Road monitoring system, vehicle, road monitoring device, road monitoring method, and program
The road monitoring system uses fixed-point observation sensing to enhance vehicle-based sensing success by detecting and requesting vehicles to capture road abnormalities, improving detection accuracy and timing.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-09-30
- Publication Date
- 2026-04-09
AI Technical Summary
The in-vehicle camera of a vehicle may fail to accurately shoot obstacles detected by a monitoring camera due to insufficient resolution, leading to a potential decrease in the success rate of sensing.
A road monitoring system that includes fixed-point observation sensing means to detect abnormal areas on the road, transmitting sensing requests to vehicles capable of capturing these areas, with the request including the location and potentially the timing of the abnormality, utilizing LiDAR or imaging devices for precise detection.
Enhances the success rate of vehicle-based sensing by ensuring vehicles can accurately detect and respond to road abnormalities at optimal times, improving overall road monitoring efficiency.
Smart Images

Figure 2026061727000001_ABST
Abstract
Description
Technical Field
[0004] , ,
[0006] , , , , , , ,<000002!7>, , ,
[0003] , , , , , ,
[0001] The present disclosure relates to a road monitoring system, a vehicle, a road monitoring device, a road monitoring method, and a program.
Background Art
[0002] Patent Document 1 discloses a road monitoring system that monitors a road using a monitoring camera installed on the side of the road and an in-vehicle camera mounted on a vehicle traveling on the road. Specifically, when an obstacle is detected based on a monitoring image obtained from the monitoring camera, the vehicle closest to the obstacle is determined based on the position of the obstacle and the self-vehicle positions of a plurality of vehicles passing near the obstacle, and a shooting command signal is output to the vehicle. When the in-vehicle camera receives the shooting command signal, it shoots the obstacle. Thus, even when the resolution sufficient to determine the size and shape of the obstacle cannot be obtained because the obstacle is at a relatively distant position from the monitoring camera, the size and shape of the obstacle can be determined with high accuracy by using the out-of-vehicle image generated by the in-vehicle camera.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] In the configuration of Patent Document 1 above, there is a possibility that the in-vehicle camera of the vehicle that has received the shooting command signal fails to shoot the obstacle.
[0005] An object of the present disclosure is to provide a technique for increasing the success rate of sensing by a vehicle.
Means for Solving the Problems
[0006] A fixed-point observation sensing result acquisition means that acquires the fixed-point observation sensing results of a fixed-point observation sensing means installed to sense roads, An abnormal area detection means for detecting an abnormal area of the road based on the fixed-point observation sensing results, When the abnormal area detection means detects the abnormal area, a request transmission means transmits an abnormal area sensing request to a vehicle capable of sensing the abnormal area. Includes, The abnormal region sensing request includes the location of the abnormal region. A road monitoring system will be provided.
[0007] A fixed-point observation sensing result acquisition means that acquires the fixed-point observation sensing results of a fixed-point observation sensing means installed to sense roads, An abnormal area detection means for detecting an abnormal area of the road based on the fixed-point observation sensing results, When the abnormal area detection means detects the abnormal area, a request transmission means transmits an abnormal area sensing request to a vehicle capable of sensing the abnormal area. Includes, The abnormal region sensing request includes the location of the abnormal region. Road monitoring equipment will be provided.
[0008] Computers The fixed-point observation sensing results are obtained from a fixed-point observation sensing means installed to sense the road. Based on the fixed-point observation sensing results, the abnormal area of the road is detected. When the aforementioned abnormal region is detected, an abnormal region sensing request is sent to a vehicle capable of sensing the abnormal region. The abnormal region sensing request includes the location of the abnormal region. Road monitoring methods are provided.
[0009] Computers Fixed observation sensing result acquisition means for acquiring the fixed observation sensing results of the fixed observation sensing means installed to sense the road, Abnormal area detection means for detecting an abnormal area of the road based on the fixed observation sensing results, Request transmission means for transmitting an abnormal area sensing request to a vehicle capable of sensing the abnormal area when the abnormal area detection means detects the abnormal area, Function as, The abnormal area sensing request includes the position of the abnormal area, A program is provided.
Effect of the Invention
[0010] According to the present disclosure, the success rate of sensing by a vehicle can be increased.
Brief Description of the Drawings
[0011] [Figure 1] It is a block diagram of a road monitoring system. [Figure 2] It is a control flow of a road monitoring system. [Figure 3] It is a schematic diagram of a road monitoring system. [Figure 4] It is a block diagram of a local processing device. [Figure 5] It is a block diagram of a road monitoring server. [Figure 6] It is a block diagram of a vehicle. [Figure 7] It is a control flow of a vehicle. [Figure 8] It is a control flow of a local processing device. [Figure 9] It is a control flow of a road monitoring server. [Figure 10] It is a block diagram illustrating the hardware configuration of a computer.
Modes for Carrying Out the Invention
[0012] (Summary of the Present Disclosure) First, an overview of this disclosure will be provided. Figure 1 is a block diagram of the road monitoring system 100. The road monitoring system 100 includes a fixed-point observation sensing result acquisition means 101, an abnormal area detection means 102, and a request transmission means 103.
