ABSTRACT
Urban remote sensing is crucial for mapping and monitoring city areas. In these areas, the prominent class is buildings. Very high resolution (VHR) satellite images provide the ideal data for building mapping. However, these images lack the height information and are usually acquired off-nadir. These two limitations pose a challenge for mapping buildings in off-nadir VHR satellite images. Therefore, this chapter identifies the challenges associated with building detection in off-nadir VHR satellite images based on stereo 3D information. Additionally, the chapter describes three solutions developed to mitigate the effects of the identified problems. The applicability of these solutions is demonstrated through stereo-based building detection in off-nadir images. The outcome of this research proved the possibility of using off-nadir VHR satellite images for accurate building detection. It also increases the data source scope for building detection since most VHR satellite images are acquired off-nadir and traditional methods cannot effectively handle off-nadir images.
