Information processing device, information processing system, information processing method, and recording medium

Abstract

This information processing device is provided with a first acquisition unit, a second acquisition unit, and a generation unit. The first acquisition unit acquires first data regarding vibrations on a road as observed by distributed acoustic sensing using an optical fiber installed along the road. The second acquisition unit acquires second data including at least one of an attribute and a moving state of a vehicle. The generation unit uses the first data and the second data corresponding to the same observation time and observation point to generate road condition data in which the second data of a vehicle is associated with a travel trajectory of the vehicle on the road.

Description

Information processing device, information processing system, information processing method, and recording medium

[0001] The present invention relates to an information processing device, an information processing system, an information processing method, and a recording medium.

[0002] For road monitoring, there is a technology that estimates the trajectory of each vehicle traveling on a road by performing distributed acoustic sensing using optical fibers installed along the road. Such trajectories are also called waterfalls.

[0003] For example, according to the description in Patent Document 1, distributed acoustic sensors are connected to optical fibers, transmit optical signals to the optical fibers, and detect return light from the optical fibers. The resulting data is called waterfall data. The waterfall data provides information about the number of vehicles, the direction of travel of the vehicles, the trajectory and speed of the vehicles, and the lane position of the vehicles on the road.

[0004] The traffic monitoring device described in Patent Document 1 also includes at least one memory that stores instructions, and at least one processor configured to execute the instructions.

[0005] The processor described in Patent Document 1 is configured to perform the following steps (1) to (4): (1) acquiring waterfall data from distributed acoustic sensors. The waterfall data includes a vibration occurrence location on a road adjacent to the distributed acoustic sensors, a vibration occurrence time, and a vibration amplitude; (2) preprocessing the waterfall data; (3) estimating at least one correction of the processed waterfall data. The correction corresponds to a traffic flow characteristic; and (4) estimating at least one traffic flow characteristic of the road from the correction of the processed waterfall data.

[0006] According to the description in Patent Document 1, the processor is further configured to execute instructions for estimating a correction using a pre-trained model. The pre-trained model is generated by training a portion of the processed waterfall data and at least one correction of the processed waterfall data to be used as a label. The corrected waterfall data is obtained from a secondary acquisition means. The secondary acquisition means includes a video and / or induction loop-based traffic monitoring system.

[0007] International Publication No. 2021 / 152648

[0008] According to the technology described in Patent Document 1, images from a traffic monitoring system provided in the secondary acquisition means are used to train a trained model for estimating corrections to the processed waterfall data.

[0009] In general, by performing distributed acoustic sensing using optical fibers installed along a road, it is possible to estimate the travel trajectory of a vehicle moving (traveling) on ​​the road over a wide area.

[0010] However, such distributed acoustic sensing can sometimes result in a decrease in the accuracy of vehicle trajectory estimation. For example, it can be difficult to distinguish between small and large vehicles traveling in the same direction in lanes close to and far from the optical fiber. Therefore, various technologies are expected to be developed to accurately estimate vehicle trajectories based on the results of distributed acoustic sensing using optical fibers installed along roads.

[0011] One of the objectives of the present disclosure is to provide a result of estimating the travel trajectory of a vehicle moving on a road with high accuracy.

[0012] The information processing device of the present disclosure includes: a first acquisition means for acquiring first data relating to vibrations on a road observed by distributed acoustic sensing using optical fibers installed along the road; a second acquisition means for acquiring second data including at least one of a vehicle's attributes and movement state; and a generation means for generating road condition data that associates the second data of the vehicle with the vehicle's travel trajectory on the road, using the first data and the second data that correspond to an observation time and an observation point.

[0013] The information processing system of the present disclosure comprises an information processing device and a display device, wherein the information processing device comprises: a first acquisition means for acquiring first data relating to vibrations on a road observed by distributed acoustic sensing using optical fibers installed along the road; a second acquisition means for acquiring second data including at least one of a vehicle's attributes and movement state; and a generation means for generating road condition data that associates the second data of the vehicle with the vehicle's travel trajectory on the road using the first data and the second data that correspond to the observation time and observation point; and the display device comprises: a second selection means for accepting second selection information for selecting the road condition data to be displayed on the display means; and a display control means for displaying the selected road condition data on the display means.

[0014] The information processing method disclosed herein includes one or more computers acquiring first data relating to vibrations on a road observed by distributed acoustic sensing using optical fibers installed along the road, acquiring second data including at least one of vehicle attributes and movement status, and using the first data and the second data corresponding to the observation time and observation point, generating road condition data that associates the second data of the vehicle with the vehicle's travel trajectory on the road.

[0015] The recording medium in the present disclosure is a recording medium having recorded thereon a program for causing one or more computers to acquire first data regarding vibrations on a road observed by distributed acoustic sensing using optical fibers installed along the road, acquire second data including at least one of a vehicle's attributes and movement state, and generate road condition data that associates the second data of the vehicle with the vehicle's travel trajectory on the road using the first data and the second data that correspond to the observation time and observation point.

[0016] According to the present disclosure, it is possible to provide a result of estimating the travel trajectory of a vehicle traveling on a road with high accuracy.

[0017] 4 is a block diagram showing an example of a configuration of a first information processing device according to the present disclosure. FIG. 5 is a flowchart showing an example of a processing operation of the first information processing device according to the present disclosure. FIG. 6 is a block diagram showing an example of a configuration of a first information processing system according to the present disclosure. FIG. 7 is a diagram showing an example of a road on which optical fiber according to the present disclosure is provided, vehicles traveling on the road, and the travel trajectories of each of these vehicles. FIG. 8 is a block diagram showing an example of a configuration of a generation unit according to the present disclosure. FIG. 9 is a flowchart showing an example of a processing operation of the generation unit according to the present disclosure. FIG. 10 is a diagram showing an example of the degree of vibration levels of a large vehicle and a small vehicle indicated by first data when the large vehicle and the small vehicle each travel in a lane. FIG. 11 is a diagram showing a physical configuration of a first information processing device according to the present disclosure. FIG. 12 is a block diagram showing an example of a configuration of a second information processing system according to the present disclosure. FIG. 13 is a flowchart showing an example of a processing operation of the second information processing device according to the present disclosure. FIG. 14 is a diagram showing an example of road condition data when a large vehicle is selected from the travel trajectories illustrated in FIG. 4. FIG. 15 is a block diagram showing an example of a configuration of a third information processing system according to the present disclosure. FIG. 16 is a block diagram showing an example of a configuration of a first display device according to the present disclosure. FIG. 17 is a flowchart showing an example of a detailed processing operation of the first display device according to the present disclosure.

[0018] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all drawings, similar components are designated by similar reference numerals, and descriptions thereof will be omitted as appropriate. In addition, in this disclosure, the drawings relate to one or more embodiments.

