dc.contributor.author | Wang, Chunyu | |
dc.contributor.author | Wang, Yizhou | |
dc.contributor.author | Lin, Zhouchen | |
dc.contributor.author | Yuille, Alan L. | |
dc.contributor.author | Gao, Wen | |
dc.date.accessioned | 2015-12-10T22:43:51Z | |
dc.date.available | 2015-12-10T22:43:51Z | |
dc.date.issued | 2014-06-10 | |
dc.identifier.uri | http://hdl.handle.net/1721.1/100177 | |
dc.description.abstract | 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 L1 -norm error between the projection of the 3D pose and the corresponding 2D detection. The L1-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. | en_US |
dc.description.sponsorship | This work was supported by the Center for Brains, Minds and Machines
(CBMM), funded by NSF STC award CCF - 1231216. | en_US |
dc.language.iso | en_US | en_US |
dc.publisher | Center for Brains, Minds and Machines (CBMM), arXiv | en_US |
dc.relation.ispartofseries | CBMM Memo Series;013 | |
dc.rights | Attribution-NonCommercial 3.0 United States | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc/3.0/us/ | * |
dc.subject | Action Recognition | en_US |
dc.subject | Artificial Intelligence | en_US |
dc.subject | Machine Learning | en_US |
dc.subject | Computer vision | en_US |
dc.title | Robust Estimation of 3D Human Poses from a Single Image | en_US |
dc.type | Technical Report | en_US |
dc.type | Working Paper | en_US |
dc.type | Other | en_US |
dc.identifier.citation | arXiv:1406.2282v1 | en_US |