SYSTEM AND METHOD FOR SELECTIVE DETERMINATION OF POINT CLOUDS

• US 20150015602A1
• Filed: 07/10/2013
• Published: 01/15/2015
• Est. Priority Date: 07/10/2013
• Status: Active Grant

• Current Assignee: Cognex Corporation
• Original Assignee: Cognex Corporation
• Inventors: Beaudoin, Robert Emile
• Granted Patent: US 9,443,297 B2
• Time in Patent Office: Days
• US Class Current: 345/619
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/20016 Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: G06T 7/74 involving reference images or patches

Abstract

A computer-implemented method is provided. The method may include receiving or identifying a first point cloud associated with a train-time object or model. The method may further include selecting one or more probes associated with the first point cloud wherein selection of the one or more probes is based upon, at least in part, a score of a particular feature associated with the first point cloud. The method may also include analyzing a second point cloud associated with a run-time object, wherein the analysis is based upon the first point cloud. This analysis may produce an estimate of the difference in pose between the train time object and the run time object. Pose estimates may be obtained by matching points between the two point clouds based in part on features used during probe selection. Pose estimates may be scored, and refined, using the points selected as probes.

Claims

1. A computer-implemented method comprising:

receiving, using one or more computing devices, a first point cloud associated with an object; and

selecting one or more probes associated with the first point cloud wherein selection of the one or more probes is based upon, at least in part, a score of a particular feature associated with the first point cloud.

2. The computer-implemented method of claim 1, further comprising:

analyzing a second point cloud associated with the object, wherein the analysis is based upon, at least in part, the probes and the first point cloud

3. The computer-implemented method of claim 2, further comprising:

selecting one of more probes from the second point cloud based upon, at least in part, the one or more probes of the first point cloud.

4. The computer-implemented method of claim 1, wherein the particular feature associated with the one or more probes includes a measure of curvature.

5. The computer-implemented method of claim 1, further comprising:

analyzing surface normal information associated with at least one of the first point cloud and the second point cloud.

6. The computer-implemented method of claim 1, further comprising:

determining a change in pose of the object based upon the first point cloud and the second point cloud.

7. The computer-implemented method of claim 1, wherein one or more points associated with the first point cloud does not correspond identically with one or more points associated with the second point cloud.

8. The computer-implemented method of claim 1, wherein the object is partially obscured in either or both point clouds, and wherein more than one instance of the object, and instances of other objects, are present in a point cloud.

9. The computer-implemented method of claim 1, wherein the particular feature associated with the one or more probes includes at least one of a Gaussian curvature feature, a mean curvature feature, a crease edge feature, and a boundary feature.

10. The computer-implemented method of claim 1, further comprising:

generating estimated pose differences between the object in the two point clouds by establishing correspondences between points of the two clouds, wherein the number of points used to form correspondences is reduced either by the use of the probes or the associated features.

11. The computer-implemented method of claim 1, further comprising:

evaluating candidate pose differences between the object in the two point clouds by mapping the points selected as probes in the first point cloud via the candidate pose difference and computing the distances between the mapped images of the probes and points associated with the second cloud.

12. The computer-implemented method of claim 1, further comprising:

refining estimated pose differences between the object in the two point clouds by optimizing pose scores computed by mapping the points selected as probes in the first point cloud via the estimated pose difference and computing the distances between the mapped images of the probes and points associated with the second cloud.

13. A computer program product residing on a computer readable storage medium having a plurality of instructions stored thereon, which when executed by a processor, cause the processor to perform operations comprising:

receiving, using one or more computing devices, a first point cloud associated with an object; and

selecting one or more probes associated with the first point cloud wherein selection of the one or more probes is based upon, at least in part, a score of a particular feature associated with the first point cloud.

14. The computer program product of claim 13, further comprising:

analyzing a second point cloud associated with the object, wherein the analysis is based upon, at least in part, the probes and the first point cloud

15. The computer program product of claim 14, further comprising:

selecting one of more probes from the second point cloud based upon, at least in part, the one or more probes of the first point cloud.

16. The computer program product of claim 13, wherein the particular feature associated with the one or more probes includes a measure of curvature.

17. The computer program product of claim 13, further comprising:

analyzing surface normal information associated with at least one of the first point cloud and the second point cloud.

18. The computer program product of claim 13, further comprising:

determining a change in pose of the object based upon, at least in part, the first point cloud and the second point cloud.

19. The computer program product of claim 13, wherein one or more points associated with the first point cloud does not correspond identically with one or more points associated with the second point cloud.

20. The computer program product of claim 13, wherein the object is partially obscured in either or both point clouds, and wherein more than one instance of the object is present in a point cloud.

21. The computer program product of claim 13, wherein the particular feature associated with the one or more probes includes at least one of a Gaussian curvature feature, a mean curvature feature, a crease edge feature and a boundary feature.

22. The computer program product of claim 13, further comprising:

generating estimated pose differences between the object in the two point clouds by establishing correspondences between points of the two clouds, wherein the number of points used to form correspondences is reduced either by the use of the probes or the associated features.

23. The computer program product of claim 13, further comprising:

evaluating candidate pose differences between the object in the two point clouds by mapping the points selected as probes in the first point cloud via the candidate pose difference and computing the distances between the mapped images of the probes and points associated with the second cloud.

24. The computer program product of claim 13, further comprising:

refining estimated pose differences between the object in the two point clouds by optimizing pose scores computed by mapping the points selected as probes in the first point cloud via the estimated pose difference and computing the distances between the mapped images of the probes and points associated with the second cloud.