a stop signal from the railroad crossing control device 60, the driver stops the train 100 just before the railroad crossing 40.

[0015] <Configuration of the control device 30> As shown in FIG. 2, the control device 30 includes, for example, a processing circuit 31, a communication unit 32, and a storage unit 33. The processing circuit 31 is configured with, for example, a hardware processor such as a CPU (Central Processing Unit). The hardware processor executes a program, which allows the processing circuit 31 to execute various processes. The program may be stored in the storage unit 33 in advance. The storage unit 33 is realized by, for example, a non-transitory storage medium such as an HDD (Hard Disk Drive) or a flash memory. The communication unit 32 includes, for example, a communication circuit or a communication module, and transmits and receives various data to and from the server device 20 and other devices based on the control of the processing circuit 31.

[0016] The storage unit 33 stores, for example, a trained model 331. The trained model 331 is a result of performing machine learning to determine whether or not a surrounding image generated by the imaging unit 11 is a stopping factor image. Specifically, the trained model 331 is a result of performing machine learning to determine whether or not at least one of (A1) and (A2) is captured in the surrounding image generated by the imaging unit 11.

[0017] (A1) 100 trains stopped between stations (A2) Track 101 near train 100 stopped between stations An example of the trained model 331 is a neural network. When a surrounding image is input as an input variable to the trained model 331, the trained model 331 outputs an output variable indicating the probability that the surrounding image is a stopping cause image. For example, the trained model 331 outputs a larger value as the output variable as the probability that the train 100 or the track 101 is included in the surrounding image increases.

[0018] When the processing circuit 31 receives an instruction to provide the server device 20 with a stop cause image through the communication unit 32, the processing circuit 31 judges whether or not the surrounding image generated by the imaging unit 11 at the time of reception is a stop cause image. When the processing circuit 31 receives an instruction to provide the server device 20 with a stop cause image through the communication unit 32, the processing circuit 31 judges whether or not the surrounding image generated by the imaging unit 11 at a time a predetermined time before the reception time is a stop cause image. For example, the processing circuit 31 reads out the surrounding image generated by the imaging unit 11 at a time a predetermined time before from among the surrounding images stored in the storage unit of the drive recorder, and uses it for the determination process of the stop cause image. The predetermined time is, for example, a time of about several [seconds] to several [minutes].

[0019] The processing circuit 31 inputs a surrounding image generated by the imaging unit 11 at the time of reception to the trained model 331, and if the output variable is equal to or greater than a threshold, determines that the surrounding image is a stopping cause image. The processing circuit 31 also inputs a surrounding image generated by the imaging unit 11 at a time a predetermined time before the time of reception to the trained model 331, and if the output variable is equal to or greater than a threshold, determines that the surrounding image is a stopping cause image. On the other hand, if the output variable is less than the threshold, the processing circuit 31 determines that the surrounding image input to the trained model 331 is not a stopping cause image.

[0020] The processing circuit 31 causes the communication unit 32 to transmit the stop cause image determined to be the stop cause image to the server device 20. <Configuration of the railroad crossing control device 60> As shown in FIG. 2, the railroad crossing control device 60 includes, for example, a processing circuit 64, a communication unit 65, and a storage unit 66. The processing circuit 64 is configured with, for example, a hardware processor such as a CPU. The hardware processor executes a program, which enables the processing circuit 64 to execute various processes. The program may be stored in advance in the storage unit 66. The storage unit 66 is realized by, for example, a non-transitory storage medium such as an HDD or a flash memory. The communication unit 65 includes, for example, a communication circuit or a communication module, and transmits and receives various data to and from the server device 20 and other devices based on the control of the processing circuit 64.

[0021] The processing circuit 64 judges whether or not the emergency stop button 61 connected to the crossing control device 60 has been pressed. When at least one of the following two conditions (E1) and (E2) is satisfied, the processing circuit 64 transmits information indicating that the emergency stop button 61 has been pressed to the server device 20 while controlling the special signal light emitter and the transmission of the stop signal.

