US 12,169,783 B2
Pedestrian detection method and apparatus, computer-readable storage medium, and chip
Qixiang Ye, Beijing (CN); Tianliang Zhang, Shenzhen (CN); Jianzhuang Liu, Shenzhen (CN); Xiaopeng Zhang, Shanghai (CN); Qi Tian, Shenzhen (CN); and Lihui Jiang, Shenzhen (CN)
Assigned to Huawei Technologies Co., Ltd., Shenzhen (CN)
Filed by HUAWEI TECHNOLOGIES CO., LTD., Guangdong (CN)
Filed on Jan. 27, 2022, as Appl. No. 17/586,136.
Application 17/586,136 is a continuation of application No. PCT/CN2020/105020, filed on Jul. 28, 2020.
Claims priority of application No. 201910697411.3 (CN), filed on Jul. 30, 2019.
Prior Publication US 2022/0148328 A1, May 12, 2022
Int. Cl. G06N 3/084 (2023.01); G06F 18/25 (2023.01); G06N 3/045 (2023.01); G06V 10/20 (2022.01); G06V 10/77 (2022.01); G06V 10/80 (2022.01); G06V 10/82 (2022.01); G06V 20/40 (2022.01); G06V 20/52 (2022.01); G06V 20/58 (2022.01); G06V 40/10 (2022.01)
CPC G06N 3/084 (2013.01) [G06F 18/253 (2023.01); G06N 3/045 (2023.01); G06V 10/255 (2022.01); G06V 10/7715 (2022.01); G06V 10/806 (2022.01); G06V 10/809 (2022.01); G06V 10/82 (2022.01); G06V 20/40 (2022.01); G06V 20/52 (2022.01); G06V 20/58 (2022.01); G06V 40/10 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A pedestrian detection method, comprising:
obtaining an image;
performing feature extraction on the image to obtain a basic feature map of the image;
determining, based on the basic feature map of the image, a proposal of the image, wherein the proposal of the image is a bounding box of a region comprising a pedestrian in the image;
processing the basic feature map of the image to obtain an object visibility map of the image, wherein a pixel value of a pedestrian visible part in the object visibility map of the image is greater than a pixel value of a pedestrian invisible part in the object visibility map of the image;
performing fusion processing on the basic feature map of the image and the object visibility map of the image to obtain an enhanced feature map of the image;
determining, based on the proposal of the image and the enhanced feature map of the image, a feature corresponding to the proposal of the image, wherein the feature corresponding to the proposal of the image comprises a region feature of the proposal of the image, and the region feature of the proposal of the image is a feature of a region that is in the enhanced feature map and that is located in the proposal of the image; and
determining, based on the feature corresponding to the proposal of the image, the bounding box comprising the pedestrian in the image and a confidence level of the bounding box comprising the pedestrian in the image.