Control device, control system, control method, and program

Abstract

To provide a control device, a control system, a control method, and a program that can expand an area in which detection accuracy can be ensured when detecting a front and rear of a vehicle using each of sensors.SOLUTION: A control device comprises: a first acquisition unit that acquires first tracking data obtained by a first sensor that detects a rear surface shape of a vehicle traveling in a traffic lane from a first direction; a second acquisition unit that acquires second tracking data obtained by a second sensor that detects a front surface shape of the vehicle from a second direction different from the first direction; and a threshold value adjusting unit that lowers a threshold value for acquisition of tracking data by the other sensor based on the tracking data of one of the first sensor and the second sensor.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a control device, a control system, a control method, and a program. [Background technology]

[0002] It is known that a vehicle traveling in a lane is detected by a sensor installed from the roadside facing the lane direction.

[0003] For example, Patent Document 1 discloses that the width, height, and length of a vehicle are obtained based on detection information from a first sensor that detects a vehicle traveling in a lane from a first direction and a second sensor that detects the vehicle from a second direction different from the first direction. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2022-157795 Summary of the Invention [Problem to be solved by the invention]

[0005] Typically, these sensors that detect vehicles are installed on the roadside and perform sensing from the roadside in the direction of the lane. However, the accuracy of the sensor's object detection decreases as the distance between the sensor and the vehicle increases. Therefore, if two sensors are used to detect vehicles from different directions, the area in which each sensor can ensure detection accuracy when detecting the front and rear of the vehicle is limited.

[0006] An object of the present disclosure is to provide a control device, a control system, a control method, and a program that can expand the area in which detection accuracy can be ensured when each sensor detects the front and rear of a vehicle. [Means for solving the problem]

[0007] The control device of the present disclosure includes a first acquisition unit that acquires first tracking data obtained by a first sensor that detects the rear shape of a vehicle traveling in a lane from a first direction, a second acquisition unit that acquires second tracking data obtained by a second sensor that detects the front shape of the vehicle from a second direction different from the first direction, and a threshold adjustment unit that lowers the threshold for acquisition of tracking data by one of the first and second sensors based on the tracking data from the other sensor.

[0008] The control method disclosed herein includes the steps of acquiring first tracking data obtained by a first sensor that detects the rear shape of a vehicle traveling in a lane from a first direction, acquiring second tracking data obtained by a second sensor that detects the front shape of the vehicle from a second direction different from the first direction, and lowering a threshold for acquiring tracking data by one of the first and second sensors based on the tracking data from the other sensor.

[0009] The program disclosed herein is a program for causing a computer to execute the following steps: acquiring first tracking data obtained by a first sensor that detects the rear shape of a vehicle traveling in a lane from a first direction; acquiring second tracking data obtained by a second sensor that detects the front shape of the vehicle from a second direction different from the first direction; and lowering a threshold for acquiring tracking data by one of the first and second sensors based on the tracking data from the other sensor. [Effects of the Invention]

[0010] According to the control device, control system, control method, and program of the present disclosure, it is possible to expand the area in which the detection accuracy can be ensured when each sensor detects the front and rear of the vehicle. [Brief explanation of the drawings]

[0011] [Figure 1]1 is an overall view of a control system according to a first embodiment of the present disclosure. [Figure 2] FIG. 2 is a diagram illustrating an example of a detection range of a first sensor according to the first embodiment of the present disclosure. [Figure 3] FIG. 4 is a diagram illustrating an example of a detection range of a second sensor according to the first embodiment of the present disclosure. [Figure 4] FIG. 2 is a diagram illustrating an example of overlapping detection ranges of a first sensor and a second sensor according to the first embodiment of the present disclosure. [Figure 5] FIG. 10 is an explanatory diagram I for lowering the threshold for acquiring tracking data from the second sensor by the control device according to the first embodiment of the present disclosure. [Figure 6] FIG. 2 is an explanatory diagram II for lowering the threshold for acquiring tracking data from the second sensor by the control device according to the first embodiment of the present disclosure. [Figure 7] FIG. 3 is an explanatory diagram III for lowering the threshold for acquiring tracking data from the second sensor by the control device according to the first embodiment of the present disclosure. [Figure 8] FIG. 10 is an explanatory diagram I for lowering a threshold for acquisition of tracking data from a first sensor by a control device according to a first embodiment of the present disclosure. [Figure 9] FIG. 2 is an explanatory diagram II for lowering the threshold for acquiring tracking data from the first sensor by the control device according to the first embodiment of the present disclosure. [Figure 10] FIG. 3 is an explanatory diagram III for lowering the threshold for acquiring tracking data from the first sensor by the control device according to the first embodiment of the present disclosure. [Figure 11] 4 is a flowchart illustrating an example of a process of a control method according to the first embodiment of the present disclosure. [Figure 12] FIG. 1 is a hardware configuration diagram illustrating a configuration of a computer according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, each embodiment of the present disclosure will be described with reference to the drawings. Note that the drawings and specific configurations used in each embodiment should not be used to interpret the disclosure. The same or corresponding configurations in all drawings will be assigned the same reference numerals, and common descriptions will be omitted.