[0013] The fixed-point observation sensing result acquisition means 101 acquires the fixed-point observation sensing results from the fixed-point observation sensing means installed to sense the road.
[0014] The abnormal area detection means 102 detects abnormal areas of the road based on the results of fixed-point observation sensing.
[0015] When the abnormal area detection means 102 detects an abnormal area, the request transmission means 103 transmits an abnormal area sensing request to a vehicle capable of sensing the abnormal area.
[0016] Furthermore, the abnormal area sensing request includes the location of the abnormal area.
[0017] Next, the operation of the road monitoring system 100 will be explained. Figure 2 shows the control flow of the road monitoring system.
[0018] First, the fixed-point observation sensing result acquisition means 101 acquires the fixed-point observation sensing results from the fixed-point observation sensing means installed to sense the road (S101). Next, the abnormal area detection means 102 detects abnormal areas on the road based on the fixed-point observation sensing results (S102). Then, if the abnormal area detection means 102 detects an abnormal area, it sends an abnormal area sensing request to a vehicle capable of sensing the abnormal area (S103).
[0019] With the above configuration, the success rate of vehicle-based sensing can be increased.
[0020] (First Embodiment) Next, a road monitoring system in the first embodiment of this disclosure will be described.
[0021] The present invention will be described below through embodiments of the invention, but the invention claimed is not limited to the following embodiments. Furthermore, not all of the configurations described in the embodiments are necessarily essential as means of solving the problem. For clarity of explanation, the following descriptions and drawings have been omitted and simplified as appropriate. In each drawing, the same elements are denoted by the same reference numerals, and redundant explanations have been omitted where necessary.
[0022] In the following embodiments, the description will be divided into multiple sections or embodiments where necessary for convenience. Unless otherwise specified, these are not unrelated, and one may be a modification, application, detailed explanation, or supplementary explanation of part or all of the other. Furthermore, in the following embodiments, when referring to the number of elements (including number, numerical value, quantity, and range), unless otherwise specified or clearly limited to a specific number in principle, it is not limited to that specific number, and may be greater than or less than that number.
[0023] Furthermore, in the following embodiments, the components (including operation steps, etc.) are not necessarily essential unless specifically stated or considered to be fundamentally essential. Similarly, in the following embodiments, when referring to the shape or positional relationship of components, etc., it shall include those substantially similar to or resembling their shape, etc., unless specifically stated or considered to be fundamentally different. The same applies to the numbers, etc. (including number, numerical value, quantity, and range) mentioned above.
[0024] Figure 3 is a schematic diagram of the road monitoring system 1. As shown in Figure 3, the road monitoring system 1 includes a road monitoring server 2, multiple local processing units 3, multiple fixed-point observation devices 4, and multiple vehicles 5.
[0025] The road monitoring server 2 and the multiple local processing units 3 typically communicate bidirectionally via a Wide Area Network (WAN), such as the Internet. Each local processing unit 3 is permanently installed to the side or above the road 6. Each local processing unit 3 typically communicates bidirectionally with one or more vehicles 5 traveling or parked near the local processing unit 3 via Dedicated Short Range Communication (DSRC). The road monitoring server 2 also typically communicates bidirectionally with multiple vehicles 5 via a Wide Area Network (WAN).
[0026] The road monitoring system 1 includes at least a road monitoring server 2 and a plurality of local processing units 3. The road monitoring server 2 and the plurality of local processing units 3 cooperate with each other to constitute the road monitoring system 1. In this embodiment, the road monitoring system 1 is implemented by distributed processing using a plurality of devices. The plurality of devices are typically the road monitoring server 2 and the plurality of local processing units 3. However, the road monitoring system 1 may be implemented by a single device. Also, for example, each local processing unit 3 may implement some or all of the functions of the road monitoring server 2.
[0027] Multiple local processing units 3 and multiple fixed-point observation devices 4 are typically arranged in a one-to-one configuration. Each local processing unit 3 and each fixed-point observation device 4 are typically connected by a wire.
[0028] Each fixed-point observation device 4 is a specific example of a fixed-point observation sensing means installed to sense the road 6. In this embodiment, each fixed-point observation device 4 is a LiDAR (Light Detection and Ranging) device. Each fixed-point observation device 4 measures the distance of the space including the road surface of the road 6 to generate a 3D point cloud and outputs the generated 3D point cloud as a fixed-point observation sensing result to the corresponding local processing unit 3. However, instead, each fixed-point observation device 4 may be a Radar (Radio Detection and Ranging) device or a stereo camera. In this case as well, each fixed-point observation device 4 measures the distance of the space including the road surface of the road 6 to generate a 3D point cloud and outputs the generated 3D point cloud as a fixed-point observation sensing result to the corresponding local processing unit 3. Alternatively, each fixed-point observation device 4 may be an imaging device. In this case, each fixed-point observation device 4 images the space including the road surface of the road 6 to generate a 2D image and outputs the generated 2D image as a fixed-point observation sensing result to the corresponding local processing unit 3.