[0022] (E1) When the emergency stop button 61 is pressed. (E2) When the obstacle detection device 62 determines that an obstacle has been detected within the railroad crossing 40. <Configuration of the server device 20> As shown in FIG. 2, the server device 20 includes, for example, a processing circuit 21, a communication unit 22, and a storage unit 23. The processing circuit 21 is configured with, for example, a hardware processor such as a CPU. The hardware processor executes a program, which allows the processing circuit 21 to execute various processes. The program may be stored in the storage unit 23 in advance. The storage unit 23 is realized by, for example, a non-transitory storage medium such as an HDD or a flash memory. The communication unit 22 includes, for example, a communication circuit or a communication module, and transmits and receives various data to and from the control device 30, the railroad crossing control device 60, and other devices based on the control of the processing circuit 21.

[0023] The memory unit 23 stores, for example, a trained model 231. The trained model 231 is a model that has undergone machine learning to estimate the stopping cause of the train 100 based on the stopping cause image received from the control device 30 by the communication unit 22. An example of the trained model 231 is a neural network. When the stopping cause image is input to the trained model 231 as an input variable, the trained model 231 outputs a plurality of output variables indicating the probability of each predetermined stopping cause. In this case, the processing circuit 21 of the server device 20 estimates the stopping cause with the highest output variable as the stopping cause of the train 100.

[0024] Here, the factors that cause the train 100 to stop, such as pressing the emergency stop button 61 or stopping just before or at the crossing 40, are determined to a certain extent. Specifically, the factors that cause the train 100 to stop include the following six events (B1) to (B6). Note that the six events (B1) to (B6) are merely examples and are not limited to these.

[0025] (B1) There is an object such as a stone placed in the direction of travel of train 100. (B2) There is a vehicle 10 in the direction of travel of the train 100. (B3) There is a pedestrian in the direction of travel of train 100.

[0026] (B4) Train 100 derails from track 101. (B5) Train 100 comes into contact with car 10. (B6) Train 100 collided with a pedestrian.

[0027] The trained model 231 has undergone machine learning to learn from images of stopping causes when the following six events (B1) to (B6) occur, so that it can estimate which of the events (B1) to (B6) is the cause of the stopping of the train 100 shown in the stopping cause image.

[0028] The processing circuit 21 judges whether the train 100 is stopped between stations based on the result of the train 100 being present on the track, which is specified by the operation management function of the server device 20. When the processing circuit 21 judges that the train 100 is stopped between stations, it sets an information collection area including the stop position of the train 100. In this case, the information collection area is an area from the stop position of the train 100 to a position away from the stop position by a predetermined distance. As described above, the processing circuit 21 receives position information indicating the position of the vehicle 10 from the control device 30 at predetermined time intervals by the communication unit 22. The processing circuit 21 identifies the vehicle 10 located within the set information collection area based on the received position information. The processing circuit 21 transmits an instruction to the identified vehicle 10 to provide the server device 20 with a stop cause image by the communication unit 22. When the control device 30 receives an instruction to provide the server device 20 with a stop cause image, as described above, it transmits the stop cause image to the server device 20.

[0029] Furthermore, the processing circuit 21 judges whether or not the following two conditions (C1) or (C2) are satisfied. (C1) Information indicating that the emergency stop button 61 has been pressed has been received from the railroad crossing control device 60.

[0030] (C2) Information indicating that an obstacle has been detected by the obstacle detection device 62 has been received from the railroad crossing control device 60. When the processing circuit 21 determines that at least one of the conditions (C1) and (C2) is satisfied, it sets an information collection area including the position of the railroad crossing 40 corresponding to the railroad crossing control device 60 that transmitted the information. In this case, the information collection area is an area extending from the position of the railroad crossing 40 to a position a predetermined distance away. The processing circuit 21 identifies a vehicle 10 located within the set information collection area based on the position information received from the vehicle 10. The processing circuit 21 transmits an instruction to the identified vehicle 10 via the communication unit 22 to provide the server device 20 with a stop cause image.

[0031] The processing circuit 21 determines whether or not the stop cause image received from the control device 30 as a result of the above-mentioned processing includes a first image. The first image is a stop cause image that satisfies at least one of the following three conditions (D1) to (D3).