[0019] First Embodiment (Configuration Example of Information Processing Apparatus 100) As shown in FIG. 1, the information processing apparatus 100 includes a first acquisition unit 110, a second acquisition unit 120, and a generation unit 130.

[0020] The first acquisition unit 110 acquires first data relating to vibrations on a road observed by distributed acoustic sensing using optical fibers installed along the road.

[0021] The second acquisition unit 120 acquires second data including at least one of an attribute and a moving state of the vehicle.

[0022] The generating unit 130 uses the first data and the second data, which correspond to the observation time and the observation point, to generate road condition data in which the second data of the vehicle is associated with the travel path of the vehicle on the road.

[0023] According to the information processing device 100, in order to estimate which vehicle a travel trajectory obtained from the first data corresponds to, not only the first data but also the second data can be used. Therefore, even if it is difficult to accurately estimate which vehicle a travel trajectory corresponds to from the first data alone, for example, the accuracy of the estimation can be improved.

[0024] Then, road condition data in which the second data is associated with the travel locus can be provided as an estimation result.

[0025] Therefore, it is possible to provide a result of estimating the travel trajectory of a vehicle traveling on a road with high accuracy.

[0026] (Example of Operation of Information Processing Device 100) The information processing device 100 executes information processing as shown in FIG.

[0027] The first acquisition unit 110 acquires first data relating to vibrations on a road observed by distributed acoustic sensing using optical fibers installed along the road (step S110).

[0028] The second acquisition unit 120 acquires second data including at least one of an attribute and a moving state of the vehicle (step S120).

[0029] The generation unit 130 generates road condition data that associates the second data of the vehicle with the vehicle's travel path on the road, using the first data and the second data that correspond to the observation time and observation point (step S130).

[0030] According to this information processing, in order to estimate which vehicle a travel trajectory obtained from the first data corresponds to, not only the first data but also the second data can be used. Therefore, even in cases where it is difficult to accurately estimate which vehicle a travel trajectory corresponds to from the first data alone, for example, the accuracy of the estimation can be improved.

[0031] Then, road condition data in which the second data is associated with the travel locus can be provided as an estimation result.

[0032] Therefore, it is possible to provide a result of estimating the travel trajectory of a vehicle traveling on a road with high accuracy.

[0033] (Detailed Example) Hereinafter, a detailed example of the information processing device 100 and the information processing executed thereby will be described.

[0034] FIG. 3 is a diagram showing an example of the configuration of an information processing system S1 including the information processing device 100.

[0035] 3, the information processing system S1 includes an optical fiber 50, a sensing device 60, an information processing device 100, a plurality of sensors 102, a plurality of sensor information processing devices 104, and an aggregation device 106. The optical fiber 50 and the plurality of sensors 102 are provided in association with a road R to be observed.

[0036] The information processing device 100, the sensing device 60, and the aggregation device 106 are connected to each other via communication networks NT1 and NT2, which may be wired, wireless, or a combination of these, and can send and receive information between them.

[0037] The optical fiber 50 and the sensing device 60 are configured, for example, so as to be able to input and output optical signals to and from each other.

[0038] The multiple sensors 102 are connected to each of the multiple sensor information processing devices 104 via a communication network NT3 configured by wired or wireless means or a combination of these, and can transmit and receive information to and from each other.

[0039] Each of the multiple sensor information processing devices 104 and the aggregation device 106 are connected to each other via a communication network NT4 that may be wired, wireless, or a combination of these, and can send and receive information to and from each other.

[0040] A part or all of these communication networks NT1 to NT4 may be a common communication network, or may be different communication networks.

[0041] The connection relationship between the optical fiber 50, the sensing device 60, the information processing device 100, the multiple sensors 102, the multiple sensor information processing devices 104, and the aggregation device 106 is not limited to that exemplified here, and may be changed as appropriate.

[0042] Now, further reference will be made to Fig. 4. Fig. 4 is a diagram showing an example of a road R on which an optical fiber 50 is installed, vehicles traveling (running) on ​​the road R, and the travel trajectories of each of these vehicles. The road R is, for example, a highway, but is not limited to this.

[0043] The road R shown in Fig. 4 is made up of four lanes, L1 to L4, arranged in order of proximity to the optical fiber 50 installed along the road R. The lanes L1 and L2 and the lanes L3 and L4 are opposite to the correct traveling direction of vehicles (so-called contra-traffic lanes). The road R shown in Fig. 4 is also connected to a merging lane S, which allows vehicles to merge into lane L1.

[0044] FIG. 4 includes an example of road condition data in which vehicle size types are associated with a travel trajectory shown as a diagram with the vehicle position on the horizontal axis and time on the vertical axis. The travel trajectory is information that indicates changes in the vehicle position over time. FIG. 4 includes an example of a travel trajectory shown as a diagram with the vehicle position on the horizontal axis and time on the vertical axis. The travel trajectory shown in FIG. 4 is an example in which the travel trajectory is represented by lines of a thickness that corresponds to the vibration level. Details of the travel trajectory, road condition data, and vibration level will be described later.

[0045] Although the travel trajectory shown in Fig. 4 is a straight line, this corresponds to the case where the vehicle moves at a constant speed, and the travel trajectory is not limited to a straight line, but may be a curved line or a bent line corresponding to the acceleration / deceleration of the vehicle. The travel trajectory shown in Fig. 4 does not include the travel trajectory of a vehicle moving on the merging lane S, but the travel trajectory may include the travel trajectory of a vehicle moving on the merging lane S. Fig. 4 shows an example in which there are two lanes moving in the same direction on road R, but the configuration of lanes on road R is not limited to this and may be changed depending on the lanes that make up the actual road.

[0046] (Regarding the Optical Fiber 50) As shown in Fig. 4, the optical fiber 50 is an optical fiber cable installed along the road R. The optical fiber 50 is, for example, one core of a multi-core optical fiber cable for communication that is generally laid on the shoulders of expressways, medians, etc. The optical fiber 50 has, for example, one end connected to a sensing device 60, and the other end subjected to termination processing to suppress reflection of optical signals. Note that multiple fiber cables of the multi-core optical fiber cable may be used as the optical fiber 50 for optical fiber sensing.

[0047] (Regarding the Sensing Device 60) The sensing device 60 generates first data observed by distributed acoustic sensing (described in detail below) using the optical fiber 50. The first data is data related to vibrations on the road R. The sensing device 60 may, for example, continuously generate the first data in real time.

[0048] Such first data is generated, for example, by the sensing device 60 inputting an optical signal into the optical fiber 50 and observing the amount of change in optical interference intensity, which is the intensity of light resulting from interference between backscattered lights that occurs in response to the input of the optical signal. In this case, the first data indicates the amount of change in optical interference intensity.

[0049] The change in the optical interference intensity occurs when vibrations caused by a vehicle traveling on the road R are transmitted to the optical fiber 50. Therefore, the first data indicating the amount of change in the optical interference intensity corresponds to data related to vibrations on the road R.