[0029] Figure 4 shows a block diagram of the local processing unit 3. As shown in Figure 4, the local processing unit 3 includes a fixed-point observation sensing result acquisition unit 10, an abnormal area detection unit 11, an abnormal area detection result transmission unit 12, and a vehicle information transfer unit 13.
[0030] The fixed-point observation sensing result acquisition unit 10 acquires fixed-point observation sensing results from the corresponding fixed-point observation device 4.
[0031] The abnormal area detection unit 11 detects abnormal areas on the road 6 based on the fixed-point observation sensing results.
[0032] Specifically, when the fixed-point observation sensing result is a 3D point cloud, the anomaly region detection unit 11 typically uses PointNet to detect foreign objects on the road surface of road 6 as anomaly regions. When the fixed-point observation sensing result is a 3D point cloud, the anomaly region detection unit 11 may detect the road surface of road 6 and also detect point clouds that are separated above a predetermined distance or more from the road surface, thereby detecting foreign objects on the road surface of road 6 as anomaly regions. Furthermore, when the fixed-point observation sensing result is a 2D image, the anomaly region detection unit 11 typically uses Faster R-CNN (Region-based Convolutional Neural Networks), YOLO (You Only Look Once), or SSD (Single Shot MultiBox Detector) to detect foreign objects on the road surface of road 6 as anomaly regions. In addition to detecting foreign objects on the road surface of road 6 as anomaly regions, the anomaly region detection unit 11 may also detect depressions or bulges on the road surface of road 6 as anomaly regions. The abnormal region detection unit 11 generates an abnormal region detection result for each detected abnormal region.
[0033] The anomaly area detection unit 11, when detecting anomalies on the road 6, acquires a detection score for each class output to the output layer of the neural network. If the detection score exceeds a predetermined threshold, the anomaly area detection unit 11 detects an anomaly area classified into the class corresponding to the detection score. The location of the anomaly area is typically represented in a geographic coordinate system. The anomaly area detection result typically includes the class of the corresponding anomaly area, the detection score of the corresponding anomaly area, and the location of the corresponding anomaly area.
[0034] The abnormal area detection result transmission unit 12 transmits the abnormal area detection result generated by the abnormal area detection unit 11 to the road monitoring server 2.
[0035] The vehicle information transfer unit 13 acquires vehicle information from one or more vehicles 5 that are traveling or parked within the range from which it can communicate via DSRC from the local processing unit 3, and transmits the acquired vehicle information to the road monitoring server 2.
[0036] Vehicle information includes the position, speed, direction of travel, sensing range, and other vehicle-related information for the corresponding vehicle 5. The position of vehicle 5 is typically expressed in a geographic coordinate system. The sensing range is typically expressed as a plane angle based on the forward direction of vehicle 5 in a plan view.
[0037] Figure 5 shows a block diagram of the road monitoring server 2. As shown in Figure 5, the road monitoring server 2 includes an abnormal area detection result receiving unit 20, a vehicle information receiving unit 21, a request transmission unit 22, a vehicle sensing result receiving unit 23, an abnormality determination unit 24, and an output unit 25.
[0038] The abnormal region detection result receiving unit 20 receives abnormal region detection results from each local processing unit 3.
[0039] The vehicle information receiving unit 21 receives vehicle information from each local processing unit 3. However, the vehicle information receiving unit 21 may also receive vehicle information directly from each vehicle 5 without going through each local processing unit 3.
[0040] When the abnormal area detection result receiving unit 20 receives an abnormal area detection result, the request transmission unit 22 transmits an abnormal area sensing request to a vehicle 5 capable of sensing the abnormal area corresponding to the abnormal area detection result.
[0041] Specifically, the request transmission unit 22 identifies a vehicle 5 capable of sensing the abnormal area based on vehicle information. For example, the request transmission unit 22 identifies a vehicle 5 whose sensing range will capture the abnormal area, either currently or in the future, based on vehicle information of multiple vehicles 5 that are driving or parked near the abnormal area. If multiple vehicles 5 are identified as vehicles whose sensing range will capture the abnormal area, either currently or in the future, the request transmission unit 22 may further identify a vehicle 5 that can sense the abnormal area at the closest distance. The request transmission unit 22 may also consider a vehicle 5 that is driving or parked near the abnormal area as a vehicle capable of sensing the abnormal area.
[0042] An abnormal area sensing request requests the destination vehicle 5 to sense the abnormal area and to transmit the vehicle sensing result, which is the sensing result, to the road monitoring server 2. In this embodiment, the abnormal area sensing request includes the location of the abnormal area. This allows vehicle 5 to sense the abnormal area at a suitable timing. The abnormal area sensing request may also include the sensing timing at which vehicle 5 senses the abnormal area. This allows vehicle 5 to sense the abnormal area at a suitable timing. Here, the request transmission unit 22 can typically generate the sensing timing based on the location of the abnormal area, the location and driving speed of vehicle 5, driving direction, and sensing range.
