Embedding Geometry in Generative Models for Pose Estimation of Object Categories

Michele Fenzi and Jörn Ostermann

In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.22

Abstract

Regression-based models built on local gradient-based feature descriptors have showed to be successful for continuous pose estimation of object categories. Nonetheless, a crucial weakness of these methods is that no geometric information is taken into account. Therefore, geometrically inconsistent poses may be preferred, and this forces to employ a coarse-grained pose estimator as a pre-processing step to avoid potentially large estimation errors. In this paper, we propose a method that combines generative feature models and graph matching techniques in a unified probabilistic formulation of the continuous pose estimation problem. On the one hand, our approach retains the lightness and generality of generative feature modeling, while, on the other hand, favors geometrically consistent results and experimentally shows that pose pre-processing steps are not needed. We evaluated our approach on two different car datasets and we experimentally show that our algorithm outperforms state-of-the-art methods by 25%.

Session

Segmentation and Object Detection

Files

Extended Abstract (PDF, 1 page, 412K)

Paper (PDF, 11 pages, 1.3M)

Bibtex File

Presentation

Citation

Michele Fenzi, and Jörn Ostermann. Embedding Geometry in Generative Models for Pose Estimation of Object Categories. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.

BibTex

@inproceedings{BMVC.28.22
	title = {Embedding Geometry in Generative Models for Pose Estimation of Object Categories},
	author = {Fenzi, Michele and Ostermann, Jörn},
	year = {2014},
	booktitle = {Proceedings of the British Machine Vision Conference},
	publisher = {BMVA Press},
	editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
	doi = { http://dx.doi.org/10.5244/C.28.22 }
}