基于深度学习的人体姿态估计方法综述  

Review of Deep Learning-Based Human Pose Estimation

作　　者：卢健[1] 杨腾飞 赵博 王航英 罗毛欣 周嫣然 李哲 Lu Jian;Yang Tengfei;Zhao Bo;Wang Hangying;Luo Maoxin;Zhou Yanran;Li Zhe(School of Electronics and Information,Xi'an Polytechnic University,Xi'an,Shaanei 710048,China)

机构地区：[1]西安工程大学电子信息学院,陕西西安710048

出　　处：《激光与光电子学进展》2021年第24期61-80,共20页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61971339,61471161);陕西省自然科学基金(2018JQ4016);西安市碑林区应用技术研发项目(GX2007)。

摘　　要：全面综述了基于深度学习的人体姿态估计方法的研究进展。在比较分析各类单人姿态估计方法的基础上,从自上而下和自下而上两个方法角度总结了多人姿态估计算法。在自上而下方法中,着重介绍了局部区域重叠、关节点混淆、人体非典型部位关节点难以检测等问题的解决方案;在自下而上的方法中,重点关注聚类方法对关节点检测的贡献。对目前公共数据集上取得优异性能的代表性方法进行了对比和分析。这样做的目的是使研究者了解和熟悉该领域已有的研究成果,拓展研究思路和方法,并展望未来可能出现的研究方向。The research progress of human pose estimation method based on deep learning is comprehensively summarized. On the basis of comparison and analysis of various single-person pose estimation methods, a variety of multi-person pose estimation algorithms are summarized from the top-down and bottom-up approaches. In the top-down approach, the solutions to local area overlap, articulation point confusion, and difficulty in detecting the articulation point of atypical parts of human body are mainly introduced. In the bottom-up approach, the contribution of clustering method to articulation point detection is emphasized. Representative methods to achieve excellent performance on current public datasets are compared and analyzed. The review enables researchers to understand and familiarize themselves with the existing research results in this field, expand research ideas and methods, and look forward to the possible research directions in the future.

关 键 词：机器视觉 深度学习 人体姿态估计 关节点检测 公共数据集 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]