[0032] (D1) The stopping location of train 100 is shown. (D2) The photograph shows tracks 101 near where train 100 is stopping. (D3) The image shows the tracks 101 between the station in the direction of travel of the train 100 and the stopping position.

[0033] The vicinity of the stopping position is, for example, a range of several tens of centimeters to several meters from the stopping position of the train 100. Therefore, a stopping cause image that satisfies the condition (D2) is, for example, an image in which both the train 100 and the track 101 are shown and the size of the train 100 shown in the stopping cause image is equal to or larger than a predetermined size.

[0034] The processing circuit 21 determines whether the stop cause image received from the control device 30 is a first image or a second image, which is a stop cause image other than the first image, by identifying the subject captured in the stop cause image through general image analysis. When the processing circuit 21 receives at least the first image from the control device 30, the processing circuit 21 estimates the stop cause of the train 100 based only on the first image excluding the second image from among the received stop cause images. The second image will be described later.

[0035] Next, the processing circuit 21 assigns a higher priority to the first image that more clearly depicts the cause of stopping the train 100. Hereinafter, the processing circuit 21 assigns a higher priority to the first image, the higher the angle of the first image. For example, the processing circuit 21 assigns a priority while specifying whether the first image is a high-angle image, a horizontal image, or a low-angle image by general image analysis. The processing circuit 21 estimates the cause of stopping the train 100 based on the first images with a priority equal to or higher than a predetermined threshold, while excluding the first images with a priority lower than a predetermined threshold from the specified first images.

[0036] The processing circuitry 21 estimates the cause of stopping the train 100 based on the output variables of the trained model 231 when the first image, to which a priority equal to or higher than a predetermined threshold is assigned, is input to the trained model 231. As described above, the processing circuitry 21 estimates the stop cause having the highest output variable as the stop cause of the train 100.

[0037] <Series of processes executed in the server device 20: Request for provision of stop cause image> 3 and 4, a process for requesting a stop cause image executed in the server device 20 will be described. Note that, separate from the process shown in Figs. 3 and 4, the processing circuit 21 executes a process for receiving, via the communication unit 22, position information indicating the position of the vehicle 10 from the control device 30 at predetermined time intervals.

[0038] As shown in FIG. 3, first, the processing circuit 21 judges whether the train 100 is stopped between stations based on the result of the train 100 being present on the track, which is specified by the operation management function of the server device 20 (step S100). If the processing circuit 21 judges that the train 100 is not stopped between stations (step S100; NO), there is no need to request a stop cause image from the control device 30, and therefore the series of processes is terminated. If the processing circuit 21 judges that the train 100 is stopped between stations (step S100; YES), the processing circuit 21 specifies the stop position of the train 100 based on the result of the train 100 being present on the track (step S102). Next, the processing circuit 21 sets an information collection area based on the stop position of the train 100 specified in step S102 (step S104). This information collection area is an area from the stop position of the train 100 to a position away from the stop position by a predetermined distance. Next, the processing circuit 21 requests the vehicle 10 located within the information collection area to provide a stop cause image based on the position information received from the control device 30 (step S106). After that, the processing circuit 21 ends the series of processes.

[0039] As shown in FIG. 4, first, the processing circuit 21 judges whether or not at least one of the two conditions (C1) and (C2) is satisfied (step S200). When the processing circuit 21 judges that neither the condition (C1) nor the condition (C2) is satisfied (step S200; NO), it does not need to request a stop cause image from the control device 30, and ends the series of processes. When the processing circuit 21 judges that at least one of the conditions (C1) and the condition (C2) is satisfied (step S200; YES), it specifies the position of the crossing 40 corresponding to the crossing control device 60 that transmitted the information related to step S200 (step S202). Next, the processing circuit 21 sets an information collection area based on the position of the crossing 40 specified in step S202 (step S204). This information collection area is an area from the corresponding crossing 40 to a position away from the corresponding crossing 40 by a predetermined distance. Next, the processing circuit 21 requests the vehicle 10 located within the information collection area to provide a stop cause image based on the position information received from the control device 30 (step S206). After that, the processing circuit 21 ends the series of processes.

