A new approach for surface water change detection: Integration of pixel level image fusion and image classification techniques

摘要: Abstract Normally, to detect surface water changes, features are extracted individually using multi-temporal satellite data, and then analyzed compared their changes. This study introduced a new approach for change detection, which is based on integration of pixel level image fusion classification techniques. The proposed has the advantages producing pansharpened multispectral image, simultaneously highlighting changed areas, as well providing high accuracy result. In doing so, various techniques including Modified IHS, High Pass Filter, Gram Schmidt, Wavelet-PC were investigated merge Landsat ETM+ 2000 TM 2010 images highlight suitability resulting fused detection was evaluated edge visual interpretation, quantitative analysis methods. Subsequently, artificial neural network (ANN), support vector machine (SVM), maximum likelihood (ML) applied extract map highlighted Furthermore, applicability in comparison with some common methods differencing, principal components analysis, post comparison. results indicate that Lake Urmia lost about one third its area period 2000–2010. illustrate effectiveness approach, especially Schmidt-ANN Schmidt-SVM detection.