Stereo Matching By Hierarchical, Microcanonical Annealing
by Barnard, Stephen T.
Technical Note 414
Institution: AI Center, SRI International
Address: 333 Ravenswood Ave., Menlo Park, CA 94025
Feb 1987.
An improved stochastic stereo-matching algorithm is presented. It incorporates two substantial modifications to an earlier version: a new variation of simulated annealing that is faster, simpler, and more controllable than the conventional ``heat-bath’’ version, and a hierarchical, coarse-to-fine-resolution control structure. The Hamiltonian used in the original model is minimized, but far more efficiently. The basis of microcanonical annealing is the Creutz algorithm . Unlike its counterpart, the familiar Metropolis algorithm, the Creutz algorithm simulates a thermally isolated system at equilibrium. The hierarchical control structure, together with a Brownian state-transition function, tracks ground states across scale, beginning with small, coarsely coded levels. Results are shown for a 512 x 512 pair with 50 pixels of disparity.
 Adobe PDF |
 BibTeX |
 EndNote |
