Learning to track with multiple observers
- 1 June 2009
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2647-2654
- https://doi.org/10.1109/cvpr.2009.5206634
Abstract
We propose a novel approach to designing algorithms for object tracking based on fusing multiple observation models. As the space of possible observation models is too large for exhaustive on-line search, this work aims to select models that are suitable for a particular tracking task at hand. During an off-line training stage observation models from various off-the-shelf trackers are evaluated. From this data different methods of fusing the observers on-line are investigated, including parallel and cascaded evaluation. Experiments on test sequences show that this evaluation is useful for automatically designing and assessing algorithms for a particular tracking task. Results are shown for face tracking with a handheld camera and hand tracking for gesture interaction. We show that for these cases combining a small number of observers in a sequential cascade results in efficient algorithms that are both robust and precise.Keywords
This publication has 18 references indexed in Scilit:
- Dependent Multiple Cue Integration for Robust TrackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- AIDIA - Adaptive Interface for Display InterActionPublished by British Machine Vision Association and Society for Pattern Recognition ,2008
- Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different LifespansPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- A General Framework for Combining Visual Trackers – The "Black Boxes" ApproachInternational Journal of Computer Vision, 2006
- A Unified Framework for Tracking through Occlusions and across Sensor GapsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Fast 2D Hand Tracking with Flocks of Features and Multi-Cue IntegrationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Data Fusion for Visual Tracking With ParticlesProceedings of the IEEE, 2004
- Multimodal human-computer interaction for crisis management systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Towards robust multi-cue integration for visual trackingMachine Vision and Applications, 2003
- Multi-modal system for locating heads and facesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002