SDICP: Semi-Dense Tracking based on Iterative Closest Points

Laurent Kneip, Zhou Yi and Hongdong Li

Abstract

This paper introduces a novel strategy for real-time monocular camera tracking over the recently introduced, efficient semi-dense depth maps. We employ a geometric iterative closest point technique instead of a photometric error criterion, which has the conceptual advantage of requiring neither isotropic enlargement of the employed semi-dense regions, nor pyramidal subsampling. We outline the detailed concepts leading to robustness and efficiency even for large frame-to-frame disparities. We demonstrate successful real-time processing over very large view-point changes and significantly corrupted semi-dense depth-maps, thus underlining the validity of our geometric approach.

Session

Poster 2

Files

PDF iconExtended Abstract (PDF, 362K)
PDF iconPaper (PDF, 2M)

DOI

10.5244/C.29.100
https://dx.doi.org/10.5244/C.29.100

Citation

Laurent Kneip, Zhou Yi and Hongdong Li. SDICP: Semi-Dense Tracking based on Iterative Closest Points. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 100.1-100.12. BMVA Press, September 2015.

Bibtex

@inproceedings{BMVC2015_100,
	title={SDICP: Semi-Dense Tracking based on Iterative Closest Points},
	author={Laurent Kneip and Zhou Yi and Hongdong Li},
	year={2015},
	month={September},
	pages={100.1-100.12},
	articleno={100},
	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.29.100},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.100}
}