Genetic Stereo Matching Algorithm with Fuzzy Fitness

Haythem Ghazouani (1)

1 UCAR - Université de Carthage (Tunisie)

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.

Mots clés: Fuzzy fitness; Genetic algorithm; Disparity map; Dense stereo matching

Domaines: Intelligence artificielle [cs.AI]; Traitement des images [eess.IV]

Haythem Ghazouani. Genetic Stereo Matching Algorithm with Fuzzy Fitness. SoCPaR: Soft Computing and Pattern Recognition, Aug 2014, Tunis, Tunisia. pp.1-5. ⟨lirmm-01057539⟩