[0013] FIG. 1 is an overall diagram of a control system according to a first embodiment of the present disclosure. FIG. 2 is a diagram illustrating an example of a detection range of a first sensor according to the first embodiment of the present disclosure. FIG. 3 is a diagram illustrating an example of a detection range of a second sensor according to the first embodiment of the present disclosure. FIG. 4 is a diagram illustrating an example of overlapping detection ranges of a first sensor and a second sensor according to the first embodiment of the present disclosure. FIGS. 5 to 7 are explanatory diagrams for lowering a threshold for acquisition of tracking data by a second sensor by a control device according to the first embodiment of the present disclosure. FIGS. 8 to 10 are explanatory diagrams for lowering a threshold for acquisition of tracking data by a first sensor by a control device according to the first embodiment of the present disclosure. FIG. 11 is a flowchart illustrating an example of processing of a control method according to the first embodiment of the present disclosure. FIG. 12 is a hardware configuration diagram illustrating a configuration of a computer according to the present disclosure.

[0014] The control device according to the present disclosure will be described below with reference to FIGS.

[0015] (Control system configuration) FIG. 1 is a diagram showing the configuration of a control system according to the first embodiment. As shown in FIG. 1, the control system 1 includes a first sensor 11, a second sensor 12, and a control device 13. The control system 1 and control device 13 of the present disclosure are used to lower the threshold for acquiring tracking data from one of two sensors that detect a vehicle VV from different directions, based on the tracking data from the other sensor. The control device 13 is communicably connected to the first sensor 11 and the second sensor 12 via a dedicated communication line or a public communication line.

[0016] Each of the multiple vehicles VV to be detected is traveling on a road RR along the X direction. The road RR may be, for example, a main road such as an expressway. For example, the road RR may have multiple lanes LL on one side. For the sake of simplicity, the direction in which the road RR extends in this disclosure is approximately the same as the X direction. The Y direction is the width direction of the road. The Z direction is the direction pointing upward from the road RR.

[0017] For example, at least one of the vehicles VV may be an autonomous vehicle.

[0018] The first sensor 11 and the second sensor 12, which will be described in detail, are installed on the roadside of the road RR and perform sensing from the roadside toward the lane direction. For example, the first sensor 11 and the second sensor 12 may be installed at approximately the same height.

[0019] (Configuration of the first sensor) The first sensor 11 detects the shape of the rear surface of each vehicle VV traveling on the lane LL from a first direction. For example, the first direction is the X direction. For example, as shown in Fig. 2, the first sensor 11 acquires image data from a position overlooking a predetermined area UA of a road RR including a plurality of vehicles VV, and acquires first tracking data TD1 from the image data. Alternatively, the first sensor 11 may repeatedly capture images at predetermined times to acquire multiple pieces of tracking data over different times.

[0020] The first sensor 11 is an area sensor capable of detecting three-dimensional information. Examples of area sensors include LiDAR (Light Detection And Ranging), cameras, etc. Image data acquired by the first sensor includes point cloud data of an object. Distance information between the first sensor and the object is acquired from this point cloud data. The first sensor 11 is installed on the upstream side (X=A) of the road RR relative to the second sensor 12.

[0021] As the distance between the first sensor 11 and each vehicle increases, that is, as the vehicle is positioned closer to the downstream side (X=B), the accuracy of detection of the object as point cloud data by the first sensor 11 decreases.

