Particle dynamics and multi-channel feature dictionaries for robust visual tracking

Srikrishna Karanam, Yang Li and Richard J. Radke

Abstract

We present a novel approach to solve the visual tracking problem in a particle filter framework based on sparse visual representations. Current state-of-the-art trackers use low-resolution image intensity features in target appearance modeling. Such features often fail to capture sufficient visual information about the target. Here, we demonstrate the efficacy of visually richer representation schemes by employing multi-channel feature dictionaries as part of the appearance model. To further mitigate the tracking drift problem, we propose a novel dynamic adaptive state transition model, taking into account the dynamics of the past states. Finally, we demonstrate the computational tractability of using richer appearance modeling schemes by adaptively pruning candidate particles during each sampling step, and using a fast augmented Lagrangian technique to solve the associated optimization problem. Extensive quantitative evaluations and robustness tests on several challenging video sequences demonstrate that our approach substantially outperforms the state of the art, and achieves stable results.

Session

Tracking and Pose Estimation

Files

Extended Abstract (PDF, 114K)
Paper (PDF, 261K)
Supplemental Materials (ZIP, 26M)

DOI

10.5244/C.29.183
https://dx.doi.org/10.5244/C.29.183

Citation

Bibtex

@inproceedings{BMVC2015_183,
	title={Particle dynamics and multi-channel feature dictionaries for robust visual tracking},
	author={Srikrishna Karanam and Yang Li and Richard J. Radke},
	year={2015},
	month={September},
	pages={183.1-183.12},
	articleno={183},
	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.29.183},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.183}
}