The invariance of the similarity measure in photometric distortions as well as its capability in producing subpixel accuracy are two desired and often required features in most stereo vision applications. In this paper we propose a new correlation-based measure which incorporates both mentioned requirements. Specifically, by using an appropriate interpolation scheme in the candidate windows of the matching image, and using the classical zero mean normalized cross correlation function, we introduce a suitable measure. Although the proposed measure is a nonlinear function of the sub-pixel displacement parameter, its maximization results in a closed form solution, resulting in reduced complexity for its use in matching techniques. Application of the proposed measure in a number of benchmark stereo pair images reveals its superiority over existing correlation-based techniques used for subpixel accuracy.
An enhanced correlation-based method for stereo correspondence with subpixel accuracy
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 ; 1 ; 907-912 Vol. 1
2005-01-01
568821 byte
Conference paper
Electronic Resource
English
An Enhanced Correlation-Based Method for Stereo Correspondence with Sub-Pixel Accuracy
British Library Conference Proceedings | 2005
|The Estimation of Curves to Subpixel Accuracy
British Library Conference Proceedings | 1994
|Locating cross-shaped image feature with subpixel accuracy based on NCCO
British Library Online Contents | 2005
|On the estimation of subpixel motion using phase correlation
British Library Online Contents | 2007
|Contextual Inference in Contour-Based Stereo Correspondence
British Library Online Contents | 2006
|