US 12,327,414 B2
Systems and methods for enhancement of 3D object detection using point cloud semantic segmentation and attentive anchor generation
Ehsan Taghavi, Markham (CA); Ryan Razani, Toronto (CA); and Bingbing Liu, Markham (CA)
Assigned to HUAWEI TECHNOLOGIES CO., LTD., Shenzhen (CN)
Filed by Ehsan Taghavi, Markham (CA); Ryan Razani, Toronto (CA); and Bingbing Liu, Markham (CA)
Filed on May 30, 2022, as Appl. No. 17/827,963.
Prior Publication US 2023/0410530 A1, Dec. 21, 2023
Int. Cl. G06V 20/00 (2022.01); B60W 30/00 (2006.01); G01S 17/89 (2020.01); G06V 10/26 (2022.01); G06V 10/762 (2022.01); G06V 10/764 (2022.01); G06V 20/58 (2022.01)
CPC G06V 20/58 (2022.01) [B60W 30/00 (2013.01); G01S 17/89 (2013.01); G06V 10/26 (2022.01); G06V 10/762 (2022.01); G06V 10/764 (2022.01); B60W 2420/408 (2024.01)] 16 Claims
OG exemplary drawing
 
1. A method of performing an object detection task comprising:
obtaining a semantic segmentation map representing a real-world space, the semantic segmentation map including an array of elements that each represent a respective location in the real-world space, the array of elements including elements that are each assigned a respective element classification label selected from a set of possible classification labels that correspond to different classifications of dynamic objects;
clustering groups of the elements based on the assigned respective element classification labels to identify at least a first cluster of elements that have each been assigned the same respective element classification label;
generating, based on a location of the first cluster within the semantic segmentation map, a plurality of anchors, each of the plurality of anchors defining a different respective probable object location of a first dynamic object, wherein generating the plurality of anchors comprises:
computing an approximate location for the first dynamic object in the semantic segmentation map based on the locations of the elements of the first cluster;
generating a lower resolution map corresponding to the semantic segmentation map, and mapping the approximate location for the first dynamic object to a corresponding coarse element location in the lower resolution map:
generating a plurality of candidate anchors each indicating a different respective probable location of the first dynamic object relative to the coarse element location; and
mapping at least some of the plurality of candidate anchors to respective element locations of a higher resolution map to provide the plurality of anchors; and
generating, based on the semantic segmentation map and the at least one plurality of anchors, a respective bounding box and object instance classification label for the first dynamic object.