16th International Conference on Pattern Recognition (ICPR'02) - Volume 3
A Real-Time System for Classification of Moving Objects
Quebec City, QC, Canada
August 11-August 15
ISBN: 0-7695-1695-X
E. Rivlin, Technion - Israel Institute of Technology
M. Rudzsky, Technion - Israel Institute of Technology
S. Lepchev, Technion - Israel Institute of Technology
The paper describes a system for moving object classification. Being restricted by real-time system constraints we found a small set of features, characterizing object shape and motion dynamics. The system was tested on a large movies database including more than 100 images sequences showing people, animals, vehicles and plants in motion. The SVM classifier [1] was used in our system, yielding very good classification results.
Citation:
E. Rivlin, M. Rudzsky, R. Goldenberg, U. Bogomolov, S. Lepchev, "A Real-Time System for Classification of Moving Objects," icpr, vol. 3, pp.30688, 16th International Conference on Pattern Recognition (ICPR'02) - Volume 3, 2002