Optimization of multiresolution segmentation by using a genetic algorithm

Maryam Nikfar; Mohammad J. Valadan Zoej; Ali Mohammadzadeh; Mehdi Mokhtarzade; Afshin Navabi

doi:10.1117/1.JRS.6.063592

30 October 2012 Optimization of multiresolution segmentation by using a genetic algorithm

Maryam Nikfar, Mohammad J. Valadan Zoej, Ali Mohammadzadeh, Mehdi Mokhtarzade, Afshin Navabi

Author Affiliations +

Journal of Applied Remote Sensing, Vol. 6, Issue 1, 063592 (October 2012). https://doi.org/10.1117/1.JRS.6.063592

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.

Citation Download Citation

Maryam Nikfar, Mohammad J. Valadan Zoej, Ali Mohammadzadeh, Mehdi Mokhtarzade, and 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

Published: 30 October 2012

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available