Roadside sensor and information providing system

Abstract

To provide a roadside sensor and an information providing system having the roadside sensor, capable of surely restraining erroneous detection, while being a simple technique, in object detection.SOLUTION: In a road surface sensor 10, a detection part DT detects a target TG existing in a monitoring area DD on a road on the basis of the reflection intensity of light, a determination part JG determines whether or not there is an object on the road on the basis of the detection result of the detection part DT, and a communication device 52 reports the determination result of the determination part JG to the outside.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present invention relates to a roadside sensor that is installed, for example, near a road to sense objects that exist on the road and in its surroundings, and an information providing system that has the roadside sensor. [Background technology]

[0002] Regarding object detection, an object detection device (see Patent Document 1) is known that prevents erroneous detection of moving objects even when the position of the background changes by comparing the orientation of the object and the distance to the object with background definition information generated from information repeatedly acquired over time over the entire detection target area. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-95409 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the above-mentioned Patent Document 1, it is necessary to repeat detection in time series over the entire detection target area, which may result in a large information processing load.

[0005] The present invention has been made in consideration of the above-mentioned points, and aims to provide a roadside sensor and an information provision system having a roadside sensor that can reliably suppress false detections while using a simple method for object detection. [Means for solving the problem]

[0006] To achieve the above objective, the roadside sensor includes a detection unit that detects targets present in a monitoring area on the road based on the intensity of reflected light, and a determination unit that determines whether there are any objects on the road based on the detection results of the detection unit.

[0007] The roadside sensor uses the results of detecting targets on the road based on the intensity of reflected light as a reference point to confirm that there are no objects on the road, thereby easily and reliably preventing the sensor from determining that there are no objects when there are.

[0008] In a specific aspect of the present invention, the determination unit determines the presence or absence of an object on the road based on a change in the intensity of reflected light, using the state of light reflected by a target when there is no object as a reference. In this case, the presence or absence of an object on the road can be reliably determined based on the detection of the change in the intensity of reflected light.

[0009] In another aspect of the present invention, the detection unit has a distance measuring unit that measures distance by capturing a reflected component of light irradiated onto the monitoring area, and the distance measuring unit detects the reflection intensity of the light irradiated onto the high-reflection-intensity paint as a target. In this case, by detecting the reflection intensity of light from the high-reflection-intensity paint through distance measurement by the distance measuring unit, it is possible to accurately capture the reflected component of light for object detection.

[0010] In yet another aspect of the present invention, the determination unit determines the presence or absence of an object on the road based on the distance measurement result by the distance measurement unit of the detection unit and the light reflection intensity at the distance measurement point. In this case, accurate distance measurement enables quick and accurate determination of the presence or absence of an object.

[0011] In yet another aspect of the present invention, the determination unit determines whether or not there is an abnormality in the operation of the device itself based on the detection result of the detection unit, thereby making it possible to confirm whether or not the operation of the device itself is normal.

[0012] In yet another aspect of the present invention, a free space information generating unit is provided that generates free space information indicating a range of the monitoring area where no object is present when the determining unit determines that an object is present. In this case, for example, the traffic situation in the monitoring area can be accurately grasped.

[0013] To achieve the above object, an information providing system includes any one of the roadside sensors described above and a communication device that notifies the outside of the determination result of the determination unit.

[0014] In the above information provision system, by being equipped with the above roadside sensor, it is possible to easily and reliably prevent the system from determining that an object is not present when an object is actually present when detecting an object on the roadside, and to report the determination result from the determination unit of the roadside sensor to the outside. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram for explaining an outline of a roadside sensor and an information providing system including the roadside sensor according to an embodiment; [Figure 2] FIG. 1 is a block diagram showing an example of the configuration of an information providing system. [Figure 3] 10A to 10F are conceptual image diagrams for explaining how light is reflected by a target. [Figure 4] 1A to 1C are conceptual diagrams for explaining data acquisition and data processing by roadside sensors. [Figure 5] FIG. 1 is a block diagram for explaining an information providing system from a functional aspect. [Figure 6] 10(A) to 10(E) are conceptual diagrams for explaining detection of the presence or absence of an object based on the intensity of reflected light. [Figure 7] 10 is a flowchart illustrating a series of processes in an information providing system including a roadside sensor. [Figure 8] FIG. 10 is a block diagram for explaining a modified information providing system from a functional aspect. [Figure 9] FIG. 1 is a conceptual diagram for explaining an overview of an information providing system equipped with a roadside sensor. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of a roadside sensor according to an embodiment and an information provision system including the roadside sensor will be described below with reference to Fig. 1 etc. Fig. 1 is a conceptual diagram for providing an overview of a roadside sensor 10 according to this embodiment and an information provision system 100 including the roadside sensor 10, and shows an intersection CS on a road where the information provision system 100 is installed.