[0043] The vehicle sensing result receiving unit 23 receives vehicle sensing results from the vehicle 5. The vehicle sensing results are in the form of a 3D point cloud or a 2D image, similar to the fixed-point observation sensing results.
[0044] The anomaly detection unit 24 determines the degree of abnormality of the abnormal area based on the vehicle sensing results. The degree of abnormality is evaluated on a five-point scale, for example. The anomaly detection unit 24 may generate integrated sensing information by sensor fusion of the fixed-point observation sensing results and the vehicle sensing results, and determine the degree of abnormality of the abnormal area based on the integrated sensing information. For example, the anomaly detection unit 24 may determine the size, type, material, etc., of foreign objects present in the abnormal area based on the vehicle sensing results, and determine the degree of abnormality of the abnormal area based on the determination results. In this case, the anomaly detection unit 24 may use object detection technologies such as PointNet, Faster R-CNN, YOLO, and SSD as described above.
[0045] The output unit 25 outputs an abnormality avoidance command to one or more vehicles 5 traveling near the abnormality area, based on the determination result by the abnormality determination unit 24. Specifically, the output unit 25 decides whether or not to output an abnormality avoidance command based on the result of comparing the degree of abnormality of the abnormality area with a preset threshold. The abnormality avoidance command typically includes the location of the abnormality area. The abnormality avoidance command may further include the class of the abnormality area. In addition to outputting an abnormality avoidance command to one or more vehicles 5 traveling near the abnormality area, the output unit 25 may also notify the road administrator 6.
[0046] Figure 6 shows a block diagram of vehicle 5. As shown in Figure 6, vehicle 5 includes a LiDAR device 29, a vehicle information acquisition unit 30, a vehicle information transmission unit 31, an abnormal area sensing request receiving unit 32, a sensing timing determination unit 33, a sensing execution unit 34, a vehicle sensing result trimming unit 35, a vehicle sensing result transmission unit 36, an abnormality avoidance command receiving unit 37, and a vehicle control unit 38.
[0047] The LiDAR device 29 typically measures the distance in the space in front of the vehicle 5 and generates a 3D point cloud. The LiDAR device 29 may also measure the distance in the space behind and to the sides of the vehicle 5 and generate a 3D point cloud. The vehicle 5 may be equipped with a radar device or a stereo camera instead of the LiDAR device 29 as a device for generating a 3D point cloud. Alternatively, the vehicle 5 may be equipped with an imaging device that images the space in front of the vehicle 5 and generates a 2D image instead of the LiDAR device 29. In this case, the imaging device may also image the space behind and to the sides of the vehicle 5 and generate a 2D image.
[0048] The vehicle information acquisition unit 30 acquires vehicle information. As described above, the vehicle information includes the position of vehicle 5, driving speed, driving direction, sensing range, and other information related to the vehicle. As an example of a self-position estimation means, the vehicle information acquisition unit 30 acquires the position of vehicle 5 using a GNSS module (Global Navigation Satellite System). Typical GNSS modules include GPS modules (Global Positioning System), GLONASS modules (Global Navigation Satellite System), Galileo modules, BeiDou modules, and QZSS modules (Quasi-Zenith Satellite System). As another example of a self-position estimation means, the vehicle information acquisition unit 30 may acquire the position of vehicle 5 using SLAM (Simultaneous Localization and Mapping).
[0049] The vehicle information transmission unit 31 transmits the vehicle information acquired by the vehicle information acquisition unit 30 to the local processing unit 3.
[0050] The abnormal area sensing request receiving unit 32 receives an abnormal area sensing request from the road monitoring server 2.
[0051] If the abnormal area sensing request does not include a sensing timing, the sensing timing determination unit 33 determines the sensing timing at which the vehicle 5 will sense the abnormal area. Specifically, the sensing timing determination unit 33 determines the sensing timing based on the location of the abnormal area included in the abnormal area sensing request, the position and speed of the vehicle 5, the direction of travel, and the sensing range.
[0052] The sensing execution unit 34 performs sensing of the abnormal region using the LiDAR device 29 according to the sensing timing included in the abnormal region sensing request, or the sensing timing determined by the sensing timing determination unit 33. As a result, the sensing execution unit 34 acquires the 3D point cloud generated by the LiDAR device 29. The 3D point cloud generated by the LiDAR device 29 is a specific example of the vehicle sensing result. The coordinates of the 3D point cloud generated by the LiDAR device 29 are expressed in the LiDAR coordinate system, which is the coordinate system unique to the LiDAR device 29. Therefore, the sensing execution unit 34 transforms the coordinates of the 3D point cloud expressed in the LiDAR coordinate system into a geographic coordinate system based on the position and speed of the vehicle 5, the direction of travel, and the sensing range.