[0050] (Regarding Distributed Acoustic Sensing and First Data) Distributed acoustic sensing is a technology for detecting the location of vibrations, etc., using an optical fiber 50 as a sensing medium. This technology can use a general optical fiber 50, which is a transmission medium for communication data, as a linear passive sensor, and therefore can grasp the traffic situation over a wide area in real time without installing a new sensor, etc.

[0051] For example, the sensing device 60 receives an optical signal with a pulse waveform as input from one end of the optical fiber 50. An optical signal with high coherence is preferably used for this input, which generates weak backscattered light, or return light, from all positions in the optical fiber 50.

[0052] Generally, when an environmental change occurs around the optical fiber 50, the structure and characteristic parameters of the silica glass that constitutes the optical fiber 50 change in accordance with the environmental change, which in turn changes the signal quality of the return light from the location where the change occurred.

[0053] The environmental change occurring around the optical fiber 50 is typically vibration caused by a vehicle moving (driving) on ​​the road R. For example, when vibration caused by a vehicle moving on the road R is transmitted to the optical fiber 50, the phase state of the returning light changes. This change in the phase state of the returning light is observed as a change in light intensity due to interference with other returning light received at the same time.

[0054] In this way, the sensing device 60 can generate first data related to vibrations on the road R by inputting an optical signal into the optical fiber 50 and observing the amount of change in the optical interference intensity. The first data may further include the time when the observation that served as the basis for generating the first data was made (observation time).

[0055] The optical signal is preferably input repeatedly at a constant frequency so that the return light from the other end of the optical fiber 50 (i.e., the farthest end from the sensing device 60) does not mix with the next optical signal to be input.

[0056] (Second Data) The second data may include at least one of the attributes and the movement state of the vehicle traveling on the road R.

[0057] The vehicle attributes may include, for example, the size type of the vehicle, which is information indicating the size type of the vehicle, such as large vehicle or small vehicle, as described above.

[0058] The number of size types may be three or more. Each size type may be represented by a predetermined number, letter, symbol, or a combination thereof.

[0059] The vehicle movement state may include, for example, at least one of the vehicle position, the lane in which the vehicle is moving, the vehicle movement speed, and congestion.

[0060] The vehicle position is the position of the vehicle, and may be expressed using, for example, the distance along the road R from a reference position that is predetermined with respect to the road R.

[0061] The travel lane of a vehicle is the lane that the vehicle is traveling in. In the example of Figure 4, the travel lane is one of lanes L1 to L4.

[0062] The moving speed of a vehicle is the speed at which the vehicle is moving. This movement may include stops due to traffic jams, accidents, etc. In other words, the moving speed may be zero. The moving speed may also include a negative value indicating wrong-way driving.

[0063] A traffic jam means, for example, a state in which the movement of vehicles is delayed on road R. A traffic jam may be determined, for example, by whether or not a vehicle is moving at a speed slower than a reference speed and the distance between the front and rear vehicles of the vehicle is shorter than a predetermined reference distance.

[0064] Each of the sensor information processing devices 104 generates second data using sensor information generated by each of the sensors 102 provided to observe the road R.

[0065] The sensor 102 may be, for example, at least one of a photographing device, a traffic meter (coil), or other sensor installed along the road R. The photographing device as the sensor 102 may be, for example, a CCTV (closed-circuit television) camera installed at intervals along the road R, but is not limited to this. Furthermore, each of the sensor information processing devices 104 may further use probe information of ETC (Electronic Toll Collection System) 2.0 to generate the second data.

[0066] The method for generating the second data is not limited to the example given here, and may be any method other than that used for observation by distributed acoustic sensing.

[0067] In the following, an example will be described in which each of the sensors 102 is an image capturing device.

[0068] The plurality of sensor information processing devices 104 acquires, for example, a plurality of images (e.g., moving images) as sensor information from the plurality of sensors 102 connected to each of them. Then, each of the sensor information processing devices 104 processes, for example, the acquired plurality of images to generate processing results corresponding to each image. The processing results may be information including at least one of attributes and movement states of vehicles included in the images.

[0069] The image processing here can use general techniques such as pattern matching, a technique for detecting objects such as vehicles using a machine learning model, etc. Below, an example will be described in which an image of road R captured by an imaging device is input, and a vehicle detection model that detects vehicles moving on road R is used to detect vehicles included in the image.

[0070] The vehicle detection model is a machine learning model configured using a neural network, etc. The vehicle detection model extracts, for example, image features of an input image and outputs a processing result including at least one of the attributes and the movement state of each vehicle included in the image. This processing result may include the extracted image features.

[0071] The aggregating device 106 acquires the processing results generated by each of the sensor information processing devices 104, aggregates the acquired processing results, and generates second data. For example, the aggregating device 106 may use processing results based on images captured at the same time to generate second data including at least one of attributes and movement states of vehicles moving on road R. Such second data is data generated by processing multiple images captured by multiple imaging devices installed on road R.

[0072] The second data may include at least one of attributes and movement states of all or some of the vehicles moving on the entire road R or a predetermined part of the road R. The part of the vehicles may be, for example, a predetermined vehicle (e.g., a vehicle other than a motorcycle), but is not limited to this.

[0073] Here, the same period means substantially the same time, and also includes different times where the difference is within a predetermined range. The period is expressed using, for example, time. In this case, the same period means, for example, times where the difference is within a predetermined range.

[0074] To perform such aggregation processing, the processing result may further include the time when the sensor information that was the source of the processing result was observed (the observation time, e.g., the observation time). When the sensor information is an image, the observation time may be the time when the image was captured (e.g., the capture time). The second data may also further include a similar observation time, i.e., the time when the sensor information that was the source of the second data was observed. Furthermore, the second data may further include the location of the image capture device that captured the image that was the source of the second data.

[0075] In addition, the aggregation device 106 may acquire at least one of the image and image feature amount corresponding to the second data.

[0076] In addition, when the processing from observation to aggregation is performed in real time, the observation time may be the transmission time, reception time, etc. of the sensor information that is substantially the same time as the observation time.

[0077] Furthermore, a plurality of sensors 102 may be connected to the sensor information processing device 104. In this case, the sensor information processing device 104 connected to a plurality of sensors 102 may process each of a plurality of images generated by each of the plurality of sensors 102 to generate a processing result. This processing result may be generated for each of the plurality of images, or may be information that aggregates the plurality of images.

[0078] Furthermore, the aggregation device 106 may have some or all of the functions of multiple sensor information processing devices 104.

[0079] (Details of the Information Processing Device 100) The first acquisition unit 110 acquires the first data generated by the sensing device 60 described above, for example, via the network NT1.

[0080] Note that the method by which the first acquisition unit 110 acquires the first data is not limited to this. For example, the information processing device 100 may have the functions of the sensing device 60. In this case, for example, the first acquisition unit 110 may acquire the first data by executing the same process as the sensing device 60 described above to generate the first data.