[0017] The information provision system 100 sets a predetermined range including the intersection CS and its surrounding area as a monitoring range for detecting traffic conditions. An example configuration will be described in detail later, but the information provision system 100 is an information provision device that uses LiDAR (Light Detection And Ranging) or the like to capture traffic conditions in the monitoring range and provide the acquired various information to an external party, and is equipped with a roadside sensor 10 and a control device 50.

[0018] In the information provision system 100, the roadside sensor 10 is an object detection device for obtaining information about objects present on the road RD and its surroundings, and includes a ranging unit 11, such as a LiDAR. The ranging unit 11 continuously (continuously) acquires point cloud data through ranging. One or more ranging units 11 may be provided depending on the monitoring range, etc. In the example shown in the figure, one ranging unit 11 is configured to monitor a predetermined area DD of a road upstream of an intersection CS. The one ranging unit 11 functions as a data acquisition unit that acquires data about moving objects MB present in the monitoring area DD. As will be described in detail with reference to FIG. 2 and other figures, the roadside sensor 10 performs various processes, such as calculations to determine the shape and moving speed of the moving object MB, based on the point cloud data about the moving object MB acquired by continuous ranging by the ranging unit 11, and is able to determine the type of the moving object MB based on the processing results. The roadside sensor 10 outputs to the control device 50 various pieces of information (target information) extracted from the point cloud data as described above.

[0019] Regarding the detection of the presence of a moving object MB as described above, particularly in this embodiment, the roadside sensor 10 uses LiDAR to illuminate the monitoring area DD, and detects the moving object MB in the monitoring area DD based on the reflection intensity of light reflected from a target TG formed by applying high-reflection-intensity paint on the road, i.e., the road RD, in addition to the moving object MB, and determines from the detection results whether an object is present on the road in the monitoring area DD.

[0020] The target TG can be painted, for example, the same color (black) as the asphalt that forms the road RD, so that it is not apparent that it has been painted. On the other hand, since the target TG has high reflection intensity, that is, it has high reflectivity against the light irradiation by the LiDAR, the roadside sensor 10 can distinguish the areas where the target TG has been painted from the moving object MB and other areas based on the reflection intensity value when receiving light.

[0021] The control device 50 of the information provision system 100 is composed of, for example, various circuit boards, and aggregates information about the moving object MB from the roadside sensor 10 described above and information from the signal controller SC that controls the four traffic lights TL installed at the intersection CS. Based on this information, the control device 50 integrates and organizes information about traffic conditions at the intersection CS and its surroundings and transmits it to various locations. In the illustrated example, the information provision system 100 functions as an information provision device (alarm device) by wirelessly outputting and transmitting various necessary data to an autonomous vehicle AD attempting to pass through the intersection CS, as well as to external devices such as a display device DS, such as a signage SN, installed at the intersection CS, or a traffic volume recording device TR. In other words, the control device 50 functions as an I2V (Infrastructure to Vehicle) control device that provides information from the infrastructure side to the vehicle side.

[0022] In the example shown in the figure, the information provision system 100 communicates with the autonomous vehicle AD as it passes through an intersection CS and provides driving assistance information (such as information about blind spots that cannot be seen from the autonomous vehicle AD) from among the various pieces of information it has acquired, thereby functioning as a driving assistance device. More specifically, in the figure, the autonomous vehicle AD is attempting to enter the intersection CS from a direction opposite to the monitoring area DD and make a right turn, as indicated by the dashed arrow AR1. This direction intersects with the direction of travel of a moving object MB traveling straight from the monitoring area DD. The information provision system 100 recognizes this situation through two-way wireless communication. In this case, it is extremely important for traffic safety that the information provision system 100 accurately communicates the traffic conditions in the monitoring area DD to the autonomous vehicle AD as early as possible. In particular, in this embodiment, the roadside sensor 10 determines whether the road (road RD) is free of objects based on the detection of the light reflection intensity of the target TG, and the result is included in the target information provided by the information provision system 100. This makes it possible to easily and reliably prevent the roadside sensor 10 from judging that an object is not present when it is actually present, and to externally notify the roadside sensor 10 of the judgment result. On the other hand, the information provision system 100 can also be said to accurately detect when an object is not present, that is, to reliably identify empty spaces, safe spaces, and free spaces.

