A sparse probabilistic learning algorithm for real-time tracking
Authors:
- Andrew BlakeABAndrew Blake
- Roberto CipollaRCRoberto Cipolla
- 1 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 353-360 vol.1
Abstract
We address the problem of applying powerful pattern recognition algorithms based on kernels to efficient visual tracking. Recently S. Avidan, (2001) has shown that object recognizers using kernel-SVMs can be elegantly adapted to localization by means of spatial perturbation of the SVM, using optic flow. Whereas Avidan's SVM applies to each frame of a video independently of other frames, the benefits of temporal fusion of data are well known. Using a fully probabilistic 'relevance vector machine' (RVM) to generate observations with Gaussian distributions that can be fused over time is addressed. To improve performance further, rather than adapting a recognizer, we build a localizer directly using the regression form of the RVM. A classification SVM is used in tandem, for object verification, and this provides the capability of automatic initialization and recovery. The approach is demonstrated in real-time face and vehicle tracking systems. The 'sparsity' of the RVMs means that only a fraction of CPU time is required to track at frame rate. Tracker output is demonstrated in a camera management task in which zoom and pan are controlled in response to speaker/vehicle position and orientation, over an extended period. The advantages of temporal fusion in this system are demonstrated.Keywords
This publication has 11 references indexed in Scilit:
- Rapid object detection using a boosted cascade of simple features2005
- Training support vector machines: an application to face detection2002
- Computationally efficient face detection2002
- An Introduction to Support Vector Machines and Other Kernel-based Learning Methods2000
- Moderating the outputs of support vector machine classifiersIEEE Transactions on Neural Networks, 1999
- A Tutorial on Support Vector Machines for Pattern RecognitionData Mining and Knowledge Discovery, 1998
- Prediction with Gaussian Processes: From Linear Regression to Linear Prediction and Beyond1998
- Active Contours1998
- 3D position, attitude and shape input using video tracking of hands and lips1994
- Robust model-based motion tracking through the integration of search and estimationInternational Journal of Computer Vision, 1992