Detecting Complex Building Shapes in Panchromatic Satellite Images for Digital Elevation Model Enhancement

Since remote sensing field provides new sensors and techniques to accumulate data on urban region, three-dimensional representation of these regions gained much interest for various applications. Three-dimensional urban region representation can be used for detailed urban monitoring, change and damage detection purposes. In order to obtain three-dimensional representation, one of the easiest and cheapest way is to use Digital Elevation Models (DEMs) which are generated from very high resolution stereo satellite images using stereovision techniques. Unfortunately after applying the DEM generation process, we can not directly obtain three-dimensional urban region representation. In the DEM which is generated using only one stereo image pairs, generally noise, matching errors, and uncertainty on building wall locations are very high. These undesirable effects increase the complexity in the three-dimensional representation. Therefore, automatic DEM enhancement is an open and challenging problem. In order to enhance DEM, herein we propose an approach based on building shape detection. We use DEM and orthorectified panchromatic Ikonos images of München to explain our method. After applying pre-processing to both DEM and Ikonos image, we apply local thresholding to DEM to detect approximate locations of high urban objects like buildings. In order to detect complex building shapes, we develop our previous rectangular shape detection (box-fitting) algorithm. Unfortunately, building shapes are very complex in our study region. We assume that shapes of these complex buildings can be detected by fitting small rectangles like a chain. Therefore, we divide detected buildings into elongated subparts. Then, we apply our previous rectangular shape detection algorithm to these subparts. In shape detection, we consider Canny edges of Ikonos image to fit rectangular boxes. After merging all detected rectangles, we detect shapes of even very complex building structures. Finally, using detected building shapes, we refine building edges in the DEM and smooth the noise on building rooftops. We believe that the implemented enhancement will not only provide better visual three-dimensional urban region representation, but also will lead to detailed change and damage investigations.