Robust Estimation of 3D Human Poses from a Single Image | |
Wang, Chunyu ; Wang, Yizhou ; Lin, Zhouchen ; Yuille, Alan L. ; Gao, Wen | |
2014 | |
关键词 | ACTION RECOGNITION BODY POSE |
英文摘要 | Human pose estimation is a key step to action recognition. We propose a method of estimating 3D human poses from a single image, which works in conjunction with an existing 2D pose/joint detector. 3D pose estimation is challenging because multiple 3D poses may correspond to the same 2D pose after projection due to the lack of depth information. Moreover, current 2D pose estimators are usually inaccurate which may cause errors in the 3D estimation. We address the challenges in three ways: (i) We represent a 3D pose as a linear combination of a sparse set of bases learned from 3D human skeletons. (ii) We enforce limb length constraints to eliminate anthropomorphically implausible skeletons. (iii) We estimate a 3D pose by minimizing the L-1-norm error between the projection of the 3D pose and the corresponding 2D detection. The L-1-norm loss term is robust to inaccurate 2D joint estimations. We use the alternating direction method (ADM) to solve the optimization problem efficiently. Our approach outperforms the state-of-the-arts on three benchmark datasets.; CPCI-S(ISTP); 2369-2376 |
语种 | 中文 |
出处 | 2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) |
DOI标识 | 10.1109/CVPR.2014.303 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/424323] |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Wang, Chunyu,Wang, Yizhou,Lin, Zhouchen,et al. Robust Estimation of 3D Human Poses from a Single Image. 2014-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论