Title :
Genetic stereo matching algorithm with fuzzy fitness
Author :
Ghazouani, Haythem
Author_Institution :
Dept. of Comput. Sci., Ecole Super. de Technol. et d´Inf., Tunis, Tunisia
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.
Keywords :
genetic algorithms; image matching; image sensors; stereo image processing; disparity matrix; evolutionary operators; fuzzy evaluation function; fuzzy fitness function; genetic stereo matching algorithm; noise camera measurements; uncertain camera measurements; Biological cells; Encoding; Genetic algorithms; Genetics; Sociology; Statistics; Stereo vision; Dense stereo matching; Disparity map; Fuzzy fitness; Genetic algorithm;
Conference_Titel :
Soft Computing and Pattern Recognition (SoCPaR), 2014 6th International Conference of
Conference_Location :
Tunis
DOI :
10.1109/SOCPAR.2014.7007972
