Motion-Based Feature Selection and Adaptive Template Update Strategy for Robust Visual Tracking

Baofeng Wang, Zhiquan Qi, Sizhong Chen

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

4 Citations (Scopus)

Abstract

The Kanade-Lucas-Tomasi(KLT) method is a classictracking algorithm, which however suffers from a longexisting gradual template drift problem. In this paper, wepresent an improved tracking algorithm which can sustain thetracking performance for a long term against drift. In thisapproach, we formulate the tracking over a state comprisingof a template with kinematic motion. Based on the sparsemotion field generated by KLT, a motion consistency basedmethod is applied to filer out the outliers which are the causeof cumulative drift errors. To sustain the tracking performancein a long term, an adaptive template update strategy monitoredby the appearance and motion continuities of the template isproposed. Finally, quantitative testing on several benchmarksequences demonstrate the advances of the proposed methodin long term tracking.

Original languageEnglish
Title of host publicationProceedings - 2016 3rd International Conference on Information Science and Control Engineering, ICISCE 2016
EditorsShaozi Li, Yun Cheng, Ying Dai
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages462-467
Number of pages6
ISBN (Electronic)9781509025350
DOIs
Publication statusPublished - 31 Oct 2016
Event3rd International Conference on Information Science and Control Engineering, ICISCE 2016 - Beijing, China
Duration: 8 Jul 201610 Jul 2016

Publication series

NameProceedings - 2016 3rd International Conference on Information Science and Control Engineering, ICISCE 2016

Conference

Conference3rd International Conference on Information Science and Control Engineering, ICISCE 2016
Country/TerritoryChina
CityBeijing
Period8/07/1610/07/16

Keywords

  • Object tracking
  • Template drift
  • Template update

Fingerprint

Dive into the research topics of 'Motion-Based Feature Selection and Adaptive Template Update Strategy for Robust Visual Tracking'. Together they form a unique fingerprint.

Cite this