A framework for a dense matching algorithm : Results using matching metrics and order statistic filters


Autoria(s): Banks, Jasmine
Data(s)

30/05/2001

Resumo

An algorithm for computing dense correspondences between images of a stereo pair or image sequence is presented. The algorithm can make use of both standard matching metrics and the rank and census filters, two filters based on order statistics which have been applied to the image matching problem. Their advantages include robustness to radiometric distortion and amenability to hardware implementation. Results obtained using both real stereo pairs and a synthetic stereo pair with ground truth were compared. The rank and census filters were shown to significantly improve performance in the case of radiometric distortion. In all cases, the results obtained were comparable to, if not better than, those obtained using standard matching metrics. Furthermore, the rank and census have the additional advantage that their computational overhead is less than these metrics. For all techniques tested, the difference between the results obtained for the synthetic stereo pair, and the ground truth results was small.

Formato

application/pdf

Identificador

http://eprints.qut.edu.au/58756/

Relação

http://eprints.qut.edu.au/58756/1/icav3d2001.pdf

http://www.iti.gr/icav3d/

Banks, Jasmine (2001) A framework for a dense matching algorithm : Results using matching metrics and order statistic filters. In Proceedings of the International Conference on Augmented, Virtual Environments and Three-Dimensional Imaging (ICAV3D’01), Santa Marina Hotel, Ornos, Mykonos, Greece.

Direitos

Copyright 2001 Please consult the author.

Fonte

School of Electrical Engineering & Computer Science; Science & Engineering Faculty

Palavras-Chave #080106 Image Processing #stereo matching #area-based #rank filter #census filter
Tipo

Conference Paper