Stereopsis and image registration from extended edge features in the absence of camera pose information

Published 10 December 2002

Nitin M. Vaidya, Kim L. Boyer

DOI10.1109/cvpr.1991.139664

Citations7

TL;DR

The authors solve the stereo correspondence problem in uncalibrated domains using extended edge contours as a source of primitives, as opposed to traditional point-based algorithms.

Abstract

The authors solve the stereo correspondence problem in uncalibrated domains using extended edge contours as a source of primitives, as opposed to traditional point-based algorithms. This work represents a novel approach to implementation of the structural stereopsis concept of K.L. Boyr and A.C. Kak (1988), in particular with regard to speed. Judiciously exploiting the contiguity relation among primitives, correspondence solutions without prior knowledge of the epipolar condition for feature-rich stereopairs, previously requiring several days of processing by the Boyer and Kak algorithm are now acquired in tens of seconds on the same equipment.>

Keywords

Computer Science

IEEE Transactions on Systems Man and CyberneticsStructure from stereo-a review

863 Citations1989U.R. Dhond, J.K. Aggarwal

Broad categories of stereo algorithms are identified on the basis of differences in imaging geometry, matching primitives, and the computational structure used for the extraction of the 3D structure of a scene.

IEEE Transactions on Pattern Analysis and Machine IntelligenceStereo correspondence through feature grouping and maximal cliques

314 Citations1989Radu Horaud, Thomas Skordas

The authors propose a method for solving the stereo correspondence problem by extracting local image structures and matching similar such structures between two images using a benefit function.

View PDF

International Journal of Computer VisionEfficient registration of stereo images by matching graph descriptions of edge segments

189 Citations1987Nicholas Ayache, B. Faverjon

This approach to the stereo-matching problem appears to be fast and robust enough for mobile robot navigation and three-dimensional part-positioning applications.

View PDF

IEEE Transactions on Pattern Analysis and Machine IntelligenceStructural stereopsis for 3-D vision

163 Citations1988Kim L. Boyer, A.C. Kak

A novel approach to solving the stereo correspondence problem in computer vision and an entropy-based figure of merit for attribute selection and ordering are defined.

IEEE Transactions on Pattern Analysis and Machine IntelligenceRobust contour decomposition using a constant curvature criterion

133 Citations1991D.M. Wuescher, Kim L. Boyer

The problem of decomposing an extended boundary or contour into simple primitives is addressed with particular emphasis on Laplacian-of-Gaussian zero-crossing contours, and a technique is introduced for partitioning such contours into constant curvature segments.

IEEE Transactions on Systems Man and CyberneticsDynamic edge warping: an experimental system for recovering disparity maps in weakly constrained systems

9 Citations1991Kim L. Boyer, D.M. Wuescher +1 more

Dynamic edge warping (DEW) is presented, a technique for recovering reasonably accurate disparity maps from uncalibrated stereo image pairs, and substitutes high-level information and constraints for precise geometric knowledge in driving and constraining the early correspondence process.