3D Pose-by-Detection of Vehicles via Discriminatively Reduced Ensembles of Correlation Filters

Yair Movshovitz-Attias, Yaser Sheikh, Vishnu Naresh Boddeti and Zijun Wei

In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.53

Abstract

Estimating the precise pose of a 3D model in an image is challenging; explicitly identifying correspondences is difficult, particularly at smaller scales and in the presence of occlusion. Exemplar classifiers have demonstrated the potential of detection-based approaches to problems where precision is required. In particular, correlation filters explicitly suppress classifier response caused by slight shifts in the bounding box. This property makes them ideal exemplar classifiers for viewpoint discrimination, as small translational shifts can often be confounded with small rotational shifts. However, exemplar based pose-by-detection is not scalable because, as the desired precision of viewpoint estimation increases, the number of exemplars needed increases as well. We present a training framework to reduce an ensemble of exemplar correlation filters for viewpoint estimation by directly optimizing a discriminative objective. We show that the discriminatively reduced ensemble outperforms the state-of-the-art on three publicly available datasets and we introduce a new dataset for continuous car pose estimation in street scene images.

Session

Poster Session

Files

Extended Abstract (PDF, 1 page, 1.1M)

Paper (PDF, 12 pages, 4.2M)

Supplemental Materials (ZIP, 2.0M)

Bibtex File

Citation

Yair Movshovitz-Attias, Yaser Sheikh, Vishnu Naresh Boddeti, and Zijun Wei. 3D Pose-by-Detection of Vehicles via Discriminatively Reduced Ensembles of Correlation Filters. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.

BibTex

@inproceedings{BMVC.28.53
	title = {3D Pose-by-Detection of Vehicles via Discriminatively Reduced Ensembles of Correlation Filters},
	author = {Movshovitz-Attias, Yair and Sheikh, Yaser and Naresh Boddeti, Vishnu and Wei, Zijun},
	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.28.53 }
}