Information processor

Abstract

To identify an object using a simplified method.SOLUTION: This information processor obtains point cloud information of a detection area on a road, clusters point clouds contained in the point cloud information into clusters, and, for each of the clusters, identifies an object corresponding to the cluster based on a length of the cluster in a width direction of the road and a length of the cluster in a direction in which the road extends.SELECTED DRAWING: Figure 10

Description

[Technical Field]

[0001] The present invention relates to an information processing device. [Background technology]

[0002] A technology has been developed that uses LiDAR (Light Detection and Ranging; Laser Imaging Detection and Ranging) to identify the type of vehicle traveling on a road. For example, in Patent Document 1, a rectangle corresponding to a cluster of points is estimated, the width and / or depth of the estimated rectangle is estimated, and the estimated width and / or depth is used to identify the vehicle corresponding to the cluster. [Prior art documents] [Non-patent literature]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2012-52838 Summary of the Invention [Problem to be solved by the invention]

[0004] In Patent Document 1, when estimating a rectangle corresponding to a cluster of points, a process with a heavy calculation load, such as a process for detecting the sides of the cluster, is performed.

[0005] Therefore, an object of the present invention is to identify an object using a simple method. [Means for solving the problem]

[0006] In order to solve the above problem, an information processing device according to one embodiment of the present invention has a point cloud information acquisition unit that acquires point cloud information of a detection area on a road, a clustering processing unit that clusters the point clouds included in the point cloud information into clusters, and an object discrimination processing unit that discriminates an object corresponding to each cluster based on the length of the cluster in the width direction of the road and the length in the direction in which the road extends.

[0007] For each type of object, a first numerical range for the width of the road and a second numerical range for the length of the road in the direction in which the road extends are set, and the object discrimination processing unit may be configured to discriminate the object corresponding to each cluster based on the first numerical range, the second numerical range, the width of the road for that cluster, and the length of the road in the direction in which the road extends.

[0008] The information processing device may further include a movement direction calculation unit that calculates the movement direction of each of the clusters, and the object discrimination processing unit may discriminate an object corresponding to each of the clusters based on the movement direction of the cluster, the first numerical range, the second numerical range, the length of the cluster in the width direction of the road, and the length of the cluster in the direction in which the road extends.

[0009] The object discrimination processing unit may calculate a third numerical range for each of the clusters by correcting the first numerical range for each type of object based on the movement direction of the cluster, calculate a fourth numerical range for each type of object by correcting the second numerical range for each of the clusters based on the movement direction of the cluster, and discriminate the object corresponding to the cluster based on the third numerical range, the fourth numerical range, the length of the cluster in the width direction of the road, and the length of the cluster in the direction in which the road extends.

[0010] The object discrimination processing unit may be configured to discriminate an object corresponding to each of the clusters based on whether the width direction length of the road of the cluster is included in the third numerical range or not, and whether the length of the cluster in the direction in which the road extends is included in the fourth numerical range or not.

[0011] The movement direction calculation unit may calculate, for each of the clusters, the movement direction of the cluster based on a tracking history of the cluster.

[0012] The movement direction calculation unit may calculate, for each of the clusters, a movement direction of the cluster based on a movement of a representative point of the cluster.

[0013] The representative point of the cluster may be the center or center of gravity of the cluster.

[0014] An information processing method according to one embodiment of the present invention is an information processing method executed by a computer, and includes a point cloud information acquisition step of acquiring point cloud information of a detection area on a road, a clustering processing step of clustering the point clouds included in the point cloud information into clusters, and an object discrimination processing step of discriminating an object corresponding to each cluster based on the length of the cluster in the width direction of the road and the length in the direction in which the road extends.

