Dynamic visual tracking based on multi-cue matching

Ming-Yang Cheng, Chun Kai Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Due to attractive features such as "computation efficient" and "model free", the template matching approaches have been used in many dynamic visual tracking systems to detect moving targets. However, in practical visual tracking applications, the image of the moving target may experience shape variations due to movement or illumination changes, in which it could end up with a detection failure. To overcome these difficulties, a multi-cue matching approach with a fuzzy logic based data fusion mechanism is proposed in this study. To evaluate the performance of the proposed approach, a real-time pan-tilt dynamic visual tracking system is used as a test platform and several experiments have been conducted. Experimental results demonstrate the effectiveness of the proposed approach.

Original languageEnglish
Title of host publicationProceedings of the 2007 4th IEEE International Conference on Mechatronics, ICM 2007
DOIs
Publication statusPublished - 2007 Dec 1
Event4th IEEE International Conference on Mechatronics, ICM 2007 - Kumamoto, Japan
Duration: 2007 May 82007 May 10

Publication series

NameProceedings of the 2007 4th IEEE International Conference on Mechatronics, ICM 2007

Other

Other4th IEEE International Conference on Mechatronics, ICM 2007
CountryJapan
CityKumamoto
Period07-05-0807-05-10

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Dynamic visual tracking based on multi-cue matching'. Together they form a unique fingerprint.

Cite this