Skip to main navigation Skip to search Skip to main content

Visual Tracking via Local Sparse Correlation Filters

  • Harbin Institute of Technology Shenzhen
  • Shenzhen Konka Communication Technology Company

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

Abstract

Visual tracking is a challenging problem due to the intricate appearance variation of the objects in video sequences. Recently, correlation filters(CFs) technique has become a powerful tool for building a robust and high-speed visual tracker. However, there are still some intractable problems need to be solved: 1) The updating strategy of the CF's appearance model is linear, this strategy can not distinguish objects from the occlusions, may adding non-objects to the linear appearance model, 2) The conventional CFs can not handle the affine transforms of the objects. In this paper, we combine the local sparse method and CFs to construct an appearance model of the objects, and use the particle filters to find the objects' affine transforms. The experiments show that our approach outperforms the original local sparse coding approach and other state-of-the-art trackers.

Original languageEnglish
Title of host publicationProceedings - 2015 3rd International Conference on Robot, Vision and Signal Processing, RVSP 2015
EditorsXin-Hua Jiang, Tien-Szu Pan, Pei-Wei Tsai, Hsiang-Cheh Huang
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages27-30
Number of pages4
ISBN (Electronic)9781467396462
DOIs
StatePublished - 3 Feb 2016
Externally publishedYes
Event3rd International Conference on Robot, Vision and Signal Processing, RVSP 2015 - Kaohsiung, Taiwan, Province of China
Duration: 18 Nov 201520 Nov 2015

Publication series

NameProceedings - 2015 3rd International Conference on Robot, Vision and Signal Processing, RVSP 2015

Conference

Conference3rd International Conference on Robot, Vision and Signal Processing, RVSP 2015
Country/TerritoryTaiwan, Province of China
CityKaohsiung
Period18/11/1520/11/15

Keywords

  • correlation filters
  • sparse coding
  • visual tracking

Fingerprint

Dive into the research topics of 'Visual Tracking via Local Sparse Correlation Filters'. Together they form a unique fingerprint.

Cite this