PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Deformable Part Models Revisited: A Performance Evaluation for Object Category Pose Estimation
R.J. Lopez-Sastre, Tinne Tuytelaars and S. Savarese
In: ICCV, 1st IEEE Workshop on Challenges and Opportunities in Robot Perception, 12 November 2011, Barcelona, Spain.

Abstract

Deformable Part Models (DPMs) as introduced by Felzenszwalb et al. have shown remarkably good results for category-level object detection. In this paper, we explore whether they are also well suited for the related problem of category-level object pose estimation. To this end, we extend the original DPM so as to improve its accuracy in object category pose estimation and design novel and more effective learning strategies. We benchmark the methods using various publicly available data sets. Provided that the training data is sufficiently balanced and clean, our method outperforms the state-of-the-art.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:9293
Deposited By:Tinne Tuytelaars
Deposited On:21 February 2012