Research On The Technology Of Building Reconstruction Based On Geometric Features

Digital city technology is growing rapidly, but the less-automated workload of data acquisition and modeling is heavy. This paper focuses on the technology of building reconstruction based on the geometric features of the man-made constructions. The main contents of this paper are as follows:(1) A vanishing points detection algorithm based on a cluster-based adaptive switching median (CASWM) filter is proposed to improve the accuracy during the vanishing point detection, despite the probable false detection resulting from the noise;(2) A novel SIFT algorithm based on valid region detection drawn from vanishing points information is designed and implemented. Detection on regions outside the buildings is avoided, which greatly improves the efficiency of the algorithm and reduce the implementation time;(3) An improved LO-RANSAC algorithm is proposed to make the estimation of fundamental matrix robuster and more effective;(4) A camera self-calibration method is implemented using vanishing points. After the process of CASWM filtering and MSAC estimation, the self-calibration algorithm works well in both speed and accuracy;(5) An image sequence based 3D reconstruction system for buildings is delevoped on the algorithms above to meet the specific requirements of photogrammetry and experiments are conducted to veridate the algorithms above.