ENERGY MINIMIZATION APPROACH TO MOTION ESTIMATION

被引：10

作者：

ABDELQADER, IM ^{[1
]}

RAJALA, SA ^{[1
]}

SNYDER, WE ^{[1
]}

BILBRO, GL ^{[1
]}

机构：

[1] N CAROLINA STATE UNIV,DEPT ELECT & COMP ENGN,BOX 7911,RALEIGH,NC 27695

来源：

SIGNAL PROCESSING | 1992年 / 28卷 / 03期

关键词：

MOTION ESTIMATION; MEAN FIELD ANNEALING;

D O I：

10.1016/0165-1684(92)90045-X

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this paper, we cast motion estimation as a problem in energy minimization. This is achieved by modeling the displacement field as a Markov random field. The equivalence of a Markov random field and a Gibbs distribution is then used to convert the problem into one of defining an appropriate energy function that describes the motion and any constraints imposed on it. The energy function is then minimized using the Mean Field Annealing algorithm, a technique which finds the global or near global minima in nonconvex optimization problems. An analysis of the algorithm and experiment results are presented.

引用

页码：291 / 309

页数：19

共 24 条

[1]

Aarts, Korst, Simulated Annealing and Boltzmann Machines, (1989)

[2]

Bilbro, Snyder, Range image restoration using mean-field annealing, Advances in Neural Network Information Processing Systems I, pp. 101-594, (1988)

[3]

Bilbro, Mann, Miller, Snyder, Bout, White, Optimization by mean-field annealing, Advances in Neural Network Information Processing Systems I, pp. 91-108, (1988)

[4]

Carnevali, Coletti, Patarnello, Image processing by simulated annealing, IBM Journal of Research and Development, 29, pp. 560-579, (1985)

[5]

Carter, Computer-aided design for integrated circuits, Comput., 19, pp. 19-36, (1986)

[6]

Geman, Geman, Stochastic relaxation, Gibbs distribution, and the Bayesian restoration of images, IEEE Trans. Pattern Anal. Machine Intell., 6 PAMI, 6, pp. 721-741, (1984)

[7]

Hildreth, The computation of the velocity field, Proceedings of the Royal Society B: Biological Sciences, pp. 189-220, (1984)

[8]

Hiriyannaiah, Bilbro, Snyder, Mann, Restoration of piecewise-constant images by mean-field annealing, Journal of the Optical Society of America A, 6, 12, pp. 1901-1912, (1989)

[9]

Hopfield, Tank, Neural computation of decisions in optimization problems, Biol. Cybernat., 52, pp. 141-152, (1985)

[10]

Horn, Schunk, Determining optical flow, Artificial Intell., 17, pp. 185-204, (1981)

← 1 2 3 →