Information processing device

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 apparatus.

Background Art

[0002] Techniques for discriminating the types of vehicles traveling on a road using LiDAR (Light Detection and Ranging; Laser Imaging Detection and Ranging) have been developed. For example, in Patent Document 1, a rectangle corresponding to a cluster of point clouds is estimated, the width and / or depth of the estimated rectangle is estimated, and the vehicle corresponding to the cluster is discriminated using the estimated width and / or depth.

Prior Art Documents

Non-Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

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

[0005] Therefore, an object of the present invention is to discriminate an object by a simple method.

Means for Solving the Problems

[0006] To solve the above problems, an information processing device according to one embodiment of the present invention includes: 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, for each of the clusters, determines the object corresponding to the 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 is set for the length in the width direction of the road, and a second numerical range is set for the length in the direction in which the road extends. The object discrimination processing unit may then determine the object corresponding to each cluster based on the first numerical range, the second numerical range, the length of the road in the width direction of the cluster, and the length in the direction in which the road extends.

[0008] The information processing device further includes a movement direction calculation unit that calculates the movement direction of each of the clusters, and the object discrimination processing unit may determine the 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 in the direction in which the road extends.

[0009] The object discrimination processing unit may calculate a third numerical range for each cluster based on the direction of movement of the cluster, correcting the first numerical range for each type of object, and calculate a fourth numerical range based on the direction of movement of the cluster, correcting the second numerical range for each type of object, and then determine 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 in the direction in which the road extends.

[0010] The object discrimination processing unit may also determine the object corresponding to each of the clusters based on whether the length of the road in the width direction of the cluster is included in the third numerical range, and whether the length in the direction in which the road extends of the cluster is included in the fourth numerical range.

[0011] The movement direction calculation unit may also calculate the movement direction of each cluster based on the tracking history of that cluster.

[0012] The movement direction calculation unit may calculate the movement direction of each cluster based on the movement of the representative point of that cluster.

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

[0014] An information processing method according to one embodiment of the present invention is an information processing method performed by a computer, comprising: 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 determining the object corresponding to each of the clusters 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 one embodiment of the present invention causes a computer to execute the above-described information processing method. [Effects of the Invention]

[0016] This invention makes it possible to identify objects using a simple method. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

[0018] <Object discrimination device 100> Figure 1 shows an object identification device 100 according to one embodiment of the present invention. The object identification device 100 is a device that identifies objects on a road (for example, vehicles), and as shown in Figures 2 and 3, it detects objects present in a predetermined detection area A on the road RW and identifies the detected objects. In the example shown in Figure 2, the object identification 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. In the example shown in Figure 3, the object identification 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 exemplified in Figures 2 and 3 (rectangular parallelepiped) and can be set as appropriate.

[0019] The object recognition device 100 includes a LiDAR 110 and a control unit 120. The LiDAR 110 is installed near the detection area A and irradiates the detection area A with laser light. By receiving the reflected light that is reflected back by an object present in the detection area A, the LiDAR measures the distance to the object and generates three-dimensional point cloud information of the detection area A. The control unit 120 is an information processing device (computer) that processes the information. Similar to the LiDAR 110, it may be installed near the detection area A, or it may be located at a distance from the detection area A.

[0020] The rider 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 consists of multiple frames generated at the predetermined frame rate.

[0021] In each frame, each point is represented in 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 the X-axis direction, the direction in which the road RW extends is the Y-axis direction, and the direction perpendicular to the width direction and the direction in which the road RW extends (height direction) is the z-axis direction. In the example shown in Figures 2 and 3, the position where the pole to which the rider 110 is attached is set as the origin O.

[0022] Figure 4 shows an example of the control unit 120. It 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 the detection area A on the road RW from the lidar 110. In this embodiment, the control unit 120 only needs to acquire information relating to the length of the object in the width direction (X-axis direction) of the road RW and information relating 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 it may be the two-dimensional point cloud information (x-coordinate and y-coordinate values ​​of each point) from 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 into clusters. In other words, the clustering processing unit 122 clusters the point clouds included in each frame of the point cloud information in detection region A and divides them into clusters.

[0025] At this time, the clustering processing unit 122 clusters the point cloud contained in each frame of the point cloud information based on the distance between two points. Specifically, the clustering processing unit 112 divides the point cloud contained in each frame so that two points less than or equal to a predetermined distance are included in the same cluster. The distance between two points (P1(x1, y1, z1), P2(x2, y2, z2)) is the three-dimensional distance (((x1-x2)) 2 +(y1-y2) 2 +(z1-z2) 2 ) 1 / 2 ) is also acceptable, or the two-dimensional distance (((x1-x2) 2 +(y1-y2) 2 ) 1 / 2 ) is also acceptable.

