A sparse probabilistic learning algorithm for real-time tracking
- 1 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 353-360 vol.1
- https://doi.org/10.1109/iccv.2003.1238366
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 featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Training support vector machines: an application to face detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Computationally efficient face detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- An Introduction to Support Vector Machines and Other Kernel-based Learning MethodsPublished by Cambridge University Press (CUP) ,2000
- 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 BeyondPublished by Springer Nature ,1998
- Active ContoursPublished by Springer Nature ,1998
- 3D position, attitude and shape input using video tracking of hands and lipsPublished by Association for Computing Machinery (ACM) ,1994
- Robust model-based motion tracking through the integration of search and estimationInternational Journal of Computer Vision, 1992