In this paper we present new methods for accelerating object-based image analysis using distributed computing. This is demonstrated on imagery from the refugee camp Lukole in Tanzania. An IKONOS scene from the refugee camp was chosen and relevant dwelling units were extracted. Promising results were achieved coping with an increasing data load and likewise with the demanded timeliness while a h...

Currently available image fusion techniques are not efficient for fusing the new satellite images such as IKONOS and Landsat 7. Significant colour distortion is one of the major problems. Reasons for this distortion are analyzed in this paper. A new initial automatic solution for fusing the new images is introduced. The new solution has reached an optimum fusion result – with minimized colour d...

We proposed a new method based on supervised locality preserving projections (SLPP) for classification of high resolution satellite images. Compared with other subspace methods such as PCA and ICA, SLPP can preserve local geometric structure of data and enhance within-class local information. The proposed method has been successfully applied to IKONOS images and experimental results show that t...