PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Clustered pose and nonlinear appearance models for human pose estimation
S Johnson and Mark Everingham
In: BMVC 2010, 31 Aug - 3rd Sep 2010, Aberystwyth.

Abstract

We investigate the task of 2D articulated human pose estimation in unconstrained still images. This is extremely challenging because of variation in pose, anatomy, clothing, and imaging conditions. Current methods use simple models of body part appearance and plausible configurations due to limitations of available training data and constraints on computational expense. We show that such models severely limit accuracy. Building on the successful pictorial structure model (PSM) we propose richer models of both appearance and pose, using state-of-the-art discriminative classifiers without introducing unacceptable computational expense. We introduce a new annotated database of challenging consumer images, an order of magnitude larger than currently available datasets, and demonstrate over 50% relative improvement in pose estimation accuracy over a stateof-the-art method.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:7025
Deposited By:Sunando Sengupta
Deposited On:28 November 2010