Ensemble tracking

Shai Avidan*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

We consider tracking as a binary classification problem, where an ensemble of weak classifiers is trained online to distinguish between the object and the background. The ensemble of weak classifiers is combined into a strong classifier using AdaBoost. The strong classifier is then used to label pixels in the next frame as either belonging to the object or the background, giving a confidence map. The peak of the map and, hence, the new position of the object, is found using mean shift. Temporal coherence is maintained by updating the ensemble with new weak classifiers that are trained online during tracking. We show a realization of this method and demonstrate it on several video sequences.

Original languageEnglish
Pages (from-to)261-271
Number of pages11
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume29
Issue number2
DOIs
StatePublished - Feb 2007
Externally publishedYes

Keywords

  • AdaBoost
  • Concept learning
  • Video analysis
  • Visual tracking

Fingerprint

Dive into the research topics of 'Ensemble tracking'. Together they form a unique fingerprint.

Cite this