Skip to Main content Skip to Navigation
Conference papers

3D Human Pose from Silhouettes by Relevance Vector Regression

Ankur Agarwal 1 Bill Triggs 1
1 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor prior labelling of body pans in the image. Instead, it recovers pose by direct nonlinear regression against shape descriptor vectors extracted automatically from image silhouettes. For robustness against local silhouette segmentation errors, silhouette shape is encoded by histogram-of-shape-contexts descriptors. For the main regression, we evaluate both regularized least squares and relevance vector machine (RVM) regressors over both linear and kernel bases. The RVM's provide much sparser regressors without compromising performance, and kernel bases give a small but worthwhile improvement in performance. For realism and good generalization with respect to viewpoints, we train the regressors on images resynthesized from real human motion capture data, and test it both quantitatively on similar independent test data, and qualitatively on a real image sequence. Mean angular errors of 6-7 degrees are obtained - a factor of 3 better than the current state of the art for the much simpler upper body problem.
Document type :
Conference papers
Complete list of metadata


https://hal.inria.fr/inria-00548551
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 9:09:42 AM
Last modification on : Monday, December 28, 2020 - 3:44:02 PM
Long-term archiving on: : Monday, March 21, 2011 - 3:16:14 AM

Identifiers

Collections

IMAG | CNRS | INRIA | UGA

Citation

Ankur Agarwal, Bill Triggs. 3D Human Pose from Silhouettes by Relevance Vector Regression. International Conference on Computer Vision & Pattern Recognition (CVPR '04), Jun 2004, Washington, United States. pp.882--888, ⟨10.1109/CVPR.2004.1315258⟩. ⟨inria-00548551⟩

Share

Metrics

Record views

961

Files downloads

3382