Details
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the British Machine Vision Conference 2014 |
| Editors | Michel Valstar, Andrew French, Tony Pridmore |
| Publication status | Published - 2014 |
| Event | 25th British Machine Vision Conference, BMVC 2014 - Nottingham, United Kingdom (UK) Duration: 1 Sept 2014 → 5 Sept 2014 |
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. Our approach retains the lightness and generality of generative feature modeling, while favoring geometrically consistent results. Experiments show that pose pre-processing steps are not needed if geometry is embedded in the matching stage. We evaluated our approach on two different car datasets and we experimentally show that our algorithm outperforms state-of-the-art methods by 25%.
ASJC Scopus subject areas
- Computer Science(all)
- Computer Vision and Pattern Recognition
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Proceedings of the British Machine Vision Conference 2014. ed. / Michel Valstar; Andrew French; Tony Pridmore. 2014.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Embedding Geometry in Generative Models for Pose Estimation of Object Categories
AU - Fenzi, Michele
AU - Ostermann, Jörn
PY - 2014
Y1 - 2014
N2 - 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. Our approach retains the lightness and generality of generative feature modeling, while favoring geometrically consistent results. Experiments show that pose pre-processing steps are not needed if geometry is embedded in the matching stage. We evaluated our approach on two different car datasets and we experimentally show that our algorithm outperforms state-of-the-art methods by 25%.
AB - 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. Our approach retains the lightness and generality of generative feature modeling, while favoring geometrically consistent results. Experiments show that pose pre-processing steps are not needed if geometry is embedded in the matching stage. We evaluated our approach on two different car datasets and we experimentally show that our algorithm outperforms state-of-the-art methods by 25%.
UR - http://www.scopus.com/inward/record.url?scp=85085406097&partnerID=8YFLogxK
U2 - 10.5244/c.28.22
DO - 10.5244/c.28.22
M3 - Conference contribution
AN - SCOPUS:85085406097
SN - 1-901725-52-9
BT - Proceedings of the British Machine Vision Conference 2014
A2 - Valstar, Michel
A2 - French, Andrew
A2 - Pridmore, Tony
T2 - 25th British Machine Vision Conference, BMVC 2014
Y2 - 1 September 2014 through 5 September 2014
ER -