Apparatus and method for detecting intersection edges

Patent metadata

Field	Value
Publication number	US-11965967-B2
Application number	US-202218056247-A
Country	US
Kind code	B2
Filing date	Nov 16, 2022
Priority date	Aug 16, 2019
Publication date	Apr 23, 2024
Grant date	Apr 23, 2024

Abstract

A computer implemented scheme for a light detection and ranging (LIDAR) system where point cloud feature extraction and segmentation by efficiently is achieved by: (1) data structuring; (2) edge detection; and (3) region growing.

First claim

What is claimed is:

1. A non-transitory machine-readable storage media having instructions stored thereon, that when executed, cause one or more processors to perform a method, the method comprising:
detecting one or more intersection edges by:
generating a mesh around a point associated with a physical object, which is not a silhouette edge point, of a scan pattern grid with neighbor points forming shared edges between regions of the mesh; and
computing a normal gradient across an individual shared edge to determine whether the point is lying on an intersection edge of a smooth surface;

detecting one or more silhouette edges using the scan pattern grid and a point cloud data, wherein detecting the one or more silhouette edges comprises:
determining mixed pixels, between two objects, from the scan pattern grid; and
distinguishing silhouette edge points of the two objects from the mixed pixels by determining whether a point in the scan pattern grid is on one of the two objects.

2. The non-transitory machine-readable storage media of claim 1 , wherein the one or more intersection edges intersect two or more smooth surfaces.

3. The non-transitory machine-readable storage media of claim 1 , wherein the mesh comprises a triangular mesh around the point, and wherein the regions of the mesh are triangles of the triangular mesh.

4. The non-transitory machine-readable storage media of claim 1 , wherein detecting the one or more intersection edges is independent of a normal vector at each point of the scan pattern grid.

5. The non-transitory machine-readable storage media of claim 1 , wherein detecting the one or more intersection edges comprises comparing a maximum normal gradient, from among the normal gradient, with a threshold of the maximum normal gradient.

6. The non-transitory machine-readable storage media of claim 1 , having further instructions stored thereon, that when executed, cause the one or more processors to perform a further method comprising:
receiving scan pattern information and the point cloud data from a LIDAR system, wherein the scan pattern information and the point cloud data are associated with the physical object.

7. The non-transitory machine-readable storage media of claim 6 , wherein the scan pattern grid comprises a 2-D grid structure having cells organized in rows and columns, wherein an individual row corresponds to a vertical angle of a scan from a scanner of the LIDAR system, and wherein an individual column corresponds to a horizontal angle from the scanner of the LIDAR system.

8. The non-transitory machine-readable storage media of claim 6 , wherein the LIDAR system comprises a mobile LIDAR system, wherein the scan pattern grid comprises a 2-D grid structure having cells organized in rows and columns, wherein an individual row corresponds to a time of a scan from a scanner of the LIDAR system, and wherein an individual column corresponds to a scan angle from the scanner of the LIDAR system.

9. The non-transitory machine-readable storage media of claim 1 , wherein an individual cell of the scan pattern grid represents a laser pulse from a scanner, wherein the individual cell includes information of a return point, wherein the information of the return point includes scan coordinates, color, and/or intensity.

10. The non-transitory machine-readable storage media of claim 1 , having further instructions stored thereon, that when executed, cause the one or more processors to perform a further method comprising:
generating the scan pattern grid from scan pattern information and the point cloud data, wherein the scan pattern information and the point cloud data are received from a LIDAR system.

11. The non-transitory machine-readable storage media of claim 1 , wherein the one or more silhouette edges comprises points lying on an edge between an object scanned by a LIDAR system and a shadow of the object.

12. The non-transitory machine-readable storage media of claim 1 , having further instructions stored thereon, that when executed, cause the one or more processors to perform a further method comprising:
growing a region based on the one or more silhouette edges and the one or more intersection edges.

13. The non-transitory machine-readable storage media of claim 12 , wherein the scan pattern grid is a first scan pattern grid, wherein growing the region comprises:
analyzing points in the first scan pattern grid and a second scan pattern grid; and
generating clusters of homogeneous points continuous in space.

14. The non-transitory machine-readable storage media of claim 1 , wherein detecting the one or more silhouette edges comprises:
determining, from the scan pattern grid, points with no return; and
identifying points in the scan pattern grid that neighbor the points with no return as silhouette edge points, wherein the silhouette edge points form the one or more silhouette edges.

15. The non-transitory machine-readable storage media of claim 1 , wherein detecting the one or more silhouette edges comprises:
comparing an incidence angle, associated with a point, against a threshold;
identifying the point as a silhouette edge point if the incidence angle exceeds the threshold, wherein the silhouette edge point forms the one or more silhouette edges; and
identifying the point as a mixed pixel if the incidence angle is below the threshold.

16. A method comprising:
detecting one or more intersection edges by:
generating a mesh around a point associated with a physical object, which is not a silhouette edge point, of a scan pattern grid with neighbor points forming shared edges between regions of the mesh; and
computing a normal gradient across an individual shared edge to determine whether the point is lying on an intersection edge of a smooth surface; and

detecting one or more silhouette edges using the scan pattern grid and a point cloud data, wherein detecting the one or more silhouette edges comprises:
determining mixed pixels, between two objects, from the scan pattern grid; and
distinguishing silhouette edge points of the two objects from the mixed pixels by determining whether a point in the scan pattern grid is on one of the two objects.

17. A system comprising:
a memory;
a processor coupled to the memory; and
a communication interface coupled to the processor, wherein the processor is to detect one or more intersection edges by:
generation of a mesh around a point associated with a physical object, which is not a silhouette edge point, of a scan pattern grid with neighbor points forming shared edges between regions of the mesh; and
computation of a normal gradient across an individual shared edge to determine whether the point is lying on an intersection edge of a smooth surface:, and

detect one or more silhouette edges using the scan pattern grid and a point cloud data, wherein the processor is to detect of the one or more silhouette edges by:
determination of mixed pixels, between two objects, from the scan pattern grid; and
distinguishment of silhouette edge points of the two objects from the mixed pixels based on a determination of whether a point in the scan pattern grid is on one of the two objects.

18. The system of claim 17 , wherein the mesh comprises a triangular mesh around the point, and wherein the regions of the mesh are triangles of the triangular mesh.

Assignees

• Univ Oregon State

Inventors

• Che Erzhuo
• Olsen Michael

Classifications

• G01S17/89 Primary

  for mapping or imaging · CPC title

• G01S7/4804

  Auxiliary means for detecting or identifying lidar signals or the like, e.g. laser illuminators · CPC title

• G06T7/11

  Region-based segmentation · CPC title

• G06T7/13

  Edge detection · CPC title

• G06T7/136

  involving thresholding · CPC title