Contour-based classification of video objects

Richter, Stephan ; Kuehne, Gerald ; Schuster, Oliver

Preview

PDF
Richter_2001a.pdf - Published
Download (199kB)

URL:	https://ub-madoc.bib.uni-mannheim.de/38967
Additional URL:	http://citeseerx.ist.psu.edu/viewdoc/download?doi=...
URN:	urn:nbn:de:bsz:180-madoc-389673
Document Type:	Conference or workshop publication
Year of publication:	2001
Book title:	Storage and Retrieval for Media Databases 2001 : 24 - 26 January 2001, San Jose, USA
The title of a journal, publication series:	Proceedings of SPIE
Volume:	4315
Page range:	608-618
Date of the conference:	2001
Publisher:	Yeung, Minerva M.
Place of publication:	Bellingham, Wash.
Publishing house:	SPIE Press
ISBN:	0-8194-3993-2
Publication language:	English
Institution:	School of Business Informatics and Mathematics > Praktische Informatik IV (Effelsberg -2017)
Subject:	004 Computer science, internet
Abstract:	The recognition of objects that appear in a video sequence is an essential aspect of any video content analysis system. We present an approach which classifies a segmented video object base don its appearance in successive video frames. The classification is performed by matching curvature features of the contours of these object views to a database containing preprocessed views of prototypical objects using a modified curvature scale space technique. By integrating the result of an umber of successive frames and by using the modified curvature scale space technique as an efficient representation of object contours, our approach enables the robust, tolerant and rapid object classification of video objects.