[0022] (Configuration of the second sensor) The second sensor 12 detects the front shape of each vehicle in the vehicle group VV from a second direction. The second direction is different from the first direction. For example, the second direction is the opposite direction (-X direction) to the first direction. For example, as shown in Fig. 3, the second sensor 12 acquires image data from a position overlooking a predetermined area DA of a road RR including a plurality of vehicles VV, and acquires second tracking data TD2 from the image data. Alternatively, the second sensor 12 may repeatedly capture images at predetermined times to acquire multiple pieces of tracking data over different times.

[0023] For example, the second sensor 12 is an area sensor capable of detecting three-dimensional information, similar to the first sensor 11. Examples of area sensors include LiDAR (Light Detection And Ranging), cameras, etc. Image data acquired by the second sensor includes point cloud data of an object. Distance information between the second sensor and the object is acquired from this point cloud data. The second sensor 12 is installed on the downstream side (X=B) of the road RR relative to the first sensor 11.

[0024] If the distance between the second sensor 12 and each vehicle is large, that is, if the vehicle is located near the upstream side (X=A), the accuracy of object detection by the second sensor 12 decreases.

[0025] For example, the X direction of the predetermined areas (predetermined areas UA, DA) overlooked by the first sensor 11 and the second sensor 12 may be set to be areas that can accommodate multiple vehicles VV traveling on the road RR. For example, the Y direction of the predetermined areas (predetermined areas UA and DA) overlooked by the first sensor 11 and the second sensor 12 may be set to be areas that accommodate a plurality of lanes LL.

[0026] In the present disclosure, the first sensor 11 and the second sensor 12 are installed so that the predetermined area UA and the predetermined area DA overlap. When each vehicle is located at a position as shown in Figure 4, vehicles having the same vehicle ID in both the first tracking data TD1 and the second tracking data TD2 are present in the specified area UA and the specified area DA, respectively, and are determined to be in the same position or approximately the same position on the road RR.

[0027] The first tracking data TD1 and the second tracking data TD2 consist of a vehicle ID (an identifier for uniquely identifying a vehicle) and vehicle information indicating the position of the vehicle, the speed of the vehicle, the acceleration of the vehicle, or the direction of movement of the vehicle. The first tracking data TD1 is based on the position of the rear surface shape of the vehicle. The second tracking data TD2 is based on the position of the front shape of the vehicle.

[0028] Hereinafter, when there is no particular distinction between the first tracking data TD1 and the second tracking data TD2, they will simply be referred to as tracking data.

[0029] (Vehicle information calculated from information acquired by the first sensor) By subjecting image data of a predetermined area UA of a road RR including a plurality of vehicles VV to coordinate transformation, an image showing the rear shape of each vehicle as viewed from a first direction can be acquired. From this image, the width and height of each vehicle are calculated.

[0030] (Vehicle information calculated from information acquired by the second sensor) By subjecting image data of a predetermined area DA of a road RR including a plurality of vehicles VV to coordinate transformation, an image showing the front shape of each vehicle as viewed from a first direction can be acquired. From this image, the width and height of each vehicle are calculated.

[0031] 4 again, the first sensor 11 and the second sensor 12 are installed so that the predetermined area UA and the predetermined area DA overlap. For vehicles located on the road RR within the range SC near the midpoint between the upstream side (X=A) and the downstream side (X=B), the vehicle length of each vehicle can be obtained by obtaining the distance between each sensor and each vehicle from the image data obtained by each sensor.

[0032] The detection accuracy of the first sensor 11 and the second sensor 12 for detecting a vehicle located on the road RR within the range SC is guaranteed to a certain degree.

[0033] (Tracking processing) Here, the "tracking process" as an example of the present disclosure will be described in detail. By performing the tracking process, tracking data (for example, first tracking data TD1, second tracking data TD2) is acquired. Note that the tracking process is performed by each sensor (first sensor 11, second sensor 12). The tracking process is carried out as follows: first, segmentation processing is carried out, then filtering processing is carried out, and finally condition processing is carried out. As described above, each sensor may capture images repeatedly at a predetermined time, and therefore, tracking processing may be performed on multiple captured images to obtain multiple tracking data sets over different times.

