Can mean shift trackers perform better?

Huiyu Zhou; Gerald Schaefer; Yuan Yuan; M. Emre Celebi

doi:10.1109/SITIS.2010.26

Can mean shift trackers perform better?

Huiyu Zhou^*, Gerald Schaefer, Yuan Yuan, M. Emre Celebi

^*Corresponding author for this work

Computer Science Research Group

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

Many tracking algorithms have difficulties dealing with occlusions and background clutters, and consequently don't converge to an appropriate solution. Tracking based on the mean shift algorithm has shown robust performance in many circumstances but still fails e.g. when encountering dramatic intensity or colour changes in a pre-defined neighbourhood. In this paper, we present a robust tracking algorithm that integrates the advantages of mean shift tracking with those of tracking local invariant features. These features are integrated into the mean shift formulation so that tracking is performed based both on mean shift and feature probability distributions, coupled with an expectation maximisation scheme. Experimental results show robust tracking performance on a series of complicated real image sequences.

Original language	English
Title of host publication	Proceedings of the 6th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2010
Editors	Kokou Yetongnon, Richard Chbeir, Albert Dipanda
Place of Publication	Piscataway, NJ (US)
Publisher	IEEE
Pages	98-101
Number of pages	4
ISBN (Print)	978-0-7695-4319-2
DOIs	https://doi.org/10.1109/SITIS.2010.26
Publication status	Published - 2010
Event	6th International Conference on Signal Image Technology and Internet Based Systems - Kuala Lumpur, Malaysia Duration: 15 Dec 2010 → 18 Dec 2010

Conference

Conference	6th International Conference on Signal Image Technology and Internet Based Systems
Abbreviated title	SITIS 2010
Country/Territory	Malaysia
City	Kuala Lumpur
Period	15/12/10 → 18/12/10

Keywords

invariants
mean shift
object tracking

Access to Document

10.1109/SITIS.2010.26

Cite this

@inproceedings{1ce9cd918dbc41f7972604c3b112a74a,

title = "Can mean shift trackers perform better?",

abstract = "Many tracking algorithms have difficulties dealing with occlusions and background clutters, and consequently don't converge to an appropriate solution. Tracking based on the mean shift algorithm has shown robust performance in many circumstances but still fails e.g. when encountering dramatic intensity or colour changes in a pre-defined neighbourhood. In this paper, we present a robust tracking algorithm that integrates the advantages of mean shift tracking with those of tracking local invariant features. These features are integrated into the mean shift formulation so that tracking is performed based both on mean shift and feature probability distributions, coupled with an expectation maximisation scheme. Experimental results show robust tracking performance on a series of complicated real image sequences.",

keywords = "invariants, mean shift, object tracking",

author = "Huiyu Zhou and Gerald Schaefer and Yuan Yuan and Celebi, {M. Emre}",

year = "2010",

doi = "10.1109/SITIS.2010.26",

language = "English",

isbn = "978-0-7695-4319-2",

pages = "98--101",

editor = "Kokou Yetongnon and Richard Chbeir and Albert Dipanda",

booktitle = "Proceedings of the 6th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2010",

publisher = "IEEE",

address = "United States",

note = "6th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2010 ; Conference date: 15-12-2010 Through 18-12-2010",

}

Zhou, H, Schaefer, G, Yuan, Y & Celebi, ME 2010, Can mean shift trackers perform better? in K Yetongnon, R Chbeir & A Dipanda (eds), Proceedings of the 6th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2010. IEEE, Piscataway, NJ (US), pp. 98-101, 6th International Conference on Signal Image Technology and Internet Based Systems, Kuala Lumpur, Malaysia, 15/12/10. https://doi.org/10.1109/SITIS.2010.26

Can mean shift trackers perform better? / Zhou, Huiyu; Schaefer, Gerald; Yuan, Yuan et al.
Proceedings of the 6th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2010. ed. / Kokou Yetongnon; Richard Chbeir; Albert Dipanda. Piscataway, NJ (US): IEEE, 2010. p. 98-101.

Research output: Chapter in Book/Published conference output › Conference publication