Genetic Stereo Matching Algorithm with Fuzzy Fitness

TL;DR

This paper introduces a genetic stereo matching algorithm utilizing fuzzy evaluation to produce accurate dense disparity maps efficiently, suitable for real-time applications.

Contribution

It proposes a novel encoding scheme and fuzzy fitness function for genetic stereo matching, improving robustness to noise and measurement uncertainty.

Findings

Accurate dense disparity maps achieved

Algorithm operates in reasonable time for real-time use

Fuzzy fitness enhances robustness to noise

Abstract

This paper presents a genetic stereo matching algorithm with fuzzy evaluation function. The proposed algorithm presents a new encoding scheme in which a chromosome is represented by a disparity matrix. Evolution is controlled by a fuzzy fitness function able to deal with noise and uncertain camera measurements, and uses classical evolutionary operators. The result of the algorithm is accurate dense disparity maps obtained in a reasonable computational time suitable for real-time applications as shown in experimental results.