Stereo Matching by Hierarchical, Microcanonical Annealing
Proceedings of the Tenth International Joint Conference on Artificial Intelligence. Perception. Pages 832-834.
Abstract
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 "heatbath" 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.
@inproceedings{ijcai1987p174,
title = {Stereo Matching by Hierarchical, Microcanonical Annealing},
author = {Barnard, Stephen T.},
booktitle = {Proceedings of the Tenth International Joint Conference on
Artificial Intelligence, {IJCAI-87}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {John McDermott},
pages = {832--834},
year = {1987},
note = {Perception},
url = {https://ijcai.org/proceedings/1987/174},
}
TY - CPAPER TI - Stereo Matching by Hierarchical, Microcanonical Annealing AU - Barnard, Stephen T. T2 - Proceedings of the Tenth International Joint Conference on Artificial Intelligence, IJCAI-87 PB - International Joint Conferences on Artificial Intelligence PY - 1987 SP - 832 EP - 834 UR - https://ijcai.org/proceedings/1987/174 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
