a Real-Time System for Classification of Moving Objects
A Real-Time System for Classification of Moving Objects.
In ICPR (3), 688-691, 2002
Online Version
A pdf version is available for download.
Abstract
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.
Co-authors
Bibtex Entry
@inproceedings{RivlinRGBL02i,
title = {A Real-Time System for Classification of Moving Objects.},
author = {Ehud Rivlin and Michael Rudzsky and Roman Goldenberg and Yuri Bogomolov and Stanislav Lapchev},
year = {2002},
booktitle = {ICPR (3)},
pages = {688-691},
abstract = {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.}
}