[0023] Hereinafter, the functional aspects of each component of the information provision system 100 will be described with reference to the block diagram shown in Fig. 2. As shown in the figure, in this example, the roadside sensor 10 of the information provision system 100 includes a data processing device DU that processes various types of data, in addition to a distance measurement unit 11. The control device 50 also includes a main control unit 51 that processes various types of data, and a communication device 52 that functions as a notification unit AN by communicating with the outside.

[0024] First, of the roadside sensor 10, the ranging unit 11 is composed of, for example, a laser, a galvanometer mirror, a polygon mirror, etc., and as mentioned above, performs sensing by optical scanning of the monitoring area DD, and as a data acquisition unit, is capable of acquiring point cloud data as ranging data necessary to understand the situation of targets TG and moving bodies MB present in the monitoring area DD.

[0025] Furthermore, the data processing device DU of the roadside sensor 10 is composed of various electronic circuit elements, etc., and analyzes the point cloud data acquired by the distance measurement unit 11 to extract target information about the moving object MB, such as the position, traveling direction, and traveling speed of the moving object MB. In addition, particularly in this embodiment, as described above, the data processing device DU also captures the targets TG painted on the road RD, thereby making it possible to easily, quickly, and reliably determine the presence or absence of the moving object MB. Note that an example of the configuration for data analysis and extraction in the data processing device DU will be described later with reference to Figures 4 and 5.

[0026] Next, the main control unit 51 of the control device 50 is composed of various electronic circuit elements and performs processes such as collecting and analyzing information to be reported to the outside as part of the information provision system 100. In the example shown in FIG. 1 , the main control unit 51 is connected to a roadside sensor 10, which is an internal device, and a signal controller SC, which is an external device. The main control unit 51 acquires target information, which is information about moving objects MB, from the roadside sensor 10, and light color information, which is information about signal lights TL (see FIG. 1), from the signal controller SC. The main control unit 51 processes and edits the collected information to suit the destination (autonomous vehicle AD, signage SN, traffic volume recording device TR), and outputs it via a communication device 52 (announcement unit AN), which is an interface with external devices. For example, it is conceivable to provide the autonomous vehicle AD with information such as the entry status of moving objects MB into an intersection CS from an oncoming lane or the timing of switching on and off the signal lights TL, the signage SN with information about the possibility of hazards occurring due to traffic conditions, and the traffic volume recording device TR with information such as the number (number of people) of each type of moving objects MB.

[0027] Hereinafter, an overview of sensing of a target TG on a road RD in a monitoring area DD by the roadside sensor 10 will be described with reference to the conceptual image diagrams shown in FIGS. 3(A) to 3(F).

[0028] In Figures 3(A) to 3(F), each image G1 to G6 shows the state of the monitoring area DD as seen (distance measured) from the installation location of the roadside sensor 10 (see Figure 1), and here, in particular, the changes that occur when reflected light is received from a target TG installed on the road RD within the monitoring area DD are shown.

[0029] First, image G1 in Fig. 3(A) shows the appearance without taking into consideration distance measurement by the roadside sensor 10 (see Fig. 1). As mentioned above, the target TG is painted in the same color as the road RD in the monitoring area DD and is not visually distinguishable, so it is shown with a dashed line in the illustration. In contrast, as shown by hatching in image G2 shown in Fig. 3(B), the area that receives the reflected component of light irradiated onto the target TG can be captured as a partial image RR corresponding to the target TG by applying appropriate data processing.

[0030] To give a more specific example, in a state where no object is present on the road RD as shown in image G3 in Fig. 3(C), a partial image RR corresponding to the entire target TG is extracted as shown in image G4 in Fig. 3(D). Here, by making the reflectance of the target TG particularly high with respect to the light (scanning light) irradiated by the distance measuring unit 11, it becomes possible to distinguish the target TG from other parts, such as white lines on the road, based on the received light intensity at the time of light reception. That is, by setting an appropriate threshold for the received light intensity in advance according to the high reflectivity characteristics of the target TG and extracting areas where the received light intensity is higher than the threshold, it becomes possible to extract only the partial image RR corresponding to the target TG as shown in image G4.

