Remote sensing image change detection using Gray system theory

Abstract

Remote sensing image change detection techniques are widely used in environmental change detection such as landuse change monitor, flood monitor. Many change detection techniques are used in practice today. This paper reports the development of techniques based on artificial neural networks and presents a new method of integrating artificial neural networks (ANN) with gray system theory for remote sensing image change detection. Gray system theory, founded by Professor Deng Julong, can handle undetermined problem .It is effective when the sample datum can not satisfy some distribution. The accuracy of image change detection based on traditional ANN is influenced by some factors such as network architecture, training set. The number of hidden layers and the number of nodes in a hidden layer are not easy to deduce. The traditional neural network architecture which gives the best results for image change detection can only be determined experimentally, and this can be a lengthy process especially for large image. This paper presents a new method that the number of nodes in hidden layers is deduced by using gray correlation analysis in gray system theory. A neural network based change detection system using the backpropagation training is developed. The trained three-layered neural network was able to provide information of changes and detect land-cover change with an overall accuracy of 91.3 percent. Using the same training data, a maximum-likelihood supervised classification produced an accuracy of 85.1 percent. The experimental results by using multitemporal TM imagery and SPOT imagery. Findings of this study demonstrated the potential and advantages of using neural network and gray system theory in multitemporal change analysis.