Review of low-baseline stereo algorithms and benchmarks

Sabater, N.; Blanchet, G.; Moisan, L.; Almansa, A.; Morel, J.-M.

doi:10.1117/12.865087

by N. Sabater, G. Blanchet, L. Moisan, A. Almansa, J.-M. Morel

Abstract:

The purpose of this work is to review and evaluate the performance of several algorithms which have been designed for satellite imagery in a geographic context. In particular we are interested in their performance with low-baseline image pairs like those which will be produced by the Pleiades satellite. In this study local and global state of the art algorithms have been considered and compared: CARMEN, MARC, MARC2 and MICMAC. This paper aims also at proposing a new benchmark to compare stereo algorithms. A set of simulated stereo images for which the ground truth is perfectly known will be presented. The obtained accuracy for the ground truth is more than a hundredth of pixel. The existence of an accurate ground truth is a major improvement for the community, allowing to quantify very precisely the disparity error in a realistic setting.

View PDF

Reference:

Review of low-baseline stereo algorithms and benchmarks (N. Sabater, G. Blanchet, L. Moisan, A. Almansa, J.-M. Morel), In Proc. SPIE 7830, Image and Signal Processing for Remote Sensing XVI (Lorenzo Bruzzone, ed.), volume 7830, 2010.

Bibtex Entry:

@inproceedings{Sabater2010:SPIE:review,
	Abstract = {The purpose of this work is to review and evaluate the performance of several algorithms which have been designed for satellite imagery in a geographic context. In particular we are interested in their performance with low-baseline image pairs like those which will be produced by the Pleiades satellite. In this study local and global state of the art algorithms have been considered and compared: CARMEN, MARC, MARC2 and MICMAC. This paper aims also at proposing a new benchmark to compare stereo algorithms. A set of simulated stereo images for which the ground truth is perfectly known will be presented. The obtained accuracy for the ground truth is more than a hundredth of pixel. The existence of an accurate ground truth is a major improvement for the community, allowing to quantify very precisely the disparity error in a realistic setting.},
	Address = {Toulouse, France},
	Author = {Sabater, N. and Blanchet, G. and Moisan, L. and Almansa, A. and Morel, J.-M.},
	Booktitle = {Proc. SPIE 7830, Image and Signal Processing for Remote Sensing XVI},
	Date-Added = {2015-02-18 16:55:46 +0000},
	Date-Modified = {2015-02-18 16:55:46 +0000},
	Doi = {10.1117/12.865087},
	Editor = {Bruzzone, Lorenzo},
	Keywords = {stereo},
	Mendeley-Tags = {stereo},
	Month = oct,
	Pages = {783005--783005--12},
	Title = {{Review of low-baseline stereo algorithms and benchmarks}},
	Url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=725703},
	Volume = {7830},
	Year = {2010},
	Bdsk-Url-1 = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=725703},
	Bdsk-Url-2 = {http://dx.doi.org/10.1117/12.865087}}