[0081] The second acquisition unit 120 acquires, for example, via the network NT2, the second data generated by the aggregation device 106. The second acquisition unit 120 may acquire, along with the second data, at least one of an image and image feature corresponding to the second data.

[0082] Note that the method by which the second acquisition unit 120 acquires the second data is not limited to this. For example, the information processing device 100 may have the functions of the aggregation device 106. In this case, for example, the second acquisition unit 120 may acquire the second data by executing the same process as the aggregation device 106 described above to generate the second data.

[0083] The generating unit 130 generates road condition data using, for example, the first data and the second data acquired by the first acquiring unit 110 and the second acquiring unit 120, respectively.

[0084] The road condition data is data in which the second data of a vehicle is associated with a travel path of the vehicle on road R. In other words, the road condition data may be data in which the travel path of at least one vehicle on road R is associated with at least one of an attribute and a movement state of the vehicle.

[0085] In more detail, for example, the road condition data is generated using first data and second data that correspond to the observation time and observation point.

[0086] The road condition data includes a travel path, which indicates a time-series change in the vehicle position.

[0087] Therefore, the first data and the second data of the observation time period included in the period for which the traveling trajectory is to be generated (the period to be analyzed) may be used to generate the traveling trajectory.

[0088] Furthermore, the generation of the travel trajectory may use the first data and the second data of the observation target points included in the section for which the travel trajectory is to be generated (the analysis target section). Each of the analysis target section and the observation target points may be represented, for example, using the distance along the road R from the reference position, similar to the above-mentioned vehicle position. Note that the method of identifying each of the analysis target section, the observation target points, and the vehicle position is not limited to the method exemplified here.

[0089] The road condition data may be generated by using the first data and the second data, which have corresponding observation times and observation points, and associating these data. For example, the road condition data may be generated by associating the first data and the second data, which have the same observation time and observation point.

[0090] The first data and second data corresponding to the observation time and the observation target point are not limited to the first data and second data having the same observation time and observation target point, but may be, for example, the first data and second data satisfying a predetermined association condition for each of the observation time and the observation target point.

[0091] (Example of configuration of generation unit 130) As described above, the generation unit 130 uses first data and second data corresponding to the observation time and observation point to generate road condition data in which the second data of the vehicle is associated with the vehicle's travel trajectory on the road.

[0092] In detail, the generating unit 130 may include a target setting unit 131, an analyzing unit 132, and an associating unit 133, as shown in FIG.

[0093] The target setting unit 131 sets an analysis target that includes at least one of an analysis target period and an analysis target section.

[0094] The analysis unit 132 generates a travel locus by analyzing the first data of the analysis target period and analysis target section set by the target setting unit 131.

[0095] The travel locus generated here is a travel locus generated using the first data, that is, a travel locus to which no second data is associated.

[0096] The associating unit 133 generates road condition data using the travel path generated by the analyzing unit 132 and second data in which the observation time and observation target point on the travel path correspond to each other.

[0097] As described above, the road condition data is data in which the second data of the vehicle is associated with the travel path of the vehicle on road R. Such road condition data is a travel path associated with the second data. (Detailed Example of Generation Process (Step S130)) The generation unit 130 executes the generation process (step S130) as shown in FIG. 6, for example.

[0098] The target setting unit 131 sets an analysis target including at least one of an analysis target period and an analysis target section (step S131).

[0099] The analysis unit 132 generates a travel locus by analyzing the first data of the analysis period and analysis section set in step S131 (step S132).

[0100] The associating unit 133 generates road condition data using the travel path generated in step S132 and the second data corresponding to the observation time and observation target point on the travel path (step S133).

[0101] (Regarding setting of analysis target) The analysis target may be set by user input or according to predetermined target setting conditions. The target setting conditions may, for example, be that when a process is executed, a predetermined analysis target section is analyzed from the time of execution of the process to a predetermined period before that time. Note that the target setting conditions are not limited to this example.

[0102] (Regarding Traveling Locus) The location of an environmental change occurring around the optical fiber 50 can be calculated, for example, from the round-trip time from when an optical signal is input until the return light is observed, and the propagation speed of the optical signal. If the environmental change is vibration caused by the vehicle moving (traveling) on ​​the road R, the location of the vibration corresponds to the position of the vehicle on the road R (vehicle position). Therefore, by using the continuously generated first data, a traveling locus indicating a time-series change in the vehicle position can be obtained.

[0103] Here, when there are vehicles traveling in different lanes L1 and L2 that are relatively close to each other, such as vehicles Ca and Cb shown in Fig. 4, the vibration level can be used to distinguish between them. This vibration level is the magnitude of the vibration generated by the vehicles Ca and Cb traveling on road R, and corresponds to the magnitude of the change in optical interference intensity.

[0104] Generally, the vibration level of the vehicle indicated by the first data tends to increase as the vehicle becomes larger. Furthermore, the vibration level also tends to increase as the vehicle's travel lane (i.e., the lane in which the vehicle is traveling) becomes closer to the optical fiber 50.

[0105] FIG. 7 shows an example of the degree of vibration level of a large vehicle and a small vehicle, which are indicated by the first data, when the large vehicle and the small vehicle are traveling on lanes L1 and L2, respectively.

[0106] In the example of Fig. 4, vehicle Ca is a small vehicle traveling in lane L1 close to the optical fiber 50. Vehicle Cb is a large vehicle traveling in lane L2 far from the optical fiber 50. In such a case, referring to Fig. 4, the vibration level is medium. In such a case, it may be difficult to estimate from the first data which of the vehicles Ca and Cb the traveling trajectories Ha and Hb of the vehicles Ca and Cb, which are located close to each other, correspond to.

[0107] Furthermore, unlike the traveling trajectory shown in Fig. 4, a traveling trajectory to which the second data is not associated may have gaps (i.e., breaks in the traveling trajectory) along the way. Causes of such gaps include, for example, signal noise and the influence of vibrations caused by structures on which the road is installed, such as bridges and tunnels. In such cases, it may be difficult to estimate from the first data which vehicle the traveling trajectory before and after the gap corresponds to.

[0108] 7 is not intended to limit the number of size types to two, but may be three or more. Also, the lanes L1 and L2 in FIG. 7 are examples of lanes having different distances from the optical fiber 50, and are not intended to limit the number of lanes constituting a road to two.

[0109] For example, the associating unit 133 further uses the second data to associate information included in the second data with the traveling trajectory generated by the analyzing unit 132, for observation periods and observation points that are difficult to estimate from the first data. In this way, the associating unit 133 generates road condition data. Here, the information included in the second data is at least one of vehicle attributes and moving states.

[0110] There may be a plurality of such combinations of observation times and observation target locations, and the road condition data may be generated using the first data and the second data corresponding to the observation times and observation target locations included in each combination.

