Multipath affinage stacked-hourglass networks for human pose estimation  

作　　者：Guoguang HUA Lihong LI Shiguang LIU 

机构地区：[1]School of Information and Electrical Engineering,Hebei University of Engineering,Handan,056038,China [2]School of Computer Science and Technology,Division of Intelligence and Computing,Tianjin University,Tianjin,300350,China

出　　处：《Frontiers of Computer Science》2020年第4期155-165,共11页中国计算机科学前沿（英文版）

基　　金：This work was supported by the National Natural Science Foundation of China(Grant Nos.61672375 and 61170118).

摘　　要：Recently,stacked hourglass network has shown outstanding performance in human pose estimation.However,repeated bottom-up and top-down stride convolution operations in deep convolutional neural networks lead to a significant decrease in the initial image resolution.In order to address this problem,we propose to incorporate affinage module and residual attention module into stacked hourglass network for human pose estimation.This paper introduces a novel network architecture to replace the stacked hourglass network of up-sampling operation for getting high-resolution features.We refer to the architecture as an affinage module which is critical to improve the performance of the stacked hourglass network.Additionally,we also propose a novel residual attention module to increase the supervision of up-sample process.The effectiveness of the introduced module is evaluated on standard benchmarks.Various experimental results demonstrated that our method can achieve more accurate and more robust human pose estimation results in images with complex background.

关 键 词：human pose estimation stacked hourglass network affinage module residual attention module 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]