[0053] The vehicle sensing result trimming unit 35 is a specific example of a trimming means for trimming vehicle sensing results. Specifically, when the vehicle sensing result is a 3D point cloud, the vehicle sensing result trimming unit 35 spatially trims the vehicle sensing result so as to leave the point cloud of the abnormal region and remove the point cloud of other parts. For example, the vehicle sensing result trimming unit 35 may trim the vehicle sensing result, which is a 3D point cloud of vehicle sensing results, so as to leave the point cloud inside a sphere having a predetermined radius centered on the location of the abnormal region and remove the point cloud outside of it. Alternatively, for example, the vehicle sensing result trimming unit 35 may use the aforementioned PointNet to detect an abnormal region on the road 6 and trim the vehicle sensing result so as to leave the 3D point cloud corresponding to the abnormal region and remove the other 3D point clouds. Therefore, the vehicle sensing result trimming unit 35 is a specific example of an abnormal region detection means for detecting an abnormal region based on a 3D point cloud.
[0054] Furthermore, if vehicle 5 is equipped with an imaging device instead of the LiDAR device 29, that is, if the vehicle sensing result is a two-dimensional image consisting of multiple frames, the vehicle sensing result trimming unit 35 may spatially trim the vehicle sensing result so as to leave the abnormal area and remove the other parts. In addition, the vehicle sensing result trimming unit 35 may trim the vehicle sensing result on the time axis so as to extract the frame in which the abnormal area is most clearly depicted among the multiple frames.
[0055] The vehicle sensing result transmission unit 36 transmits the vehicle sensing results to the road monitoring server 2.
[0056] The abnormality avoidance command receiving unit 37 receives abnormality avoidance commands from the road monitoring server 2.
[0057] When the abnormality avoidance command receiving unit 37 receives an abnormality avoidance command from the road monitoring server 2, the vehicle control unit 38 controls the vehicle's movement to avoid the abnormality area based on the location of the abnormality area indicated by the abnormality avoidance command. Controlling the vehicle's movement to avoid the abnormality area includes, for example, steering the vehicle 5, accelerating or decelerating the vehicle 5, and other controls on the vehicle 5.
[0058] Next, the operation of vehicle 5 will be explained with reference to Figure 7. Figure 7 shows the control flow of vehicle 5.
[0059] First, the vehicle information acquisition unit 30 acquires vehicle information (S200). Next, the vehicle information transmission unit 31 transmits the vehicle information acquired by the vehicle information acquisition unit 30 to the local processing unit 3 (S210). Next, the abnormality avoidance command receiving unit 37 determines whether or not it has received an abnormality avoidance command from the road monitoring server 2 (S220). If it has not received an abnormality avoidance command from the road monitoring server 2 (S220: NO), the abnormality area sensing request receiving unit 32 proceeds to step S240. On the other hand, if it has received an abnormality avoidance command from the road monitoring server 2 (S220: YES), the abnormality area sensing request receiving unit 32 proceeds to step S230. Next, the vehicle control unit 38 controls the driving of the vehicle 5 to avoid the abnormal area (S230).
[0060] Next, the abnormal area sensing request receiving unit 32 determines whether or not it has received an abnormal area sensing request from the road monitoring server 2 (S240). If it has not received an abnormal area sensing request from the road monitoring server 2 (S240: NO), the abnormal area sensing request receiving unit 32 returns to step S200. On the other hand, if it has received an abnormal area sensing request from the road monitoring server 2 (S240: YES), the abnormal area sensing request receiving unit 32 proceeds to step S250.
[0061] The sensing timing determination unit 33 determines whether the abnormal area sensing request includes a sensing timing (S250). If the abnormal area sensing request does not include a sensing timing (S250: NO), the sensing timing determination unit 33 determines the sensing timing (S260) and proceeds to step S270. On the other hand, if the abnormal area sensing request includes a sensing timing (S250: YES), the sensing timing determination unit 33 proceeds to step S270.
[0062] Next, the sensing execution unit 34 performs sensing of the abnormal region using the LiDAR device 29 according to the sensing timing included in the abnormal region sensing request, or the sensing timing determined by the sensing timing determination unit 33 (S270). Next, the vehicle sensing result trimming unit 35 trims the 3D point cloud, which is the vehicle sensing result, so as to leave the abnormal region and remove the other parts (S280). Then, the vehicle sensing result transmission unit 36 transmits the trimmed 3D point cloud as the vehicle sensing result to the road monitoring server 2 (S290), and the process returns to step S200.
[0063] Next, the operation of the local processing unit 3 will be explained with reference to Figure 8. Figure 8 shows the control flow of the local processing unit 3.
[0064] First, the vehicle information transfer unit 13 acquires vehicle information from one or more vehicles 5 traveling within the range of communication via DSRC from the local processing unit 3, and transmits the acquired vehicle information to the road monitoring server 2 (S300). Next, the fixed-point observation sensing result acquisition unit 10 acquires fixed-point observation sensing results from the corresponding fixed-point observation device 4 (S310). Next, the abnormal area detection unit 11 detects abnormal areas on the road 6 based on the fixed-point observation sensing results (S320). If no abnormal areas are detected on the road 6 based on the fixed-point observation sensing results (S320: NO), the abnormal area detection unit 11 returns to step S300. On the other hand, if an abnormal area is detected on the road 6 based on the fixed-point observation sensing results (S320: YES), the abnormal area detection unit 11 proceeds to step S330. Next, the abnormal area detection result transmission unit 12 transmits the abnormal area detection result generated by the abnormal area detection unit 11 to the road monitoring server 2 (S330), and the process returns to step S300.
