Automatic Classification of Remote Sensing Images Using Multiple Classifier Systems

Bin Yang,Xiaowen Li,Ying Xing,Chunxiang Cao

doi:10.1155/2015/954086

Abstract

It is a challenge to obtain accurate result in remote sensing images classification, which is affected by many factors. In this paper, aiming at correctly identifying land use types reflec ted in remote sensing images, support vector machine, maximum likelihood classifier, backpropagation neural network, fuzzy c-means, and minimum distance classifier were combined to construct three multiple classifier systems (MCSs). Two MCSs were implemented, namely, comparative major voting (CMV) and Bayesian average (BA). One method called WA-AHP was proposed, which introduced analytic hierarchy process into MCS. Classification results of base classifiers and MCSs were compared with the ground truth map. Accuracy indicators were computed and receiver operating characteristic curves were illustrated, so as to evaluate the performance of MCSs. Experimental results show that employing MCSs can increase classification accuracy significantly, compared with base classifiers. From the accuracy evaluation result and visual check, the best MCS is WA-AHP with overall accuracy of 94.2%, which overmatches BA and rivals CMV in this paper. The producer’s accuracy of each land use type proves the good performance of WA-AHP. Therefore, we can draw the conclusion that MCS is superior to base classifiers in remote sensing image classification, and WA-AHP is an efficient MCS.

Highlights

With the development of remote sensing technology, it has been widely applied in many different fields such as land use land cover (LULC) monitoring, investigation of forest resources, disaster monitoring, and urban planning [1, 2], where the identification of land use types by image classification technology plays a very important role
Many artificial intelligence (AI) methods have been utilized in remote sensing images classification including neural networks [3,4,5], support vector machine (SVM) [6,7,8], and maximum likelihood classifier (MLC) [9, 10]
We aimed at improving the classification accuracy for remote sensing images by combining multiple classifiers

Summary

Introduction

With the development of remote sensing technology, it has been widely applied in many different fields such as land use land cover (LULC) monitoring, investigation of forest resources, disaster monitoring, and urban planning [1, 2], where the identification of land use types by image classification technology plays a very important role. There are a large number of land use types with irregular distribution on the surface of earth. Multiple classifier systems (MCSs) naturally become a good choice. Combining strategies for multiple classifiers has been widely investigated, the aim of which is to determine an efficient combination method that makes full use of the complementary advantages of each classifier and tackles the drawbacks of individual classifiers, to improve the accuracy of classification. MCS theory was developed in pattern recognition such as signal processing, handwriting

Methods

Results

Conclusion