Support vector tracking
Avidan, S.
MobilEye Vision Technol. LTD, Jerusalem, Israel;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Aug. 2004
Volume: 26,
Issue: 8
On page(s): 1064-1072
ISSN: 0162-8828
INSPEC Accession Number: 8061456
Digital Object Identifier: 10.1109/TPAMI.2004.53
Current Version Published: 2004-06-21
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 SVT for vehicle tracking in image sequences.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
