Information processing method

Abstract

The invention provides an information processing method. The information processing method is a method performed by an information processing system including: a vehicle including an imaging unit and a communication unit; and a server device. The information processing method includes: when a train stops between stations, requesting, by the server device, the vehicle located in an information collection area including a stop position of the train moving on a railway track to provide a surrounding image; and transmitting, by the communication unit of the vehicle located in the information collection area, a stop factor image to the server device, the stop factor image being a peripheral image in which at least one of the train that has stopped at the stop position and the railroad track in the vicinity of the train appears.

Description

Technical Field

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

[0002] In railway operation, the running status of trains in the railway section is mastered and the railway track environment is monitored in the command center. When an event causing a train running problem occurs, the driver or the conductor of the train stops the train and sends a message about the details of the event to the command center. For example, Japanese Unexamined Patent Application Publication No. 2010-176612 (JP 2010-176612 A) discloses that a message indicating that an event causing a train running problem has occurred is sent to the driver or the conductor of another train in the railway section of the command center. Summary of the invention

[0003] For example, when a train stops between stations, the driver or conductor needs to know the stopping factors of the train. At the same time, since the driver or conductor needs to communicate with the command center and give instructions to passengers through train broadcasting, it may be difficult for the driver or conductor to immediately know the stopping factors. In the technology disclosed in JP 2010-176612A, even if the driver or conductor of another train can be informed that an event that causes a train operation problem has occurred, the stopping factors of the train cannot be known.

[0004] An information processing method for solving the above-mentioned problem is performed by an information processing system. The information processing system includes: a vehicle, which includes: an imaging unit, which generates a peripheral image by imaging the surrounding situation, and a communication unit, which communicates with the outside; and a server device, which is installed on the outside of the vehicle. The peripheral image is sent from the communication unit of the vehicle to the server device via a communication network. The information processing method includes: when a train stops between stations, the server device requires the vehicle located in an information collection area to provide the peripheral image, and the information collection area includes a stop position of the train moving on a railway track; and the communication unit of the vehicle located in the information collection area sends a stop factor image to the server device, and the stop factor image is the peripheral image of at least one of the train that has stopped at the stop position and the railway track near the train.

[0005] According to this configuration, an effect is exhibited in which it is possible to reduce the time-consuming process of grasping the factors causing the train to stop. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] Features, advantages, and technical and industrial significance of exemplary embodiments of the present invention will be described hereinafter with reference to the accompanying drawings, in which like reference numerals represent like elements, and in which:

[0007] Figure 1 A diagram used in the description of an information processing system;

[0008] Figure 2 A diagram showing an example of the configuration of a server device, a control device, and a railway crossing control device;

[0009] Figure 3 is a flowchart showing an example of processing performed in a server device;

[0010] Figure 4 is a flowchart showing an example of processing performed in a server device;

[0011] Figure 5 is a flowchart showing an example of a process performed in the control device; and

[0012] Figure 6 1 is a flowchart showing an example of processing executed in the server device. DETAILED DESCRIPTION

[0013] Example

[0014] Refer to below Figures 1 to 6 An embodiment of an information processing method is described.

[0015] Complete configuration of information processing system 1

[0016] like Figure 1 As shown, for example, an information processing system 1 for implementing the information processing method includes one or more vehicles 10, a server device 20, and one or more railway crossing control devices 60. For example, the vehicle 10 includes an imaging unit 11, a position information acquisition unit 12, and a control device 30. The railway crossing control devices 60 are respectively installed in railway crossing equipment boxes 50 set near different railway crossings 40. The control device 30, the server device 20, and the railway crossing control device 60 are connected to each other so as to be able to transmit and receive information to each other via a communication network 70. For example, the communication network 70 includes the Internet, a wide area network (WAN), a local area network (LAN), a provider terminal, a wireless communication network, a wireless base station, and a dedicated line.

[0017] For example, the imaging unit 11 is a digital camera using a solid-state image sensor such as a charge coupled device (CCD) and a complementary metal oxide semiconductor (CMOS). An example of the imaging unit 11 is a digital camera configured as a dashboard camera. The imaging unit 11 images the surrounding conditions of the vehicle 10. Depending on the installation position of the imaging unit 11 in the vehicle 10, the imaging unit 11 can image the front side, the rear side, and the side of the vehicle 10. The imaging unit 11 generates a surrounding image by imaging the surrounding conditions of the vehicle 10. When the vehicle 10 travels near a railway crossing 40 or a railway track 101, the train 100 or the railway track 101 may appear in the surrounding image generated by the imaging unit 11.

