ER-Net:Efficient Recalibration Network for Multi-ViewMulti-Person 3D Pose Estimation

作     者：Mi Zhou Rui Liu Pengfei Yi Dongsheng Zhou 

作者机构：National and Local Joint Engineering Laboratory of Computer Aided DesignSchool of Software EngineeringDalian UniversityDalian116622China School of Computer Science and TechnologyDalian University of TechnologyDalian116024China 

出 版 物：《Computer Modeling in Engineering & Sciences》 (工程与科学中的计算机建模（英文）)

年 卷 期：2023年第136卷第8期

页      面：2093-2109页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：supported in part by the Key Program of NSFC (Grant No.U1908214) Special Project of Central Government Guiding Local Science and Technology Development (Grant No.2021JH6/10500140) Program for the Liaoning Distinguished Professor,Program for Innovative Research Team in University of Liaoning Province (LT2020015) Dalian (2021RT06)and Dalian University (XLJ202010) the Science and Technology Innovation Fund of Dalian (Grant No.2020JJ25CY001) Dalian University Scientific Research Platform Project (No.202101YB03) 

主　　题：Multi-view multi-person pose estimation attention mechanism computer vision 

摘      要：Multi-view multi-person 3D human pose estimation is a hot topic in the field of human pose estimation due to its wide range of application *** the introduction of end-to-end direct regression methods,the field has entered a new stage of ***,the regression results of joints that are more heavily influenced by external factors are not accurate enough even for the optimal *** this paper,we propose an effective feature recalibration module based on the channel attention mechanism and a relative optimal calibration strategy,which is applied to themulti-viewmulti-person 3D human pose estimation task to achieve improved detection accuracy for joints that are more severely affected by external ***,it achieves relative optimal weight adjustment of joint feature information through the recalibration module and strategy,which enables the model to learn the dependencies between joints and the dependencies between people and their corresponding *** call this method as the Efficient Recalibration Network(ER-Net).Finally,experiments were conducted on two benchmark datasets for this task,Campus and Shelf,in which the PCP reached 97.3% and 98.3%,respectively.