[0031] By adopting the above-described embodiment, for example, in a state where a moving object MB exists on the road RD as shown in image G5 of Fig. 3(E) (in the illustrated example, vehicles VE1 and VE2 exist as the moving objects MB), a partial image RR is extracted in a state where the portion obscured by the moving objects MB (vehicles VE1 and VE2) is omitted, as shown in image G6 of Fig. 3(F). Looking at it from another perspective, data for a case where it is known that the state is as shown in image G4 of Fig. 3(D) is prepared in advance as a reference, and then, when a state different from the reference state, such as image G6 of Fig. 3(F), is captured, this can be compared with data showing the reference state (reference image), and the presence or absence of a moving object MB such as a vehicle can be determined from the situation when the target TG was captured.

[0032] Hereinafter, data acquisition and data processing by the roadside sensor 10 will be described with reference to the conceptual diagrams shown in FIGS. 4(A) to 4(C).

[0033] First, as shown in FIG. 4(A), the distance measurement unit 11 of the roadside sensor 10 has a laser 11L that emits irradiated light IL and a light receiving element 11R that receives reflected light RL that is a reflected component of the irradiated light IL.

[0034] Here, the laser 11L optically scans the entire monitoring area DD, including the road RD, and is capable of detecting the direction of emission of the irradiated light IL. The light-receiving element 11R receives the component of the irradiated light IL that hits the object OB and returns, thereby receiving the component of the reflected light RL corresponding to the irradiated light IL. For example, the laser 11L emits a pulsed light (pulsed light 1) in a known direction (orientation) that is predefined according to time. The time taken for the reflected component (reflected component 2) corresponding to the emitted pulsed light 1 to be received by the light-receiving element 11R is measured, thereby obtaining data on the time difference between the light emission and the light reception. Furthermore, during the time measurement, the received intensities of pulsed light 1 and reflected component 2 are also measured, as shown in the graph of FIG. 4(B). Of these, a threshold is set in advance for reflected component 2, and if the value of reflected component 2 is greater than the threshold, it is assumed to be a component reflected by target TG.By combining this with information on distance and direction (azimuth), it becomes possible to extract partial image RR corresponding to target TG, as exemplified in image G4 in Figure 3(D) and image G6 in Figure 3(F).

[0035] A series of operations performed by the roadside sensor 10 described above will be summarized below with reference to the functional block diagram shown in FIG. 4(C).

[0036] First, as described above, in accordance with the light reception result at the light receiving element 11R, the data processing device DU acquires data on the time difference (acquires time difference TS1) and also acquires data on the intensity of received light (acquires received light intensity RS1).

[0037] First, after time difference acquisition TS1, the data processing device DU calculates the distance to the object OB based on the time difference (distance calculation TS2) and accumulates the distance data as the calculation result (distance data accumulation TS3). Note that the distance data accumulated here is not limited to distance data corresponding to the target TG, but also includes distance data for the moving object MB. Furthermore, based on the accumulated distance data, a detection process (object detection TS4) is performed on the position of the road RD on which the target TG is located and the position (displacement) of the moving object MB.

[0038] Meanwhile, after receiving light intensity acquisition RS1, the data processing device DU compares the received light intensity with a threshold (threshold comparison RS2) and accumulates light intensity data as the comparison result (light intensity data accumulation RS3). Furthermore, based on the accumulated light intensity data, a process is performed to extract the range of the target TG (i.e., partial image RR in FIG. 3) (target range extraction RS4), and the extracted range is compared (verified) with a reference image for the target TG RS5. That is, the range of the target TG extracted in target range extraction RS4 (partial image RR) is compared with a reference image in which no moving object MB is present, and the presence or absence of a moving object MB in the monitoring area DD is determined. The object detection results and target verification results obtained as a result of the above processes are transmitted (output) from the roadside sensor 10.

[0039] Hereinafter, with reference to the block diagram shown in Fig. 5, a detailed description will be given of an example configuration of the roadside sensor 10 of the information provision system 100 for performing the series of data processing outlined with reference to Fig. 4(C). Therefore, in particular, a description will be given here of an example configuration of the data processing device DU.