[0065] Next, the operation of the road monitoring server 2 will be explained with reference to Figure 9. Figure 9 shows the control flow of the road monitoring server 2.
[0066] First, the vehicle information receiving unit 21 receives vehicle information from each local processing unit 3 (S400). Next, the abnormal area detection result receiving unit 20 receives abnormal area detection results from each local processing unit 3 (S410). If no abnormal area detection results have been received from each local processing unit 3 (S410: NO), the abnormal area detection result receiving unit 20 returns to step S400. On the other hand, if an abnormal area detection result has been received from each local processing unit 3 (S410: YES), the abnormal area detection result receiving unit 20 proceeds to step S420. Next, the request transmission unit 22 sends an abnormal area sensing request to a vehicle 5 capable of sensing the abnormal area corresponding to the abnormal area detection result (S420). Next, the vehicle sensing result receiving unit 23 waits until it receives vehicle sensing results from vehicle 5 (S430: NO), and once received (S430: YES), proceeds to step S440. Next, the abnormality determination unit 24 determines the degree of abnormality in the abnormal area based on the vehicle sensing results (S440). Then, the output unit 25 outputs an abnormality avoidance command to one or more vehicles 5 traveling near the abnormal area based on the determination result by the abnormality determination unit 24 (S450), and returns the process to step S400.
[0067] The first embodiment of this disclosure has been described above. The first embodiment has the following features.
[0068] The local processing unit 3 includes a fixed-point observation sensing result acquisition unit 10 (fixed-point observation sensing result acquisition means) that acquires fixed-point observation sensing results from a fixed-point observation device 4 (fixed-point observation sensing means) installed to sense the road 6. The local processing unit 3 also includes an abnormal area detection unit 11 (abnormal area detection means) that detects abnormal areas of the road 6 based on the fixed-point observation sensing results. The road monitoring server 2 includes a request transmission unit 22 (request transmission means) that, when the abnormal area detection unit 11 detects an abnormal area, transmits an abnormal area sensing request to a vehicle 5 capable of sensing the abnormal area. The abnormal area sensing request includes the location of the abnormal area. With the above configuration, the success rate of sensing by the vehicle 5 can be increased.
[0069] Furthermore, the abnormal area sensing request includes the sensing timing at which vehicle 5 senses the abnormal area. With the above configuration, vehicle 5 can sense the abnormal area at a suitable timing.
[0070] Furthermore, the request transmission unit 22 determines the sensing timing based on the location of the abnormal area, the position of the vehicle 5, and the driving speed. With the above configuration, it is possible to determine a sensing timing suitable for sensing the abnormal area.
[0071] Furthermore, the road monitoring server 2 further includes a vehicle sensing result receiving unit 23 (vehicle sensing result receiving means) that receives vehicle sensing results from the vehicle 5. With the above configuration, abnormal areas can be evaluated using the vehicle sensing results.
[0072] Furthermore, the vehicle sensing results are trimmed to retain abnormal areas. With this configuration, the amount of communication between the road monitoring server 2 and the vehicle 5 can be reduced.
[0073] Furthermore, the vehicle 5 includes a sensing timing determination unit 33 (sensing timing determination means) that determines the sensing timing for sensing the abnormal region based on the location of the abnormal region, the position of the vehicle 5, and the driving speed. With the above configuration, the abnormal region can be sensed at a suitable timing.
[0074] Furthermore, vehicle 5 includes a vehicle sensing result trimming unit 35 (trimming means) that detects abnormal areas based on vehicle sensing results (sensing results) and trims the image to leave the abnormal areas intact. With this configuration, the amount of communication between the road monitoring server 2 and vehicle 5 can be reduced.
[0075] The first embodiment described above can be modified, for example, as follows: When the abnormal area detection unit 11 receives notification of foreign object detection from the vehicle 5, it may slightly over-detect abnormal areas by lowering the threshold of the detection score used to detect abnormal areas.
[0076] Furthermore, the request transmission unit 22 may assign an ID to each of the abnormal areas detected by the abnormal area detection unit 11, and may refrain from sending an abnormal area sensing request to the vehicle 5 for abnormal areas with a relatively low degree of abnormality.
[0077] Furthermore, based on the determination results from the abnormality determination unit 24, the threshold of the detection score used by the abnormality area detection unit 11 to detect abnormal areas may be changed. For example, if in 80% of the determination results from the abnormality determination unit 24 the degree of abnormality of the abnormal area is not sufficient to warrant outputting an abnormality avoidance command, it is possible that the abnormality area detection unit 11 is over-detecting abnormal areas. In this case, it is possible to lower the threshold of the detection score used by the abnormality area detection unit 11 to detect abnormal areas.