[0018] The position information acquisition unit 12 is, for example, a receiver of a global navigation satellite system (GNSS). The position information acquisition unit 12 specifies 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.

[0019] The control device 30 transmits the position information to the server device 20 at every predetermined time interval, thereby enabling the server device 20 to specify the position of the vehicle 10. When there is a request from the server device 20, the control device 30 transmits the stopping factor image to the server device 20. The stopping factor image is a surrounding image in which at least one of the train 100 stopped between stations or the railroad track 101 near the train 100 appears in the surrounding image. In other words, the stopping factor image is an image with a high probability that the stopping factor of the train 100 appears in the image.

[0020] For example, the server device 20 is a device that collects information used in the operation management of the train 100 running in the managed railway section. For example, the server device 20 is set in the command center. The dispatcher of the command center refers to the information collected in the server device 20 and performs operation management on the train 100 running in the managed railway section.

[0021] The railway crossing control device 60 controls the railway crossing 40 to be controlled. Specifically, when the electronic train detector of the railway crossing 40 detects that the train 100 is approaching, the railway crossing control device 60 rings the alarm device of the railway crossing 40, lowers the barrier pole, and flashes the alarm light. When the electronic train detector of the railway crossing 40 detects that the train 100 passes, the railway crossing control device 60 stops the alarm device of the railway crossing 40, raises the barrier pole, and stops flashing the alarm light.

[0022] An emergency stop button 61 and an obstacle detection device 62 are connected to the railway crossing control device 60. The emergency stop button 61 is operated by a pedestrian passing through the railway crossing 40 or a driver of a vehicle 10 passing through the railway crossing 40. When the emergency stop button 61 is operated, the railway crossing control device 60 flashes an obstacle warning indicator light provided in front of the railway crossing 40 and sends a stop signal to the train 100 near the railway crossing 40. The obstacle detection device 62 detects an obstacle in the railway crossing 40. The obstacle detection device 62 detects an obstacle through a detection system such as an optical sensor system, a loop coil system, and a three-dimensional laser radar system. When the obstacle detection device 62 detects an obstacle, the railway crossing control device 60 flashes the obstacle warning indicator light and sends a stop signal. When the obstacle warning indicator light flashes or a stop signal is received from the railway crossing control device 60, the driver of the train 100 approaching the railway crossing 40 stops the train 100 in front of the railway crossing 40.

[0023] Configuration of the control device 30

[0024] like Figure 2 As shown, for example, the control device 30 includes a processing circuit 31, a communication unit 32, and a storage unit 33. For example, the processing circuit 31 is configured by a hardware processor such as a central processing unit (CPU). As a result of the hardware processor executing the program, the processing circuit 31 is able to perform various processes. The program can be pre-stored in the storage unit 33. For example, the storage unit 33 is implemented by a non-temporary storage medium such as a hard disk drive (HDD) or a flash memory. For example, the communication unit 32 includes a communication circuit or a communication module, and sends various data to the server device 20 and other devices based on the control of the processing circuit 31 and receives various data from the server device 20 and other devices.

[0025] For example, the storage unit 33 stores therein a learning model 331. The learning model 331 is obtained by performing machine learning to determine whether the peripheral image generated by the imaging unit 11 is a stop factor image. Specifically, the learning model 331 is obtained by performing machine learning to determine whether at least one of (A1) and (A2) appears in the peripheral image generated by the imaging unit 11.

[0026] (A1) Trains stopping between stations 100

[0027] (A2) Railway tracks near train 100 stopped between stations

[0028] One example of the learning model 331 is a neural network. When the surrounding image is input as an input variable to the learning model 331, the learning model 331 outputs an output variable indicating the probability that the surrounding image is a stop factor image. For example, as the probability that the train 100 and the railroad track 101 appear in the surrounding image becomes higher, the learning model 331 outputs a larger value as the output variable.

[0029] When the communication unit 32 receives a command to provide the stop factor image to the server device 20, the processing circuit 31 determines whether the surrounding image generated by the imaging unit 11 at the receiving time point is a stop factor image. When the communication unit 32 receives a command to provide the stop factor image to the server device 20, the processing circuit 31 determines whether the surrounding image generated by the imaging unit 11 at a time point a predetermined time earlier than the receiving time point is a stop factor image. For example, the processing circuit 31 reads out the surrounding image generated by the imaging unit 11 at a time point a predetermined time earlier from the surrounding images stored in the storage unit of the dashboard camera, and uses the surrounding image in the process of determining the stop factor image. For example, the predetermined time is a time of about several seconds to several minutes.

