Tracker fusion for robustness in visual feature tracking

Kentaro Toyama, Gregory D. Hager

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

Abstract

Task-directed vision obviates the need for general image comprehension by focusing attention only on features which contribute useful information to the task at hand. Window-based visual tracking fits into this paradigm as motion tracking becomes a problem of local search in a small image region. While the gains in speed from such methods allow for real-time feature tracking on off-the-shelf hardware, they lose robustness by giving up a more global perspective: Window-based feature trackers are prone to such problems as distraction, illumination changes, fast features, and so forth. To add robustness to feature tracking, we present `tracker fusion,' where multiple trackers simultaneously track the same feature while watching for various problematic circumstances and combine their estimates in a meaningful way. By categorizing different situations in which mistracking occurs, finding appropriate trackers to deal with each such situation, and fusing the resulting trackers together, we construct robust feature trackers which maintain the speed of simple window-based trackers, yet afford greater resistance to mistracking.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsPaul S. Schenker, Gerard T. McKee
Pages38-49
Number of pages12
StatePublished - Dec 1 1995
Externally publishedYes
EventSensor Fusion and Networked Robotics VIII - Philadelphia, PA, USA
Duration: Oct 23 1995Oct 24 1995

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume2589
ISSN (Print)0277-786X

Other

OtherSensor Fusion and Networked Robotics VIII
CityPhiladelphia, PA, USA
Period10/23/9510/24/95

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Tracker fusion for robustness in visual feature tracking'. Together they form a unique fingerprint.

Cite this