Method and apparatus for detecting ground point cloud points

1. A method for detecting ground point cloud points, comprising:

selecting an estimated ground point cloud from a point cloud collected by a lidar;

dividing a three-dimensional space where the estimated ground point cloud is located, to obtain a segmentation plane, and determining a ground by judging a plane in the divided three-dimensional space based on a first distance threshold;

segmenting the point cloud into a first sub point cloud and a second sub point cloud based on the segmentation plane, distances between point cloud points of the first sub point cloud and the lidar being shorter than a distance between the segmentation plane and the lidar, and distances between point cloud points of the second sub point cloud and the lidar being not shorter than the distance between the segmentation plane and the lidar; and

determining the point cloud points whose distances from the ground are smaller than the first distance threshold in the first sub point cloud as ground point cloud points, and determining the point cloud points whose distances from the ground are smaller than a second distance threshold in the second sub point cloud as the ground point cloud points, the first distance threshold being smaller than the second distance threshold.

2. The method according to claim 1 , wherein the dividing a three-dimensional space where the estimated ground point cloud is located, to obtain a segmentation plane comprises:

determining a density of point cloud points in the point cloud;

generating a corresponding relationship between the density of point cloud points in the point cloud and a distance of the point cloud from the lidar; and

querying the corresponding relationship based on a preset segmentation density to obtain the segmentation plane.

3. The method according to claim 2 , wherein the determining the density of point cloud points in the point cloud comprises:

calculating, for the point cloud points of the same beam in the point cloud, a distance between adjacent point cloud points; and

determining the density of point cloud points of the beam based on the distance between the adjacent point cloud points.

4. The method according to claim 2 , wherein the determining the density of point cloud points in the point cloud comprises:

calculating, in response to determining that the point cloud comprises point cloud points of at least two beams, a distance between point cloud points of adjacent beams in the point cloud; and

determining the density of point cloud points of the adjacent beams based on the distance between the point cloud points of the adjacent beams.

5. The method according to claim 1 , wherein the determining a ground by judging a plane in the divided three-dimensional space based on a first distance threshold comprises:

drawing a distribution histogram of the point cloud by taking a height interval as a horizontal ordinate and a number of point cloud points as a longitudinal coordinate; and

fitting the ground based on the point cloud points falling into a peak interval of the distribution histogram.

6. The method according to claim 1 , wherein the dividing a three-dimensional space where the estimated ground point cloud is located, to obtain a segmentation plane, and determining a ground by judging a plane in the divided three-dimensional space based on a first distance threshold comprises:

dividing a first three-dimensional space where the estimated ground point cloud is located into a plurality of second three-dimensional spaces;

performing ground estimation on estimated ground point cloud points within the plurality of second three-dimensional spaces to obtain a plurality of ground sub planes; and

generating the ground based on the plurality of ground sub planes.

7. The method according to claim 6 , wherein the performing ground estimation on estimated ground point cloud points within the plurality of second three-dimensional spaces to obtain a plurality of ground sub planes comprises:

fitting a plurality of first planes based on the estimated ground point cloud points within the plurality of second three-dimensional spaces; and

performing following fitting steps for each first plane: selecting estimated ground point cloud points whose distances from the first plane are smaller than the first distance threshold from the second three-dimensional space where the first plane is located, as candidate ground point cloud points; fitting a second plane by using the candidate ground point cloud points; determining whether the second plane is stable; and using the second plane as the ground sub plane in response to determining that the second plane is stable.

8. The method according to claim 7 , wherein the performing ground estimation on estimated ground point cloud points within the plurality of second three-dimensional spaces to obtain a plurality of ground sub planes further comprises:

replacing, in response to determining that the second plane is unstable, the first plane with the second plane, and continuing to perform the fitting steps.

9. The method according to claim 7 , wherein the determining whether the second plane is stable comprises:

determining, in response to determining that a number of performing the fitting steps is smaller than a number threshold, whether a sum of distances from the estimated ground point cloud points within the second three-dimensional space to the second plane is smaller than the second distance threshold;

determining, in response to determining that the sum of the distances from the estimated ground point cloud points within the second three-dimensional space to the second plane is smaller than the second distance threshold, that the second plane is stable; and

determining, in response to determining that the sum of the distances from the estimated ground point cloud points within the second three-dimensional space to the second plane is not smaller than the second distance threshold, that the second plane is unstable.

10. The method according to claim 6 , wherein the generating the ground based on the plurality of ground sub planes comprises:

calculating, for each ground sub plane, a weighted average of an angle of the ground sub plane and an angle of an adjacent ground sub plane; and

adjusting the angle of the ground sub plane based on the weighted average.