[0015] An information processing program according to an embodiment of the present invention causes a computer to execute the above-described information processing method. [Effects of the Invention]

[0016] The present invention makes it possible to distinguish between objects using a simple method. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a diagram showing an object discrimination device 100 according to an embodiment of the present invention. [Figure 2]1 is a diagram illustrating the relationship between a lidar 110 (object discrimination device 100), a road RW, and a detection area A. FIG. [Figure 3] 1 is a diagram illustrating the relationship between a lidar 110 (object discrimination device 100), a road RW, and a detection area A. FIG. [Figure 4] FIG. 2 illustrates an example of a control unit 120. [Figure 5] 1 is a diagram illustrating the relationship between a detection area A and vehicles AM1 and AM2. FIG. [Figure 6] 6 is a diagram illustrating point cloud information of a detection area A acquired by a lidar 110 in the case shown in FIG. 5. FIG. [Figure 7] 10 is a diagram illustrating a case where the direction DA of the vehicle AM ​​is parallel to the direction in which the road R extends (Y-axis direction). [Figure 8] 8 is a diagram illustrating point cloud information acquired by the LIDAR 110 in the case shown in FIG. 7. FIG. [Figure 9] FIG. 2 is a diagram illustrating an example of a first numerical range R1 and a second numerical range R2 set for two-wheeled vehicles and four-wheeled vehicles. [Figure 10] 10 is a diagram showing an example of a processing operation executed in a control unit 120. FIG. [Figure 11] 10 is a diagram illustrating a case where the direction DA of the vehicle AM ​​is not parallel to the direction in which the road R extends (Y direction). [Figure 12] 12 is a diagram illustrating point cloud information acquired by the lidar 110 in the case shown in FIG. 11. FIG. [Figure 13] 1 is a diagram illustrating the length of the vehicle AM ​​in the width direction (X direction) of the road R and the length of the vehicle AM ​​in the direction in which the road R extends (Y direction). [Figure 14] 10 is a diagram illustrating an example of a third numerical range R3 and a fourth numerical range R4 obtained by correcting the first numerical range R1 and the second numerical range R1 shown in FIG. 9. FIG. [Figure 15] FIG. 11 is a diagram illustrating an example of a processing operation executed in step S1003 of FIG. DETAILED DESCRIPTION OF THE INVENTION

[0018] <Object discrimination device 100> FIG. 1 is a diagram showing an object discrimination device 100 according to one embodiment of the present invention. The object discrimination device 100 is a device that discriminates, for example, objects (e.g., vehicles) on a road, and as shown in FIGS. 2 and 3, detects objects present in a predetermined detection area A on the road RW and discriminates the detected objects. In the example shown in FIG. 2, the object discrimination device 100 is installed above the road RW and detects objects present in the three-dimensional detection area A on the road RW from above, while in the example shown in FIG. 3, the object discrimination device 100 is installed beside the road RW and detects objects present in the detection area A on the road from diagonally above. The shape of the detection area A is not limited to the shape (rectangular parallelepiped) exemplified in FIGS. 2 and 3, and can be set as appropriate.

[0019] The object discrimination device 100 has a lidar 110 and a control unit 120. The lidar 110 is a LiDAR that is installed near a detection area A, irradiates the detection area A with laser light, and receives the light that is reflected by and returns from an object present in the detection area A, thereby measuring the distance to the object and generating three-dimensional point cloud information of the detection area A. The control unit 120 is an information processing device (computer) that processes information, and like the lidar 110, may be installed near the detection area A, or may be located at a position away from the detection area A.

[0020] The lidar 110 generates three-dimensional point cloud information of the detection area A on the road RW at a predetermined frame rate (i.e., at a predetermined time interval). Therefore, the three-dimensional point cloud information of the detection area A on the road R is made up of multiple frames generated at the predetermined frame rate.

[0021] In each frame, each point is expressed by Cartesian coordinates (x, y, z). In this case, for example, as shown in Figures 2 and 3, an arbitrary position is set as the origin O, the width direction of the road RW is set as the X-axis direction, the direction in which the road RW extends is set as the Y-axis direction, and the direction perpendicular to the width direction of the road RW and the direction in which the road RW extends (height direction) is set as the z-axis direction. In the example shown in Figures 2 and 3, the position where the pole to which the lidar 110 is attached is installed is set as the origin O.

