Disparity Map Estimation by Combining Cost Volume Measures Using Genetic Programming
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.
KeywordsStereo Vision Disparity Map Genetic Programming
Unable to display preview. Download preview PDF.
- 3.Cagnoni, S., Lutton, E., Olague, G.: Genetic and Evolutionary Computation for Image Processing and Analysis. In: EURASIP Book Series on Signal Processing and Communications, vol. 8. Hindawi Publishing Corporation (2008)Google Scholar
- 5.Hernández, B., Olague, G., Hammoud, R., Trujillo, L., Romero, E.: Visual learning of texture descriptors for facial expression recognition in thermal imagery. Computer Vision and Image Understanding, Special Issue on Vision Beyond the Visual Spectrum 106(2-3), 258–269 (2007)Google Scholar
- 13.Pérez, C.B., Olague, G.: Learning invariant region descriptor operators with genetic programming and the f-measure. In: 19th International Conference on Pattern Recognition (ICPR 2008), Tampa, Florida, USA, December 8-11, pp. 1–4. IEEE (2008)Google Scholar
- 15.Poli, R.: Genetic programming for feature detection and image segmentation. In: Forgarty, T.C. (ed.) AISB Workshop Evolutionary Computing, pp. 110–125 (1996)Google Scholar
- 16.Puente, C., Olague, G., Smith, S., Bullock, S., Hinojosa-Corona, A., González-Botello, M.: A genetic programming approach to estimate vegetation cover in the context of soil erosion assessment. Photogrametric Engineering and Remote Sensing 77(4), 363–376 (2011)Google Scholar
- 20.Trucco, E., Verri, A.: Introductory Techniques for 3-D Computer Vision. Prentice Hall PTR, Upper Saddle River (1998)Google Scholar
- 22.Trujillo, L., Olague, G., Lutton, E., Fernández de Vega, F.: Multiobjective design of operators that detect points of interest in images. In: Cattolico, M. (ed.) Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2008), Atlanta, GA, July 12-16, pp. 1299–1306. ACM, New York (2008)CrossRefGoogle Scholar