Issue No. 08 - August (2004 vol. 26)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2004.53
<p><b>Abstract</b>—Support Vector Tracking (<b>SVT</b>) integrates the Support Vector Machine (<b>SVM</b>) classifier into an optic-flow-based tracker. Instead of minimizing an intensity difference function between successive frames, <b>SVT</b> maximizes the <b>SVM</b> 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 <b>SVT</b> for vehicle tracking in image sequences.</p>
Support vector machines, optic-flow, visual tracking.
Shai Avidan, "Support Vector Tracking", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 26, no. , pp. 1064-1072, August 2004, doi:10.1109/TPAMI.2004.53