Can mean shift trackers perform better?

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

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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 languageEnglish
Title of host publicationProceedings of the 6th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2010
EditorsKokou Yetongnon, Richard Chbeir, Albert Dipanda
Place of PublicationPiscataway, NJ (US)
PublisherIEEE
Pages98-101
Number of pages4
ISBN (Print)978-0-7695-4319-2
DOIs
Publication statusPublished - 2010
Event6th International Conference on Signal Image Technology and Internet Based Systems - Kuala Lumpur, Malaysia
Duration: 15 Dec 201018 Dec 2010

Conference

Conference6th International Conference on Signal Image Technology and Internet Based Systems
Abbreviated titleSITIS 2010
CountryMalaysia
CityKuala Lumpur
Period15/12/1018/12/10

Keywords

  • invariants
  • mean shift
  • object tracking

Fingerprint Dive into the research topics of 'Can mean shift trackers perform better?'. Together they form a unique fingerprint.

  • Cite this

    Zhou, H., Schaefer, G., Yuan, Y., & Celebi, M. E. (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 (pp. 98-101). IEEE. https://doi.org/10.1109/SITIS.2010.26