Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling

Massimo Camplani, Sion Hannuna, Majid Mirmehdi, Dima Damen, Adeline Paiement, Lili Tao and Tilo Burghardt

Abstract

We present a real-time RGB-D object tracker which manages occlusions and scale changes in a wide variety of scenarios. Its accuracy matches, and in many cases outperforms, state-of-the-art algorithms for precision and it far exceeds most in speed. We build our algorithm on the existing colour-only KCF tracker which uses the `kernel trick' to extend correlation filters for fast tracking. We fuse colour and depth cues as the tracker's features, and furthermore, exploit the depth data to both adjust a given target's scale, and detect and manage occlusions in such a way as to maintain real-time performance, exceeding on average 40~fps. We benchmark our approach using 2 publicly available datasets and make our easy-to-extend modularised code available to other researchers.

Session

Poster 2

Files

Extended Abstract (PDF, 533K)
Paper (PDF, 1016K)

DOI

10.5244/C.29.145
https://dx.doi.org/10.5244/C.29.145

Citation

Bibtex

@inproceedings{BMVC2015_145,
	title={Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling},
	author={Massimo  Camplani and Sion Hannuna and Majid Mirmehdi and Dima Damen and Adeline Paiement and Lili  Tao and Tilo Burghardt},
	year={2015},
	month={September},
	pages={145.1-145.11},
	articleno={145},
	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.29.145},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.145}
}