Tight Integration of Feature-Based Relocalization in Monocular Direct Visual Odometry

MCML Authors

Mariia Gladkova

→ Group Daniel Cremers
 Computer Vision & Artificial Intelligence

Daniel Cremers

Prof. Dr.

Director

Computer Vision & Artificial Intelligence

Abstract

In this paper we propose a framework for inte-grating 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 accurate poses. We evaluate our method on two multi-weather datasets showing the benefits of integrating different handcrafted and learned features and demonstrating promising improvements on camera tracking accuracy.

inproceedings

---

ICRA 2021

IEEE International Conference on Robotics and Automation. Xi'an, China, May 30-Jun 05, 2021.

---

Authors

M. Gladkova • R. Wang • N. Zeller • D. Cremers

---

Links

DOI

---

Research Area

 B1 | Computer Vision