System and method for 3D blob classification and transmission

Patent metadata

Field	Value
Publication number	US-11568182-B2
Application number	US-202117494192-A
Country	US
Kind code	B2
Filing date	Oct 5, 2021
Priority date	Jul 31, 2018
Publication date	Jan 31, 2023
Grant date	Jan 31, 2023

Abstract

Embodiments described herein provide an apparatus comprising a processor to project and accumulate three-dimensional (3D) point data from a blob onto a plane; construct a histogram of the 3D point data; identify a center of mass of the blob based on histogram data; surround peaks in coordinates for data in the blob with a shape defined by a diameter of the blob based on the center of mass; obtain height data for the 3D point data; and calculate dimensions for a bounding box to surround the blob based on the shape and the height data. Other embodiments may be described and claimed.

First claim

The invention claimed is:

1. A method, comprising:
constructing a histogram of three-dimensional (3D) point data that is projected and accumulated from a blob onto a plane;
identifying a center of mass of the blob based on the histogram;
surrounding peaks in coordinates for data in the blob with a shape defined by a diameter of the blob based on the center of mass; and
calculating dimensions for a bounding box to surround the blob based on the shape.

2. The method of claim 1 , further comprising:
encoding the bounding box with coordinates for two opposing corners of the bounding box.

3. The method of claim 1 , further comprising:
implementing a classification algorithm to identify one or more blobs in a point cloud data set.

4. The method of claim 3 , wherein the classification algorithm comprises a K-means classification algorithm.

5. The method of claim 1 , further comprising:
calculating a two-dimensional (2D) distance transform for the blob to generate peaks in coordinates for data in the blob; and
surrounding the peaks with a 2D rectangle defined by a diameter of the blob.

6. The method of claim 5 , further comprising:
obtaining height data for the 3D point data, wherein the dimension for the bounding box are further based on the height data; and
merging the 2D rectangle with the height data to define the bounding box.

7. A non-transitory machine readable medium storing instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising:
constructing a histogram of three-dimensional (3D) point data that is projected and accumulated from a blob onto a plane;
identifying a center of mass of the blob based on the histogram;
surrounding peaks in coordinates for data in the blob with a shape defined by a diameter of the blob based on the center of mass; and
calculating dimensions for a bounding box to surround the blob based on the shape.

8. The non-transitory machine readable medium of claim 7 , the operations additionally comprising:
encoding the bounding box with coordinates for two opposing corners of the bounding box.

9. The non-transitory machine readable medium of claim 7 , the operations additionally comprising:
implementing a classification algorithm to identify one or more blobs in a point cloud data set.

10. The non-transitory machine readable medium of claim 9 , wherein the classification algorithm comprises a K-means classification algorithm.

11. The non-transitory machine readable medium of claim 7 , the operations additionally comprising:
calculating a two-dimensional (2D) distance transform for the blob to generate peaks in coordinates for data in the blob; and
surrounding the peaks with a 2D rectangle defined by a diameter of the blob.

12. The non-transitory machine readable medium of claim 11 , the operations additionally comprising:
obtaining height data for the 3D point data, wherein the dimension for the bounding box are further based on the height data; and

merging the 2D rectangle with the height data to define the bounding box.

13. An apparatus, comprising:
a processor to;
construct a histogram of three-dimensional (3D) point data that is projected and accumulated from a blob onto a plane;
identify a center of mass of the blob based on the histogram;
surround peaks in coordinates for data in the blob with a shape defined by a diameter of the blob based on the center of mass; and
calculate dimensions for a bounding box to surround the blob based on the shape.

14. The apparatus of claim 13 , wherein the processor is further to encode the bounding box with coordinates for two opposing corners of the bounding box.

15. The apparatus of claim 13 , wherein the processor is further to implement a classification algorithm to identify one or more blobs in a point cloud data set.

16. The apparatus of claim 15 , wherein the classification algorithm comprises a K-means classification algorithm.

17. The apparatus of claim 13 , wherein the processor is further to calculate a two-dimensional (2D) distance transform for the blob to generate peaks in coordinates for data in the blob, and surround the peaks with a 2D rectangle defined by a diameter of the blob.

18. The apparatus of claim 17 , wherein the processor is further to:
obtain height data for the 3D point data, wherein the dimension for the bounding box are further based on the height data; and
merge the 2D rectangle with the height data to define the bounding box.

19. A system comprising:
a memory; and
a graphics processor communicably coupled to the memory, the graphics processor to:
construct a histogram of three-dimensional (3D) point data that is projected and accumulated from a blob onto a plane;
identify a center of mass of the blob based on the histogram;
surround peaks in coordinates for data in the blob with a shape defined by a diameter of the blob based on the center of mass; and
calculate dimensions for a bounding box to surround the blob based on the shape.

20. The system of claim 19 , wherein the graphics processor is further to encode the bounding box with coordinates for two opposing corners of the bounding box.

Assignees

• Intel Corp

Inventors

• Distler Jonathan
• Ashkenazi Tzach
• Kaufman Itay
• Bortman Maria

Classifications

• G06T11/20

  Drawing from basic elements · CPC title

• G06T2210/12

  Bounding box · CPC title

• G06T5/40

  using histogram techniques · CPC title

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title

• G06K9/6267 Primary

  Physics · mapped topic