August 25, 2005

Support Vector Tracking

Key Points

Key points are not available for this paper at this time.

Abstract

Support Vector Tracking (SVT) integrates the Support Vector Machine (SVM) classifier into an optic-flow based tracker. Instead of minimizing an intensity difference function between successive frames, SVT maximizes the SVM classification score. To account for large motions between successive frames, we build pyramids from the support vectors and use a coarse-to-fine approach in the classification stage. We show results of using a homogeneous quadratic polynomial kernel-SVT for vehicle tracking in image sequences.

Bookmark

Cite This Study

Shai Avidan (Thu,) studied this question.

synapsesocial.com/papers/6a15324f79ff98d0de4e3bd9 https://doi.org/https://doi.org/10.1109/cvpr.2001.990474

Also Consider

Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context:

1Support vector learning1997 · 563 citations
2The Nature of Statistical Learning Theory1995 · 39,269 citations
3Combining statistical learning with a knowledge-based approach: A case study in intensive care monitoring1999 · 354 citations
4Hierarchical Model-Based Motion Estimation1993 · 187 citations

Bookmark