[0040] <Series of processes executed in the control device 30: Providing stop cause images> A process for providing a stop cause image executed in the control device 30 will be described with reference to Fig. 5. In addition to the process shown in Fig. 5, the processing circuit 31 executes a process for transmitting, via the communication unit 32, position information indicating the position of the vehicle 10 acquired by the position information acquisition unit 12 at predetermined time intervals.

[0041] As shown in FIG. 5, the processing circuit 31 judges whether or not an instruction to provide the stop cause image to the server device 20 has been received from the server device 20 (step S300). The processing circuit 31 waits while repeating the judgment process of step S300 until the instruction is received (step S300; NO). When the processing circuit 31 judges that an instruction to provide the stop cause image to the server device 20 has been received (step S300; YES), the processing circuit 31 acquires a surrounding image generated by the imaging unit 11 (step S302). The surrounding image acquired in step S302 is a surrounding image captured and generated by the imaging unit 11 at the time when the processing circuit 31 received the instruction in step S300. In addition, the surrounding image acquired in step S302 is a surrounding image captured and generated by the imaging unit 11 a predetermined time before the time when the processing circuit 31 received the instruction in step S300, and is a surrounding image stored in the drive recorder.

[0042] The processing circuit 31 determines whether the peripheral image acquired in step S302 is a stop cause image (step S304). If the processing circuit 31 determines that the peripheral image acquired in step S302 is not a stop cause image, it determines that there is no stop cause image that can be provided to the server device 20, and ends the series of processes. If the processing circuit 31 determines that the peripheral image acquired in step S302 is a stop cause image, it causes the communication unit 32 to transmit the stop cause image to the server device 20 (step S306). Thereafter, the processing circuit 31 ends the series of processes.

[0043] <Series of processes executed in the server device 20: Estimation of cause of stoppage> With reference to Fig. 6, the process related to estimation of the stop cause executed in the server device 20 will be described. As shown in Fig. 6, the processing circuit 21 receives a stop cause image from the control device 30 by the communication unit 22 (step S400). The processing circuit 21 determines whether or not the first image is included in the stop cause image received from the control device 30 (step S402). If the first image is not included in the stop cause image received from the control device 30, the processing circuit 21 ends the series of processes since it is difficult to estimate the stop cause of the train 100.

[0044] When the processing circuit 21 determines that the stop cause image includes a first image (step S402; YES), the processing circuit 21 assigns a higher priority to the image determined to be the first image in step S402, the higher the angle of the image (step S404). Next, the processing circuit 21 excludes low-priority first images, which have a priority below a predetermined threshold, from the first images to which priorities have been assigned in step S402 (step S406). Next, the processing circuit 21 estimates the stop cause of the train 100 based on the first images that have not been excluded in step S406 (step S408). After that, the processing circuit 21 ends the series of processes.

[0045] <Actions and Effects of the Embodiments> According to the above embodiment, the following actions and effects can be obtained. (1) The imaging unit 11 generates a surrounding image by capturing an image of the surroundings of the vehicle 10. In addition, the position information acquisition unit 12 acquires position information of the vehicle 10 and transmits the acquired position information to the server device 20.

[0046] When a train 100 traveling on a track 101 stops between stations, the server device 20 requests the provision of surrounding images from vehicles 10 located within an information collection area that includes the stopping position of the train 100.

[0047] In the vehicle 10 that is requested to provide the surrounding image, the processing circuit 31 identifies the stop cause image from the surrounding image generated by the imaging unit 11. The processing circuit 31 provides the surrounding image to the server device 20 by transmitting the identified stop cause image to the server device 20.

[0048] When the train 100 stops between stations, the driver or conductor of the train 100 is required to understand the cause of the train stopping by getting off the train 100 and checking the surroundings of the train 100. In addition, in order for a dispatcher at a control center to understand or estimate the cause of the train 100 stopping, it is preferable to have not only a conversation with the driver or conductor of the train 100 but also surrounding images of the train 100 and the surroundings of the train 100. In other words, it may take time to understand the cause of the train 100 stopping.