[0034] In the first segmentation process, each sensor groups point cloud data whose inter-point distances are within a specified value. For example, the following description will be given assuming that multiple groups of point cloud data are created.

[0035] After grouping the point cloud data, a filtering process is then performed. In the filtering process, each sensor selects point data to be extracted from the point cloud data contained in the group, and then sets a range from the extraction target. Then, point cloud data within the set range is extracted, and the number of point cloud data contained in the group is counted. This process is first performed in a specific direction. For example, to track a vehicle VV traveling on road RR, the process is performed in the X direction.

[0036] Each sensor uses a threshold value set for the number of counted point cloud data, and deletes groups with counts below the threshold value. For groups in which the number of point cloud data is counted to be equal to or greater than the threshold, the filtering process described below is subsequently performed.

[0037] Here, as mentioned again, as the distance between each sensor and each vehicle increases, the accuracy of each sensor's detection of objects as point cloud data decreases. As a result, the number of point data that each sensor can acquire decreases, and the point cloud data becomes coarse. When the point cloud data becomes coarse, the distance between points in the segmentation process increases, and grouping may not be performed. Therefore, the control device 13 of the present disclosure lowers the threshold for acquiring tracking data from one of the sensors based on the tracking data from the other sensor. In other words, the threshold to be lowered here is the value specified in the segmentation process described above. In this way, each sensor groups the point cloud data of vehicles in positions where detection accuracy has decreased through segmentation processing, and sets them as candidates for acquiring tracking data.

[0038] In the subsequent filtering process, each sensor performs the same process on groups for which the number of point cloud data counts exceeds a threshold, but in a specific direction different from the previous process. For example, to track a vehicle VV traveling on road RR, processing is performed in the Y direction. In this way, the average position of the point cloud data contained in the group when processing is performed in a specific direction (X direction) and a different specific direction (Y direction) is calculated. The coordinates of the representative point are obtained from the average position in each direction. These coordinates indicate the traveling position of the vehicle VV.

[0039] In the final condition processing, for example, a condition is set for each sensor so that when a representative point is obtained a predetermined number of times or more in the acquired multiple image data, the sensor detects an object. When the condition is met, each sensor starts tracking the vehicle's position (hereinafter referred to as "tracking"). This allows each sensor to acquire tracking data. Furthermore, a condition is set for each sensor so that tracking is terminated if a representative point is not obtained a predetermined number of times or more during tracking.

[0040] (Configuration of information processing device) As shown in FIG. 1 again, the control device 13 includes a first acquisition unit 131, a second acquisition unit 132, a threshold value adjustment unit 133, and a storage unit .

[0041] The operation of each unit in the control device 13 described below corresponds to at least a part of the control method of the present disclosure.

[0042] (First Acquisition Department) The first acquisition unit 131 acquires first tracking data TD1 obtained by a first sensor 11 that detects the rear shape of each vehicle VV traveling on a lane from a first direction.

[0043] (Second Acquisition Department) The second acquisition unit 132 acquires second tracking data TD2 obtained by a second sensor 12 that detects the front shape of each vehicle VV from a second direction different from the first direction.

[0044] (Threshold adjustment unit) The threshold adjustment unit 133 lowers the threshold for acquiring tracking data by one of the first sensor 11 and the second sensor 12 based on the tracking data from the other sensor.

[0045] (Storage part) The storage unit 134 stores the vehicle lengths of the vehicles located on the road RR within the range SC near the intermediate position shown in FIG. 4, obtained from the image data captured by the sensors. The storage unit 134 stores the vehicle length predicted from the image showing the rear shape of each vehicle as seen from the first direction in association with the rear shape.

[0046] The procedure for lowering the threshold for acquiring tracking data by one sensor based on the tracking data from the other sensor will be described in detail below with reference to FIGS.

[0047] (Procedure for lowering the threshold for acquiring tracking data by the second sensor) As shown in FIG. 5, it is assumed that the first sensor 11 detects a vehicle VV1 among a plurality of vehicles VV within a predetermined area UA. The first sensor 11 acquires image data from a position overlooking the predetermined area UA and detects the rear shape of the vehicle VV1 from the image data using point cloud data. After that, by the tracking process described above, the first sensor 11 starts tracking the area U1 based on the position of the rear shape of the vehicle VV1. This allows the first sensor 11 to acquire first tracking data TD1.

