Robust Estimation of 3D Human Poses from a Single Image
Name
CBMM-Memo-013.pdf
Size
510.23 KB
Format
Adobe PDF
Checksum (MD5)
baf3bfdbf65c06a62869ace525d3e771
Author(s)
Wang, Chunyu
Wang, Yizhou
Lin, Zhouchen
Yuille, Alan L.
Gao, Wen
Date Issued
June 10, 2014
Publisher
Center for Brains, Minds and Machines (CBMM), arXiv
Citation
arXiv:1406.2282v1
Series/Report no.
CBMM Memo Series;013
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.
Subjects
Action Recognition
Artificial Intelligence
Machine Learning
Computer vision
Terms of Use
Attribution-NonCommercial 3.0 United States
Persistent DSpace Link
