Title :
Support Vector Tracking
Author_Institution :
MobilEye Vision Technol., Jerusalem, Israel
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.
Keywords :
image classification; image sequences; learning automata; optimisation; tracking; vehicles; SVM classification score maximization; SVM classifier; SVT; Support Vector Machine classifier; Support Vector Tracking; classification stage; coarse-to-fine approach; homogeneous quadratic polynomial kernel-SVT; image sequences; intensity difference function; optic-flow based tracker; pyramids; successive frames; support vectors; vehicle tracking; Biomedical optical imaging; Brightness; Electronic mail; Face detection; Integrated optics; Optical character recognition software; Polynomials; Support vector machine classification; Support vector machines; Vehicle detection;
Conference_Titel :
Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on
Print_ISBN :
0-7695-1272-0
DOI :
10.1109/CVPR.2001.990474
