Ensemble Tracking
Top Cited Papers
- 2 January 2007
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 29 (2) , 261-271
- https://doi.org/10.1109/tpami.2007.35
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 sequencesKeywords
This publication has 17 references indexed in Scilit:
- Online selection of discriminative tracking featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Histograms of Oriented Gradients for Human DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Visual tracking using learned linear subspacesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Support vector trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Fast and Light Boosting for Adaptive Mining of Data StreamsPublished by Springer Nature ,2004
- Robust online appearance models for visual trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Kernel-based object trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Perceptual user interfaces: the KidsRoomCommunications of the ACM, 2000
- Learning patterns of activity using real-time trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997