A neural matching algorithm for 3-D reconstruction from stereo pairs of linear images

In this paper, we propose a neural approach for obstacle detection in front of moving cars, using linear stereo vision. The key problem is the so-called “correspondence problem” which consists in matching features extracted from two images that are projections of the same entity in the three-dimensi...

Full description

Saved in:
Bibliographic Details
Published inPattern recognition letters Vol. 17; no. 4; pp. 387 - 398
Main Authors Ruichek, Y., Postaire, J.-G.
Format Journal Article
LanguageEnglish
Published Elsevier B.V 04.04.1996
Subjects
Linear stereo vision
Matching
Neural network
Obstacle detection
Optimization
Real-time processing
Matching
Real-time processing
Obstacle detection
Neural network
Linear stereo vision
Optimization
Online AccessGet full text
ISSN0167-8655
1872-7344
DOI10.1016/0167-8655(95)00134-4

Cover

More Information
Summary:In this paper, we propose a neural approach for obstacle detection in front of moving cars, using linear stereo vision. The key problem is the so-called “correspondence problem” which consists in matching features extracted from two images that are projections of the same entity in the three-dimensional world. The linear stereo correspondence problem is first formulated as an optimization task where an energy function, which represents the constraints on the solution, is to be minimized. The optimization problem is then performed by means of a Hopfield neural network. Experimental results, using real stereo images, demonstrate the effectiveness of the method.
ISSN:0167-8655
1872-7344
DOI:10.1016/0167-8655(95)00134-4