A New Method for Spatial Feature Extraction and Classification of Remote Sensing Image

The extraction and classification problem of spatial features from high r esolution satellite sensor image, especially from the image covering urban areas, is a very significant but challenging task. However, it is very difficult to be implemented and the main obstacle comes from high-dimensional and complicated properties of spatial features. In this paper, we propose to use a two-dimension wave-let transform as well as a classification method---support vector machine (SVM) to address this issue. Also, a boosting method is involved in order to improve the accuracy of classification. We will show in our experiment that SVM with Boosting leads to a more admissible result by choosing several SVM kernels, including the linear kernel and the Gaussian kernel.