[0049] According to this configuration, the server device 20 collects stop cause images as peripheral images captured by the imaging units 11 of the vehicles 10 located within an information collection area including the stopping position of the train 100. In this way, the information processing method enables a commander at a command center to refer to the stop cause images collected by the server device 20, thereby reducing the time it takes to understand the cause of the train 100 stopping.

[0050] (2) The processing circuit 21 estimates the cause of the train 100 stopping based on the stop cause image. Specifically, the processing circuit 21 estimates the cause of the train 100 stopping based on the output variables of the trained model 231 when the stop cause image is input to the trained model 231. That is, the information processing method can estimate the cause of the train 100 stopping based on the stop cause image, which contains more objective information than a conversation with the driver or conductor of the train 100. Furthermore, the information processing method can easily estimate the cause of the train 100 stopping by using the trained model 231.

[0051] (3) When an emergency stop button 61 provided at the railroad crossing 40 is pressed, the processing circuit 21 sets an information collection area to include the position of the railroad crossing 40. Furthermore, when an obstacle is detected within the railroad crossing 40 by an obstacle detection device 62 provided at the railroad crossing 40, the processing circuit 21 sets an information collection area to include the position of the railroad crossing 40. Therefore, in the information processing method, the pressing of the emergency stop button 61 or the detection of an obstacle by the obstacle detection device 62 can be used as a trigger to collect stop cause images in the server device 20.

[0052] (4) The processing circuit 21 determines whether the stop cause image received from the control device 30 includes the first image. If the processing circuit 21 determines that the stop cause image includes the first image, it assumes that at least the first image has been received, and estimates the stop cause of the train 100 based on the first image.

[0053] When the stop cause image is a first image that satisfies the condition (D1), the situation of the stop position of the train 100 and the state of the train 100 can be confirmed by referring to the first image. When the stop cause image is a first image that satisfies the condition (D2), the state of the train 100 and the track 101 can be confirmed by referring to the first image, such as the presence or absence of an obstacle on the track 101 near the stop position of the train 100, the presence or absence of an object that has touched the train 100, and the presence or absence of damage on the track 101. When the stop cause image is a first image that satisfies the condition (D3), the state of the train 10 ... to the operation of the train 100 when the train 100 moves to a station in the travel direction. Therefore, in order to estimate the stop cause of the train 100, it is preferable to use a first image that is a stop cause image that satisfies at least one of the conditions (D1) to (D3).

[0054] On the other hand, the stop cause image includes a second image that includes at least one of (A1) and (A2) but does not satisfy conditions (D1) to (D3). In other words, the second image includes the train 100 stopped between stations and the track 101 near the train 100, but does not include enough of the train 100 or the track 101 to obtain sufficient information due to the angle of view and the distance to the train 100. If the stop cause of the train 100 is estimated using such a second image, the estimation accuracy may decrease. In the information processing method, the stop cause of the train 100 is estimated by referring only to the first image, excluding the second image, among the collected stop cause images. Therefore, the information processing method can estimate the stop cause of the train 100 with high accuracy.

[0055] (5) When a request for providing a peripheral image is received, the processing circuit 31 transmits to the server device 20 a stop cause image generated by the imaging unit 11 a predetermined time before the time when the train 100 stops. For example, when the vehicle 10 is stopped near a railroad crossing 40 or a track 101, the imaging unit 11 may capture an image of the railroad crossing 40 or the track 101 near the stop position of the train 100 and generate a peripheral image before the train 100 stops between stations. In this case, the peripheral image may include something that may be a cause of the train 100 stopping. Therefore, it is preferable that the processing circuit 31 use the stop cause image, which is a peripheral image generated by the imaging unit 11 at a time a predetermined time before the time when the instruction is received, to estimate the cause of the train 100 stopping. Therefore, the information processing method can estimate the cause of the train 100 stopping with higher accuracy.

[0056] (6) The processing circuit 21 assigns a higher priority to the first image that more clearly depicts the cause of stopping the train 100. Specifically, the processing circuit 21 assigns a higher priority to the first image that is a higher-angle image. Here, the stopping cause image may contain a larger amount of information about the surroundings of the vehicle 10 in a peripheral image generated by the imaging unit 11 provided in a vehicle 10 with a high vehicle height, such as a truck or a bus, than in a peripheral image generated by the imaging unit 11 provided in a vehicle 10 with a low vehicle height, such as a sports car. In the information processing method, the stopping cause image with a larger amount of information can be used to estimate the stopping cause of the train 100.