[0040] As shown in FIG. 5, in the roadside sensor 10, the data processing device DU has a mobile object information management unit MM and a target information management unit TM in addition to a data reception unit DR.

[0041] Of these, the data receiving unit DR receives point cloud data of the moving object MB from the distance measuring unit 11. In other words, the data processing device DU receives, from the distance measuring unit 11, information on the direction and timing of the emitted light, as well as the corresponding light reception result, as point cloud data.

[0042] Hereinafter, with reference to the mobile object information management unit MM, the handling of data relating to the mobile object MB based on the calculated distance data will be described.

[0043] The mobile object information management unit MM comprises or functions as a distance image processing unit DP (object detection processing unit OD), an ID assignment unit IG, a speed calculation unit VC, a vehicle type identification unit VI, and a mobile object data storage unit MS.

[0044] First, when the mobile object information manager MM receives point cloud data from the data receiver DR, the distance image processor DP performs processing to generate a distance image of the mobile object MB. That is, imaging (distance imaging) processing is performed to enable identification (individualization) of each mobile object MB from the point cloud data. Here, the distance image processor DP also functions as an object detection processor OD that performs object detection to individually identify each mobile object MB in the distance image, i.e., to extract a portion corresponding to each mobile object MB from the generated distance image. Note that, as described above, ranging in the ranging unit 11 is performed continuously. Accordingly, the distance image generation and object detection processing in the distance image processor DP are performed sequentially on a frame-by-frame basis for the ranging data (point cloud data) acquired through continuous operation.

[0045] Furthermore, an ID is assigned to each moving object MB in the above-mentioned distance image by the ID assigning unit IG. The identity of each moving object MB is determined based on its shape characteristics and the relative positional relationship between the distance images generated successively. That is, once the ID assigning unit IG assigns an ID corresponding to the shape characteristics to an object corresponding to a moving object MB extracted by processing in the distance image processing unit DP (object detection processing unit OD), the identity can be confirmed by checking for the presence of an object in subsequent distance images that has the shape characteristics corresponding to the assigned ID, making it possible to track the moving object MB between successive images.

[0046] For each object detected in the range image generated by the range image processor DP, i.e., for each identified moving object MB, the speed calculation unit VC calculates the moving speed of each moving object MB. That is, for moving object MBs that have been assigned IDs based on shape features and whose identity has been confirmed between successive images, the speed calculation unit VC calculates vector values ​​such as the moving speed and direction of travel of the moving object MB by comparing the displacement (difference in position change) between the images. In other words, the speed calculation unit VC determines the identity of the moving object MB to which an ID has been assigned based on shape features, and calculates the moving speed of the moving object MB based on the displacement between successively acquired data for the same moving object MB.

[0047] The vehicle type identification unit VI identifies the vehicle type of the moving object MB based on its shape characteristics and moving speed. In this example, the vehicle type identification unit VI classifies the moving object MB into a large vehicle, a standard vehicle, a bicycle, or a pedestrian based on the individual shape characteristics of the individual moving object MB. In other words, various parameters related to shape and dimensions, and criteria such as their thresholds, are determined in advance, and vehicle type identification is performed according to the determined criteria.

[0048] Next, with reference to the target information management unit TM, the handling of data relating to the target TG based on the calculated light intensity data will be described.

[0049] The target information management unit TM comprises or functions as a reflection intensity determination unit RJ (detection unit DT), a target matching unit TC (verification unit VR), an object presence / absence determination unit MJ (determination unit JG), a free space determination unit VJ, a free space information generation unit VG, and a target data storage unit TS.

[0050] First, when the target information management unit TM receives point cloud data from the data receiving unit DR, light intensity data is extracted. Based on the light intensity data, the reflection intensity determination unit RJ compares the intensity of the received reflection component with a predetermined threshold value to determine whether the reflection component originates from the target TG. In other words, it detects whether the reflection component corresponds to the reflection intensity of light (illumination light IL in FIG. 4) irradiated onto the high-reflection paint serving as the target TG. As described above, the reflection intensity determination unit RJ functions as a detection unit DT that detects targets TG present in the monitoring area DD based on the reflection intensity of light, in cooperation with the distance measurement unit 11.

