US 12,148,204 B2
Target detection method and apparatus
Feng Li, Suzhou (CN); and Xiaojuan Cheng, Suzhou (CN)
Assigned to Inspur Suzhou Intelligent Technology Co., Ltd., Suzhou (CN)
Appl. No. 17/778,662
Filed by Inspur Suzhou Intelligent Technology Co., Ltd., Suzhou (CN)
PCT Filed Jul. 23, 2020, PCT No. PCT/CN2020/103701
§ 371(c)(1), (2) Date May 20, 2022,
PCT Pub. No. WO2021/098261, PCT Pub. Date May 27, 2021.
Claims priority of application No. 201911157879.X (CN), filed on Nov. 22, 2019.
Prior Publication US 2023/0045519 A1, Feb. 9, 2023
Int. Cl. G06K 9/00 (2022.01); G06V 10/25 (2022.01); G06V 10/42 (2022.01); G06V 10/44 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/82 (2022.01) [G06V 10/25 (2022.01); G06V 10/42 (2022.01); G06V 10/44 (2022.01); G06V 2201/07 (2022.01)] 6 Claims
OG exemplary drawing
 
1. A target detection method, comprising the following steps:
acquiring an input image, and sending same to a candidate region generation network to generate a plurality of regions of interest;
adjusting the plurality of regions of interest to a same size, and then sending same to a target key point network to generate a heat map;
using a global feature map of the input image to perform convolution on the heat map, so as to generate a local depth feature map wherein the global feature map is generated by a global feature generation network; and
fusing the global feature map and the local depth feature map, and detecting a target therefrom by means of a detector.