[0030] The processing circuit 31 inputs the surrounding image generated by the imaging unit 11 at the receiving time point into the learning model 331, and determines that the surrounding image is a stop factor image when the output variable as the output is equal to or greater than the threshold value. The processing circuit 31 inputs the surrounding image generated by the imaging unit 11 at a time point a predetermined time earlier than the receiving time point into the learning model 331, and determines that the surrounding image is a stop factor image when the output variable as the output is equal to or greater than the threshold value. At the same time, when the output variable is less than the threshold value, the processing circuit 31 determines that the surrounding image input to the learning model 331 is not a stop factor image.

[0031] The processing circuit 31 causes the communication unit 32 to transmit the stop factor image determined as the stop factor image to the server device 20 .

[0032] Configuration of Railway Crossing Control Device 60

[0033] like Figure 2 As shown, for example, the railway crossing control device 60 includes a processing circuit 64, a communication unit 65, and a storage unit 66. For example, the processing circuit 64 is configured by a hardware processor such as a CPU. As a result of the hardware processor executing the program, the processing circuit 64 is able to perform various processes. The program can be pre-stored in the storage unit 66. For example, the storage unit 66 is implemented by a non-transitory storage medium such as an HDD or a flash memory. For example, the communication unit 65 includes a communication circuit or a communication module, and sends various data to the server device 20 and other devices and receives various data from the server device 20 and other devices based on the control of the processing circuit 64.

[0034] The processing circuit 64 determines whether the emergency stop button 61 connected to the railway crossing control device 60 is pressed. When at least one of the following two conditions (E1) and (E2) is satisfied, the processing circuit 64 performs control according to the transmission of the obstacle warning indicator light and the stop signal, and sends information indicating that the emergency stop button 61 is pressed to the server device 20.

[0035] (E1) When the emergency stop button 61 is pressed.

[0036] (E2) When the obstacle detection device 62 determines that an obstacle is detected at the railway crossing 40 .

[0037] Configuration of the server device 20

[0038] like Figure 2 As shown, for example, the server device 20 includes a processing circuit 21, a communication unit 22, and a storage unit 23. For example, the processing circuit 21 is configured by a hardware processor such as a CPU. As a result of the hardware processor executing the program, the processing circuit 21 is able to perform various processes. The program can be pre-stored in the storage unit 23. For example, the storage unit 23 is implemented by a non-temporary storage medium such as an HDD or a flash memory. For example, the communication unit 22 includes a communication circuit or a communication module, and sends various data to the control device 30, the railway crossing control device 60 and other devices based on the control of the processing circuit 21, and receives various data from the control device 30, the railway crossing control device 60 and other devices.

[0039] For example, the storage unit 23 stores therein a learning model 231. The learning model 231 is obtained by performing machine learning that estimates the stopping factor of the train 100 based on the stopping factor image received from the control device 30 by the communication unit 22. One example of the learning model 231 is a neural network. When the stopping factor image is input to the learning model 231 as an input variable, the learning model 231 outputs a plurality of output variables indicating the probability of each stopping factor defined in advance. In this case, the processing circuit 21 of the server device 20 estimates the stopping factor with the highest output variable as the stopping factor of the train 100.

[0040] Here, the stopping factor when the emergency stop button 61 is pressed or the train 100 stops in front of the railway crossing 40 or in the railway crossing 40 is determined to a certain extent. Specifically, as the stopping factor of the train 100, the following six events (B1) to (B6) are indicated as an example. The six events (B1) to (B6) are an example and are not limited thereto.

[0041] (B1) An object such as a stone exists in the traveling direction of the train 100 .

[0042] (B2) The vehicle 10 exists in the traveling direction of the train 100 .

[0043] (B3) There is a pedestrian in the traveling direction of the train 100.

[0044] (B4) The train 100 derails from the railway track 101.

[0045] (B5) The train 100 has come into contact with the vehicle 10 .

[0046] (B6) Train 100 has come into contact with a pedestrian.

[0047] The learning model 231 is obtained as follows: by performing machine learning so as to be able to infer which of the above six events (B1) to (B6) is the stopping factor of the train 100 appearing in the stopping factor image by performing learning from the stopping factor image obtained when the events (B1) to (B6) occur.