[0026] Each frame of the point cloud information in detection area A may contain multiple vehicles. As shown in Figure 5, if there are two vehicles (vehicle AM1 and vehicle AM2) within detection area A of road RW, the point cloud information in detection area A will contain two clusters (cluster C1 and cluster C2), as shown in Figure 6. In the examples shown in Figures 5 and 6, cluster C1 corresponds to vehicle AM1 and cluster C2 corresponds to vehicle AM2. In other words, the clustering processing unit 112 clusters the point cloud contained in each frame of the point cloud information, dividing it into clusters that correspond to objects present in detection area A.

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

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

[0030] In other words, the object discrimination processing unit 123 should determine which object corresponds to each cluster based on whether the widthwise length WC of the road RW of the cluster is included in the first numerical range R1, and whether the length LC in the direction in which the road RW of the cluster 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 object A, and the length LT of the cluster in the Y-axis direction is included in the second numerical range R2 set for object A, then the object discrimination processing unit 123 determines that the cluster corresponds to object A.

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

[0032] The first numerical range R1 and the second numerical range R2 are set separately for two-wheeled vehicles (e.g., bicycles and motorcycles) and four-wheeled vehicles (e.g., passenger cars), as shown in Figure 9. In the example shown in Figure 9, the first numerical range R1 for two-wheeled vehicles is set to WTmin≦WC≦WTmax, and 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, it is advisable to appropriately set the first numerical range R1 and the second numerical range R2 for motorcycles based on the size of the motorcycle, and to appropriately set the first numerical range R1 and the second numerical range R2 for four-wheeled vehicles based on the size of the four-wheeled vehicle. For example, it is advisable to appropriately set XTmin based on the minimum width of the motorcycle, XTmax based on the maximum width of the motorcycle, LTmin based on the minimum length (depth) of the motorcycle, and LTmax based on the maximum length (depth) of the motorcycle. Also, for example, it is advisable to appropriately set XFmin based on the minimum width of the four-wheeled vehicle, XFmax based on the maximum width of the four-wheeled vehicle, LFmin based on the minimum length (depth) of the four-wheeled vehicle, and FTmax based on the maximum length (depth) of the four-wheeled vehicle.

[0034] Alternatively, two-wheeled vehicles could be divided into bicycles and motorcycles, and a first numerical range R1 and a second numerical range R2 could be set for bicycles based on their size, and a first numerical range R1 and a second numerical range R2 could be set for motorcycles based on their size.

[0035] With respect to 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 cars, medium cars, and large cars, and a first numerical range R1 and a second numerical range R2 may be set for small cars based on their size, a first numerical range R1 and a second numerical range R2 may be set for medium cars based on their size, and a first numerical range R1 and a second numerical range R2 may be set for large cars based on their size.

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

[0037] Thus, in this embodiment, objects corresponding to a cluster are identified based on the widthwise length WC of the cluster's road RW and the length LC in the direction in which the road RW extends. Therefore, in this embodiment, objects corresponding to a cluster can be identified without estimating the rectangle of the cluster, that is, without performing computationally intensive processing such as detecting the edges of the cluster. In other words, in this embodiment, objects can be identified using a simple method.

[0038] Figure 10 shows an example of a processing operation performed in the control unit 120. The processing operation shown in Figure 10 is performed, for example, each time point cloud information for each frame is acquired by the lidar 110.

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

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

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

[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 cluster in each frame of the point cloud information of the detection region A. The movement direction calculation unit 124 may use any method as long as it can detect the movement direction of the cluster. For example, the movement direction calculation unit 124 calculates the movement direction of the cluster 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 the representative point of the cluster (for example, the center or centroid of the cluster).

[0043] The object discrimination processing unit 123 then determines the object corresponding to each cluster based on the direction of movement of the cluster, a first numerical range R1, a second numerical range R2, the widthwise length WC of the road RW of the cluster, 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 for each cluster, correcting the first numerical range R1 for each type of object based on the direction of movement of the cluster, and calculates a fourth numerical range R4 for each type of object based on the direction of movement of the cluster, correcting the second numerical range R2. Then, the object discrimination processing unit 123 determines the object corresponding to the cluster based on the third numerical range R3, the fourth numerical range R4, the widthwise length WC of the road RW of the cluster, and the length LC in the direction in which the road RW extends.

[0045] In other words, the object discrimination processing unit 123 determines the object corresponding to a cluster based on whether the widthwise length WC of the road RW of the cluster is included in the third numerical range R3, and whether the length LC in the direction in which the road RW of the cluster extends is included in the fourth numerical range R3. For example, for each cluster, the object discrimination processing unit 123 determines that the cluster corresponds to object A if the length WC of the cluster in the X-axis direction is included in the third numerical range R3 set for object A, and the length LC of the cluster in the Y-axis direction is included in the fourth numerical range R4 set for object A.

