Scale and orientation adaptive histogram-based object tracking in video sequences

  • Zicheng Ren
  • , Youngshin Ahn
  • , Jaeho Choi

Research output: Contribution to conferenceConference paperpeer-review

Abstract

Object tracking is one of the essential parts in robot vision. Among many proposed, the mean shift algorithm is robust and accurate, however, it has a room to improve when the objects of interest undergo scaling and/or rotation changes. In this paper, on top of the standard histogram-based tracking algorithm, a novel method for adapting to changes in scale and orientation is incorporated as a means to improve moving objects tracking performance. Using various test video sets, computer simulations are run to verify the tracking performance of the proposed tracking system and compared to those of the conventional mean-shift algorithm. The results show that the proposed method outperforms the conventional MSA in terms of tracking accuracy.

Original languageEnglish
Title of host publicationComputational Vision and Medical Image Processing IV - Proceedings of Eccomas Thematic Conference on Computational Vision and Medical Image Processing, VIPIMAGE 2013
EditorsJoão Manuel, R.S. Tavares, R.M. Natal Jorge
PublisherCRC Press/Balkema
Pages45-50
Number of pages6
ISBN (Print)9781138000810
DOIs
StatePublished - 2014
Event4th Eccomas Thematic Conference on Computational Vision and Medical Image Processing, VIPIMAGE 2013 - Funchal, Portugal
Duration: 2013.10.142014.10.16

Publication series

NameComputational Vision and Medical Image Processing IV - Proceedings of Eccomas Thematic Conference on Computational Vision and Medical Image Processing, VIPIMAGE 2013

Conference

Conference4th Eccomas Thematic Conference on Computational Vision and Medical Image Processing, VIPIMAGE 2013
Country/TerritoryPortugal
CityFunchal
Period13.10.1414.10.16

Quacquarelli Symonds(QS) Subject Topics

  • Computer Science & Information Systems
  • Engineering - Electrical & Electronic
  • Engineering - Petroleum
  • Data Science
  • Biological Sciences

Fingerprint

Dive into the research topics of 'Scale and orientation adaptive histogram-based object tracking in video sequences'. Together they form a unique fingerprint.

Cite this