[0048] The processing circuit 21 determines whether the train 100 stops between stations based on the on-track detection result of the train 100 specified by the operation management function of the server device 20. When the processing circuit 21 determines that the train 100 stops between stations, the processing circuit 21 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 spaced a predetermined distance from the stop position. As described above, the processing circuit 21 receives position information indicating the position of the vehicle 10 from the control device 30 through the communication unit 22 at each predetermined time interval. The processing circuit 21 specifies the vehicle 10 located in the set information collection area based on the received position information. The processing circuit 21 sends a command for sending a stop factor image to the server device 20 to the specified vehicle 10 through the communication unit 22. As described above, when the control device 30 receives a command for providing the stop factor image to the server device 20, the control device 30 sends the stop factor image to the server device 20.

[0049] The processing circuit 21 determines whether the following two conditions (C1) or (C2) are satisfied.

[0050] (C1) Information indicating that the emergency stop button 61 has been pressed is received from the railway crossing control device 60.

[0051] (C2) Information indicating that an obstacle has been detected by the obstacle detection device 62 is received from the railway crossing control device 60 .

[0052] When the processing circuit 21 determines that at least one of the conditions (C1) and (C2) is satisfied, the processing circuit 21 sets an information collection area including the position of the railway crossing 40 corresponding to the railway crossing control device 60 that has transmitted information. In this case, the information collection area is an area from the position of the railway crossing 40 to a position spaced a predetermined distance from the position. The processing circuit 21 specifies the vehicle 10 located in the set information collection area based on the position information received from the vehicle 10. The processing circuit 21 transmits a command for providing the server device 20 with a stop factor image to the specified vehicle 10 through the communication unit 22.

[0053] As a result of the above-described processing, the processing circuit 21 determines whether the first image is included in the stopping factor image received from the control device 30. The first image is a stopping factor image that satisfies at least one of the following three conditions (D1) to (D3).

[0054] (D1) The stop position of the train 100 appears.

[0055] (D2) The railroad track 101 near the stop position of the train 100 appears.

[0056] (D3) The railroad track 101 between the station in the traveling direction of the train 100 and the stop position appears.

[0057] For example, “near the stop position” is expressed as a range of several tens of centimeters to several meters from the stop position of the train 100. Therefore, for example, a stop factor image satisfying the condition (D2) is an image in which both the train 100 and the railroad track 101 appear and the size of the train 100 shown in the stop factor image is equal to or larger than a predetermined size.

[0058] The processing circuit 21 determines whether each stop factor image received from the control device 30 is a first image or a second image which is a stop factor image other than the first image by specifying a photographed object appearing in the stop factor image by general image analysis. When at least the first image has been received from the control device 30, the processing circuit 21 estimates the stop factor of the train 100 based on only the first image among the received stop factor images except for the second image. The second image will be described later.

[0059] Next, the processing circuit 21 applies a higher priority to the first image in which the stopping factor of the train 100 appears in a more easily visible manner. Thereafter, as the first image becomes a higher angle image, the processing circuit 21 applies a higher priority. For example, the processing circuit 21 specifies whether the first image is a high angle image, a horizontal image, or a low angle image through general image analysis, and applies the priority. The processing circuit 21 excludes first images having a priority less than a predetermined threshold from the specified first images, and estimates the stopping factor of the train 100 based on the first images having a priority equal to or greater than the predetermined threshold.

[0060] When the first image having a priority equal to or greater than a predetermined threshold is input to the learning model 231, the processing circuit 21 estimates the stopping factor of the train 100 based on the output variable of the learning model 231. As described above, the processing circuit 21 estimates the stopping factor with the highest output variable as the stopping factor of the train 100.

[0061] A series of processes executed in the server device 20: requesting a stop factor image

[0062] Reference Figure 3 and Figure 4 , describes the processing according to the request of the stop factor image executed in the server device 20. Figure 3 and Figure 4 In addition to the illustrated processing, the processing circuit 21 also performs processing of receiving position information indicating the position of the vehicle 10 from the control device 30 through the communication unit 22 at every predetermined time interval.

[0063] like Figure 3 As shown, first, the processing circuit 21 determines whether the train 100 stops between stations based on the on-track detection result of the train 100 specified by the operation management function of the server device 20 (step S100). When the processing circuit 21 determines that the train 100 does not stop between stations (step S100: No), the processing circuit 21 does not need to request the control device 30 for a stop factor image and thus ends a series of processing. When the processing circuit 21 determines that the train 100 stops between stations (step S100: Yes), the processing circuit 21 specifies the stop position of the train 100 based on the on-track detection result of the train 100 (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). The information collection area is an area from the stop position of the train 100 to a position spaced a predetermined distance from the stop position. Next, the processing circuit 21 requires the vehicle 10 located in the information collection area to provide a stop factor image based on the position information received from the control device 30 (step S106). Then, the processing circuit 21 ends a series of processing.