[0022] 4 is a diagram showing an example of the control unit 120. The control unit 120 includes a point cloud information acquisition processing unit 121, a clustering processing unit 122, and an object discrimination processing unit 123.

[0023] The point cloud information acquisition processing unit 121 acquires point cloud information of a detection area A on the road RW from the LIDAR 110. In this embodiment, it is sufficient for the control unit 120 to acquire information related to the length of the object in the width direction (X-axis direction) of the road RW and information related to the length in the direction in which the road RW extends (Y-axis direction). Therefore, the point cloud information of the detection area A acquired by the point cloud information acquisition processing unit 121 may be the three-dimensional point cloud information of the detection area A generated by the LIDAR 110 itself, or may be two-dimensional point cloud information (x coordinate value, y coordinate value of each point) of this three-dimensional point cloud information.

[0024] The clustering processing unit 122 clusters the point clouds included in the point cloud information acquired by the point cloud information acquisition processing unit 121. That is, for each frame of the point cloud information of the detection area A, the clustering processing unit 122 clusters the point clouds included in the frame and divides them into clusters.

[0025] At this time, the clustering processing unit 122 clusters the point cloud included in each frame of the point cloud information, for example, based on the distance between two points in that frame. Specifically, the clustering processing unit 122 divides the point cloud included in each frame so that two points within a predetermined distance are included in the same cluster. The distance between two points (P1 (x1, y1, z1), P2 (x2, y2, z2)) is calculated as the three-dimensional distance (((x1-x2) 2 +(y1-y2) 2 +(z1-z2) 2 ) 1 / 2 ) or the two-dimensional distance (((x1-x2) 2 +(y1-y2) 2 ) 1 / 2 ) may also be used.

[0026] Each frame of the point cloud information of the detection area A may contain multiple vehicles. As shown in FIG. 5, when two vehicles (vehicle AM1 and vehicle AM2) are present in the detection area A of the road RW, two clusters (cluster C1 and cluster C2) are contained in the point cloud information of the detection area A, as shown in FIG. 6. In the example shown in FIGS. 5 and 6, cluster C1 corresponds to vehicle AM1, and cluster C2 corresponds to vehicle AM2. That is, the clustering processing unit 112 clusters the points contained in each frame of the point cloud information, and divides them into clusters, each of which corresponds to an object present in the detection area A.

[0027] As shown in Figure 7, if the vehicle is traveling in a direction parallel to the direction in which road R extends (Y-axis direction), that is, if the orientation DA of vehicle AM ​​is parallel to the direction in which road R extends (Y-axis direction), then, as shown in Figure 8, the length WC of road R in cluster C in the width direction (X-axis direction) corresponds to the width WA of vehicle AM ​​corresponding to cluster C, and the length LC of cluster C in the direction in which road R extends (Y-axis direction) corresponds to the length (depth) LA of vehicle AM ​​corresponding to cluster C.

[0028] Therefore, in this embodiment, the object discrimination processing unit 123 discriminates an object corresponding to each cluster based on the length WC of the cluster in the width direction of the road RW and the length LC of the cluster in the direction in which the road RW extends, for each cluster in each frame of the point cloud information of the detection area A. For example, it is preferable to set the difference between the maximum and minimum X coordinate values ​​of the points included in the cluster as the length WC of the cluster in the width direction of the road RW, and the difference between the maximum and minimum Y coordinate values ​​of the points included in the cluster as the length LC of the cluster in the direction in which the road RW extends.

[0029] In this case, for example, a first numerical range R1 for the length in the width direction of the road (X-axis direction) and a second numerical range R2 for the length in the direction in which the road RW extends (Y-axis direction) are set in advance for each type of object, and the object discrimination processing unit 123 discriminates the object corresponding to each cluster based on this first numerical range R1, second numerical range R2, the length WC of the width direction of the road RW of the cluster, and the length LC of the direction in which the road RW extends.

