Skip to main navigation Skip to search Skip to main content

Adaptive model meanshift tracking

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

Abstract

Performance of original color-based MeanShift tracking algorithm decreases drastically under variant illumination environment. To enhance the robustness of the tracking ability under variant illumination environment, an adaptive model MeanShift tracking scheme is proposed in this paper. The statistically approximate LBP texture information is adaptively integrated into the model description to increase the descriptive ability of the model under different illuminating condition. The weighted coefficient of the color information and texture information adjust according to the discriminative ability of the character. Besides, H(Hue) element Gaussian model is introduced for more precisely decription as well as reducing the computational cost of the original histogram-based color model. Experiments on video sequences show the proposed model scheme and advance MeanShift tracking algorithm give effective and robust results in variant illumination condition.

Original languageEnglish
Title of host publicationFifth International Conference on Machine Vision, ICMV 2012
Subtitle of host publicationAlgorithms, Pattern Recognition and Basic Technologies
DOIs
StatePublished - 2013
Event2012 5th International Conference on Machine Vision: Algorithms, Pattern Recognition and Basic Technologies, ICMV 2012 - Wuhan, China
Duration: 20 Oct 201221 Oct 2012

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8784
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference2012 5th International Conference on Machine Vision: Algorithms, Pattern Recognition and Basic Technologies, ICMV 2012
Country/TerritoryChina
CityWuhan
Period20/10/1221/10/12

Keywords

  • Adaptive Clustering
  • Adaptive Model
  • LBP Texture Model
  • MeanShift
  • Visual Tracking

Fingerprint

Dive into the research topics of 'Adaptive model meanshift tracking'. Together they form a unique fingerprint.

Cite this