[0057] <Modification> The above embodiment may be modified as follows: The above embodiment and each of the following modifications may be combined with each other within a range that does not cause technical contradiction.

[0058] The processing circuitry 21 may not execute the process shown in Fig. 4 out of the process shown in Fig. 3 and the process shown in Fig. 4. Also, the processing circuitry 21 may not execute the process shown in Fig. 3 out of the process shown in Fig. 3 and the process shown in Fig. 4.

[0059] In the process of step S302, the processing circuitry 31 may acquire only the peripheral image captured and generated by the imaging unit 11 at the time when the processing circuitry 31 received the instruction in step S300.

[0060] The processing circuitry 31 may acquire peripheral images captured and generated by the imaging unit 11 during a predetermined period including the time when the instruction was received in step S302. The processing circuitry 31 may also acquire peripheral images captured and generated by the imaging unit 11 during a predetermined period including the time a predetermined time before the time when the instruction was received in step S302.

[0061] If the vehicle 10 has been moving between the time when the instruction was received and the time a predetermined time before, the processing circuit 31 may not need to acquire a surrounding image a predetermined time before the time when the instruction was received. The processing circuit 31 determines whether the vehicle 10 has been moving based on the detection result of the speed detection unit of the vehicle 10, the OFF state of the ignition switch, the gear selector being in the parking range, and the like. Here, if the vehicle 10 has been moving, the vehicle 10 may not be located within the information collection area at the time a predetermined time before the time when the instruction was received. Therefore, if the vehicle 10 has been moving, the surrounding image captured and generated by the imaging unit 11 at the time a predetermined time before the time when the instruction was received is highly likely not to be a stop factor image. According to this configuration, when the vehicle 10 has been moving, the processing circuit 31 can omit the process of determining whether the surrounding image captured and generated by the imaging unit 11 at the time a predetermined time before the time when the instruction was received is a stop factor image.

[0062] The processing circuit 21 may execute only step S400 among the processes shown in Fig. 6. In this case, the information processing method allows a commander at a command center to understand the cause of stopping the train 100 by referring to the stop cause image collected from the vehicle 10 by the server device 20.

[0063] The processing circuit 21 may not execute the process of step S402 among the processes shown in FIG. 6. In this case, the processing circuit 21 advances the process to step S404 after executing step S400. Here, in cases where the number of vehicles 10 located in the information collection area is small, the server device 20 may receive the second image as the stopping cause image but may not receive the first image. On the other hand, when the first image cannot be received, it is preferable to estimate the stopping cause of the train 100 using the second image. According to this configuration, the information processing method can estimate the stopping cause of the train 100 based on the stopping cause image collected from the vehicle 10 by the server device 20. In addition, when estimating the stopping cause using the second image, the processing circuit 21 may also add a priority to the second image.

[0064] The processing circuit 21 may not execute the processes of steps S404 and S406 in the process shown in FIG. 6. In this case, when the processing circuit 21 determines that the stop cause image includes the first image (step S402; YES), the processing circuit 21 proceeds to the process of step S408. Here, when the number of vehicles 10 located in the information collection area is small, the server device 20 may not be able to receive the first image sufficiently. On the other hand, when the server device 20 is unable to receive the first image sufficiently, it is preferable to estimate the stop cause image of the train 100 using the first image with a low priority. According to this configuration, the information processing method can estimate the stop cause of the train 100 using all of the first images collected from the vehicles 10 by the server device 20.

[0065] Instead of or in addition to a configuration in which the higher the first image is an image taken at a high angle, the processing circuit 21 may assign a higher priority to the first image if the first image is an image taken under more appropriate conditions. An image taken under appropriate conditions is, for example, an image taken with appropriate exposure and free of whiteout or blackout, an image taken with appropriate focus and free of out-of-focus, an image taken with appropriate white balance and having a color temperature that matches the real thing, etc. In assigning a priority, the processing circuit 21 may use a learned model capable of determining whether an image is taken at a high angle or under appropriate conditions, instead of general image analysis.