[0048] As shown in FIG. 6, the second sensor 12 attempts to detect a vehicle VV1 among a plurality of vehicles VV within a predetermined area DA. As with the first tracking data TD1, the second sensor 12 acquires image data from a position overlooking the predetermined area DA, and attempts to start tracking of the area D1 based on the position of the front shape of the vehicle VV1 from the image data. However, the distance between the second sensor 12 and the vehicle VV1 is large. The vehicle is located near the upstream side (X=A) of the position of the second sensor 12. As a result, the detection accuracy of the object as point cloud data by the second sensor 12 is reduced. As a result, as described above, the number of point data points that the sensor can acquire decreases, resulting in coarse point cloud data. When point cloud data becomes coarse, the distance between points increases during segmentation processing, and grouping may not be performed. As a result, the coarse point cloud data does not qualify as a candidate for tracking data acquisition, and tracking will not begin for the coarse point cloud data acquired in area D1.

[0049] From the above, as shown in Figure 7, the threshold adjustment unit 133 lowers the threshold for acquiring tracking data by the second sensor 12 for a position obtained by adding the vehicle length predicted from the rear shape to the detected position of the rear shape included in the first tracking data TD1. That is, the threshold adjustment unit 133 lowers the designated value in the segmentation process by the second sensor for the position obtained by adding the position of area U1 included in the first tracking data TD1 to the vehicle length L1 predicted from the rear shape. The position obtained by adding the position of area U1 to the vehicle length L2 is expressed as (position of U1 + L1) when the X-axis is used as the reference. This position is approximately the same as the position of area D1. This allows the second sensor 12 to acquire the second tracking data TD2 from the rough point cloud data obtained at approximately the same position as the area D1.

[0050] (Procedure for lowering the threshold for acquiring tracking data by the first sensor) As shown in FIG. 8, the first sensor 11 attempts to detect a vehicle VV2 among a plurality of vehicles VV within a predetermined area UA. The first sensor 11 acquires image data from a position overlooking the predetermined area UA and detects the rear shape of the vehicle VV2 from the image data using point cloud data. Then, by the tracking process described above, it attempts to start tracking the area U2 based on the position of the rear shape of the vehicle VV2. However, the distance between the first sensor 11 and the vehicle VV2 is large. The vehicle is located downstream (X=B) relative to the position of the first sensor 11. Therefore, the detection accuracy of the object as point cloud data by the first sensor 11 is reduced. As a result, as described above, the number of point data points that the sensor can acquire decreases, resulting in coarse point cloud data. When point cloud data becomes coarse, the distance between points increases during segmentation processing, and grouping may not be performed. As a result, the coarse point cloud data does not qualify as a candidate for tracking data acquisition, and tracking will not be initiated for the coarse point cloud data acquired in area U2.

[0051] As shown in FIG. 9, it is assumed that the second sensor 12 detects a vehicle VV2 among a plurality of vehicles VV within a predetermined area DA. As with the first tracking data TD1, the second sensor 12 acquires image data from a position overlooking the predetermined area DA, detects the front shape of the vehicle VV2 from the image data, and starts tracking of the area D2 based on the position of the front shape of the vehicle VV2, thereby enabling the second sensor 12 to acquire second tracking data TD2.

[0052] From the above, as shown in FIG. 10, the threshold adjustment unit 133 lowers the threshold for acquiring tracking data by the first sensor for a position obtained by adding the vehicle length to the front shape detection position included in the second tracking data TD2. That is, the threshold adjustment unit 133 lowers the designated value in the segmentation process by the second sensor for the position obtained by adding the vehicle length L2 to the position of area D2 included in the second tracking data TD2. The position obtained by adding the vehicle length L2 to the position of area D2 is expressed as (position of D2 - L2) when the X-axis is used as the reference. This position is the same as or approximately the same as the position of area U2. This allows the first sensor 11 to acquire the first tracking data TD1 from the rough point cloud data obtained at the same position or approximately the same position as the area U2.

[0053] (Control method) The control method in this embodiment will be described. The control method in this embodiment is carried out according to the flow shown in Fig. 11. However, the order of the flow described below is not limited to the following example, and may be changed as appropriate.

