Because better detections are still possible: Multi-aspect Object Detection with Boosted Hough Forest

Carolina Redondo-Cabrera and Roberto López-Sastre

Abstract

In this work, we proceed to deconstruct the HF learning model to investigate whether a considerable better performance can be obtained detecting multi-aspect object categories. We introduce the novel Boosted Hough Forest (BHF): a HF where all the decision trees of the forest are trained in a stage-wise fashion, by optimizing a global differentiable loss function with Gradient Boosting, and using the concept of intermediate Hough voting spaces. This is in contrast to the local optimization performed in each tree node during the training of a standard HF. We also show how the multiple aspects of the object categories can be incorporated into the learning model by simply augmenting the dimensionality of the Hough voting spaces of the BHF. This allows our approach to naturally infer the pose of an object, simultaneously with the detection, for example. The experimental validation, considering four different datasets, confirms that the performance of the HF is improved by the new BHF.

Session

Poster 1

Files

Extended Abstract (PDF, 9M)
Paper (PDF, 9M)
Supplemental Materials (ZIP, 7M)

DOI

10.5244/C.29.63
https://dx.doi.org/10.5244/C.29.63

Citation

Bibtex

@inproceedings{BMVC2015_63,
	title={Because better detections are still possible: Multi-aspect Object Detection with Boosted Hough Forest},
	author={Carolina Redondo-Cabrera and Roberto López-Sastre},
	year={2015},
	month={September},
	pages={63.1-63.12},
	articleno={63},
	numpages={12},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.63},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.63}
}