Development of high resolution satellite image classification method in land use and land cover mapping

Pao Yue-kong Library Electronic Theses Database

Development of high resolution satellite image classification method in land use and land cover mapping

 

Author: Hu, Jinyuan
Title: Development of high resolution satellite image classification method in land use and land cover mapping
Degree: M.Sc.
Year: 2015
Subject: Remote-sensing images.
Remote sensing -- Data processing.
Image processing.
Hong Kong Polytechnic University -- Dissertations
Department: Faculty of Construction and Environment
Pages: viii, 87 page : color illustrations
Language: English
InnoPac Record: http://library.polyu.edu.hk/record=b2831542
URI: http://theses.lib.polyu.edu.hk/handle/200/8331
Abstract: As the development of remote sensing technology in land use and land cover mapping, classification method of high resolution satellite image has become more and more important and popular in the application. As one of the most important technique of accuracy improvement, multiple classifier systems (MCS) not only attract increasing interest in the field of remote sensing image classification, but also become hot topics in pattern recognition and machine learning. In this thesis, Satellite Pour 1' Observation de la Terre (SPOT) VI multi-spectral satellite images are applied and classified into 8 land cover classes using four base classifiers, they are maximum likelihood classifier, neural network classifier, Mahalanobis distance classifier and minimum distance classifier. These four classifiers are trained using the same data sets. The prior probability and the a posteriori probability are derived from the confusion matrices of those classifiers, which are produce accuracy and user accuracy respectively. A multiple classifier system is designed in this thesis to combine these classifiers to improve the accuracy of the classification result.

Files in this item

Files Size Format
b2831542x.pdf 2.964Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

     

Quick Search

Browse

More Information