[0046] If the angle (acute angle) between the direction in which road R extends (Y-axis direction) and the direction of movement DM of vehicle AM ​​is θ, then as shown in Figure 13, 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. In this case, the length WC in the width direction (X direction) of road R of the cluster corresponding to vehicle AM ​​corresponds to the length of vehicle AM ​​in the width direction (X direction) (WA·cosθ + LA·sinθ), and the length LC in the direction in which road R extends (Y direction) of the cluster corresponding to vehicle AM ​​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, if 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 corrects the first numerical range R1 to Wmin·cosθ + Lmin·sinθ ≤ WC ≤ Wmax·cosθ + Lmax·sinθ, and sets this corrected numerical range as the third numerical range R3. It also corrects the second numerical range R2 to Wmin·sinθ + Lmin·cosθ ≤ LC ≤ Wmax·sinθ + Lmax·cosθ, and sets this corrected numerical range as the fourth numerical range R4.

[0048] As shown in Figure 9, when a first numerical range R1 and a second numerical range R2 are set for two-wheeled and four-wheeled vehicles respectively, as shown in Figure 14, the first numerical range R1 for two-wheeled vehicles is corrected to WTmin·cosθ+LTmin·sinθ≦WC≦WTmax·cosθ+LTmax·sinθ, and this corrected numerical range becomes the third numerical range R3 for two-wheeled vehicles. 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 the fourth numerical range R4 for two-wheeled vehicles. Furthermore, 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 the 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 the fourth numerical range R4 for four-wheeled vehicles.

[0049] Thus, 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 direction of movement 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. For this reason, 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 computationally intensive processing such as detecting 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 in a simple manner.

[0050] Figure 15 shows an example of the processing operation performed in step S1003 of Figure 10. The processing operation shown in Figure 15 is performed for each cluster in step S1003 of Figure 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 for each type of object by correcting the first numerical range R1 based on the movement direction of the cluster, and calculates a fourth numerical range R3 for each type of object by correcting the second numerical range R2 based on the movement direction of the cluster (step S1502). The object discrimination processing unit 123 determines the object corresponding to the cluster based on the third numerical range R3, the fourth numerical range R4, the widthwise length WC of the road RW of the cluster, and the length LC 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 direction of movement of the cluster cannot be calculated, the object discrimination processing unit 123 may terminate the process without discriminating the object corresponding to the cluster, or it may determine that the type of the cluster is unknown, or it may determine the object corresponding to the cluster based on the first numerical range R1, the second numerical range R2, the widthwise length WC of the road RW of the cluster, and the length LC in the direction in which the road RW extends.

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

[0054] 100 Object discrimination device 110 Rider 120 Control Unit 121 Point Cloud Information Acquisition Processing Unit 122 Clustering Processing Unit 123 Object Recognition Processing Unit 124 Movement direction calculation unit

Claims

1. A point cloud information acquisition unit that acquires point cloud information of the detection area on the road, A clustering processing unit that clusters the point clouds included in the point cloud information into clusters, For each of the aforementioned clusters, an object discrimination processing unit is provided to determine the object corresponding to the cluster based on the length of the road in the width direction and the length in the direction in which the road extends. Each of the aforementioned clusters has a movement direction calculation unit that calculates the movement direction of the cluster, For each type of object, a first numerical range is set for the length in the width direction of the road, and a second numerical range is set for the length in the direction in which the road extends. The object discrimination processing unit is an information processing device that, for each of the clusters, discriminates an object corresponding to the cluster based on the direction of movement 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 in the direction in which the road extends.

2. The object discrimination processing unit performs the following for each of the clusters: Based on the direction of movement of the cluster, a third numerical range is calculated for each type of object by correcting the first numerical range. Based on the direction of movement of the cluster, a fourth numerical range is calculated for each type of object by correcting the second numerical range. The information processing apparatus according to claim 1, which determines an object corresponding to a 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 in the direction in which the road extends.

3. The object discrimination processing unit determines, for each of the clusters, the object corresponding to that cluster based on whether the length in the width direction of the road in the cluster is included in the third numerical range and whether the length in the direction in which the road extends in the cluster is included in the fourth numerical range, as described in claim 2.

4. The information processing apparatus according to any one of claims 1 to 3, wherein the movement direction calculation unit calculates the movement direction of each of the clusters based on the tracking history of the cluster.

5. The information processing apparatus according to claim 4, wherein the movement direction calculation unit calculates the movement direction of each of the clusters based on the movement of the representative point of the cluster.

6. The information processing apparatus according to claim 5, wherein the representative point of the cluster is the center or centroid of the cluster.

7. A method of information processing performed by a computer, A point cloud information acquisition process that acquires point cloud information of the detection area on the road, A clustering process is performed to cluster the point clouds included in the aforementioned point cloud information into clusters. For each of the aforementioned clusters, an object identification process is performed to identify the object corresponding to the cluster based on the length of the road in the width direction and the length in the direction in which the road extends. The process includes a movement direction calculation step for each of the aforementioned clusters, which calculates the movement direction of the cluster. For each type of object, a first numerical range is set for the length in the width direction of the road, and a second numerical range is set for the length in the direction in which the road extends. The object discrimination process is an information processing method that, for each of the clusters, discriminates the object corresponding to the cluster based on the direction of movement 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 in the direction in which the road extends.

8. An information processing program that causes a computer to execute the information processing method described in claim 7.

Images