ICRA21 Presentation: Tight Integration of Feature-based Relocalization in Monocular Direct VO

Publication: Tight Integration of Feature-based Relocalization in Monocular Direct Visual Odometry Authors: Mariia Gladkova, Rui Wang, Niclas Zeller, and Daniel Cremers Conference: International Conference on Robotics and Automation (ICRA) 2021, Xi’an, China Abstract: In this paper we propose a framework for integrating map-based relocalization into online direct visual odometry. To achieve map-based relocalization for direct methods, we integrate image features into Direct Sparse Odometry (DSO) and rely on feature matching to associate online visual odometry (VO) with a previously built map. The integration of the relocalization poses is threefold. Firstly, they are incorporated as pose priors in the direct image alignment of the front-end tracking. Secondly, they are tightly integrated into the back-end bundle adjustment. Thirdly, an online fusion module is further proposed to combine relative VO poses and global relocalization poses in a pose graph to estimate keyframe-wise smooth and globally accura