[0111] (Method of Associating Second Data with Travel Trajectory) The method of associating second data with travel trajectory (association method) may use, for example, at least one of a graph neural network and a Kalman filter. That is, the road condition data may be generated using at least one of a graph neural network and a Kalman filter.

[0112] The method of associating the second data with the travel locus is not limited to the example given here.

[0113] Below, an example will be described in which a graph neural network (GNN) and a Kalman filter are used as the association method.

[0114] (Association Method 1: Graph Neural Network) A graph neural network (GNN) is generally a technology for obtaining a graph G, which is a data structure that indicates the relationships between nodes N, using nodes N (also referred to as "vertices" or the like) and edges E (also referred to as "sides" or "links" or the like).

[0115] When a GNN is used as the association method, the association unit 133 includes, for example, a machine learning model (association model) using a GNN. The association model outputs a graph G in which the vehicle positions of each vehicle observed by the image capture device are represented as nodes N and the travel trajectories of each vehicle moving along a road R are represented as edges E. This graph corresponds to road condition data.

[0116] For example, the travel trajectory generated by the analysis unit 132 and the second data acquired by the second acquisition unit 120 may be used as input to the association model.

[0117] The first data may be input to the association model instead of the travel trajectory generated by the analysis unit 132. In this case, the association unit 133 can generate road condition data using the first data and the second data for the analysis period and the analysis section. Therefore, the generation unit 130 does not need to include the analysis unit 132.

[0118] Instead of the second data acquired by the second acquisition unit 120, image features may be input to the association model. In this case, the second acquisition unit 120 may acquire the image features together with the second data. Furthermore, a camera may be used as a node. For example, road condition data may be generated by adding a value obtained by multiplying the image features corresponding to a certain node (camera) by a weight to the image features corresponding to an adjacent node, using the position of the node (camera) and the route of road R.

[0119] The learning data used to train the association model may include learning information based on actual measurements that corresponds to information used as input to the association model, such as a travel trajectory based on actual measurements and the second data. The learning data may also include, as a correct answer, data equivalent to road condition data that is created using the learning information. The association model can be trained using such learning data.

[0120] The input and learning data used in the association model are not limited to the above examples, and may be changed as appropriate.

[0121] Association Method 2: Kalman Filter A Kalman filter is a type of recursive Bayes filter, a technique typically used to estimate time-varying quantities (e.g., the position and velocity of an object) from discrete, error-ridden observations.

[0122] The route of the vehicle is restricted by the route of road R. The interval between the camera devices is determined depending on the installation conditions of the camera devices. Therefore, there is a certain restriction on the time it takes for a vehicle that has passed through the shooting area of ​​one camera device to pass through the shooting area of ​​an adjacent camera device along the vehicle's direction of movement.

[0123] Therefore, by using a Kalman filter, the observation results (e.g., second data) from a certain imaging device can be predicted at the time when the vehicle passes through the imaging area of ​​an adjacent imaging device along the vehicle's direction of movement, and the driving trajectory of each vehicle can be estimated.

[0124] In detail, for example, the association unit 133 may apply a Kalman filter using the vehicle position and attributes contained in the second data, which is the observation result, information indicating the route of road R (route information), and information indicating the interval between the imaging devices (spacing information).

[0125] When the associating unit 133 uses the route information and the interval information, the information may be acquired from an external device (not shown) or may be stored in the analyzing unit 132 in advance.

[0126] As a result, the association unit 133 may, for example, estimate the observation results of an imaging device installed next to the imaging device that captured the image that is the source of the second data, and generate the estimated second data.

[0127] The "adjacent camera" here refers to a camera that is adjacent to the camera that captured the image that is the source of the second data, along the direction of vehicle movement. When a Kalman filter is applied, the moving speed and other information included in the second data may also be used.

[0128] The analysis unit 132 may use, for example, the second data, which is the observation results, and the estimated second data, to classify the traveling trajectory generated by the analysis unit 132 as corresponding to any of the vehicles included in the second data, which is the observation results. This allows the analysis unit 132 to generate road condition data in which information included in the second data is associated with the traveling trajectory.

[0129] The method of associating the second data with the travel locus using a Kalman filter is not limited to the above example, and may be changed as appropriate.

[0130] (Uses of Road Condition Data) Examples of uses of road condition data include the following. However, the uses of road condition data are not limited to these examples. Monitoring at a monitoring center that monitors the road conditions of road R Display on a display device installed on road R to inform drivers of traffic conditions, etc. Safe driving support for drivers of vehicles traveling on road R Support for automatic driving of vehicles traveling on road R

[0131] In order to assist the driver in safe driving, the observation target point may be, for example, a point within a predetermined range from a merging point. The merging point is a point where a merging lane S merges with a road R.

[0132] This allows the driver of a vehicle traveling in the merging lane to refer to the road condition data related to the merging point and accurately know whether there are any vehicles traveling on road R, the lane they are traveling in, etc. This therefore makes it possible to support safe merging onto road R and to support the driver's safe driving.

[0133] Furthermore, the driver of a vehicle traveling on road R can refer to the road condition data related to the merging point and accurately know whether or not there is a vehicle traveling on merging lane S. Therefore, it is possible to support the driver in taking appropriate measures against a vehicle merging from merging lane S and to support the driver in safe driving.

[0134] To assist the driver in safe driving, the observation point may be a point with multiple lanes, such as a driving lane and an overtaking lane.

[0135] As a result, when a driver of a vehicle traveling on road R changes lanes, the driver can accurately know information (e.g., the second data) about a vehicle traveling in the lane to which the driver is changing lanes. Therefore, it is possible to support safe lane changes and safe driving by the driver.

[0136] An example of the configuration of an information processing system for realizing these will be described in another embodiment.

[0137] (Example of Physical Configuration of Information Processing Apparatus 100) As shown in FIG. 8, the information processing apparatus 100 physically includes a bus 1010, a processor 1020, a memory 1030, a storage device 1040, a network interface 1050, and a user interface 1060.

[0138] The bus 1010 is a data transmission path for transmitting and receiving data among the processor 1020, memory 1030, storage device 1040, network interface 1050, input interface 1060, and output interface 1070. However, the method of connecting the processor 1020 and the like to each other is not limited to bus connection.

[0139] The processor 1020 is implemented as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit).

[0140] The memory 1030 is a main storage device realized by a RAM (Random Access Memory) or the like.

[0141] The storage device 1040 is an auxiliary storage device realized by a hard disk drive (HDD), a solid state drive (SSD), a memory card, a read-only memory (ROM), or the like. The storage device 1040 stores program modules for realizing the functions of the device that includes the storage device 1040. The processor 1020 loads each of these program modules into the memory 1030 and executes them to realize the function corresponding to that program module.

[0142] The network interface 1050 is an interface for connecting a device equipped with it to a communication network.

[0143] The input interface 1060 is an interface for the user to input information, and is configured from, for example, a touch panel, a keyboard, a mouse, and the like.

