System and method for scoring clutter for use in 3D point cloud matching in a vision system

1. A method for aligning first three-dimensional (3D) point cloud image with a second 3D point cloud image comprising the steps of:

providing a first 3D point cloud image from a model to a vision system processor;

providing a second 3D point cloud image from a target to a vision system processor;

establishing a passing overall score for possible alignments of the first 3D point cloud image with the second 3D point cloud image;

estimating a coverage score for at least one possible alignment of the first 3D point cloud image with the second 3D point cloud image so that the coverage score describes an amount of desired features in the first 3D point cloud image present in the second 3D point cloud image; and

estimating a clutter score for at least one possible alignment of the first 3D point cloud image with the second 3D point cloud image so that the clutter score describes extraneous features in the second 3D point cloud image; and

estimating an overall score as a difference between the coverage score and the clutter score.

2. The method as set forth in claim 1 wherein at least one of the model and the target is defined using at least one of a 3D camera and a 3D computer aided design description.

3. The method as set forth in claim 2 wherein the first 3D point cloud image is a model image.

4. The method as set forth in claim 3 wherein the second 3D point cloud image is an image of the target.

5. The method as set forth in claim 1 further comprising defining a bounding volume around the first 3D point cloud image to estimate the coverage score and to estimate the clutter score.

6. The method as set forth in claim 5 wherein a size of the bounding volume is defined automatically or based upon a user-specified definition.

7. The method as set forth in claim 6 wherein the automatically defined bounding volume is set to a minimum-volume shape that completely contains the first 3D point cloud image.

8. The method as set forth in claim 1 further comprising performing an initial registration of the first 3D point cloud image and the second 3D point cloud image based upon matching of a predetermined arrangements of points in each of the first 3D point cloud image and the second 3D point cloud image.

9. The method as set forth in claim 1 wherein each point in the first 3D point cloud image and the second 3D point cloud image defines a coverage weight.

10. The method as set forth in claim 9 wherein the coverage weight is defined between a value of 0 and a value of 1.

11. The method as set forth in claim 10 wherein the overall score is estimated based upon the clutter score multiplied by a clutter rate constant.

12. The method as set forth in claim 10 wherein each point in the first 3D point cloud image and the second 3D point cloud image defines a coverage weight and clutter weight between a value of 0 and a value of 1, and (a) wherein the coverage score is a ratio of sum of values of coverage weight to a number of points in the first 3D point cloud image and (b) the clutter score is a ratio of the sums of values of clutter weight to a number of points in the first 3D point cloud image.

13. A system for aligning a first three-dimensional (3D) point cloud image with a second 3D point cloud image comprising:

a scoring module that determines a coverage score, a clutter score and an overall score for at least one possible alignment between the first 3D point cloud image and the second 3D point cloud image, the clutter score corresponding to an amount of extraneous features in the second 3D point cloud image, the overall score being a difference between the coverage score and the clutter score; and

an alignment module that bases an alignment decision for the second 3D point cloud image based upon the overall score.

14. The system as set forth in claim 13 wherein a model is defined using at least one of a 3D camera and a 3D computer aided design description.

15. The system as set forth in claim 14 wherein the second 3D point cloud image is an image of a target.

16. The system as set forth in claim 13 wherein a bounding volume is defined around the first 3D point cloud image to calculate the coverage score and the clutter score.

17. The system as set forth in claim 16 wherein a size of the bounding volume is defined automatically or based upon a user-specified definition.

18. The system as set forth in claim 17 wherein the automatically defined bounding volume is set to a minimum-volume shape that completely contains the first 3D point cloud image.

19. The system as set forth in claim 13 wherein each point in the first 3D point cloud image and the second 3D point cloud image defines a coverage weight.

20. The system as set forth in claim 19 wherein the coverage weight is defined between a value of 0 and a value of 1.

21. A non-transitory computer-readable storage medium storing a set of instructions capable of being executed by a processor, that when executed by the processor causes the processor to:

provide a first three-dimensional (3D) point cloud image from a model to a vision system processor;

provide a second 3D point cloud image from a target to a vision system processor;

establish a passing overall score for possible alignments of the first 3D point cloud image with the second 3D point cloud image;

estimate a coverage score for at least one possible alignment of the first 3D point cloud image with the second 3D point cloud image so that the coverage score describes an amount of desired features in the first 3D point cloud image present in the second 3D point cloud image; and

estimate a clutter score for at least one possible alignment of the first 3D point cloud image with the second 3D point cloud image so that the clutter score describes extraneous features in the second 3D point cloud image; and

estimate an overall score as a difference between the coverage score and the clutter score.