计算机工程与应用 ›› 2021, Vol. 57 ›› Issue (10): 26-38.DOI: 10.3778/j.issn.1002-8331.2102-0039

• 热点与综述 • 上一篇    下一篇

三维人体姿态估计研究综述

王发明,李建微,陈思喜   

  1. 福州大学 物理与信息工程学院,福州 350116
  • 出版日期:2021-05-15 发布日期:2021-05-10

Overview of Research on 3D Human Pose Estimation

WANG Faming, LI Jianwei, CHEN Sixi   

  1. College of Physics and Information Engineering, Fuzhou University, Fuzhou 350116, China
  • Online:2021-05-15 Published:2021-05-10

摘要:

三维人体姿态估计在本质上是一个分类问题和回归问题,主要通过图像估计人体的三维姿态。基于传统方法和深度学习方法的三维人体姿态估计是当前研究的主流方法。按照传统方法到深度学习方法的顺序对近年来三维人体姿态估计方法进行系统介绍,从而了解传统方法通过生成和判别等方法得到人体姿态的众多要素完成三维人体姿态的估计。基于深度学习的三维人体姿态估计方法主要通过构建神经网络,从图像特征中回归出人体姿态信息,大致可以分为基于直接回归方法、基于2D信息方法和基于混合方法的三维人体姿态估计这三类。最后对当前三维人体姿态估计研究所面临的困难与挑战进行阐述,并对未来的研究趋势做出展望。

关键词: 三维人体姿态估计, 神经网络, 深度学习, 关键点检测, 回归与检测

Abstract:

The 3D human pose estimation is essentially a classification and regression problem. It mainly estimates the 3D human pose from images. The 3D human pose estimation based on traditional methods and deep learning methods is the mainstream research method in this field. This paper follows the traditional methods to the deep learning methods to systematically introduce the 3D human posture estimation methods in recent years, and basically understands the traditional methods to obtain the many elements of the human posture through the generation and discrimination methods to complete the 3D human posture estimation. The 3D human pose estimation method based on deep learning mainly regresses the human pose information from the image features by constructing a neural network. It can be roughly divided into three categories:based on direct regression methods, based on 2D information methods, and based on hybrid methods. In the end, it summarizes the current research difficulties and challenges, and discusses the research trends.

Key words: 3D human pose estimation, neural network, deep learning, key point detection, regression and detection