[0066] The processing circuit 21 may perform processing to assign a low priority to a first image that does not clearly depict the cause of the train 100 stopping, instead of performing processing to assign a high priority to a first image that clearly depicts the cause of the train 100 stopping.

[0067] The processing circuit 31 may transmit a stop cause image to the server device 20 when it detects that a stop cause has occurred at the railroad crossing 40 or the track 101. In this case, the processing circuit 31 identifies a subject to be transferred to the stop cause image by general image analysis. When the processing circuit 31 determines that an obstacle exists on the track 101 based on the identification result, it transmits the stop cause image to the server device 20. According to this configuration, the information processing method can collect the stop cause image in the server device 20 before an event occurs, such as the train 100 stopping, the emergency stop button 61 being pressed, or an obstacle being detected by the obstacle detection device 62. Therefore, the information processing method can allow a commander at the command center to grasp an event that may be a stop cause of the train 100 before these events occur.

[0068] The processing circuitry 31 may transmit the first image to the server device 20 only when the stop cause image is the first image. In this case, the processing circuitry 31 performs a process of determining whether the stop cause image is the first image or the second image by identifying a subject captured in the stop cause image through general image analysis.

[0069] The processing circuit 21 may use a trained model that has undergone machine learning to determine whether the stopping cause image is the first image. For example, when a stopping cause image is input, the trained model outputs an output variable indicating the probability that the stopping cause image is the first image. The processing circuit 31 inputs the stopping cause image to the trained model, and if the output variable is equal to or greater than a threshold, the processing circuit 31 determines that the stopping cause image is the first image. On the other hand, if the output variable is less than the threshold, the processing circuit 31 determines that the stopping cause image input to the trained model is the second image.

[0070] The location information acquired by the location information acquisition unit 12 may be identified or supplemented by an INS (Inertial Navigation System) that uses the outputs of various sensors equipped in the vehicle 10. Some or all of the components of the processing circuit 21 and the processing circuit 31 may be realized by hardware (including circuitry) such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a GPU (Graphics Processing Unit), or may be realized by a combination of software and hardware. [Explanation of symbols]

[0071] 1...information processing system, 10...vehicle, 11...imaging unit, 12...location information acquisition unit, 20...server device, 21,31,64...processing circuit, 22,32,65...communication unit, 23,33,66...memory unit, 30...control device, 40...railroad crossing, 50...railroad crossing equipment box, 60...railroad crossing control device, 61...emergency stop button, 62...obstacle detection device, 70...communication network, 100...train, 101...railroad tracks.

Claims

1. An information processing method executed in an information processing system including a vehicle including an imaging unit that generates a surrounding image by imaging a surrounding situation and a communication unit that communicates with an outside, and a server device installed outside the vehicle, wherein the surrounding image is transmitted from the communication unit of the vehicle to the server device via a communication network, When a train traveling on a track stops between stations, the server device requests the vehicles located within an information collection area including the stopping position of the train to provide the surrounding image; a stop cause image, which is the peripheral image showing at least one of the train stopped at the stop position and the track near the train, is transmitted to the server device by the communication unit of the vehicle located within the information collection area; An information processing method comprising:

2. A processing circuit of the server device estimates a cause of the train stopping based on the stop cause image received by the server device. The information processing method according to claim 1 .

3. and when the train stops between stations due to pressing an emergency stop button provided at a railroad crossing, the server device sets the information collection area to include a position of the railroad crossing. The information processing method according to claim 1 .

4. When the server device receives at least a first image, which is the stop cause image showing at least one of a stop position of the train, the track near the stop position, and the track between a station in the traveling direction of the train and the stop position, and a second image, which is the stop cause image other than the first image, a processing circuit of the server device estimates the cause of the train stopping based on the first image. The information processing method according to claim 1 .

5. The communication unit of the vehicle located within the information collection area transmits to the server device the stop cause image, which is the surrounding image generated by the imaging unit, a predetermined time before the time when the train stops. The information processing method according to claim 1 .

Images