[0051] Next, the target matching unit TC (verification unit VR) compares (verifies) the judgment result of the reflection intensity judgment unit RJ, i.e., the range where the reflection component from the target TG is confirmed (corresponding to the partial image RR in Figure 3), with the reference image of the target TG. For the above comparison (verification), the target matching unit TC reads out the reference image of the target TG, which shows a state where no object is present, from the reference image data storage unit SG of the target data storage unit TS.

[0052] The object presence / absence determination unit MJ determines whether or not there is an object, particularly whether or not there is a moving body BM on the road RD, based on the result of matching (verification) in the target matching unit TC (verification unit VR). That is, based on the result of matching (verification) for the target TG, it determines whether or not a vehicle or the like exists depending on the range determined to be occluded. In particular, the object presence / absence determination unit MJ, as a determination unit JG, determines whether or not there is an object on the road based on the detection result in the target matching unit TC (verification unit VR).

[0053] From another perspective, in a state where the position where the moving body BM exists and the position where it does not exist are identified based on the determination by the object presence / absence determination unit MJ, the empty space determination unit VJ determines the empty space on the road RD. A typical example of empty space is one that indicates the availability of space ahead of the vehicle (the direction of travel) as the moving body BM (hereinafter, various information indicating the availability of space is referred to as empty space information). Note that the empty space information is important information for determining whether safety can be ensured for an oncoming vehicle (see the autonomous vehicle AD in Figure 1) that is about to cross the monitoring area DD, for example.

[0054] The free space information generating unit VG generates free space information based on the radius result from the free space determining unit VJ.

[0055] Information on the results of various judgments and comparisons (verifications) regarding the target TG performed as described above, and also information regarding the monitoring area DD, are stored in the target data storage unit TS and are output (transmitted) to the control device 50 as target information together with the point cloud data.

[0056] In addition, in the above, the data processing device DU can also make a judgment while taking into account both the items managed by the mobile information management unit MM and the items managed by the target information management unit TM, and for example, it is possible for the judgment unit JG to determine the presence or absence of an object on the road based on the results of distance measurement by the distance measurement unit 11 that constitutes the detection unit DT and the reflection intensity of light at the distance measurement location.

[0057] Detection of the presence or absence of an object based on the intensity of reflected light will be described below with reference to the conceptual diagrams shown in FIGS. 6(A) to 6(E).

[0058] Fig. 6(A) is a conceptual diagram showing the state of the monitoring area DD when there is no object, while Fig. 6(B) is a conceptual diagram showing the state of the monitoring area DD when there is an object, more specifically, when there are two vehicles VE (VE1, VE2) as moving bodies MB. In the example shown, on a two-lane road RD, targets TG are evenly and uniformly painted with high reflective paint on each lane.

[0059] 6(B), the points indicating the positions of the vehicles VE1, VE2 as the moving bodies MB in the direction of travel, i.e., the sides closest to the roadside sensor 10, are defined as start points SS1, SS2, and the point indicating the position of the road RD (target GT) in the direction of travel from the start points SS1, SS2 that is closest to the roadside sensor 10 is defined as end point ED. The vacant spaces VS1, VS2 formed ahead of the vehicles VE1, VE2 are calculated based on the start points SS1, SS2 and end point ED.

[0060] First, in a situation where there is no moving object MB, for example, as shown in Fig. 6(A), the roadside sensor 10 performs various processes to acquire an image Gα, for example, as shown in Fig. 6(C), which shows the target TG based on the light reflection intensity. That is, a partial image RR is obtained as a result of capturing the entire target TG without any obstructions, and it is determined from this that there is no object.

[0061] On the other hand, in a situation like that shown in Figure 6(B), for example, an image Gβ as shown in Figure 6(D) is acquired as showing the target TG. That is, within the range where the target TG should be detected, a partial image RR is obtained in which the areas corresponding to the vehicles VE1 and VE2 are occluded and not detected, resulting in defective areas SA1 and SA2. From this, it is determined that there is an object in the defective areas SA1 and SA2. Furthermore, as shown in Figure 6(E), the positions of the start points SS1 and SS2 shown in Figure 6(B) are calculated based on the defective areas SA1 and SA2 on the image Gβ, and the corresponding end point ED is also calculated, and the empty spaces VS1 and VS2 are calculated.

[0062] In this way, the presence or absence of an object is detected based on the intensity of reflected light, and empty space (empty space information) is generated based on this detection. The empty space information is also transmitted to the outside as part of the target information, for example, via the antenna AT constituting the communication device 52 of the information providing system 100.