[0064] like Figure 4 As shown, first, the processing circuit 21 determines whether at least one of the two conditions (C1) and (C2) is satisfied (step S200). When the processing circuit 21 determines that both the conditions (C1) and (C2) are not satisfied (step S200: No), the processing circuit 21 does not need to request the control device 30 for a stop factor image and thus ends a series of processing. When the processing circuit 21 determines that at least one of the conditions (C1) and (C2) is satisfied (step S200: Yes), the processing circuit 21 specifies the position of the railway crossing 40 corresponding to the railway crossing control device 60 that has sent information according to step S200 (step S202). Next, the processing circuit 21 sets an information collection area based on the position of the railway crossing 40 specified in step S202 (step S204). The information collection area is an area from the corresponding railway crossing 40 to a position spaced a predetermined distance from the railway crossing 40. Next, the processing circuit 21 requests the vehicle 10 located in the information collection area to provide a stop factor image based on the position information received from the control device 30 (step S206). Then, the processing circuit 21 ends a series of processing.

[0065] A series of processes executed in the control device 30: providing a stop factor image

[0066] Reference Figure 5 , describes the processing according to the provision of the stop factor image performed in the control device 30. Figure 5 In addition to the illustrated processing, the processing circuit 31 performs processing of transmitting, through the communication unit 32 , position information indicating the position of the vehicle 10 acquired by the position information acquisition unit 12 at every predetermined time interval.

[0067] like Figure 5 As shown, the processing circuit 31 determines whether a command for providing the stopping factor image to the server device 20 is received from the server device 20 (step S300). The processing circuit 31 repeats the determination process of step S300, and waits until a command is received (step S300: No). When the processing circuit 31 determines that a command for providing the stopping factor image to the server device 20 has been received (step S300: Yes), the processing circuit 31 acquires the peripheral image generated by the imaging unit 11 (step S302). The peripheral image acquired in step S302 is a peripheral image imaged and generated by the imaging unit 11 at the time point when the processing circuit 31 receives the command in step S300. The peripheral image acquired in step S302 is a peripheral image imaged and generated by the imaging unit 11 at a predetermined time earlier than the time point when the processing circuit 31 receives the command in step S300, and has been stored in the dashboard camera.

[0068] The processing circuit 31 determines whether the surrounding image acquired in step S302 is a stop factor image (step S304). When the processing circuit 31 determines that the surrounding image acquired in step S302 is not a stop factor image, the processing circuit 31 considers that there is no stop factor image that can be provided to the server device 20 and ends a series of processing. When the processing circuit 31 determines that the surrounding image acquired in step S302 is a stop factor image, the processing circuit 31 sends the stop factor image to the server device 20 through the communication unit 32 (step S306). Subsequently, the processing circuit 31 ends a series of processing.

[0069] A series of processes executed in the server device 20: Estimation of stop factor

[0070] Reference Figure 6 , describes the processing based on the estimation of the stop factor performed in the server device 20. Figure 6 As shown, the processing circuit 21 receives the stop factor image from the control device 30 through the communication unit 22 (step S400). The processing circuit 21 determines whether the first image is included in the stop factor image received from the control device 30 (step S402). When the first image is not included in the stop factor image received from the control device 30, the processing circuit 21 ends a series of processing because it is difficult to estimate the stop factor of the train 100.

[0071] When the processing circuit 21 determines that the first image is included in the stop factor image (step S402: Yes), the processing circuit 21 applies a higher priority to the higher angle image of the image determined as the first image in step S402 (step S404). Next, the processing circuit 21 excludes the first images whose priority is lower than a predetermined threshold value from the first images to which the priority is applied in step S402 (step S406). Next, the processing circuit 21 estimates the stop factor of the train 100 based on the first images that are not excluded in step S406 (step S408). Subsequently, the processing circuit 21 ends a series of processing.

[0072] Functions and Effects of the Embodiments

[0073] According to the above-described embodiment, the following operations and effects can be obtained.

[0074] (1) The imaging unit 11 generates a peripheral image by imaging the periphery of the vehicle 10 . The position information acquisition unit 12 acquires the position information of the vehicle 10 , and transmits the acquired position information to the server device 20 .

[0075] When the train 100 has stopped between stations, the server device 20 requests the vehicle 10 located in the information collection area including the stop position of the train 100 running on the railway track 101 to provide a peripheral image.

