This Article 
 Bibliographic References 
 Add to: 
Depth and Image Recovery Using a MRF Model
November 1994 (vol. 16 no. 11)
pp. 1117-1122

This paper deals with the problem of depth recovery and image restoration from sparse and noisy image data. The image is modeled as a Markov random field and a new energy function is developed to effectively detect discontinuities in highly sparse and noisy images. The model provides an alternative to the use of a line process. Interpolation over missing data sites is first done using local characteristics to obtain initial estimates and then simulated annealing is used to compute the maximum a posteriori (MAP) estimate. A threshold on energy reduction per iteration is used to speed up simulated annealing by avoiding computation that contributes little to the energy minimization. Moreover, a minor modification of the posterior energy function gives improved results for random as well as structured sparsing problems. Results of simulations carried out on real range and intensity images along with details of the simulations are presented.

[1] M. Shao, T. Simchony, and R. Chellappa, "New algorithms for reconstruction of a 3-D depth map from one or more images," inProc. Comput. Vision Pattern Recognition(Ann Arbor, MI), June 1988, pp. 530-535.
[2] D. Terzopoulos, "The computation of visible surface representation,"IEEE Trans. Pattern Anal. Machine Intell., vol. 10, pp. 417-438, 1988.
[3] T. E. Boult and J. R. Kender, "Visual surface reconstruction using sparse depth data,"Proc. IEEE Conf. Comp. Vision Pattern Recog., pp. 68-76, June 1986.
[4] D. J. Choi and J. R. Kender, "Solving the depth interpolation problem on a parallel architecture with a multigrid approach," inProc. IEEE Conf. Comput. Vision and Pattern Recognition, June 1988, pp. 189-194.
[5] R. T. Frankot and R. Chellappa, "A method for enforcing integrability in shape from shading algorithms,"IEEE Trans. Pattern Anal. Machine Intell., vol. 11, pp. 799-813, 1989.
[6] J. Marroquin, S. Mitter, and T. Poggio, "Probabilistic solution of ill-posed problems in computational vision,"J. Amer. Stat. Assoc., vol. 82, no. 397, pp. 76-89, 1987.
[7] K. V. Venkatesh Prasad, R. J. Mammone, and J. Yogeshwar, "3- D restoration using constrained optimization techniques,"Optical Engineering, special issue onImage Restoration and Reconstruction, May 1990.
[8] D. Geiger and F. Girosi, "Parallel and deterministic algorithms from MRFs: Surface reconstruction,"IEEE Trans. Pattern Anal. Machine Intell., vol. 13, pp. 401-412, 1991.
[9] R. M. Bolle and B. C. Vemuri, "On three-dimensional surface reconstruction methods,"IEEE Trans. Pattern Anal. Machine Intell., vol. 13, no. 1, pp. 1-13, 1991.
[10] M. Bertero, T. A. Poggio, and V. Torre, "Ill-posed problems in early vision,"Proc. IEEE, vol. 76, pp. 869-889, Aug. 1988.
[11] J. E. Besag, "Spatial interaction and statistical analysis of lattice systems,"J. Royal Stat. Soc., Series B, vol. B-36, pp. 192-236, 1974.
[12] S. Geman and D. Geman, "Stochastic relaxation, Gibbs distributions and the Bayesian distribution of images,"IEEE Trans. Pattern Anal. Machine Intell., vol. 6, pp. 721-741, 1984.
[13] S. Kirkpatrick, G. D. Gelatt, and M. P. Vecchi, "Optimization by simulated annealing,"Science, vol. 220, pp. 671-680, 1983.
[14] E. Aarts and J. Korst,Simulated Annealing and Boltzmann Machines, A Stochastic Approach to Combinational Optimization ond Neural Computing. New York: Wiley, 1989.
[15] J. Zerubia and R. Chellappa, "Mean field annealing for edge detection and image restoration,"Proc. European Signal Proc. Conf., Barcelona, Spain, Sept. 1990.
[16] S. Kapoor, P. Y. Mundkur, and U. B. Desai, "Depth recovery using Markov random fields,"Sadhana--Academy Proceedings in Engineering Sciences, vol. 18, March 1993.
[17] S. Lakshmanan and H. Derin, "Simultaneous parameter estimation and segmentation of Gibbs random fields using simulated annealing,"IEEE Trans. Pattern Anal. Machine Intell., vol. 11, pp. 799-813, 1989.
[18] S. Geman and C. Graffigne, "Markov random fields image models and their applications to computer vision,"Proc. Int. Congr. Math., A. M. Gleason, Ed. Providence, RI: Amer. Math. Soc., 1987.
[19] L. Younes, "Estimation and annealing for Gibbsian fields,"Ann. Inst. Henri Poincaré, vol. 24, no. 2, pp. 269-294, 1988.
[20] B. D. Ripley,Spatial Statistics. New York: Wiley, 1981.

Index Terms:
simulated annealing; image restoration; free energy; Markov processes; image recovery; depth recovery; image restoration; noisy image data; sparse image data; Markov random field
S. Kapoor, P.Y. Mundkur, U.B. Desai, "Depth and Image Recovery Using a MRF Model," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 11, pp. 1117-1122, Nov. 1994, doi:10.1109/34.334392
Usage of this product signifies your acceptance of the Terms of Use.