7 November 2008 The application of mixed GA-BP algorithm on remote sensing image classification
Author Affiliations +
Proceedings Volume 7147, Geoinformatics 2008 and Joint Conference on GIS and Built Environment: Classification of Remote Sensing Images; 71470A (2008) https://doi.org/10.1117/12.813210
Event: Geoinformatics 2008 and Joint Conference on GIS and Built Environment: Geo-Simulation and Virtual GIS Environments, 2008, Guangzhou, China
Abstract
In this paper, both the advantage and disadvantage of traditional Genetic Algorithm and Back Propagation Algorithm are analyzed. A mixed algorithm on combination of genetic algorithm and back propagation algorithm is adopted and it's network is trained by a sample of the spectrum, texture, position and geometry features of hyperspectral remote sensing images. The numerical experiment is designed to compare GA-BP algorithm with an evolutionary BP algorithm, which is trained by Levenberg-Marquart algorithm. The results proved that GA-BP algorithm is more efficient, robust and practical.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Wan-chun Zhou, Wan-chun Zhou, Gang-sheng Xie, Gang-sheng Xie, Bo Liu, Bo Liu, "The application of mixed GA-BP algorithm on remote sensing image classification", Proc. SPIE 7147, Geoinformatics 2008 and Joint Conference on GIS and Built Environment: Classification of Remote Sensing Images, 71470A (7 November 2008); doi: 10.1117/12.813210; https://doi.org/10.1117/12.813210
PROCEEDINGS
8 PAGES


SHARE
Back to Top