Contact: Mariia Gladkova, Brief Bio, Dr. Niclas Zeller

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 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.

If you find our work useful in your research, please consider citing:

@InProceedings{gladkova2021tight,
  author={M. Gladkova and R. Wang and N. Zeller and D. Cremers},
  title={Tight Integration of Feature-based Relocalization in Monocular Direct Visual Odometry},
  booktitle={Proc. of the IEEE International Conference on Robotics and Automation (ICRA)},
  year={2021}
}

Export as PDF, XML, TEX or BIB

Conference and Workshop Papers
2021
[]		Tight Integration of Feature-based Relocalization in Monocular Direct Visual Odometry (M Gladkova, R Wang, N Zeller and D Cremers), In Proc. of the IEEE International Conference on Robotics and Automation (ICRA), 2021. ([project page]) [bibtex] [arXiv:2102.01191]
2018
[]		LDSO: Direct Sparse Odometry with Loop Closure (X. Gao, R. Wang, N. Demmel and D. Cremers), In International Conference on Intelligent Robots and Systems (IROS), 2018. ([arxiv][video][code][project]) [bibtex]