[0063] A series of processes in the information providing system 100 equipped with the roadside sensor 10 as described above will be described below with reference to the flowchart shown in FIG.

[0064] In the roadside sensor 10 of the information providing system 100, when point cloud data, which is the light reception result at the distance measurement unit 11, is received as an information source including information on reflection intensity and information on time difference as a distance-related information, etc., by each unit constituting the data processing device DU for performing data processing (step S101), a detection process for a target TG on the road surface, i.e., the road RD, is started (step S102). Specifically, when the distance measurement is from a direction in which reflection from the target TG can be detected, a judgment is made based on the received reflection intensity (step S103), and when the judgment result shows that the reflection intensity is equal to or greater than a predetermined threshold indicating that the reflection component is from the target TG (step S104: Yes), the target TG is treated as having been detected, that is, it is judged that the reflection component from the road RD has been detected and that there is no object (such as an object MB) (step S105).

[0065] On the other hand, if the difference is not equal to or greater than the predetermined threshold in step S104 (step S104: No), the target TG is treated as not being detected, that is, it is determined that an object is present (obscured by an object) (step S106).

[0066] After step S105 or step S106, the roadside sensor 10 performs an empty space determination according to the detection result for the target TG (step S107). The information providing system 100 transmits (outputs) empty space information according to the result of the empty space determination in step S107 via the communication device 52 (step S108).

[0067] The information providing system 100 including the roadside sensor 10 repeats the series of processes exemplified in steps S101 to S108.

[0068] Hereinafter, a functional aspect of the information provision system 100 of one modified example will be described with reference to the block diagram shown in Fig. 8. Note that Fig. 8 corresponds to Fig. 5, and differs from the example shown in Fig. 5 in that the data processing device DU has an abnormality detection unit EE, as shown in the figure.

[0069] The anomaly detection unit EE performs various anomaly detections by referring to information about the target TG and information about each moving object MB obtained through various processes on the point cloud data from the distance measurement unit 11. For example, the anomaly detection unit EE detects (verifies) whether an anomaly has occurred in the roadside sensor 10's sensing, such as whether the range of light received from the target TG is unexpected, or whether there are any areas where reflected components cannot be detected for a certain period of time. Other possible detections by the anomaly detection unit EE include reading deterioration of the paint that constitutes the target TG from changes in reflection intensity over time, and detecting whether road surface anomalies (topographical changes) due to earthquakes or other events from changes in the detection range. Furthermore, the anomaly detection unit EE may also detect deterioration of road conditions (potholes and white lines).

[0070] The abnormality detection unit EE can be provided as part of the judgment unit JG, and in this case, for example, the judgment unit JG can be configured to determine whether or not there is an abnormality in its own operation based on the detection results of the detection unit DT.

[0071] In addition, various abnormalities detected by the abnormality detection unit EE may be provided to an external device, for example, a road administrator (management center) that comprehensively manages roads over a wide area, as information to be transmitted from multiple roadside sensors 10.

[0072] The following will summarize and explain an overview of the roadside sensor 10 and the information providing system 100 including the roadside sensor 10, with reference to a conceptual diagram shown in FIG.

[0073] First, as already described and as shown in the figure, the roadside sensor 10 of this embodiment detects a target TG present in the monitoring area DD on the road based on the reflection intensity of light in the detection unit DT, and then determines in the judgment unit JG whether or not there is an object on the road based on the detection result in the detection unit DT.

[0074] Furthermore, the information providing system 100 including the roadside sensor 10 causes the communication device 52 to report the determination result of the determination unit JG to the outside.

[0075] As described above, the roadside sensor 10 of this embodiment and the information provision system 100 equipped with the same can easily and reliably suppress erroneous detections in which an object is determined to be absent when it is actually present, by using the results of detection of a target TG present on the road based on the reflection intensity of light as a reference and confirming that there is no object on the road, and the information provision system 100 can also report the judgment result of the judgment unit JG of the roadside sensor 10 to the outside.

[0076] 〔others〕 The present invention is not limited to the above-described embodiment, and can be embodied in various forms without departing from the spirit and scope of the present invention.

[0077] First, among the above, the application range and application manner of the target TG are not limited to the above example and can be variously applied, and for example, the target TG may be configured to have a higher reflectivity as it is located farther from the installation location of the roadside sensor 10 (distance measuring unit 11). Also, in the above example, the high reflective paint to become the target TG is applied evenly and uniformly over the road RD, but as long as sufficient accuracy in detecting the presence or absence of an object can be maintained, the present invention is not limited to this, and for example, the target TG may be provided with gaps on the road RD.

