Subpixel stereo disparity for surface reconstruction by utilising a three-dimensional reaction-diffusion system

ABSTRACT

This paper proposes a stereo algorithm utilising a reaction-diffusion system defined in a three-dimensional domain. A previous reaction-diffusion stereo algorithm provides a stereo disparity map by utilising multi-layered reaction-diffusion systems defined in a two-dimensional domain. The previous algorithm assumes that three-dimensional structures of scenes consist of unslanted planar surfaces and approximately describes any slanted or curved surfaces with piecewise unslanted planar surfaces. However, in real scenes there are highly slanted or curved surfaces, which violate the assumption of the previous algorithm and cause inaccurate results of disparity distribution, in particular, with respect to subpixel accuracy. The reaction-diffusion system consists of reaction-diffusion equations, which are described with partial-differential equations and solved with a numerical computation technique such as a finite difference method. Thus, we revise the reaction-diffusion stereo algorithm by utilising a reaction-diffusion system defined in a three-dimensional domain consisting of the two-dimensional domain plus a disparity domain. Discretisation of the disparity domain brings subpixel accuracy and helps the algorithm to detect accurate disparity for slanted or curved surfaces. In addition, this paper proposes a two-stage algorithm for fill-in of disparity undefined areas caused by little image feature. Finally, this paper demonstrates performance of the proposed algorithm for slanted or curved surfaces with the Middlebury stereo vision data-sets.

References

1. M. Bleyer, C. Rhemann, and C. Rother. Patchmatch stereo - stereo matching with slanted support windows. In Proc. BMVC, pages 14.1--14.11, 2011.
2. R. FitzHugh. Impulses and physiological states in theoretical models of nerve membrane. Biophys. J., 1: 445--466, 1961.
3. C. A. J. Fletcher. Computational Techniques for Fluid Dynamics 1: Fundamental and General Techniques. Springer-Verlag, Berlin, Germany, 1991.
4. D. Marr and T. Poggio. Cooperative computation of stereo disparity. Science, 194: 283--287, 1976.
5. K. Miura, A. Osa, and H. Miike. Self-organized feature extraction in a three-dimensional discrete reaction-diffusion system. Forma, 23: 19--23, 2008.
6. J. D. Murray. Mathematical Biology. Springer-Verlag, Berlin, Germany, 1989.
7. J. Nagumo, S. Arimoto, and S. Yoshizawa. An active pulse transmission line simulating nerve axon. Proc. IRE, 50: 2061--2070, 1962.
8. A. Nomura, M. Ichikawa, and H. Miike. Reaction-diffusion algorithm for stereo disparity detection. Mach. Vis. Appl., 20: 175--187, 2009.
9. A. Nomura, K. Okada, H. Miike, Y. Mizukami, M. Ichikawa, and T. Sakurai. Current Advancements in Stereo Vision, chapter 4. Stereo algorithm with anisotropic reaction-diffusion systems, pages 61--92. InTech, Rijeka, Croatia, 2012.
10. B. J. Rogers and M. E. Graham. Anisotropies in the perception of three-dimensional surfaces. Science, 221: 1409--1411, 1983.
11. D. Scharstein and R. Szeliski. The Middlebury stereo vision page. http://vision.middlebury.edu/stereo/.
12. T. Tsukahara and Y. Hirai. Surface reconstruction from random dot stereogram. IEICE Trans. Inf. Syst. D-II, J76-D-II: 1676--1683, 1993.

Index Terms

• Computer systems organization

  • Architectures

    • Other architectures

      • Neural networks

• Computing methodologies

  • Machine learning

    • Machine learning approaches

      • Neural networks

• Mathematics of computing

  • Mathematical analysis

    • Numerical analysis

      • Computations in finite fields