VI-ORBSLAM(2) implementations

28 July 2020

thesis

I’ve been looking for already existing implementations of a visual-inertial ORB-SLAM or ORB-SLAM2. So far, I haven’t found anything yet.

Links of interest:

Of course, the canonical implementation of ORB-SLAM 1 and 2, provided by Raúl Mur-Artal et al. under the GPLv3 license. However, they don’t supply any visual-inertial implementations.
Russell Buchanan has started implementing some VI-integrations in a fork of the above repository. It does not seem finished, or strictly adhering to the VI-ORBSLAM paper.
Jing Wang has implemented VI-ORBSLAM on the (non-forked, copy-pasted) canonical ORB-SLAM2 implementation. I found a paper using that implementation as an implementation of VI-ORBSLAM as there is no canonical version.
VI-ORBSLAM heavily leans on the work done in this paper. GTSAM 4 improves upon that paper, and provides an implementation of this library under the simplified BSD license. I might integrate this in ORB-SLAM2.

References

Raúl Mur-Artal and Juan Domingo Tardós. Visual-inertial monocular SLAM with map reuse. IEEE Robotics and Automation Letters, 2(2):796–803, April 2017. [ bib | DOI ]


@article{murartal2017visual,
  author = {Mur-Artal, Raúl and Tardós, Juan Domingo},
  journal = {IEEE Robotics and Automation Letters},
  title = {Visual-Inertial Monocular {SLAM} With Map Reuse},
  year = {2017},
  month = apr,
  volume = {2},
  number = {2},
  pages = {796-803},
  keywords = {cameras;robot vision;SLAM (robots);visual-inertial monocular SLAM;map reuse;visual-inertial odometry;sensor incremental motion;trajectory estimation;visual-inertial simultaneous localization;zero-drift localization;camera configuration;IMU initialization method;gyroscope;accelerometer;micro-aerial vehicle public dataset;monocular camera;Optimization;Cameras;Gravity;Accelerometers;Simultaneous localization and mapping;Tracking loops;Sensor fusion;SLAM;visual-based navigation},
  doi = {10.1109/LRA.2017.2653359},
  issn = {2377-3766}
}

Christian. Forster, Luca Carlone, Frank Dellaert, and Davide Scaramuzza. On-manifold preintegration for real-time visual–inertial odometry. IEEE Transactions on Robotics, 33(1):1–21, 2017. [ bib ]


@article{forster2017onmanifold,
  author = {Christian. {Forster} and Luca {Carlone} and Frank {Dellaert} and Davide {Scaramuzza}},
  journal = {IEEE Transactions on Robotics},
  title = {On-Manifold Preintegration for Real-Time Visual--Inertial Odometry},
  year = {2017},
  volume = {33},
  number = {1},
  pages = {1-21}
}