30 October 2012 Optimization of multiresolution segmentation by using a genetic algorithm
Author Affiliations +
Abstract
Most traditional pixel-based analyses are based on the digital number of each pixel. Whereas images can provide more details such as color, size, shape, and texture, object-oriented processing is more advantageous. Multiresolution segmentation, which was proposed by Baatz and Schäpe, is one of the most powerful segmentation algorithms. On the other hand, meaningful segmentation is the most important issue in object-oriented processing. Currently, meaningful segmentation, which is recommended by Baatz's multiresolution segmentation approach, is a trial-and-error task that is very tedious and time consuming. Therefore, a genetic algorithm (GA) is used for finding optimal parameters of Baatz's multiresolution segmentation approach for three building groups' meaningful segmentation. The optimal parameters are found by GA and its generality has been evaluated on a simulated image as well as some IKONOS and GeoEye image patches. The evaluations show the efficiency of GA for finding optimal multiresolution segmentation parameters for meaningful segmentation of the simulated image and the three groups of building images.
© 2012 Society of Photo-Optical Instrumentation Engineers (SPIE)
Maryam Nikfar, Mohammad J. Valadan Zoej, Ali Mohammadzadeh, Mehdi Mokhtarzade, Afshin Navabi, "Optimization of multiresolution segmentation by using a genetic algorithm," Journal of Applied Remote Sensing 6(1), 063592 (30 October 2012). https://doi.org/10.1117/1.JRS.6.063592 . Submission:
JOURNAL ARTICLE
18 PAGES


SHARE
Back to Top