Deep Learning Based 2D Human Pose Estimation: A Survey
Deep Learning Based 2D Human Pose Estimation: A Survey
复制标题
基于深度学习的二维人体姿势估计：一项调查
DOI：
10.26599/tst.2018.9010100
复制
发表时间：
2019-12-01
影响因子：
6.6
通讯作者：
Zheng, Wenqing
中科院分区：
文献类型：
--
作者：
Dang, Qi;Yin, Jianqin;Zheng, Wenqing
人体姿态估计由于其在现实世界中的各种应用，近年来受到了极大的关注。由于深度学习可以提高现有的人体姿态估计方法的性能，本文对基于深度学习的人体姿态估计方法进行了全面的综述，并对所采用的方法进行了分析。我们用基于方法论的分类法总结和讨论了最近的工作。首先对单人管道和多人管道分别进行审查。然后，对深度学习技术在这些管道中的应用进行了比较和分析。还讨论和比较了本任务中使用的数据集和指标。这项调查的目的是使评估渠道中的每一个步骤都可以解释，并为读者提供一个容易理解的解释。此外，还讨论了尚未解决的问题和未来研究的挑战。
Human pose estimation has received significant attention recently due to its various applications in the real world. As the performance of the state-of-the-art human pose estimation methods can be improved by deep learning, this paper presents a comprehensive survey of deep learning based human pose estimation methods and analyzes the methodologies employed. We summarize and discuss recent works with a methodology-based taxonomy. Single-person and multi-person pipelines are first reviewed separately. Then, the deep learning techniques applied in these pipelines are compared and analyzed. The datasets and metrics used in this task are also discussed and compared. The aim of this survey is to make every step in the estimation pipelines interpretable and to provide readers a readily comprehensible explanation. Moreover, the unsolved problems and challenges for future research are discussed.