An Adaptive Multiscale Information Fusion Approach for Feature Extraction and Classification of IKONOS Multispectral Imagery Over Urban Areas

An adaptive multiscale information fusion algorithm is proposed to extract the spatial features and classify IKONOS multispectral imagery. It is well known that combining spectral and spatial information can improve land use classification of very high resolution data. However, many spatial measures refer to the window size problem, and the success of the classification procedure using spatial features depends largely on the window size that was selected. In this letter, we first propose an optimal window selection method, based on the spectral and edge information in a local region, for choosing the suitable window size adaptively; second, the multiscale information is fused based on the selected optimal window size. In order to evaluate the effectiveness of the proposed multiscale feature fusion approach, the spatial features that were extracted by the gray-level cooccurrence matrix are utilized for multispectral IKONOS data. The results show that the proposed algorithm can select and fuse the multiscale features effectively and, at the same time, increase the classification accuracy.