基于深度学习的二维单人姿态估计综述  

Review on Deep Learning-Based 2D Single-Person Pose Estimation

作　　者：苏妍妍 邱志良 李帼 陆声链[1,2] 陈明[1,2] SU Yanyan;QIU Zhiliang;LI Guo;LU Shenglian;CHEN Ming(Key Lab of Education Blockchain and Intelligent Technology,Ministry of Education,Guangxi Normal University,Guilin,Guangxi 541004,China;College of Computer Science and Engineering,Guangxi Normal University,Guilin,Guangxi 541004,China)

机构地区：[1]广西师范大学教育区块链与智能技术教育部重点实验室,广西桂林541004 [2]广西师范大学计算机科学与工程学院,广西桂林541004

出　　处：《计算机工程与应用》2024年第21期18-37,共20页Computer Engineering and Applications

基　　金：国家自然科学基金(61762013)。

摘　　要：人体姿态估计是计算机视觉领域的一项关键技术,它通过检测人体关键点以识别人体姿态。随着深度学习的快速发展,其已成为人体姿态估计的主流技术并取得了显著进展。围绕单人姿态估计问题,从数据预处理、网络架构设计、监督学习方法以及后处理技术四个维度对基于深度学习的单人姿态估计研究进行回顾,同时探讨关键点表征的新方式及Transformer模型在该领域的应用,此外还介绍了常用的数据集和性能估计指标,深入讨论当前单人姿态估计领域的挑战和发展方向。Human pose estimation is a key technology in the field of computer vision that identifies human postures by detecting body keypoints.With the rapid advancement of deep learning,it has become the dominant approach in human pose estimation,achieving significant progress.This paper reviews single-person pose estimation research based on deep learning,examining the issue from four perspectives:data preprocessing,network architecture design,supervised learning methods,and post-processing techniques.It also explores new representations of keypoints and the application of Transformer models in this area.Additionally,the paper introduces common datasets and performance metrics,and delves into the current challenges and future directions in the field of single-person pose estimation.

关 键 词：二维人体姿态估计 单人姿态估计 深度学习 关键点检测 计算机视觉 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]