[0030] That is, the object discrimination processing unit 123 may discriminate an object corresponding to each cluster based on whether or not the length WC of the cluster in the width direction of the road RW is included in the first numerical range R1 and whether or not the length LC of the cluster in the direction in which the road RW extends is included in the second numerical range R2. For example, if the length WC of the cluster in the X-axis direction is included in the first numerical range R1 set for the object A and the length LT of the cluster in the Y-axis direction is included in the second numerical range R2 set for the object A, the object discrimination processing unit 123 determines that the cluster corresponds to the object A.

[0031] The first numerical range R1 and the second numerical range R2 may be set for each type of object based on the size of the object of that type. For example, the first numerical range R1 may be set for each type of object based on the width of the object of that type, and the second numerical range R2 may be set for each type of object based on the length (depth) of the object of that type.

[0032] The first numerical range R1 and the second numerical range R2 may be set for two-wheeled vehicles (e.g., bicycles and motorcycles) and four-wheeled vehicles (e.g., passenger cars), for example, as shown in Fig. 9. In the example shown in Fig. 9, the first numerical range R1 for two-wheeled vehicles is set to WTmin≦WC≦WTmax, the second numerical range R2 for two-wheeled vehicles is set to LTmin≦LC≦LTtmax, the first numerical range R1 for four-wheeled vehicles is set to WFmin≦WC≦WFmax, and the second numerical range R2 for four-wheeled vehicles is set to LFmin≦LC≦LFmax.

[0033] In this case, the first and second numerical ranges R1 and R2 for motorcycles may be set appropriately based on the size of the motorcycle, and the first and second numerical ranges R1 and R2 for four-wheeled vehicles may be set appropriately based on the size of the four-wheeled vehicle. For example, XTmin may be set appropriately based on the minimum width of the motorcycle, XTmax may be set appropriately based on the maximum width of the motorcycle, LTmin may be set appropriately based on the minimum length (depth) of the motorcycle, and LTmax may be set appropriately based on the maximum length (depth) of the motorcycle. Also, for example, XFmin may be set appropriately based on the minimum width of the four-wheeled vehicle, XFmax may be set appropriately based on the maximum width of the four-wheeled vehicle, LFmin may be set appropriately based on the minimum length (depth) of the four-wheeled vehicle, and FTmax may be set appropriately based on the maximum length (depth) of the four-wheeled vehicle.

[0034] Two-wheeled vehicles may be divided into bicycles and motorcycles, and a first numerical range R1 and a second numerical range R2 may be set for bicycles based on the size of the bicycle, and a first numerical range R1 and a second numerical range R2 may be set for motorcycles based on the size of the motorcycle.

[0035] For four-wheeled vehicles, a first numerical range R1 and a second numerical range R2 may be set for each size. For example, four-wheeled vehicles may be divided into small, medium, and large vehicles, and a first numerical range R1 and a second numerical range R2 may be set for small vehicles based on the size of the small vehicles, a first numerical range R1 and a second numerical range R2 for medium vehicles based on the size of the medium vehicles, and a first numerical range R1 and a second numerical range R2 for large vehicles based on the size of the large vehicles.

[0036] If the cluster is not determined to be either of the objects as a result of discrimination based on the first numerical range R1 and the second numerical range R2 for two-wheeled vehicles and four-wheeled vehicles, the type of the cluster may be determined to be unknown.

[0037] In this way, in this embodiment, an object corresponding to a cluster is identified based on the length WC of the cluster in the width direction of the road RW and the length LC of the cluster in the direction in which the road RW extends. Therefore, in this embodiment, it is possible to identify an object corresponding to a cluster without estimating the rectangle of the cluster, that is, without performing processing with a heavy calculation load such as processing to detect the sides of the cluster. In other words, in this embodiment, it is possible to identify an object using a simple method.