[0144] The output interface 1070 is an interface for presenting information to the user, and is configured, for example, by a liquid crystal panel, an organic EL (Electro-Luminescence) panel, or the like.

[0145] In this way, the functions of the information processing device 100 can be realized by the physical components cooperating to execute a software program. Therefore, the present invention may be realized as a software program or as a non-transitory storage medium on which the program is recorded.

[0146] Each of the sensor information processing device 104, the aggregation device 106, and the sensing device 50 may be physically configured in the same manner as, for example, the information processing device 100. However, the sensing device 50 may further include a configuration for transmitting and receiving optical signals to and from the optical fiber 50.

[0147] (Operations and Effects) As described above, according to this embodiment, the information processing device 100 includes the first acquisition unit 110, the second acquisition unit 120, and the generation unit 130.

[0148] The first acquisition unit 110 acquires first data related to vibrations on a road observed by distributed acoustic sensing using optical fibers installed along the road. The second acquisition unit 120 acquires second data including at least one of vehicle attributes and movement states. The generation unit 130 generates road condition data that associates the second data of the vehicle with the vehicle's travel trajectory on the road, using the first data and the second data corresponding to the observation time and observation point.

[0149] This makes it possible to provide a result of estimating the travel trajectory of a vehicle traveling on road R with high accuracy, as described above.

[0150] According to this embodiment, the road condition data is generated using at least one of a graph neural network and a Kalman filter.

[0151] This makes it possible to generate road condition data by associating the second data of the vehicle with the travel trajectory of the vehicle on road R. Therefore, it becomes possible to provide a result of estimating the travel trajectory of the vehicle traveling on road R with high accuracy.

[0152] According to this embodiment, the attributes include a size type.

[0153] Generally, as described above, the size of the vehicle can affect the difficulty of estimating from the first data which vehicle a travel trajectory corresponds to. By including the size type in the attributes, road condition data can be generated using the size type. Therefore, it is possible to provide a more accurate estimation result of the travel trajectory of a vehicle traveling on road R.

[0154] According to this embodiment, the travel state includes at least one of a vehicle position, a travel lane, a travel speed, and a traffic jam.

[0155] As a result, road condition data can be generated by associating the second data of the vehicle with the travel trajectory of the vehicle on road R using at least one of the vehicle position, travel lane, travel speed, and congestion. Therefore, it is possible to provide a result of estimating the travel trajectory of the vehicle traveling on road R with high accuracy.

[0156] According to this embodiment, the second data is data generated by processing an image captured by an image capturing device installed on the road R.

[0157] This allows the second data to be obtained using a photographing device that is generally installed on a main road or the like, eliminating the need to install a special sensor for obtaining the second data. This makes it possible to easily provide a result of estimating the travel trajectory of a vehicle traveling on road R with high accuracy.

[0158] According to this embodiment, the observation target points include at least one of points within a predetermined range from the merging point where the merging lane S merges with the road R, and points where multiple lanes are provided.

[0159] This makes it possible to assist the driver in driving safely, as described above.

[0160] According to this embodiment, there are a plurality of image capturing devices. The second data is generated using a plurality of images captured by each of the plurality of image capturing devices. There are a plurality of combinations of observation times and observation target points. The road condition data is generated using the first data and the second data corresponding to the observation times and observation target points included in each combination.

[0161] This makes it possible to generate road condition data for the wide area of ​​roads R. Therefore, it becomes possible to provide a result of estimating the travel trajectory of a vehicle traveling on the wide area of ​​roads R with high accuracy.

[0162] [Modification 1] The information processing system S2 may include only one sensor 102 and one sensor information processing device 104, as shown in Fig. 9. Except for this, the information processing system S2 may be configured similarly to the information processing system S1. This also achieves the same effects as those of the first embodiment.

[0163] [Embodiment 2] In embodiment 2, an example of an information processing device 200 that further has a function of transmitting road condition data to another device will be described. The example of the information processing device 200 according to this embodiment further has a function of selecting information to be transmitted from the road condition data.

[0164] As shown in FIG. 10, the information processing device 200 includes a first selection unit 140 and a transmission unit 150 in addition to the first acquisition unit 110, second acquisition unit 120, and generation unit 130 described above.

[0165] The first selection unit 140 receives first selection information for selecting road condition data.

[0166] The transmitting unit 150 transmits the selected road condition data to an external device (not shown).

[0167] The information processing device 200 executes information processing as shown in FIG.

[0168] The first selection unit 140 receives first selection information for selecting road condition data (step S140).

[0169] The transmitting unit 150 transmits the selected road condition data to an external device (not shown) (step S150).

[0170] (Method for selecting road condition data to be transmitted) The road condition data to be transmitted may be selected using, for example, information included in the second data. As described above, the information included in the second data may be at least one of vehicle attributes and movement status. As described above, the movement status may include at least one of the vehicle position, the lane in which the vehicle is moving, the vehicle's movement speed, and congestion. The first selection information may be information indicating, for example, information selected by the user from the information included in the second data.

[0171] FIG. 12 shows an example of road condition data when a large vehicle is selected from the travel locus shown in FIG.

[0172] (Regarding the External Device) The external device may be an external device appropriate for the purpose of the road condition data. The external device may, for example, have a function to receive the road condition data transmitted in step S150 and a function to perform processing using the received road condition data. The processing using the road condition data may, for example, be processing to display the road condition data on a display means such as a display. An external device equipped with a display means may also be referred to as a display device. The display device may, for example, be a bulletin board that displays the status of road R in a monitoring center. Alternatively, for example, the display device may be a bulletin board installed on road R and display the status of road R. For example, the display device may be a car navigation device or a terminal device (e.g., a tablet terminal used for road guidance, a smartphone, etc.) installed in a vehicle. When the external device is a display device such as a bulletin board, a car navigation device, or a terminal device, upon receiving the selected road condition data, the selected road condition data may be displayed on the external device.

[0173] The process using the road condition data may be, for example, a process for controlling the traveling of an autonomous vehicle. In this case, the external device may be, for example, a control device for controlling the traveling of the autonomous vehicle.

[0174] The information processing device 200 does not need to include the first selection unit 140. In this case, the transmission unit 150 may transmit, for example, the road condition data generated by the generation unit 130 to an external device. Furthermore, the processing using the road condition data is not limited to the above example.

[0175] (Operations and Effects) As described above, according to this embodiment, the information processing device 200 further includes a first selection unit 140 and a transmission unit 150. The first selection unit 140 receives first selection information for selecting road condition data. The transmission unit 150 transmits the selected road condition data to an external device.

[0176] This makes it possible to support safe traffic by utilizing the results of accurately estimating the travel trajectory of a vehicle traveling on road R. Therefore, it becomes possible to ensure traffic safety.

