文献类型：期刊文献

英文题名：Lightweight human pose estimation algorithm based on polarized self-attention

作者：Liu, Shengjie[1];He, Ning[2];Wang, Cheng[1];Yu, Haigang[1];Han, Wenjing[2]

第一作者：Liu, Shengjie

通讯作者：He, N[1]

机构：[1]Beijing Union Univ, Coll Robot, Beijing Key Lab Informat Serv Engn, Beijing, Peoples R China;[2]Beijing Union Univ, Coll Smart City, Beijing, Peoples R China

第一机构：北京联合大学北京市信息服务工程重点实验室|北京联合大学机器人学院

通讯机构：[1]corresponding author), Beijing Union Univ, Coll Smart City, Beijing, Peoples R China.|[11417]北京联合大学;

年份：0

外文期刊名：MULTIMEDIA SYSTEMS

收录：;EI(收录号：20223412609957);Scopus(收录号：2-s2.0-85136207061);WOS:【SCI-EXPANDED(收录号:WOS:000841119100002)】；

基金：This work was supported by the National Natural Science Foundation of China (61872042, 62172045), the Key Project of Beijing Municipal Commission of Education (KZ201911417048), the National Key Research and Development Program (2018AAA0100804), the Science and Technology Project of Beijing Municipal Commission of Education (No. KM201811417005202111417009), Beijing Union University Scientific Research Project (No. ZK50202001).

语种：英文

外文关键词：Human pose estimation; Polarized self-attention; Ghost module; Coordinate decoding

摘要：In recent years, human pose estimation has been widely used in human-computer interaction, augmented reality, video surveillance, and many other fields, but the task of pose estimation still faces many challenges. To address the large number of parameters and complicated calculation in the current mainstream human pose estimation network, this paper proposes a lightweight pose estimation network (Lightweight Polarized Network, referred to as LPNet) based on a polarized self-attention mechanism. First, ghost convolution is used to reduce the number of parameters of the feature extraction network; second, by introducing the polarized self-attention module, the pixel-level regression task can be better solved, the lack of extracted features due to the decrease in the number of parameters can be reduced, and the accuracy of the regression of human keypoints can be improved; finally, a new coordinate decoding method is designed to reduce the error in the heatmap decoding process and improve the accuracy of keypoint regression. The method proposed in this paper was evaluated on the human keypoint detection datasets COCO and MPII, and compared with the current mainstream methods. The experimental results show that the proposed method greatly reduces the number of parameters of the model while ensuring a small loss in accuracy.