Urban building extraction from high-resolution satellite panchromatic image using clustering and edge detection

For decades, large-scale aerial photos have been employed to extract building for mapping application. With the successively launching of high-resolution commercial satellites (e.g. IKONOS and QuickBird), high-resolution satellite imagery has been shown to be a cost-effective alternative to aerial photography in many applications. Drawing on the traditional building extraction approach, this paper proposes an algorithm to extract urban building from high-resolution panchromatic QuickBird image using clustering and edge detection. In the first step, an unsupervised clustering by histogram peak selection is used to split the image into a number of classes. The shadows of building are extracted from the lowest gray class. In the second step, the shadows are used as one of the evidences to verify the presence of buildings. Thus, the candidate building objects are extracted from the clustering classes except for the shadow class. Finally, to refine building boundary and further exclude some false building objects, the Canny operator is applied to detect edge of the candidate building objects in the PAN image. From the Hough transform of the detected edges, the main lines, which compose the polyhedral description of the building, can be found. The building extraction results are compared with manually delineated results. The comparison illustrates the efficiency of the proposed algorithm