Sciweavers

Share
ACCV
2009
Springer

Estimating Human Pose from Occluded Images

9 years 9 months ago
Estimating Human Pose from Occluded Images
We address the problem of recovering 3D human pose from single 2D images, in which the pose estimation problem is formulated as a direct nonlinear regression from image observation to 3D joint positions. One key issue that has not been addressed in the literature is how to estimate 3D pose when humans in the scenes are partially or heavily occluded. When occlusions occur, features extracted from image observations (e.g., silhouettes-based shape features, histogram of oriented gradient, etc.) are seriously corrupted, and consequently the regressor (trained on un-occluded images) is unable to estimate pose states correctly. In this paper, we present a method that is capable of handling occlusions using sparse signal representations, in which each test sample is represented as a compact linear combination of training samples. The sparsest solution can then be efficiently obtained by solving a convex optimization problem with certain norms (such as l1-norm). The corrupted test image can ...
Jia-Bin Huang and Ming-Hsuan Yang
AttachmentsSize
ACCV Oral Presentation Slides2.78 MB
Added 26 Jan 2010
Updated 19 Mar 2010
Type Conference
Year 2009
Where ACCV
Authors Jia-Bin Huang and Ming-Hsuan Yang
Attachments 1 file(s)
Comments (0)
books