US 11,055,540 B2
Method for determining anchor boxes for training neural network object detection models for autonomous driving
Ka Wai Tsoi, Sunnyvale, CA (US); Tae Eun Choe, Sunnyvale, CA (US); Yuliang Guo, Sunnyvale, CA (US); Guang Chen, Sunnyvale, CA (US); and Weide Zhang, Sunnyvale, CA (US)
Assigned to BAIDU USA LLC, Sunnyvale, CA (US)
Filed by Baidu USA LLC, Sunnyvale, CA (US)
Filed on Jun. 28, 2019, as Appl. No. 16/457,820.
Prior Publication US 2020/0410252 A1, Dec. 31, 2020
Int. Cl. G06K 9/00 (2006.01); G06K 9/62 (2006.01)
CPC G06K 9/00791 (2013.01) [G06K 9/6202 (2013.01); G06K 9/6218 (2013.01); G06K 9/6256 (2013.01)] 20 Claims
OG exemplary drawing
1. A computer-implemented method for determining anchor boxes for training a neural network object detection model for autonomous driving, the method comprising:
plotting a plurality of bounding boxes in a two-dimensional (2D) space based on their respective dimensions;
clustering the plurality of bounding boxes into one or more clusters of the bounding boxes based on a distribution density of the bounding boxes on the 2D space;
for each of the clusters of bounding boxes, determining an anchor box to represent the corresponding cluster;
determining whether a distribution of the bounding boxes assigned to the anchor boxes satisfies a predetermined condition;
in response to determining that the predetermined condition has not been satisfied, adjusting a dimension of at least one of the anchor boxes on the 2D space; and
training a neural network model for detecting objects using the anchor boxes, wherein the neural network model is utilized to detect objects based on at least one of an image or a point cloud captured by a sensor of an autonomous driving vehicle.