Shading-Based Two-View Matching
Proceedings of the Twelfth International Joint Conference on Artificial Intelligence. Vision. Pages 1286-1290.
Abstract
This paper presents a region-based stereo matching algorithm, in which the regions are computed from the Gaussian (I<) and mean (H) curvature information of the image intensity surface. A region is defined as a connected area of constant KIH sign combination, and thus constitutes the footprint of a local section of the intensity surface, whose shape is a peak, a pit, a positive or a negative saddle. Region adjacency information is explicited by means of a Voronoi graph representation of the region map. Matching between nodes of identical shape types in the two region maps is established by comparing the topological configuration of their immediate neighborhoods. The disparity map is established through a coarseto-fine strategy.
@inproceedings{ijcai1991p189,
title = {Shading-Based Two-View Matching},
author = {Audette, Michel A. and Cohen, Paul R. and Weng, Juyang},
booktitle = {Proceedings of the Twelfth International Joint Conference on
Artificial Intelligence, {IJCAI-91}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {John Mylopoulos and Ray Reiter},
pages = {1286--1290},
year = {1991},
month = {8},
note = {Vision},
url = {https://ijcai.org/proceedings/1991/189},
}
TY - CPAPER TI - Shading-Based Two-View Matching AU - Audette, Michel A. AU - Cohen, Paul R. AU - Weng, Juyang T2 - Proceedings of the Twelfth International Joint Conference on Artificial Intelligence, IJCAI-91 PB - International Joint Conferences on Artificial Intelligence PY - 1991 SP - 1286 EP - 1290 UR - https://ijcai.org/proceedings/1991/189 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