[0177] [Embodiment 3] In embodiment 3, an example of an information processing system configured so that when road condition data is transmitted to a display device such as a bulletin board device, a car navigation device, or a terminal device, the road condition data to be displayed can be selected on the display device.

[0178] For example, as shown in FIG. 13, the information processing system S3 includes an optical fiber 50, a sensing device 60, an information processing device 200, a plurality of sensors 102, a plurality of sensor information processing devices 104, an aggregation device 106, and a display device 210.

[0179] The information processing device 100 and the display device 210 are connected to each other via a communication network NT5 that is configured, for example, by wired or wireless means or a combination of these, and can transmit and receive information to and from each other. A part or the entire communication network NT5 may be a communication network common to the communication networks NT1 to NT4, or may be a different communication network.

[0180] (Configuration Example of Display Device 210) The display device 210 includes, for example, a second selection unit 211, a display control unit 212, and a display unit 213, as shown in FIG.

[0181] The second selection unit 211 receives second selection information for selecting road condition data to be displayed on the display unit 213 .

[0182] The display control unit 212 causes the display unit 213 to display the selected road condition data.

[0183] The display unit 213 displays various types of information under the control of the display control unit 212, for example.

[0184] (Example of Operation of Display Device 210) The display device 210 executes information processing as shown in FIG. 15, for example.

[0185] The second selection unit 211 receives second selection information for selecting road condition data to be displayed on the display unit 213 (step S211).

[0186] The display control unit 212 causes the display unit 213 to display the road condition data selected in step S211 (step S212).

[0187] The information processing executed by the display device 210 may be started, for example, when the display device 210 (more specifically, for example, the second selection unit 211 or the display control unit 212) acquires road condition data from the information processing device 200. Note that the trigger for starting the information processing executed by the display device 210 is not limited to this.

[0188] (Method for selecting road condition data to be displayed) The road condition data to be displayed may be selected using, for example, information included in the second data. In detail, for example, the road condition data to be displayed may be selected using information included in the road condition data acquired by the display device 210 from the information processing device 200, among the information included in the second data.

[0189] The information included in the second data may be at least one of the vehicle attributes and the travel state, as described above. The travel state may include at least one of the vehicle position, the travel lane of the vehicle, the travel speed of the vehicle, and congestion, as described above.

[0190] The second selection information may be information indicating, for example, information selected by the user from among the information included in the second data.

[0191] An example of road condition data displayed when a large vehicle is selected from the travel trajectory illustrated in FIG. 4 may be the same as that shown in FIG.

[0192] The display device 210 may be physically configured in the same manner as the information processing device 100, for example.

[0193] (Actions and Effects) As described above, according to this embodiment, the display device 210 includes the second selection unit 211, the display control unit 212, and the display unit 213. The second selection unit 211 accepts second selection information for selecting road condition data to be displayed on the display unit 213. The display control unit 212 causes the display unit 213 to display the selected road condition data.

[0194] This makes it possible to support safe traffic by utilizing the results of accurately estimating the travel trajectory of a vehicle traveling on road R. Therefore, it becomes possible to ensure traffic safety.

[0195] [Fourth Embodiment] The second selection information described in the third embodiment may include a display condition. The display condition is information that determines the conditions for display. In detail, for example, the display condition may be, but is not limited to, that there is another vehicle traveling in a different lane within a predetermined range from the vehicle.

[0196] The display device 210 may execute information processing as shown in FIG. 16, for example.

[0197] The second selection unit 211 receives second selection information including display conditions for selecting road condition data to be displayed on the display unit 213 (step S311).

[0198] The display control unit 212 determines whether the road condition data acquired from the information processing device 200 satisfies the display conditions accepted in step S311 (step S312).

[0199] If the display conditions are not satisfied (step S312; No), the display control unit 212 ends the information processing. If the display conditions are satisfied (step S312; Yes), the display control unit 212 causes the display unit 213 to display a message containing road condition data according to the display conditions selected in step S311 (i.e., the selected road condition data) (step S313).

[0200] This message is, for example, a warning message.

[0201] In detail, for example, when a vehicle is moving in a merging lane S and there is another vehicle moving in a different lane L1 within a predetermined range of the vehicle, the message may be, for example, "Watch out for passing vehicles when merging."

[0202] When a vehicle Ca traveling in lane L1 is within a predetermined range of another vehicle traveling in a different lane (merging lane S), a message such as "Watch out for merging vehicles" may be displayed. This message may be displayed on a display device located in a position where the vehicle Ca can be seen. Such a message is not limited to the example shown here, and may be predetermined according to the content of the display conditions, for example.

[0203] (Actions and Effects) As described above, according to this embodiment, the second selection unit 211 accepts second selection information including display conditions for selecting road condition data to be displayed on the display unit 213. When the display conditions are satisfied, the display control unit 212 causes the display unit 213 to display, as a message, road condition data according to the selected display conditions.

[0204] This makes it possible to support safe traffic by utilizing the results of accurately estimating the travel trajectory of a vehicle traveling on road R. Therefore, it becomes possible to ensure traffic safety.

[0205] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0206] In addition, although the flowcharts used in the above description show a sequence of steps (processes), the order of steps executed in each embodiment is not limited to the sequence shown in the flowcharts. In each embodiment, the order of steps shown in the diagrams can be changed as long as it does not cause any problems in terms of the content.

