3D reconstruction based on SIFT and Harris feature points

Abstract

This paper presents a new 3D reconstruction method using feature points extracted by the SIFT and Harris corner detector. Since the SIFT feature points can be detected stably and relatively accurately, the proposed algorithm first uses the SIFT matching points to calculate the fundamental matrix. On the other hand many of the feature points detected by the SIFT are not what we need for reconstruction, so by combining the SIFT feature points with the Harris corners it is possible to obtain more vivid and detailed 3D information. Experiments have been conducted to validate the proposed method. © 2009 IEEE.