[0078] <Example hardware configuration> The following describes how the functional configurations of each device, such as the road monitoring server 2, local processing unit 3, and vehicle 5, are realized through a combination of hardware and software.
[0079] Figure 10 is a block diagram illustrating the hardware configuration of a computer. The device in this disclosure can realize the above-described functions using a computer 500 including the hardware configuration shown in Figure 10. The computer 500 may be a portable computer such as a smartphone or tablet terminal, or a stationary computer such as a PC. The computer 500 may be a dedicated computer designed to realize each device, or it may be a general-purpose computer. The computer 500 can realize the corresponding functions by installing a predetermined program.
[0080] Computer 500 has a bus 502, a processor 504, memory 506, a storage device 508, an input / output interface 510 (an interface is also called an I / F (Interface)), and a network interface 512. Bus 502 is a data transmission path for the processor 504, memory 506, storage device 508, input / output interface 510, and network interface 512 to send and receive data to and from each other. However, the method of connecting the processor 504 and the other components to each other is not limited to bus connection.
[0081] Processor 504 is a variety of processors such as a CPU, GPU, or FPGA. Memory 506 is main memory implemented using RAM (Random Access Memory), etc.
[0082] The storage device 508 is an auxiliary storage device implemented using a hard disk, SSD, memory card, or ROM (Read Only Memory). The storage device 508 stores a program for implementing a predetermined function. The processor 504 reads this program into memory 506 and executes it to implement each functional component of each device.
[0083] The input / output interface 510 is an interface for connecting the computer 500 with input / output devices. For example, input devices such as keyboards and output devices such as display devices are connected to the input / output interface 510.
[0084] Network interface 512 is an interface for connecting computer 500 to a network.
[0085] The above describes examples of hardware configurations in this disclosure, but the embodiments described above are not limited thereto. This disclosure can also be implemented by having a processor execute a computer program to perform any processing.
[0086] In the examples described above, the program includes a set of instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more of the functions described in the embodiments. The program may be stored on a non-temporary computer-readable medium or a physical storage medium. Examples, but not limited to, include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technologies, CD-ROM, digital versatile disc (DVD), Blu-ray® disc or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices. The program may be transmitted over a temporary computer-readable medium or a communication medium. Examples, but not limited to, include temporary computer-readable medium or a communication medium that includes electrical, optical, acoustic or other forms of propagating signals.
[0087] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure can be understood by those skilled in the art within the scope of the present disclosure.
[0088] Each drawing is merely illustrative to illustrate one or more embodiments. Each drawing may be associated with one or more other embodiments rather than with only one specific embodiment. As those skilled in the art will understand, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings, for example, to create embodiments not explicitly shown or described. Not all features or steps shown in any one drawing to illustrate an exemplary embodiment are necessarily required, and some features or steps may be omitted. The order of steps shown in any of the drawings may be changed as appropriate.
[0089] Some or all of the above embodiments may also be described as follows, but are not limited to the following: (Note 1) A fixed-point observation sensing result acquisition means that acquires the fixed-point observation sensing results of a fixed-point observation sensing means installed to sense roads, An abnormal area detection means for detecting an abnormal area of the road based on the fixed-point observation sensing results, When the abnormal area detection means detects the abnormal area, a request transmission means transmits an abnormal area sensing request to a vehicle capable of sensing the abnormal area. Includes, The abnormal region sensing request includes the location of the abnormal region. Road monitoring system. (Note 2) The road monitoring system described in Appendix 1, The abnormal area sensing request includes a sensing timing for the vehicle to sense the abnormal area. Road monitoring system. (Note 3) The road monitoring system described in Appendix 2, The request transmission means determines the sensing timing based on the location of the abnormal area, the location of the vehicle, and the travel speed. Road monitoring system. (Note 4) The road monitoring system described in Appendix 1, The system further includes a vehicle sensing result receiving means for receiving vehicle sensing results from the vehicle, Road monitoring system. (Note 5) The road monitoring system described in Appendix 4, The vehicle sensing results are trimmed to retain the abnormal region. Road monitoring system. (Note 6) The vehicles listed in Appendix 1, Includes sensing timing determination means for determining the sensing timing for sensing the abnormal region based on the location of the abnormal region, the position of the vehicle, and the travel speed. vehicle. (Note 7) The vehicles listed in Appendix 1, The system further includes a trimming means for detecting an abnormal region based on the sensing results and trimming the sensing results so as to leave the abnormal region intact. vehicle. (Note 8) A fixed-point observation sensing result acquisition means that acquires the fixed-point observation sensing results of a fixed-point observation sensing means installed to sense roads, An abnormal area detection means for detecting an abnormal area of the road based on the fixed-point observation sensing results, When the abnormal area detection means detects the abnormal area, a request transmission means transmits an abnormal area sensing request to a vehicle capable of sensing the abnormal area. Includes, The abnormal region sensing request includes the location of the abnormal region. Road monitoring equipment. (Note 9) Computers The fixed-point observation sensing results are obtained from a fixed-point observation sensing means installed to sense the road. Based on the fixed-point observation sensing results, the abnormal area of the road is detected. When the aforementioned abnormal region is detected, an abnormal region sensing request is sent to a vehicle capable of sensing the abnormal region. The abnormal region sensing request includes the location of the abnormal region. Road monitoring method. (Note 10) Computers A fixed-point observation sensing result acquisition means that acquires the fixed-point observation sensing results of a fixed-point observation sensing means installed to sense roads, An abnormal area detection means for detecting an abnormal area of the road based on the fixed-point observation sensing results, When the abnormal area detection means detects the abnormal area, a request transmission means transmits an abnormal area sensing request to a vehicle capable of sensing the abnormal area. To make it function as, The abnormal region sensing request includes the location of the abnormal region. program.