[0038] Fig. 10 is a diagram showing an example of processing operations executed by the control unit 120. The processing operations shown in Fig. 10 are executed, for example, every time the LIDAR 110 acquires point cloud information for each frame.

[0039] The point cloud information acquisition processing unit 121 acquires point cloud information of a detection area A on the road RW from the lidar 110 (step S1001). The clustering processing unit 122 clusters the points included in the point cloud information acquired by the point cloud information acquisition processing unit 121 into clusters (step S1002). The object discrimination processing unit 123 discriminates an object corresponding to each cluster based on the length WC of the cluster in the width direction of the road RW and the length LT of the cluster in the direction in which the road RW extends (step S1003).

[0040] <Numeric range correction> As shown in Figure 7, if the vehicle is traveling in a direction parallel to the direction in which road R extends (Y-axis direction), that is, if the orientation DA of vehicle AM ​​is parallel to the direction in which road R extends (Y-direction), then, as shown in Figure 8, the length WC of road R in cluster C in the width direction (X-axis direction) corresponds to the width WA of vehicle AM ​​corresponding to cluster C, and the length LC of cluster C in the direction in which road R extends (Y-axis direction) corresponds to the length (depth) LA of vehicle AM ​​corresponding to cluster C, and it is possible to identify the object corresponding to cluster C using the above method.

[0041] However, as shown in Figure 11, if the vehicle AM ​​is traveling in a direction that is not parallel to the direction in which the road R extends (Y direction), that is, if the orientation DA of the vehicle AM ​​is not parallel to the direction in which the road R extends (Y direction), then, as shown in Figure 12, the length WC of the cluster C corresponding to the vehicle AM ​​in the width direction (X-axis direction) of the road R does not correspond to the width WA of the vehicle AM, and the length LC of the cluster C corresponding to the vehicle AM ​​in the direction in which the road R extends (Y-axis direction) does not correspond to the length (depth) LA of the vehicle AM, and the object corresponding to the cluster cannot be identified using the above method.

[0042] Therefore, in this embodiment, the control unit 120 further includes a movement direction calculation unit 124. The movement direction calculation unit 124 calculates the movement direction of each cluster (i.e., the orientation of the object corresponding to the cluster) for each frame of the point cloud information of the detection area A. The movement direction calculation unit 124 may use any method as long as it can detect the movement direction of the cluster. The movement direction calculation unit 124 calculates the movement direction of the cluster, for example, by using the tracking history of the cluster. In this case, it is preferable that the movement direction calculation unit 124 calculates the movement direction of each cluster based on the movement of a representative point of the cluster (e.g., the center or center of gravity of the cluster), for example.

[0043] Then, for each cluster, the object discrimination processing unit 123 discriminates the object corresponding to the cluster based on the movement direction of the cluster, the first numerical range R1, the second numerical range R2, the width direction length WC of the cluster of the road RW, and the length LW in the direction in which the road RW extends.

[0044] At this time, the object discrimination processing unit 123 calculates a third numerical range R3 by correcting the first numerical range R1 for each type of object based on the movement direction of the cluster, and calculates a fourth numerical range R4 by correcting the second numerical range R2 for each type of object based on the movement direction of the cluster.The object discrimination processing unit 123 then discriminates an object corresponding to the cluster based on the third numerical range R3, the fourth numerical range R4, the length WC of the cluster in the width direction of the road RW, and the length LC of the cluster in the direction in which the road RW extends.

[0045] That is, the object discrimination processing unit 123 discriminates the object corresponding to the cluster based on whether the length WC of the cluster in the width direction of the road RW is included in the third numerical range R3 or not, and whether the length LC of the cluster in the direction in which the road RW extends is included in the fourth numerical range R3 or not. For example, if the length WC of the cluster in the X-axis direction is included in the third numerical range R3 set for the object A and the length LC of the cluster in the Y-axis direction is included in the fourth numerical range R4 set for the object A, the object discrimination processing unit 123 determines that the cluster corresponds to the object A.