[0054] First, the first acquisition unit 131 of the control device 13 acquires the first tracking data TD1 obtained by the first sensor 11 that detects the rear shape of each vehicle VV traveling on a lane from a first direction (step ST11).

[0055] Next, the second acquisition unit 132 of the control device 13 acquires second tracking data TD2 obtained by the second sensor 12 that detects the front shape of each vehicle VV from a second direction different from the first direction (step ST12).

[0056] Next, the control device 13 determines whether or not the vehicle to be detected is near the first sensor 11 (step ST13). If the vehicle to be detected is near the first sensor 11 (step ST13: YES), the process proceeds to step ST16, which will be described later. If the vehicle to be detected is not near the first sensor 11 (step ST13: NO), the control device 13 determines whether the vehicle to be detected is near the second sensor 12 (step ST14).

[0057] If the vehicle to be detected is near the second sensor 12 (step ST14: YES), the process proceeds to step 17, which will be described later. If the vehicle to be detected is not near the second sensor 12 (step ST14: NO), the control device 13 acquires the vehicle length of each vehicle obtained from image data captured by each sensor (step ST15). After that, the process returns to step ST11. Note that the position of the vehicle at step ST15 is on the road RR within a range SC near the midpoint between the upstream side (X=A) and downstream side (X=B) where each sensor is installed, as shown in FIG. 4 again.

[0058] Step 16, which is executed when the vehicle to be detected is near the first sensor 11 (step ST13: YES), will be described. Next, the threshold adjustment unit 133 of the control device 13 lowers the threshold for acquiring tracking data by the second sensor 12 for a position obtained by adding the detected position of the rear shape included in the first tracking data TD1 to the vehicle length predicted from the rear shape (step ST16).

[0059] Step 17, which is executed when the vehicle to be detected is near the second sensor 12 (step ST14: YES), will be described. Next, the threshold adjustment unit 133 of the control device 13 lowers the threshold for acquiring tracking data by the first sensor for a position obtained by adding the vehicle length to the front shape detection position included in the second tracking data TD2 (step ST17).

[0060] In this way, based on the tracking data of one of the first sensor 11 and the second sensor 12, the threshold for acquiring tracking data by the other sensor is lowered. (End)

[0061] (Action and effect) According to the control device 13 of this embodiment, of two sensors (first sensor, second sensor) that detect vehicles from different directions, the threshold for acquiring tracking data by one sensor is lowered based on the tracking data from the other sensor. Therefore, the control device according to the present disclosure can expand the area in which the detection accuracy can be ensured when each sensor detects the front and rear of the vehicle.

[0062] (Other embodiments) The above describes in detail the embodiments of the present disclosure with reference to the drawings, but the specific configuration is not limited to this embodiment, and design changes and the like are also included within the scope that does not deviate from the gist of the present disclosure.

[0063] In the present disclosure, the vehicle length and vehicle position acquired during tracking by each sensor may be transmitted as information to another device. According to the control device 13 of the present disclosure, the threshold of one sensor is lowered based on the tracking data of the other sensor, thereby extending the tracking distance of the other sensor. Therefore, by transmitting the information acquired during tracking to a device installed at a merging point with a vehicle traveling on a highway ramp, for example, it is possible to more easily prevent collisions between vehicles traveling on the main road at the merging point and vehicles traveling on the ramp.

[0064] 12 is a hardware configuration diagram showing the configuration of a computer 1100 according to this embodiment. The computer 1100 includes, for example, a processor 1110, a main memory 1120, a storage 1130, and an interface 1140.

[0065] Each of the functional units of the control device 13 described above is implemented in a computer 1100. The operation of each of the functional units described above is stored in the form of a program in a storage 1130. The processor 1110 reads the program from the storage 1130, loads it into the main memory 1120, and executes the above-described processing in accordance with the program. The processor 1110 also allocates storage areas in the main memory 1120 to be used by each of the functional units described above in accordance with the program.

