Enhanced adaptive bandwidth tracking using mean shift algorithm

Seyed Amir Mohammadi, Sana Amoozegar, Alireza Jolfaei, Abdolrasoul Mirghadri

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

8 Citations (Scopus)

Abstract

The traditional color-based mean shift tracking algorithm is a popular method in colored object tracking due to its simple and efficient procedure, however, its constant tracking bandwidth makes it unsuitable for objects that have variable size during tracking. In this paper, we propose Enhanced Mean Shift Tracker (EMST) which has adaptive bandwidth. Our proposed method solves the problems of the original algorithms related to accuracy and rigid bandwidth. The experimental results show that the new method is feasible, robust and has a good speed in comparison with other algorithms.
Original languageEnglish
Title of host publicationIEEE 3rd International Conference on Communication Software and Networks
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages494-498
Number of pages5
ISBN (Electronic)9781612844862
ISBN (Print)9781612844855
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event2011 IEEE 3rd International Conference on Communication Software and Networks, ICCSN 2011 - Xi'an, China
Duration: 27 May 201129 May 2011

Other

Other2011 IEEE 3rd International Conference on Communication Software and Networks, ICCSN 2011
Country/TerritoryChina
CityXi'an
Period27/05/1129/05/11

Keywords

  • adaptive bandwidth
  • mean shift algorithm
  • object tracking

Fingerprint

Dive into the research topics of 'Enhanced adaptive bandwidth tracking using mean shift algorithm'. Together they form a unique fingerprint.

Cite this