[0046] If the angle (acute angle) formed by the direction in which road R extends (Y-axis direction) and the direction of movement DM of vehicle AM ​​is θ, then the length of vehicle AM ​​in the width direction (X direction) of road R is WA·cosθ+LA·sinθ, and the length of vehicle AM ​​in the direction in which road R extends (Y direction) is WA·sinθ+LA·cosθ, as shown in Figure 13. In this case, the length WC of road R in the width direction (X direction) of the cluster corresponding to vehicle AM ​​corresponds to the length of road R in the width direction (X direction) of vehicle AM ​​(WA·cosθ+LA·sinθ), and the length LC of the cluster corresponding to vehicle AM ​​in the direction in which road R extends (Y direction) corresponds to the length of vehicle AM ​​in the direction in which road R extends (Y direction) (WA·sinθ+LA·cosθ).

[0047] Therefore, in this embodiment, when the first numerical range R1 is set to Wmin≦WC≦Wmax and the second numerical range R2 is set to Lmin≦LC≦Lmax, the object discrimination processing unit 123, for example, corrects the first numerical range R1 to Wmin·cosθ+Lmin·sinθ≦WC≦Wmax·cosθ+Lmax·sinθ, and sets this corrected numerical range as a third numerical range R3, and corrects the second numerical range R2 to Wmin·sinθ+Lmin·cosθ≦LC≦Wmax·sinθ+Lmax·cosθ, and sets this corrected numerical range as a fourth numerical range R4.

[0048] When a first numerical range R1 and a second numerical range R2 are set for two-wheeled vehicles and four-wheeled vehicles, as shown in FIG. 9, the first numerical range R1 for two-wheeled vehicles is corrected to WTmin·cosθ+LTmin·sinθ≦WC≦WTmax·cosθ+LTmax·sinθ as shown in FIG. 14, and this corrected numerical range becomes a third numerical range R3 for two-wheeled vehicles, and the second numerical range R2 for two-wheeled vehicles is corrected to WTmin·sinθ+LTmin·cosθ≦LC≦WTmax·sinθ+LTmax·cosθ, and this corrected numerical range becomes a fourth numerical range R4 for two-wheeled vehicles. In addition, the first numerical range R1 for four-wheeled vehicles is corrected to WFmin·cosθ+LFmin·sinθ≦WC≦WFfmax·cosθ+LFmax·sinθ, and this corrected numerical range becomes a third numerical range R3 for four-wheeled vehicles.The second numerical range R2 for four-wheeled vehicles is corrected to WFmin·sinθ+LFmin·cosθ≦LC≦WFmax·sinθ+LFmax·cosθ, and this corrected numerical range becomes a fourth numerical range R4 for four-wheeled vehicles.

[0049] As described above, in this embodiment, the first numerical range R1 and the second numerical range R2, which are set based on the size of the object, are corrected based on the movement direction of the cluster (i.e., the orientation of the object corresponding to the cluster), to calculate the third numerical range R3 and the fourth numerical range, and the object corresponding to the cluster is identified based on these third numerical range R3 and the fourth numerical range. Therefore, in this embodiment, even if the orientation of the object is not parallel to the direction in which the road extends, it is possible to identify the object corresponding to the cluster without estimating the rectangle of the cluster, that is, without performing processing with a heavy computational load such as processing to detect the edges of the cluster. In other words, in this embodiment, even if the orientation of the object is not parallel to the direction in which the road extends, it is possible to identify the object using a simple method.

[0050] Fig. 15 is a diagram showing an example of the processing operation executed in step S1003 of Fig. 10. The processing operation shown in Fig. 15 is executed for each cluster in step S1003 of Fig. 10.

