Research on Monocular Visual Odometry Based on 3D-2D Motion Estimation

On the fundamental theory of Structure from Motion, we present an algorithm based on 3D-2D motion estimation monocular visual odometry. In order to resolve the problem of 3D-2D motion estimation, which need to maintain a consistent and accurate set of triangulated 3D feature points and to create precisely 3D-to-2D correspondences, and considering the complexity and variability of the outdoor scene and uncertainty of inter frame motion, a method of combining optical flow with feature matching is proposed. Experimental results show that the proposed algorithm can improve the accuracy effectively.