[0076] In the vehicle 10 requested to provide the surrounding image, the processing circuit 31 specifies the stopping factor image from the surrounding image generated by the imaging unit 11. The processing circuit 31 provides the server device 20 with the surrounding image by transmitting the specified stopping factor image to the server device 20.

[0077] When the train 100 stops between stations, the driver or conductor of the train 100 needs to grasp the stopping factor by getting off the train 100 and checking the periphery of the train 100. In order for the dispatcher at the command center to grasp or estimate the stopping factor of the train 100, in addition to talking with the driver or conductor of the train 100, it is preferable to have a peripheral image obtained by imaging the train 100 and the periphery of the train 100. In other words, there is a concern that it takes time until the stopping factor of the train 100 can be grasped.

[0078] According to this configuration, the server device 20 collects the stopping factor image which is the peripheral image imaged by the imaging unit 11 of the vehicle 10 located in the information collection area including the stop position of the train 100. Therefore, in the information processing method, the dispatcher in the command center refers to the stopping factor image collected in the server device 20, and thus it becomes possible to reduce the time consumption to grasp the situation of the stopping factor of the train 100.

[0079] (2) The processing circuit 21 estimates the stopping factor of the train 100 based on the stopping factor image. Specifically, when the stopping factor image is input to the learning model 231, the processing circuit 21 estimates the stopping factor of the train 100 based on the output variable of the learning model 231. In other words, in the information processing method, the stopping factor of the train 100 can be estimated based on the stopping factor image including more objective information than by talking to the driver or conductor of the train 100. In the information processing method, the stopping factor of the train 100 can be easily estimated by using the learning model 231.

[0080] (3) When the emergency stop button 61 provided in the railway crossing 40 is pressed, the processing circuit 21 sets the information collection area so as to include the position of the railway crossing 40. When an obstacle is detected in the railway crossing 40 by the obstacle detection device 62 provided in the railway crossing 40, the processing circuit 21 sets the information collection area so as to include the position of the railway crossing 40. Therefore, in the information processing method, the stop factor image can be collected in the server device 20 by the trigger of pressing the emergency stop button 61 or detecting an obstacle by the obstacle detection device 62.

[0081] (4) The processing circuit 21 determines whether the first image is included in the stopping factor image received from the control device 30. When the processing circuit 21 determines that the first image is included in the stopping factor image, the processing circuit 21 considers that at least the first image has been received, and estimates the stopping factor of the train 100 based on the first image.

[0082] When the stopping factor image is the first image satisfying the condition (D1), the situation of the stop position of the train 100 and the state of the train 100 can be checked by referring to the first image. When the stopping factor image is the first image satisfying the condition (D2), the state of the train 100 and the railroad track 101, such as whether there is an obstacle on the railroad track 101 near the stop position of the train 100, whether there is an object that has come into contact with the train 100, and whether there is damage on the railroad track 101, can be checked by referring to the first image. When the stopping factor image is the first image satisfying the condition (D3), when the train 100 moves toward the station in the travel direction, it can be checked by referring to the first image whether the operation of the train 100 is without problem. Therefore, it is preferable to use the first image, which is a stopping factor image satisfying at least one of the conditions (D1) to (D3), to estimate the stopping factor of the train 100.

[0083] At the same time, the stopping factor image includes a second image in which at least one of (A1) and (A2) appears but conditions (D1) to (D3) are not satisfied. In other words, the second image is an image in which the train 100 stopped between stations and the railroad track 101 near the train 100 appear, but due to the viewing angle and the distance from the train 100, the train 100 and the railroad track 101 do not appear to the extent that sufficient information can be obtained. When the stopping factor of the train 100 is estimated using the second image as above, the estimation accuracy may be reduced. In the information processing method, the stopping factor of the train 100 is estimated by referring only to the first image other than the second image in the collected stopping factor image. Therefore, in the information processing method, the stopping factor of the train 100 can be estimated with high accuracy.

[0084] (5) When there is a request to provide a peripheral image, the processing circuit 31 sends the stopping factor image generated by the imaging unit 11 at a predetermined time earlier than the time point at which the train 100 has stopped to the server device 20. For example, when the vehicle 10 stops near the railway crossing 40 or the railway track 101, the imaging unit 11 can generate a peripheral image in real time by imaging the railway crossing 40 or the railway track 101 near the stop position of the train 100 before the train 100 stops between stations. In this case, things that may become the stopping factor of the train 100 may appear in the peripheral image. Therefore, it is preferable that, in the estimation of the stopping factor of the train 100, the processing circuit 13 uses the stopping factor image as the peripheral image generated by the imaging unit 11 at a time point predetermined earlier than the time point at which the command is received. Therefore, in the information processing method, the stopping factor of the train 100 can be estimated more accurately.