[0051] The movement direction processing unit 124 calculates the movement direction of the cluster (step S1501). The object discrimination processing unit 123 calculates a third numerical range R3 by correcting the first numerical range R1 for each object type based on the movement direction of the cluster, and calculates a fourth numerical range R3 by correcting the second numerical range R2 for each object type based on the movement direction of the cluster (step S1502). The object discrimination processing unit 123 discriminates an object corresponding to the cluster based on the third numerical range R3, the fourth numerical range R4, the length WC of the cluster in the width direction of the road RW, and the length LC of the cluster in the direction in which the road RW extends (step S1503).

[0052] In step S1503, if there is no movement history for the cluster and the movement direction of the cluster cannot be calculated, the object discrimination processing unit 123 may terminate the processing without discriminating the object corresponding to the cluster, may determine that the type of the cluster is unknown, or may discriminate the object corresponding to the cluster based on the first numerical range R1, the second numerical range R2, the width direction length WC of the road RW of the cluster, and the length LC of the road RW in the extension direction.

[0053] The present invention has been described above in terms of preferred embodiments thereof. While the present invention has been described herein with reference to specific examples, various modifications and variations can be made to these examples without departing from the spirit and scope of the present invention as set forth in the claims. [Explanation of symbols]

[0054] 100 Object discrimination device 110 Rider 120 control section 121 Point cloud information acquisition processing unit 122 Clustering Processing Unit 123 Object discrimination processing section 124 Movement direction calculation unit

Claims

1. a point cloud information acquisition unit that acquires point cloud information of a detection area on a road; a clustering processing unit that clusters the point cloud included in the point cloud information into clusters; an object discrimination processing unit that discriminates an object corresponding to each of the clusters based on the length of the cluster in the width direction of the road and the length of the cluster in the direction in which the road extends.

2. a first numerical range for the length of the road in the width direction and a second numerical range for the length of the road in the extension direction are set for each type of object; 2. The information processing device according to claim 1, wherein the object discrimination processing unit discriminates an object corresponding to each of the clusters based on the first numerical range, the second numerical range, the length of the cluster in the width direction of the road, and the length of the cluster in the direction in which the road extends.

3. a movement direction calculation unit that calculates a movement direction of each of the clusters; 3. The information processing device according to claim 2, wherein the object discrimination processing unit discriminates an object corresponding to each of the clusters based on the movement direction of the cluster, the first numerical range, the second numerical range, the length of the cluster in the width direction of the road, and the length of the cluster in the direction in which the road extends.

4. The object discrimination processing unit performs the following for each of the clusters: calculating a third numerical range by correcting the first numerical range for each type of object based on the movement direction of the cluster; calculating a fourth numerical range by correcting the second numerical range for each type of object based on the movement direction of the cluster; The information processing device according to claim 3 , wherein the object corresponding to the cluster is determined based on the third numerical range, the fourth numerical range, the length of the cluster in the width direction of the road, and the length of the cluster in the direction in which the road extends.

5. 5. The information processing device according to claim 4, wherein the object discrimination processing unit discriminates an object corresponding to each of the clusters based on whether or not the length of the cluster in the width direction of the road is included in the third numerical range and whether or not the length of the cluster in the direction in which the road extends is included in the fourth numerical range.

6. The information processing device according to claim 2 , wherein the movement direction calculation unit calculates, for each of the clusters, the movement direction of the cluster based on a tracking history of the cluster.

7. The information processing apparatus according to claim 6 , wherein the movement direction calculation unit calculates, for each of the clusters, the movement direction of the cluster based on a movement of a representative point of the cluster.

8. The information processing apparatus according to claim 7 , wherein the representative point of the cluster is the center or center of gravity of the cluster.

9. 1. A computer-implemented information processing method, comprising: a point cloud information acquisition step of acquiring point cloud information of a detection area on a road; a clustering process step of clustering the points included in the point cloud information into clusters; an object discrimination processing step of discriminating an object corresponding to each of the clusters based on the length of the cluster in the width direction of the road and the length of the cluster in the direction in which the road extends.

10. An information processing program that causes a computer to execute the information processing method according to claim 9.

Images