Software Engineering White Papers
Sparse Bayesian Learning for Efficient Visual Tracking
Overview This paper extends the use of statistical learning algorithms for object localization. It has been shown that object recognizers using kernel-SVMs can be elegantly adapted to localization by means of spatial perturbation of the SVM. While this SVM applies to each frame of a video independently of other frames, the benefits of temporal fusion of data are well-known. This is addressed here by using a fully probabilistic Relevance Vector Machine (RVM) to generate observations with Gaussian distributions that can be fused over time. Rather than adapting a recognizer, it builds a displacement expert which directly estimates displacement from the target region. An object detector is used in tandem, for object verification, providing the capability for automatic initialization and recovery.
| Publisher | Institute of Electrical and Electronics Engineers | File Format | |
|---|---|---|---|
| Date Published | August 2005 | ||
| Format | White Papers | ||
| Topics | |||
-
Did you find this white paper useful? 2 out of 4 users found this white paper useful
White Paper RSS
Download
Register