11. An apparatus for detecting ground point cloud points, comprising:

at least one processor; and

a memory storing instructions, the instructions when executed by the at least one processor, causing the at least one processor to perform operations, the operations comprising:

selecting an estimated ground point cloud from a point cloud collected by a lidar;

dividing a three-dimensional space where the estimated ground point cloud is located, to obtain a segmentation plane, and determining a ground by judging a plane in the divided three-dimensional space based on a first distance threshold;

segmenting the point cloud into a first sub point cloud and a second sub point cloud based on the segmentation plane, distances between point cloud points of the first sub point cloud and the lidar being shorter than a distance between the segmentation plane and the lidar, and distances between point cloud points of the second sub point cloud and the lidar being not shorter than the distance between the segmentation plane and the lidar; and

determining the point cloud points whose distances from the ground are smaller than the first distance threshold in the first sub point cloud as ground point cloud points, and determining the point cloud points whose distances from the ground are smaller than a second distance threshold in the second sub point cloud as the ground point cloud points, the first distance threshold being smaller than the second distance threshold.

12. The apparatus according to claim 11 , wherein the dividing a three-dimensional space where the estimated ground point cloud is located, to obtain a segmentation plane comprises:

determining a density of point cloud points in the point cloud;

generating a corresponding relationship between the density of point cloud points in the point cloud and a distance of the point cloud from the lidar; and

querying the corresponding relationship based on a preset segmentation density to obtain the segmentation plane.

13. The apparatus according to claim 12 , wherein the determining the density of point cloud points in the point cloud comprises:

calculating, for the point cloud points of the same beam in the point cloud, a distance between adjacent point cloud points; and

determining the density of point cloud points of the beam based on the distance between the adjacent point cloud points.

14. The apparatus according to claim 12 , wherein the determining the density of point cloud points in the point cloud comprises:

calculating, in response to determining that the point cloud comprises point cloud points of at least two beams, a distance between point cloud points of adjacent beams in the point cloud; and

determining the density of point cloud points of the adjacent beams based on the distance between the point cloud points of the adjacent beams.

15. The apparatus according to claim 11 , wherein the determining a ground by judging a plane in the divided three-dimensional space based on a first distance threshold comprises:

drawing a distribution histogram of the point cloud by taking a height interval as a horizontal ordinate and a number of point cloud points as a longitudinal coordinate; and

fitting the ground based on the point cloud points falling into a peak interval of the distribution histogram.

16. The apparatus according to claim 11 , wherein the dividing a three-dimensional space where the estimated ground point cloud is located, to obtain a segmentation plane, and determining a ground by judging a plane in the divided three-dimensional space based on a first distance threshold comprises:

dividing a first three-dimensional space where the estimated ground point cloud is located into a plurality of second three-dimensional spaces;

performing ground estimation on estimated ground point cloud points within the plurality of second three-dimensional spaces to obtain a plurality of ground sub planes; and

generating the ground based on the plurality of ground sub planes.

17. The apparatus according to claim 16 , wherein the performing ground estimation on estimated ground point cloud points within the plurality of second three-dimensional spaces to obtain a plurality of ground sub planes comprises:

fitting a plurality of first planes based on the estimated ground point cloud points within the plurality of second three-dimensional spaces; and

performing following fitting steps for each first plane: selecting estimated ground point cloud points whose distances from the first plane are smaller than the first distance threshold from the second three-dimensional space where the first plane is located, as candidate ground point cloud points; fitting a second plane by using the candidate ground point cloud points; determining whether the second plane is stable; and using the second plane as the ground sub plane in response to determining that the second plane is stable.

18. The apparatus according to claim 17 , wherein the performing ground estimation on estimated ground point cloud points within the plurality of second three-dimensional spaces to obtain a plurality of ground sub planes further comprises:

replacing, in response to determining that the second plane is unstable, the first plane with the second plane, and continuing to perform the fitting steps.

19. The apparatus according to claim 17 , wherein the determining whether the second plane is stable comprises:

determining, in response to determining that a number of performing the fitting steps is smaller than a number threshold, whether a sum of distances from the estimated ground point cloud points within the second three-dimensional space to the second plane is smaller than the second distance threshold;

determining, in response to determining that the sum of the distances from the estimated ground point cloud points within the second three-dimensional space to the second plane is smaller than the second distance threshold, that the second plane is stable; and

determining, in response to determining that the sum of the distances from the estimated ground point cloud points within the second three-dimensional space to the second plane is not smaller than the second distance threshold, that the second plane is unstable.

20. A non-transitory computer-readable medium, storing a computer program thereon, wherein the computer program, when executed by a processor, causes the processor to perform operations, the operations comprising:

selecting an estimated ground point cloud from a point cloud collected by a lidar;

dividing a three-dimensional space where the estimated ground point cloud is located, to obtain a segmentation plane, and determining a ground by judging a plane in the divided three-dimensional space based on a first distance threshold;

segmenting the point cloud into a first sub point cloud and a second sub point cloud based on the segmentation plane, distances between point cloud points of the first sub point cloud and the lidar being shorter than a distance between the segmentation plane and the lidar, and distances between point cloud points of the second sub point cloud and the lidar being not shorter than the distance between the segmentation plane and the lidar; and

determining the point cloud points whose distances from the ground are smaller than the first distance threshold in the first sub point cloud as ground point cloud points, and determining the point cloud points whose distances from the ground are smaller than a second distance threshold in the second sub point cloud as the ground point cloud points, the first distance threshold being smaller than the second distance threshold.