[0066] The program may be for realizing some of the functions to be performed by the computer 1100. For example, the program may be combined with other programs already stored in the storage 1130 or other programs implemented in other devices to perform the functions. Furthermore, the computer 1100 may include a custom LSI (Large Scale Integrated Circuit) such as a PLD (Programmable Logic Device) in addition to or instead of the above configuration. Examples of PLDs include a PAL (Programmable Array Logic), a GAL (Generic Array Logic), a CPLD (Complex Programmable Logic Device), and an FPGA (Field Programmable Gate Array). In this case, some or all of the functions to be performed by the processor 1110 may be realized by the integrated circuit.

[0067] Examples of storage 1130 include a magnetic disk, a magneto-optical disk, and a semiconductor memory. Storage 1130 may be an internal medium directly connected to the bus of computer 1100, or an external medium connected to computer 1100 via interface 1140 or a communication line. When this program is distributed to computer 1100 via a communication line, computer 1100 that receives the program may load the program into main memory 1120 and execute the above-mentioned processing. The program may also be a program for realizing part of the above-mentioned functions. Furthermore, the program may be a program that realizes the above-mentioned functions in combination with another program already stored in storage 1130, i.e., a so-called differential file (differential program).

[0068] <Additional Notes> The control device 13 described in each embodiment can be understood, for example, as follows.

[0069] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0070] (Appendix 1) (1) The control device 13 according to the first aspect includes a first acquisition unit 131 that acquires first tracking data TD1 obtained by a first sensor 11 that detects the rear shape of a vehicle traveling on a lane from a first direction; a second acquisition unit 132 that acquires second tracking data TD2 obtained by a second sensor 12 that detects the front shape of the vehicle from a second direction different from the first direction; a threshold adjustment unit 133 that lowers a threshold for acquiring tracking data by one of the first sensor 11 and the second sensor 12 based on tracking data from the other sensor; Equipped with.

[0071] According to this configuration, of two sensors (first sensor, second sensor) that detect a vehicle from different directions, the threshold for acquiring tracking data by one sensor is lowered based on the tracking data by the other sensor. Therefore, the control device according to the present disclosure can expand the area in which the detection accuracy can be ensured when each sensor detects the front and rear of the vehicle.

[0072] (Appendix 2) (2) The control device 13 according to the second aspect is the control device described in (1), in which the threshold adjustment unit 133 lowers the threshold for acquiring tracking data by the second sensor 12 for a position obtained by adding the detected position of the rear shape included in the first tracking data TD1 to the vehicle length predicted from the rear shape.

[0073] According to this configuration, of two sensors (first sensor, second sensor) that detect a vehicle from different directions, the threshold for acquiring tracking data by one sensor is lowered based on the tracking data by the other sensor. Therefore, the control device according to the present disclosure can expand the area in which the detection accuracy can be ensured when each sensor detects the front and rear of the vehicle.

[0074] Furthermore, by lowering the threshold value of the second sensor 12, the tracking distance by the second sensor 12 is extended, and the detection timing of the second sensor 12 can be made earlier.

[0075] (Appendix 3) (3) The control device 13 according to the third aspect is a control device as described in (1) or (2), in which the threshold adjustment unit 133 lowers the threshold for acquiring tracking data by the first sensor 11 for a position obtained by adding the length of the vehicle to the detection position of the front shape included in the second tracking data TD2.

[0076] According to this configuration, of two sensors (first sensor, second sensor) that detect a vehicle from different directions, the threshold for acquiring tracking data by one sensor is lowered based on the tracking data by the other sensor. Therefore, the control device according to the present disclosure can expand the area in which the detection accuracy can be ensured when each sensor detects the front and rear of the vehicle.

[0077] In addition, when processing the threshold adjustment unit 133 of the control device 13 according to the third aspect, the vehicle length of the vehicle on the road RR within the range SC near the midpoint between the upstream side (X=A) and the downstream side (X=B) where each sensor is installed is acquired in advance. Therefore, by using the vehicle length previously acquired by the threshold adjustment unit 133 to lower the threshold of the first sensor 11, the tracking distance by the first sensor 11 is extended. The position obtained by adding the previously acquired vehicle length to the detected position of the front shape is the same as or approximately the same as the tracking position based on the position of the rear shape detected by the first sensor 11.

[0078] (Appendix 4) (4) The control device 13 according to a fourth aspect is the control device according to any one of (1) to (3), wherein the second direction is opposite to the first direction.

