Universal Hough dictionaries for object tracking

Fausto Milletari, Wadim Kehl, Federico Tombari, Slobodan Ilic, Seyed-Ahmad Ahmadi and Nassir Navab

Abstract

We propose a novel approach to online visual tracking that combines the robustness of sparse coding with the flexibility of voting-based methods. Our algorithm relies on a dictionary that is learned once and for all from a large set of training patches extracted from images unrelated to the test sequences. In this way we obtain basis functions, also known as atoms, that can be sparsely combined to reconstruct local image content. In order to adapt the generic knowledge encoded in the dictionary to the specific object being tracked, we associate a set of votes and local object appearances to each atom: this is the only information being updated during online tracking. In each frame of the sequence the object's bounding box position is retrieved through a voting strategy. Our method exhibits robustness towards occlusions, sudden local and global illumination changes as well as shape changes. We test our method on 50 standard sequences obtaining results comparable or superior to the state of the art.

Session

Poster 2

Files

Extended Abstract (PDF, 1782K)
Paper (PDF, 4M)

DOI

10.5244/C.29.122
https://dx.doi.org/10.5244/C.29.122

Citation

Bibtex

@inproceedings{BMVC2015_122,
	title={Universal Hough dictionaries for object tracking},
	author={Fausto Milletari and Wadim Kehl and Federico Tombari and Slobodan Ilic and Seyed-Ahmad Ahmadi and Nassir Navab},
	year={2015},
	month={September},
	pages={122.1-122.11},
	articleno={122},
	numpages={11},
	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.29.122},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.122}
}