A study of changes prediction by HMM with non-stationarity image data: Case of urban area

In this paper, we propose a methodology for changes prediction in urban area using Hidden Markov Model (HMM). The main focus is to study a non-stationarity data in HMM models. In order to use these data we apply a stationarity processes. We propose to calculate a spatial metrics of in urban area from satellite images. Then, a stationnarisation process was applied to remove the random variations, and to model the variations by using HMM. A comparative study is done. The performance of our method is showed by using a series of Landsat.