Substantial improvement of stereo visual odometry by multi-path feature tracking

Visual odometry (VO) studies the recovery of a camera trajectory from an image sequence. Stereo vision-based VO techniques solve the egomotion estimation problem by means of disparity-derived 3D scene structure. Typically, one of the two images is only used for disparity computation. In this paper we develop a generic feature tracking framework extending the classical VO problem into a higher dimension, where the image data of both cameras are fully used. Six tracking topologies proposed in literature, namely linear, lookahead, stereo linear, parallel, circular and cross-eye, are reviewed and evaluated. Based on the experimental results, we found benefits of taking right images into account through the feature tracking process, over the typical stereo VO implementation. The stereo-parallel configuration, which independently maintains feature tracking on each camera and have the tracked features integrated via a left-right matching, has achieved the most significant improvement of 30% over the conventional linear configuration.