Classification of moving targets based on motion and appearance

Classification of moving targets based on motion and appearance (2003)

Cached

Download Links

[www2.mta.ac.il]

by Y. Bogomolov , S. Lapchev , E. Rivlin , M. Rudzsky , G. Dror

Venue:	in: British Machine Vision Conference 2003
Citations:	2 - 0 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Classification of moving targets based on motion and appearance	INFERENCE
AUTHOR NAME	Y. Bogomolov	SVM HeaderParse 0.2
AUTHOR AFFIL	Computer Science Department, Technion- Israel Institute of Technology 32 000	SVM HeaderParse 0.2
AUTHOR ADDR	Haifa, Israel	SVM HeaderParse 0.2
AUTHOR NAME	S. Lapchev	SVM HeaderParse 0.2
AUTHOR AFFIL	Computer Science Department, Technion- Israel Institute of Technology 32 000	SVM HeaderParse 0.2
AUTHOR ADDR	Haifa, Israel	SVM HeaderParse 0.2
AUTHOR NAME	E. Rivlin	SVM HeaderParse 0.2
AUTHOR AFFIL	Computer Science Department, Technion- Israel Institute of Technology 32 000	SVM HeaderParse 0.2
AUTHOR ADDR	Haifa, Israel	SVM HeaderParse 0.2
AUTHOR NAME	M. Rudzsky	SVM HeaderParse 0.2
AUTHOR AFFIL	Computer Science Department, Technion- Israel Institute of Technology 32 000	SVM HeaderParse 0.2
AUTHOR ADDR	Haifa, Israel	SVM HeaderParse 0.2
AUTHOR NAME	G. Dror	SVM HeaderParse 0.2
AUTHOR AFFIL	The Academic College of Tel Aviv-Yaffo	SVM HeaderParse 0.2
AUTHOR ADDR	4 Antokolski St., Tel Aviv, Israel	SVM HeaderParse 0.2
ABSTRACT	We describe a system for detection and classification of moving targets. The system’s change detection and tracking modules are based on background adaptation, with the help of information about targets obtained from preceding time steps. The classification module performs a hybrid classification that combines motion and appearance features. The system is able to perform real-time detection, tracking and classification of targets in outdoor settings. Experiments demonstrate that the proposed hybrid classifier architecture improves classification significantly, thereby permitting real-time discrimination among a considerable number of classes, some of which are quite similar.	SVM HeaderParse 0.2
YEAR	2003	INFERENCE
VENUE	in: British Machine Vision Conference 2003	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	429--438	INFERENCE
VOLUME	2	INFERENCE
CITATIONS	40 found	ParsCit 1.0