Title :
Boltzmann machines for depth recovery using a MRF model
Author :
Mundkur, P.Y. ; Kapoor, S. ; Desai, U.B.
Author_Institution :
Dept. of Electr. Eng., Indian Inst. of Technol., Bombay, India
Abstract :
The authors deal with the problem of depth recovery or surface reconstruction from sparse and noisy range data. Based on earlier insights from Markov random field models for such data, a Boltzmann machine is proposed for the parallel computation of the maximum a posteriori (MAP) estimate of the data. A new consensus function is developed to effectively detect discontinuities in highly sparse and noisy images. Interpolation over missing data sites is first done using only local characteristics of the network. Simulation results are also presented
Keywords :
Boltzmann machines; Markov processes; computer vision; image reconstruction; learning (artificial intelligence); Boltzmann machines; MRF model; Markov random field models; consensus function; depth recovery; discontinuities; interpolation; local characteristics; maximum a posteriori; noisy range data; simulation; sparse range data; surface reconstruction; Computational modeling; Concurrent computing; Image reconstruction; Iterative algorithms; Markov random fields; Neural networks; Probability distribution; Simulated annealing; Stochastic processes; Surface reconstruction;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227164