[0207] Some or all of the above embodiments may be described as, but are not limited to, the following supplementary notes. 1. An information processing device comprising: a first acquisition means for acquiring first data relating to vibrations on a road observed by distributed acoustic sensing using optical fibers installed along the road; a second acquisition means for acquiring second data including at least one of a vehicle's attributes and a movement state; and a generation means for generating road condition data in which the second data of the vehicle is associated with a travel trajectory of the vehicle on the road, using the first data and the second data corresponding to an observation time and an observation target point. 2. The information processing device described in 1., in which the road condition data is generated using at least one of a graph neural network and a Kalman filter. 3. The information processing device described in 1. or 2., in which the attributes include size type. 4. The information processing device described in at least one of 1. to 3., in which the movement state includes at least one of a vehicle position, a travel lane, a movement speed, and congestion. 5. The information processing device according to at least one of 1. to 4., further comprising: first selection means for accepting first selection information for selecting the road condition data; and transmission means for transmitting the selected road condition data to an external device. 6. The information processing device according to at least one of 1. to 5., wherein the second data is data generated by processing images captured by an imaging device installed on the road. 7. The information processing device according to at least one of 1. to 6., wherein the observation target point includes at least one of a point within a predetermined range from a merging point where a merging lane merges into the road, and a point where multiple lanes are provided. 8. The information processing device according to 6., wherein there are multiple imaging devices, the second data is generated using multiple images captured by each of the multiple imaging devices, there are multiple combinations of observation times and observation target points, and the road condition data is generated using the first data and the second data corresponding to the observation times and the observation target points included in each of the combinations.9. An information processing system comprising: an information processing device; and a display device, wherein the information processing device comprises: first acquisition means for acquiring first data relating to vibrations on a road observed by distributed acoustic sensing using optical fibers installed along the road; second acquisition means for acquiring second data including at least one of a vehicle's attributes and a movement state; and generation means for generating road condition data in which the second data of the vehicle is associated with a travel trajectory of the vehicle on the road, using the first data and the second data where the observation time and observation point correspond, and the display device comprises: second selection means for accepting second selection information for selecting the road condition data to be displayed on the display means, and display control means for causing the display means to display the selected road condition data. 10. An information processing system comprising: the information processing device described in any one of 1. to 8.; and a display device, wherein the display device comprises: second selection means for accepting second selection information for selecting the road condition data to be displayed on the display means, and display control means for causing the display means to display the selected road condition data. 11. 12. An information processing method in which one or more computers acquire first data related to vibrations on a road observed by distributed acoustic sensing using optical fibers installed along the road, acquire second data including at least one of a vehicle's attributes and a movement state, and generate road condition data in which the second data of the vehicle is associated with a travel trajectory of the vehicle on the road using the first data and the second data corresponding to an observation time and an observation point. 13. The information processing method described in 11. or 12., in which the attributes include a size type. 14. The information processing method described in at least one of 11. to 13., in which the movement state includes at least one of a vehicle position, a travel lane, a movement speed, and congestion.15. The information processing method described in at least one of 11. to 14., further comprising: receiving first selection information for selecting the road condition data; and transmitting the selected road condition data to an external device. 16. The information processing method described in at least one of 11. to 15., wherein the second data is data generated by processing images captured by a camera installed on the road. 17. The information processing method described in at least one of 11. to 16., wherein the observation target point includes at least one of a point within a predetermined range from a merging point where a merging lane merges into the road, and a point where multiple lanes are provided. 18. The information processing method described in 16., wherein there are multiple camera devices; the second data is generated using multiple images captured by each of the multiple camera devices; there are multiple combinations of observation times and observation target points; and the road condition data is generated using the first data and the second data corresponding to the observation times and observation target points included in each of the combinations. 19. A program causing one or more computers to execute the following steps: acquire first data related to vibrations on a road observed by distributed acoustic sensing using optical fibers installed along the road; acquire second data including at least one of a vehicle's attributes and a vehicle's movement state; and generate road condition data in which the second data of the vehicle is associated with a travel trajectory of the vehicle on the road using the first data and the second data corresponding to an observation time and an observation point. 20. The program described in 19., in which the road condition data is generated using at least one of a graph neural network and a Kalman filter. 21. The program described in 19. or 20., in which the attributes include a size type. 22. The program described in at least one of 19. to 21., in which the movement state includes at least one of a vehicle position, a travel lane, a movement speed, and congestion. 23. The program described in at least one of 19. to 22., further causing the computer to receive first selection information for selecting the road condition data; and transmit the selected road condition data to an external device.24. The program described in at least one of 19. to 23., wherein the second data is data generated by processing images captured by a camera installed on the road. 25. The program described in at least one of 19. to 24., wherein the observation target point includes at least one of a point within a predetermined range from a merging point where a merging lane merges into the road, and a point where multiple lanes are provided. 26. The program described in 24., wherein there are multiple camera devices, the second data is generated using multiple images captured by each of the multiple camera devices, there are multiple combinations of observation times and observation target points, and the road condition data is generated using the first data and the second data corresponding to the observation time and the observation target point included in each of the combinations. 27. A recording medium having recorded thereon the program described in any one of 19. to 26.

[0208] This application claims priority based on Japanese Patent Application No. 2023-188264, filed November 2, 2023, the disclosure of which is incorporated herein by reference in its entirety.

[0209] 50 Optical fiber 60 Sensing device 100, 200 Information processing device 110 First acquisition unit 120 Second acquisition unit 130 Generation unit 131 Target setting unit 132 Analysis unit 133 Association unit 140 First selection unit 150 Transmission unit 210 Display device 211 Second selection unit 212 Display control unit 213 Display unit

Claims

1. An information processing device comprising: a first acquisition means for acquiring first data relating to vibrations on a road observed by distributed acoustic sensing using optical fibers installed along the road; a second acquisition means for acquiring second data including at least one of a vehicle's attributes and movement state; and a generation means for generating road condition data that associates the second data of the vehicle with the vehicle's travel trajectory on the road, using the first data and the second data that correspond to an observation time and an observation point.

2. The information processing device according to claim 1, wherein the road condition data is generated using at least one of a graph neural network and a Kalman filter.

3. The information processing device according to claim 1 or 2, wherein the attributes include a size type.

4. The information processing device according to claim 1 or 2, wherein the movement state includes at least one of a vehicle position, a moving lane, a moving speed, and a traffic jam.

5. The information processing device according to claim 1 or 2, further comprising: a first selection means for accepting first selection information for selecting the road condition data; and a transmission means for transmitting the selected road condition data to an external device.

6. The information processing device according to claim 1 or 2, wherein the second data is data generated by processing an image captured by a photographing device installed on the road.

7. An information processing device according to claim 1 or 2, wherein the observation target points include at least one of points within a predetermined range from a merging point where a merging lane merges into the road, and points where multiple lanes are provided.

8. The information processing device according to claim 6, wherein the number of said photographing devices is multiple, the second data is generated using multiple images photographed by each of said multiple photographing devices, there are multiple combinations of observation times and observation target points, and the road condition data is generated using the first data and the second data corresponding to the observation times and the observation target points included in each of said combinations.

9. An information processing system comprising: an information processing device; and a display device, wherein the information processing device comprises: a first acquisition means for acquiring first data relating to vibrations on a road observed by distributed acoustic sensing using optical fibers installed along the road; a second acquisition means for acquiring second data including at least one of an attribute and a moving state of a vehicle; and a generation means for generating road condition data in which the second data of the vehicle is associated with a travel trajectory of the vehicle on the road, using the first data and the second data having corresponding observation times and observation points; and the display device comprises: a second selection means for accepting second selection information for selecting the road condition data to be displayed on the display means; and a display control means for displaying the selected road condition data on the display means.

10. An information processing method in which one or more computers acquire first data relating to vibrations on a road observed by distributed acoustic sensing using optical fibers installed along the road, acquire second data including at least one of vehicle attributes and movement status, and generate road condition data that associates the second data of the vehicle with the vehicle's travel trajectory on the road using the first data and the second data, which correspond to each other in observation time and observation point.

11. A recording medium having recorded thereon a program for causing one or more computers to acquire first data relating to vibrations on a road observed by distributed acoustic sensing using optical fibers installed along the road, acquire second data including at least one of vehicle attributes and movement status, and generate road condition data that associates the second data of the vehicle with the vehicle's travel trajectory on the road using the first data and the second data corresponding to the observation time and observation point.

Images