Building Reconstruction Based on the Data Fusion of Lidar Point Cloud and Aerial Imagery

Today, 3D models of urban as one of the most important information are needed in many engineering applications such as urban planning, virtual tourism, navigation and emergency response. In recent years, by introducing the LiDAR system and using the 3D geo-referenced data, different methods have been proposed for 3D building modeling. Due to direct accessibility of 3D coordinate of LiDAR points, planar patch’s mathematical equations of building roofs could be determined accurately. However, extracting the edges and boundary of buildings with high accuracy from LiDAR points is a difficult task and will not be always precise. In new aerial laser scanning systems, in addition to using laser to adopt 3D point’s cloud of surface features, equipped by high resolutions small format RGB camera. So besides spatial data of features, RGB and spectral information are also available. In this research a method based on fusion of LiDAR point cloud and aerial image data sources has been proposed. In this study, firstly by using 2D plane (building footprint), points located inside polygon of each building are extracted from the overall scatter, individually. In the next step, the mean shift clustering algorithm applied to the points of different buildings in the feature space. Finally the segmentation stage ended with the separation of parallel and coplanar segments. Then using the adjacency matrix, adjacent segments are intersected and inner vertices are determined. In the other space, the region of any building cropped in the image space and the mean shift algorithm applied to it. Then, the lines of roof’s outline edge extracted bythe Hough transform algorithm and the points obtained from the intersection ofthese lines transformed to the ground space. Finally, by integration of structuralpoints of intersected adjacent facets and the transformed points from image space, reconstruction performed. In order to evaluate the efficiency of proposed method, buildings with different shapes and different level of complexity selected and the results of the 3D model reconstruction evaluated. The results showed credible efficiency of method for different buildings.