Fast stereovision by coherence detection
A new approach to stereo vision based on similarities between optical flow estimation and disparity computation is introduced. The fully parallel algorithm utilizes fast filter operations and aliasing effects of simple disparity detectors within a coherence detection scheme. It is able to calculate dense disparity maps, verification counts and the cyclopean view of a scene within a single computational structure.
KeywordsOptical Flow Stereo Vision Disparity Estimate Alias Effect Stereo Algorithm
Unable to display preview. Download preview PDF.
- 1.U. R. Dhond and J. K. Aggarwal, Structure from Stereo-A Review, IEEE Trans. Syst., Man and Cybern. 19, 1489–1510, 1989.Google Scholar
- 2.J. P. Frisby, Stereo Correspondence and Neural Networks, in “Handbook of Brain Theory”, ed. M. A. Arbib, 937–941, MIT Press 1995.Google Scholar
- 9.D. Marr and T. Poggio, A Computational Theory of Human Stereo Vision, Proc. R. Sec. Lond. B 204, 301–328, 1979.Google Scholar
- 10.N. Qian and Y. Zhu, Physiological Computation of Binocular Disparity, to appear in Vision Research '97.Google Scholar
- 11.R. D. Freeman, G. C. DeAngelis, and I. Ohzawa, Depth is Encoded in the Visual Cortex by a Specialized Receptive Field Structure, Nature 11, 156–159, 1991.Google Scholar
- 12.E. H. Adelson and J. R. Bergen, Spatiotemporal Energy Models for the Perception of Motion, J. Opt. Sec. Am. A 2, 284–299, 1985.Google Scholar
- 14.A. Fusiello, V. Roberto, and E. Trucco, A Symmetry-based Stereo Algorithm, Research report Udmi/53/96/Rr, submitted to CVPR 97, Machine Vision Lab, University of Udine, Italy, 1996.Google Scholar