[0085] (6) The processing circuit 21 applies a higher priority to the first image in which the stopping factors of the train 100 appear in a more easily visible manner. Specifically, the processing circuit 21 applies a higher priority when the first image becomes a higher angle image. Here, with respect to the stopping factor image, the peripheral graphics generated by the imaging unit 11 included in the vehicle 10 with a high vehicle height such as a truck or a bus may have a larger amount of information about the periphery of the vehicle 10 than the peripheral graphics generated by the imaging unit 11 included in the vehicle 10 with a low vehicle height such as a sports car. In the information processing method, the stopping factors of the train 100 can be estimated using the stopping factor images having a larger amount of information.

[0086] Variations

[0087] The embodiment can be changed as follows. The embodiment and each of the following other examples can be combined with each other insofar as there is no technical contradiction.

[0088] -exist Figure 3 The processing and Figure 4 In the process shown, the processing circuit 21 does not necessarily need to execute Figure 4 The processing shown. Figure 3 The processing and Figure 4 In the process shown, the processing circuit 21 does not necessarily need to execute Figure 3 Processing shown.

[0089] In the process of step S302 , the processing circuit 31 can acquire only the peripheral image imaged and generated by the imaging unit 11 at the time point when the processing circuit 31 receives the command in step S300 .

[0090] In the process of step S302, the processing circuit 31 may acquire the peripheral image imaged and generated by the imaging unit 11 in a predetermined period including the time point at which the command is received. In step S302, the processing circuit 31 may acquire the peripheral image imaged and generated by the imaging unit 11 in a predetermined period including the time point a predetermined time earlier than the time point at which the command is received.

[0091] -When the vehicle 10 moves until a time point a predetermined time earlier than the time point when the command is received, the processing circuit 31 may not acquire a peripheral image a predetermined time earlier than the time point when the command is received. The processing circuit 31 determines whether the vehicle 10 has moved based on the detection result of the speed detection unit of the vehicle 10, the off state of the ignition switch, the shift selector being in the parking gear, etc. Here, when the vehicle 10 has moved, there may be a case where the vehicle 10 is not located in the information collection area at a time point a predetermined time earlier than the time point when the command is received. Therefore, when the vehicle 10 has moved, there is a high possibility that the peripheral image imaged and generated by the imaging unit 11 of the vehicle 10 at a time point a predetermined time earlier than the time point when the command is received may not be a stop factor image. According to this configuration, when the vehicle 10 has moved, the processing circuit 31 can omit the process of determining whether the peripheral image imaged and generated by the imaging unit 11 at a time point a predetermined time earlier than the time point when the command is received is a stop factor image.

[0092] - The processing circuit 21 is capable of executing only Figure 6 In this case, the information processing method enables the dispatcher of the command center to grasp the stopping factor of the train 100 by referring to the stopping factor image collected from the vehicle 10 by the server device 20 .

[0093] - The processing circuit 21 does not necessarily need to execute Figure 6 The processing of step S402 in the processing shown. In this case, the processing circuit 21 causes the processing to proceed to step S404 after executing step S400. Here, for example, when the number of vehicles 10 located in the information collection area is small, there may be a case where the server device 20 can receive the second image but cannot receive the first image as the stopping factor image. Meanwhile, when the first image cannot be received, it is preferred to estimate the stopping factor of the train 100 using the second image. According to this configuration, the information processing method is able to estimate the stopping factor of the train 100 based on the stopping factor image collected by the server device 20 from the vehicles 10. When estimating the stopping factor using the second image, the processing circuit 21 may also apply priority to the second image.

[0094] - The processing circuit 21 does not necessarily need to execute Figure 6The processing of step S404 and step S406 in the processing shown. In this case, when the processing circuit 21 determines that the first image is included in the stop factor image (step S402; yes), the processing circuit 21 causes the processing to proceed to step S408. Here, for example, when the number of vehicles 10 located in the information collection area is small, there may be a case where the server device 20 cannot sufficiently receive the first image. At the same time, when the first image cannot be sufficiently received, it is preferred to estimate the stop factor image of the train 100 using the first image with a low priority. According to this configuration, the information processing method is able to estimate the stop factor of the train 100 using all the first images collected from the vehicles 10 by the server device 20.

