Automatic 3D Reconstruction of Urban Areas, by using Epipolar Geometry and Template Matching

\ Abstract In this work we describe a novel technique for automatic 3D reconstruction of urban areas, from airborne stereo-pair images whose output is VRML. The main challenge is to compute the relevant information building’s height, roof’s description and texture – algorithmically, since it is very time consuming and thus expensive to produce it manually for large urban areas. The algorithm requires some initial calibration input and is able to compute the above mentioned building characteristics from the stereo pair, without no knowledge of the camera pose or its intrinsic parameters (other than the camera lens distortion parameters). To achieve this, we have used epipolar geometry, automatic feature extraction and we have solved the feature correspondence problem in the stereo pair, by using template matching.