Title :
Genetic algorithm for depth images in RGB-D cameras
Author :
Danciu, Gabriel ; Szekely, Iuliu
Author_Institution :
Dept. of Electron. & Comput., Univ. of Brasov, Braşov, Romania
Abstract :
In this paper, a new method for unsupervised image segmentation that can be applied to RGB-D (red, green, blue - depth) cameras is presented. The method consists in using a genetic algorithm to optimize the homogeneity of the segmented regions of a depth image. It searches for the best gray level ranges for which the segmentation of the image is closer to the ground truth. Experimental results and comparisons to existing algorithms demonstrate how the proposed method works.
Keywords :
cameras; genetic algorithms; image segmentation; unsupervised learning; RGB-D cameras; depth images; genetic algorithm; gray level ranges; ground truth; homogeneity optimization; red-green-blue-depth cameras; unsupervised image segmentation; Algorithm design and analysis; Cameras; Cost function; Electronics packaging; Genetic algorithms; Histograms; Image segmentation; RGB-D camera; genetic algorithm; segmentation;
Conference_Titel :
Design and Technology in Electronic Packaging (SIITME), 2014 IEEE 20th International Symposium for
Conference_Location :
Bucharest
DOI :
10.1109/SIITME.2014.6967036
