DocumentCode :
3231726
Title :
Connected-component stereo aggregation
Author :
Oon-Ee, Ng ; Ganapathy, Velappa ; Ponnambalam, S.G.
Author_Institution :
Sch. of Eng., Monash Univ. Sunway, Bandar, Malaysia
fYear :
2010
fDate :
6-9 Dec. 2010
Firstpage :
348
Lastpage :
351
Abstract :
Stereo vision algorithms can be divided into several general stages. Detailed analysis on each specific stage allows focused improvement of the entire algorithm. Existing stereo vision algorithms typically prioritize pixel and sub-pixel accuracy, focusing on the optimization stage, while commercial algorithms which prioritize real-time operation typically focus on the cost calculation stage. This paper presents a novel approach to cost aggregation, a module within the cost calculation stage, based on connected-component analysis. The conventional connected-component analysis algorithm is extended for use in the stereo vision matching cost aggregation problem, resulting in an algorithm which is comparable in efficiency to the best current aggregation algorithms while performing well at object boundaries, typically the most difficult problem for aggregation-based approaches.
Keywords :
image matching; stereo image processing; visual perception; connected-component analysis; connected-component stereo aggregation; cost calculation stage; object boundaries; optimization stage; stereo vision algorithms; stereo vision matching cost aggregation problem; sub-pixel accuracy; Algorithm design and analysis; Computer vision; Conferences; Equations; Pattern recognition; Pixel; Stereo vision; Aggregation; Connected-component Analysis; Stereo Vision;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems (APCCAS), 2010 IEEE Asia Pacific Conference on
Conference_Location :
Kuala Lumpur
Print_ISBN :
978-1-4244-7454-7
Type :
conf
DOI :
10.1109/APCCAS.2010.5775011
Filename :
5775011
Link To Document :
بازگشت