Skip to main navigation Skip to search Skip to main content

Robust visual tracking based on L1 expanded template

  • Dansong Cheng
  • , Yongqiang Zhang
  • , Feng Tian
  • , Daming Shi
  • , Xiangfang Liu
  • School of Computer Science and Technology, Harbin Institute of Technology
  • Bournemouth University
  • Shenzhen University
  • School of Electrical Engineering and Automation, Harbin Institute of Technology

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

Abstract

Most video tracking algorithms including L1 tracker often fail to track correctly under adverse conditions such as object occlusion, disappearance, etc. To address this issue, we propose an improved L1 tracker algorithm called Tracker-2, based on what we call the expanded template which includes the reference template and trail template. The reference template keeps the original features of the target and prevents errors from being introduced by false tracking results with the template update, which leads to the deviation of the target. The trail template records the trail tracking results to avoid massive use of trivial templates which may result in the false detection of occlusion. The experimental results on a number of standard data sets have proved that our Tracker-2 approach is able to deal with the occlusion problem effectively while maintaining the advantages of L1 tracker.

Original languageEnglish
Title of host publicationProceedings of 2017 International Conference on Machine Learning and Cybernetics, ICMLC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages397-403
Number of pages7
ISBN (Electronic)9781538604069
DOIs
StatePublished - 14 Nov 2017
Externally publishedYes
Event16th International Conference on Machine Learning and Cybernetics, ICMLC 2017 - Ningbo, China
Duration: 9 Jul 201712 Jul 2017

Publication series

NameProceedings of 2017 International Conference on Machine Learning and Cybernetics, ICMLC 2017
Volume2

Conference

Conference16th International Conference on Machine Learning and Cybernetics, ICMLC 2017
Country/TerritoryChina
CityNingbo
Period9/07/1712/07/17

Keywords

  • L1 Tracker
  • Reference Template
  • Sparse Representation
  • Trail Template
  • Visual Tracking

Fingerprint

Dive into the research topics of 'Robust visual tracking based on L1 expanded template'. Together they form a unique fingerprint.

Cite this