Identification of planar points in lidar point cloud obtained with vehicle lidar system
A system in a vehicle includes a lidar system to transmit incident light and receive reflections from one or more objects as a point cloud of points. The system also includes processing circuitry to identify feature points among the points of the point cloud, the feature points being horizontal feature points reflected from a horizontal surface or vertical feature points reflected from a vertical surface. The processing circuitry processes the point cloud by obtaining a normal vector corresponding to each of the points of the point cloud. The normal vector includes a first component associated with a first dimension, a second component associated with a second dimension, and a third component associated with a third dimension.
1. A system in a vehicle comprising:
a lidar system configured to transmit incident light and receive reflections from one or more objects as a point cloud of points;
processing circuitry configured to identify feature points among the points of the point cloud, the feature points being horizontal feature points reflected from a horizontal surface or vertical feature points reflected from a vertical surface, wherein the processing circuitry is configured to process the point cloud by obtaining a normal vector corresponding to each of the points of the point cloud, the normal vector including a first component associated with a first dimension, a second component associated with a second dimension, and a third component associated with a third dimension; and
wherein the processing circuitry is configured to obtain a subset H of the points of the point cloud for which the first component of the normal vector is below a first threshold value and the second component of the normal vector is below a second threshold value.
2. The system according to claim 1 , wherein the lidar system is a beam-based lidar system that transmits each beam of incident light across a horizontal scan line.
3. The system according to claim 1 , wherein the lidar system is a non-beam-based lidar system that transmits each beam of incident light over an area.
4. The system according to claim 1 , wherein the processing circuitry is configured to identify a subset of points associated with each of the points of the point cloud.
5. The system according to claim 4 , wherein the processing circuitry is configured to perform principal component analysis on the subset of points associated with each of the points of the point cloud to obtain the normal vector corresponding to each of the points of the point cloud.
6. The system according to claim 1 , wherein the processing circuitry is configured to identify the horizontal feature points using a random sample consensus (RANSAC) algorithm on the subset H of the points.
7. The system according to claim 1 , wherein the processing circuitry is configured to obtain a subset V of the points of the point cloud for which the third component of the normal vector is below a third threshold value.
8. The system according to claim 7 , wherein the processing circuitry is configured to normalize directions of the normal vectors of the subset V of the points of the point cloud to obtain normalized directions.
9. The system according to claim 8 , wherein the processing circuitry is configured to cluster the subset V of the points of the point cloud using spatial clustering of applications with noise (DBSCAN) on the normalized directions and to identify the vertical feature points as those in a predefined number of clusters with a highest density or number of points.
10. A method comprising:
configuring a lidar system to transmit incident light and receive reflections from one or more objects as a point cloud of points;
configuring processing circuitry to identify feature points among the points of the point cloud, the feature points being horizontal feature points reflected from a horizontal surface or vertical feature points reflected from a vertical surface, wherein the processing circuitry is configured to process the point cloud by obtaining a normal vector corresponding to each of the points of the point cloud, the normal vector including a first component associated with a first dimension, a second component associated with a second dimension, and a third component associated with a third dimension; and
wherein the configuring the processing circuitry includes obtaining a subset V of the points of the point cloud for which the third component of the normal vector is below a third threshold value.
11. The method according to claim 10 , wherein the lidar system is a beam-based lidar system that transmits each beam of incident light across a horizontal scan line.
12. The method according to claim 10 , wherein the lidar system is a non-beam-based lidar system that transmits each beam of incident light over an area.
13. The method according to claim 10 , wherein the configuring the processing circuitry includes identifying a subset of points associated with each of the points of the point cloud.
14. The method according to claim 13 , wherein the configuring the processing circuitry includes performing principal component analysis on the subset of points associated with each of the points of the point cloud to obtain the normal vector corresponding to each of the points of the point cloud.
15. The method according to claim 10 , wherein the configuring the processing circuitry includes obtaining a subset H of the points of the point cloud for which the first component of the normal vector is below a first threshold value and the second component of the normal vector is below a second threshold value.
16. The method according to claim 15 , wherein the configuring the processing circuitry includes identifying the horizontal feature points using a random sample consensus (RANSAC) algorithm on the subset H of the points.
17. The method according to claim 10 , wherein the configuring the processing circuitry includes normalizing directions of the normal vectors of the subset V of the points of the point cloud to obtain normalized directions.
18. The method according to claim 17 , wherein the configuring the processing circuitry includes clustering the subset V of the points of the point cloud using spatial clustering of applications with noise (DBSCAN) on the normalized directions and identifying the vertical feature points as those in a predefined number of clusters with a highest density or number of points.
19. The system according to claim 2 , further comprising limiting a vertical resolution of the beam-based lidar system according to how closely the beams are spaced.
20. The method according to claim 11 further comprising limiting a vertical resolution of the beam-based lidar system according to how closely the beams are spaced.