[0095] -Instead of a configuration in which a higher priority is applied as the first image becomes a higher angle image, or in addition to a configuration in which a higher priority is applied as the first image becomes a higher angle image, the processing circuit 21 may apply a higher priority as the first image becomes an image with more suitable conditions. For example, an image with suitable conditions means an image that is imaged by performing appropriate exposure and does not produce blown out highlights and blocked upshadows, an image that does not produce blur due to appropriate focusing, and an image that is imaged by performing appropriate white balance and applies a color temperature that matches an actual object. When applying the priority, when determining whether the image is a high-angle image or an image with suitable conditions, instead of general image analysis, the processing circuit 21 may use a learning model that can determine the above.

[0096] Instead of applying high priority to the processing of the first image in which the stopping factors of the train 100 appear in an easily visible manner, the processing circuit 21 may perform processing of applying low priority to the first image in which the stopping factors of the train 100 do not appear in an easily visible manner.

[0097] -When the processing circuit 31 detects that there is a stopping factor in the railway crossing 40 and the railway track 101, the processing circuit 31 may send a stopping factor image to the server device 20. In this case, the processing circuit 31 specifies the photographed object appearing in the stopping factor image by general image analysis. When the processing circuit 31 determines that there is an obstacle on the railway track 101, the processing circuit 31 will send the stopping factor image to the server device 20 based on the specified result. According to this configuration, the information processing method can collect the stopping factor image in the server device 20 before the event that the train 100 stops, the emergency stop button 61 is pressed, or the obstacle detection device 62 detects an obstacle occurs. Therefore, the information processing method enables the dispatcher of the command center to grasp the events that may become the stopping factors of the train 100 before these events occur.

[0098] - Only when the stopping factor image is the first image, the processing circuit 31 may transmit the first image to the server device 20. In this case, the processing circuit 31 performs processing of determining whether the stopping factor image is the first image or the second image by specifying a photographed object appearing in the stopping factor image by general image analysis.

[0099] - The processing circuit 21 may use a learning model obtained by performing machine learning that determines whether the stop factor image is the first image. For example, when the stop factor image is input, the learning model outputs an output variable indicating the probability of being the first image. When the processing circuit 31 inputs the stop factor image into the learning model and the output variable is equal to or greater than a threshold value, the processing circuit 31 determines that the stop factor image is the first image. At the same time, when the output variable is less than the threshold value, the processing circuit 31 determines that the stop factor image input into the learning model is the second image.

[0100] The position information acquired by the position information acquisition unit 12 may be specified or supplemented using outputs of various sensors included in the vehicle 10 by an inertial navigation system (INS).

[0101] -Some or all of the components of the processing circuit 21 and the processing circuit 31 may be implemented by hardware, such as a large-scale integrated circuit (LSI), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), and a graphics processing unit (GPU) (including circuit units; circuits), or may be implemented by the collaboration of software and hardware.

Claims

1. An information processing method, which is performed by an information processing system, the information processing system comprising: Vehicle, including an imaging unit that generates a peripheral image by imaging the peripheral situation, and a communication unit for communicating with the outside; as well as a server device installed outside the vehicle, the peripheral image being transmitted from the communication unit of the vehicle to the server device via a communication network, The information processing method comprises: When the train stops between stations, the server device requests the vehicle located in an information collection area to provide the surrounding image, the information collection area including the stop position of the train moving on the railway track; as well as A stopping factor image is transmitted to the server device by the communication unit of the vehicle located in the information collection area, the stopping factor image being the surrounding image in which at least one of the train that has stopped at the stop position and the railroad track near the train appears. 2 . The information processing method according to claim 1 , further comprising estimating, by a processing circuit of the server device, a stop factor of the stop of the train based on the stop factor image received by the server device. 3 .

3. The information processing method according to claim 1 further includes, when the train stops between stations due to pressing of an emergency stop button set in a railway crossing, setting the information collection area by the server device so as to include the position of the railway crossing.

4. The information processing method according to claim 1 further includes, when at least a first image can be received by the server device, the processing circuit of the server device infers the stopping factor of the train based on the first image of the first image and a second image, the first image being an image of the stopping factor of at least one of the stopping position where the train appears, the railway track near the stopping position, and the railway track between the station in the traveling direction of the train and the stopping position, and the second image being an image of the stopping factor other than the first image.

5. The information processing method according to claim 1 further includes sending the stopping factor image to the server device by the communication unit of the vehicle located in the information collection area, wherein the stopping factor image is the surrounding image generated by the imaging unit a predetermined time earlier than the time point when the train stops.

Images