Automatic Building Detection and Delineation from High Resolution Space Images Using Model-based Approach

An approach was developed for updating the buildings of an existing vector database from high resolution space images by using spectral values, Digital Elevation Models (DEM) and model-based extraction techniques. First, the building areas are detected using image classification and normalized Digital Surface Model (nDSM). Those areas other than the buildings are excluded from further processing. Then, the buildings in the existing vector database are updated through evaluating the detected building areas and using the proposed model-based building extraction technique. The method was implemented in a selected urban area of Batikent, Ankara using IKONOS pan-sharpened and panchromatic images (2002). First, the building areas were detected by classifying the pansharpened image. The classified output provides the shapes and the approximate locations of the buildings. However, those buildings that have similar reflectance values with the other classes were not able to be detected. Therefore, nDSM was generated by subtracting the Digital Terrain Model (DTM) from Digital Surface Model (DSM). Next, the buildings were differentiated from the trees by using the Normalized Difference Vegetation Index (NDVI). Then, the buildings that exist in vector database and missing in the image were detected through analyzing the building areas coming from both the classification and nDSM for each building boundary and deleted from the vector database. Finally, the buildings constructed after the date of the compilation of existing vector database were extracted through the proposed model-based approach and the vector database was updated with the new building boundaries. The preliminary results show that the proposed approach is quite satisfactory for detecting and delineating the buildings from high resolution space images.