[0079] According to this configuration, of two sensors (first sensor, second sensor) that detect a vehicle from different directions, the threshold for acquiring tracking data by one sensor is lowered based on the tracking data by the other sensor. Therefore, the control device according to the present disclosure can expand the area in which the detection accuracy can be ensured when each sensor detects the front and rear of the vehicle.

[0080] (Appendix 5) A control device according to any one of (1) to (4), the first sensor 11; the second sensor 12; Equipped with Control system.

[0081] According to this configuration, of two sensors (first sensor, second sensor) that detect a vehicle from different directions, the threshold for acquiring tracking data by one sensor is lowered based on the tracking data by the other sensor. Therefore, the control system 1 according to the present disclosure can expand the area in which the detection accuracy when detecting the front and rear of the vehicle by each sensor can be ensured.

[0082] (Appendix 6) acquiring first tracking data obtained by a first sensor that detects a rear shape of a vehicle traveling in a lane from a first direction; acquiring second tracking data obtained by a second sensor that detects a front shape of the vehicle from a second direction different from the first direction; lowering a threshold for acquiring tracking data by one of the first sensor and the second sensor based on tracking data from the other sensor; Contains Control method.

[0083] According to this configuration, of two sensors (first sensor, second sensor) that detect a vehicle from different directions, the threshold for acquiring tracking data by one sensor is lowered based on the tracking data by the other sensor. Therefore, the control method according to the present disclosure can expand the area in which the detection accuracy can be ensured when each sensor detects the front and rear of the vehicle.

[0084] (Appendix 7) acquiring first tracking data obtained by a first sensor that detects a rear shape of a vehicle traveling in a lane from a first direction; acquiring second tracking data obtained by a second sensor that detects a front shape of the vehicle from a second direction different from the first direction; lowering a threshold for acquiring tracking data by one of the first sensor and the second sensor based on tracking data from the other sensor; Have your computer run program.

[0085] According to this configuration, of two sensors (first sensor, second sensor) that detect a vehicle from different directions, the threshold for acquiring tracking data by one sensor is lowered based on the tracking data by the other sensor. Therefore, the program according to the present disclosure can expand the area in which detection accuracy can be ensured when each sensor detects the front and rear of the vehicle. [Explanation of symbols]

[0086] 1. Control System 11 First Sensor 12 Second sensor 13 Control device 131 First Acquisition Department 132 Second Acquisition Department 133 Threshold adjustment unit 134 Storage section D1 Area D2 Area TD1 First Tracking Data TD2 Second Tracking Data U1 Area U2 Area

Claims

1. a first acquisition unit that acquires first tracking data obtained by a first sensor that detects a rear shape of a vehicle traveling in a lane from a first direction; a second acquisition unit that acquires second tracking data obtained by a second sensor that detects a front shape of the vehicle from a second direction different from the first direction; a threshold adjustment unit that lowers a threshold for acquiring tracking data by one of the first sensor and the second sensor based on tracking data from the other sensor; Equipped with Control device.

2. The threshold adjustment unit lowers a threshold for acquiring tracking data by the second sensor for a position obtained by adding a vehicle length predicted from the rear shape to a detection position of the rear shape included in the first tracking data. The control device according to claim 1 .

3. The threshold adjustment unit lowers a threshold for acquiring tracking data by the first sensor for a position obtained by adding a vehicle length to a detection position of the front shape included in the second tracking data. The control device according to claim 1 or 2.

4. The second direction is opposite to the first direction. The control device according to claim 1 or 2.

5. The control device according to claim 1 or 2; the first sensor; the second sensor; Equipped with Control system.

6. acquiring first tracking data obtained by a first sensor that detects a rear shape of a vehicle traveling in a lane from a first direction; acquiring second tracking data obtained by a second sensor that detects a front shape of the vehicle from a second direction different from the first direction; lowering a threshold for acquiring tracking data by one of the first sensor and the second sensor based on tracking data from the other sensor; Contains Control method.

7. acquiring first tracking data obtained by a first sensor that detects a rear shape of a vehicle traveling in a lane from a first direction; acquiring second tracking data obtained by a second sensor that detects a front shape of the vehicle from a second direction different from the first direction; lowering a threshold for acquiring tracking data by one of the first sensor and the second sensor based on tracking data from the other sensor; Have your computer run program.

Images