Disparity Map Estimation by Combining Cost Volume Measures Using Genetic Programming

Book Chapters

  1. Enrique Naredo, Enrique Dunn and Leonardo Trujillo. Disparity Map Estimation by Combining Cost Volume Measures Using Genetic Programming. In Oliver Schütze, Carlos A Coello Coello, Alexandru-Adrian Tantar, Emilia Tantar, Pascal Bouvry, Pierre Del Moral and Pierrick Legrand (eds.). EVOLVE - A Bridge between Probability, Set Oriented Numerics, and Evolutionary Computation II. Advances in Intelligent Systems and Computing series, volume 175, Springer Berlin Heidelberg, 2013, pages 71-86. URL, DOI BibTeX

    @incollection{,
    	year = 2013,
    	isbn = "978-3-642-31518-3",
    	booktitle = "EVOLVE - A Bridge between Probability, Set Oriented Numerics, and Evolutionary Computation II",
    	volume = 175,
    	series = "Advances in Intelligent Systems and Computing",
    	editor = "Schütze, Oliver and Coello Coello, Carlos A. and Tantar, Alexandru-Adrian and Tantar, Emilia and Bouvry, Pascal and Del Moral, Pierre and Legrand, Pierrick",
    	doi = "10.1007/978-3-642-31519-0_5",
    	title = "Disparity Map Estimation by Combining Cost Volume Measures Using Genetic Programming",
    	url = "http://dx.doi.org/10.1007/978-3-642-31519-0_5",
    	publisher = "Springer Berlin Heidelberg",
    	keywords = "Stereo Vision; Disparity Map; Genetic Programming",
    	author = "Naredo, Enrique and Dunn, Enrique and Trujillo, Leonardo",
    	pages = "71-86"
    }
    

Abstract

Stereo vision is one of the most active research areas in modern computer vision. The objective is to recover 3-D depth information from a pair of 2-D images that capture the same scene. This paper addresses the problem of dense stereo correspondence, where the goal is to determine which image pixels in both images are projections of the same 3-D point from the observed scene. The proposal in this work is to build a non-linear operator that combines three well known methods to derive a correspondence measure that allows us to retrieve a better approximation of the ground truth disparity of stereo image pair. To achieve this, the problem is posed as a search and optimization task and solved with genetic programming (GP), an evolutionary paradigm for automatic program induction. Experimental results on well known benchmark problems show that the combined correspondence measure produced by GP outperforms each standard method, based on the mean error and the percentage of bad pixels. In conclusion, this paper shows that GP can be used to build composite correspondence algorithms that exhibit a strong performance on standard tests.

Published in
EVOLVE - A Bridge between Probability, Set Oriented Numerics, and Evolutionary Computation II
Advances in Intelligent Systems and Computing
Pages 71-86
Volume 175
http://link.springer.com/chapter/10.1007%2F978-3-642-31519-0_5
Copyright
2012
ISSN
2194-5357
ISBN
978-3-642-31519-0
Last modified onSaturday, 12 October 2013 17:28
(0 votes)
Read 1967 times
Log in
G+