[0090] Some or all of the elements (e.g., configuration and function) described in Appendices 2 to 7 that are dependent on Appendice 1 may also be dependent on Appendices 8 to 10 in the same way as in Appendices 2 to 7. Some or all of the elements described in any appendice may be applicable to various hardware, software, recording means, systems, and methods for recording software. [Explanation of Symbols]
[0091] 1. Road monitoring system 2 Road monitoring servers 3 Local Processing Unit 4. Fixed-point observation device 5 vehicles 6 road 10 Fixed-point observation sensing result acquisition unit 11 Anomaly Area Detection Unit 12 Abnormal Area Detection Result Transmission Unit 13. Vehicle Information Transfer Unit 20 Abnormal Area Detection Result Receiving Unit 21 Vehicle Information Receiving Unit 22 Request transmission unit 23 Vehicle sensing result receiving unit 24 Abnormality determination section 25 Output section 29 LiDAR device 30 Vehicle Information Acquisition Unit 31 Vehicle Information Transmission Unit 32 Anomaly Area Sensing Request Receiving Unit 33 Sensing timing determination unit 34 Sensing Execution Unit 35 Vehicle Sensing Results Trim Section 36 Vehicle Sensing Result Transmission Unit 37 Anomaly Avoidance Command Receiving Unit 38 Vehicle Control Unit 500 computers Bus 502 504 Processors 506 memory 508 Storage Devices 510 Input / Output Interface 512 Network Interfaces
Claims
1. A fixed-point observation sensing result acquisition means that acquires the fixed-point observation sensing results of a fixed-point observation sensing means installed to sense roads, An abnormal area detection means for detecting an abnormal area of the road based on the fixed-point observation sensing results, When the abnormal area detection means detects the abnormal area, a request transmission means transmits an abnormal area sensing request to a vehicle capable of sensing the abnormal area. Includes, The abnormal region sensing request includes the location of the abnormal region. Road monitoring system.
2. A road monitoring system according to claim 1, The abnormal area sensing request includes a sensing timing for the vehicle to sense the abnormal area. Road monitoring system.
3. A road monitoring system according to claim 2, The request transmission means determines the sensing timing based on the location of the abnormal area, the location of the vehicle, and the travel speed. Road monitoring system.
4. A road monitoring system according to claim 1, The system further includes a vehicle sensing result receiving means for receiving vehicle sensing results from the vehicle, Road monitoring system.
5. A road monitoring system according to claim 4, The vehicle sensing results are trimmed to retain the abnormal region. Road monitoring system.
6. A vehicle according to claim 1, Includes sensing timing determination means for determining the sensing timing for sensing the abnormal region based on the location of the abnormal region, the position of the vehicle, and the travel speed. vehicle.
7. A vehicle according to claim 1, The system further includes a trimming means for detecting an abnormal region based on the sensing results and trimming the sensing results so as to leave the abnormal region intact. vehicle.
8. A fixed-point observation sensing result acquisition means that acquires the fixed-point observation sensing results of a fixed-point observation sensing means installed to sense roads, An abnormal area detection means for detecting an abnormal area of the road based on the fixed-point observation sensing results, When the abnormal area detection means detects the abnormal area, a request transmission means transmits an abnormal area sensing request to a vehicle capable of sensing the abnormal area. Includes, The abnormal region sensing request includes the location of the abnormal region. Road monitoring equipment.
9. Computers The fixed-point observation sensing results are obtained from a fixed-point observation sensing means installed to sense the road. Based on the fixed-point observation sensing results, the abnormal area of the road is detected. When the aforementioned abnormal region is detected, an abnormal region sensing request is sent to a vehicle capable of sensing the abnormal region. The abnormal region sensing request includes the location of the abnormal region. Road monitoring method.
10. Computers A fixed-point observation sensing result acquisition means that acquires the fixed-point observation sensing results of a fixed-point observation sensing means installed to sense roads, An abnormal area detection means for detecting an abnormal area of the road based on the fixed-point observation sensing results, When the abnormal area detection means detects the abnormal area, a request transmission means transmits an abnormal area sensing request to a vehicle capable of sensing the abnormal area. To make it function as, The abnormal region sensing request includes the location of the abnormal region. program.
Citation Information
Patent Citations
Road monitoring system
JP1998091899A