[0078] Furthermore, in the above embodiment, the roadside sensor 10 including the data processing device DU is described as being provided in the information provision system 100, but the present invention is not limited to this. For example, it is also conceivable to store analyzed data in the data processing device DU and use the stored data when analyzing, for example, when an accident or the like occurs. Note that, for the accident analysis described above, it is also conceivable to install only a device equivalent to the distance measurement unit 11 capable of acquiring distance measurement data at the site where the information provision system 100 is installed, transmit the distance measurement data from the site to an external device such as a traffic volume recorder TR, and provide a data processing device DU in the traffic volume recorder TR or the like to perform the necessary data processing.

[0079] Furthermore, it is also conceivable that the distance measurement data (point cloud data) and various information obtained as a result of analyzing this data may be managed and processed in the cloud.

[0080] In the above description, the location where the information provision system 100 is installed is an intersection CS, but the location is not limited to this and the system can be installed in various other locations. For example, the present invention can be applied to a monitoring area DD that includes a lane junction or a lane change section.

[0081] Furthermore, the shape of the intersection CS is merely an example, and is not limited to this and can be applied to cases with various shapes and structures. [Explanation of symbols]

[0082] 10...roadside sensor, 11...distance measuring unit, 11L...laser, 11R...light receiving element, 50...control device, 51...main control unit, 52...communication device, 100...information provision system, AD...autonomous driving vehicle, AN...alarm unit, AR1...arrow, AT...antenna, BM...moving body, CS...intersection, DD...monitoring area, DP...distance image processing unit, DR...data reception unit, DS...display device, DT...detection unit, DU...data processing device, ED...end point, EE...anomaly detection unit, G1-G6, Gα, Gβ...image, GT...target, IG...ID assignment unit, IL...irradiated light, JG...judgment unit, MB...moving body, MJ...object presence / absence judgment unit, MM...moving body information management unit, MS...moving body data storage unit, OB...target, OD...object detection processing unit, RD...road, RJ...reflection intensity judgment unit, RL ...reflected light, RR...partial image, RS1...received light intensity, RS2...threshold comparison, RS3...light intensity data accumulation, RS4...target range extraction, RS5...comparison with reference image (verification), SA1, SA2...missing area, SC...signal controller, SG...reference image data storage unit, SN...signage, SS1, SS2...starting point, TC...target comparison unit, TG...target, TL...signal lamp, TM...target information management unit, TR...traffic volume recording device, TS...target data storage unit, TS1...time difference acquisition, TS2...distance calculation, TS3...distance data accumulation, TS4...object detection, VC...speed calculation unit, VE, VE1, VE2...vehicle, VG...vacant space information generation unit, VI...vehicle type identification unit, VJ...vacant space determination unit, VR...verification unit, VS1, VS2...vacant space

Claims

1. a detection unit that detects targets present in a road surveillance area based on the intensity of reflected light; a determination unit that determines whether there is an object on the road based on the detection result of the detection unit; A roadside sensor comprising:

2. The roadside sensor according to claim 1 , wherein the determining unit determines the presence or absence of an object on the road based on a change in the intensity of reflected light, using the state of light reflected by the target in a state where no object is present as a reference.

3. The roadside sensor of claim 1, wherein the detection unit has a ranging unit that captures the reflected component of light irradiated onto the monitoring area and measures the distance, and the ranging unit detects the reflection intensity of light irradiated onto high-reflection-strength paint as the target.

4. The roadside sensor according to claim 3 , wherein the determination unit determines the presence or absence of an object on the road based on a result of distance measurement by the distance measurement unit of the detection unit and a reflection intensity of light at a distance measurement point.

5. The roadside sensor according to claim 1 , wherein the determination unit determines whether or not there is an abnormality in the operation of the roadside sensor itself based on the detection result of the detection unit.

6. The roadside sensor according to claim 1 , further comprising: a free space information generating unit that generates free space information indicating a range of the monitoring area where no object is present when the determining unit determines that an object is present.

7. A roadside sensor according to any one of claims 1 to 6; a communication device that notifies the outside of the determination result in the determination unit; An information provision system comprising:

Images