Title:	TEXTURE ANALYSIS FOR THE ADAPTION OF CORRELATION WINDOWS IN STEREO CORRESPONDENCE
Author(s):	Dominik M. Aufderheide , Markus Steffens , Stephan Kieneke , Werner Krybus , Christine Kohring , Danny Morton
ISBN:	978-972-8924-84-3
Editors:	Yingcai Xiao, Tomaz Amon and Piet Kommers
Year:	2009
Edition:	Single
Keywords:	Stereo vision, scene analysis, texture analysis, block-matching algorithm, stereo correspondence
Type:	Short Paper
First Page:	229
Last Page:	234
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	This paper presents a new framework for the automatic adaption of correlation windows for stereo correspondence analysis. Basis for the automatic adjustment of the used window size is an analysis and classification of the scene structure due to its texture and intensity distribution. For this reason different descriptors are described and empirically evaluated on a typical synthetic test-pattern. The method outperforms typical schemes based on affixed window-size in terms of accuracy and complex multiple-window approaches in terms of computational complexity.
	Go Back