#528 · Primary category: Computer Vision

HybVIO

aalto-university computer-vision sensor-fusion slam visual-inertial-odometry

HybVIO visual-inertial odometry and SLAM system

Project last updated:05/05/22

GitHub Stars

551

Forks

104

Contributors

3

License

GPL-3.0

Why we included this project

HybVIO is a research release of a real-time visual-inertial odometry system with an optional SLAM module, published alongside a WACV paper so the results can be checked and reproduced. It fuses camera imagery with inertial measurements to track a device's position and orientation. The authors are upfront that this is a research codebase, not a polished product, so it works best as a baseline and a source of ideas rather than something to drop into a shipping app. It builds a runnable main binary, with flags for stereo, SLAM, and GPU visualization, plus tooling to benchmark against standard datasets like EuRoC, TUM, and SenseTime. That makes it a good reference for comparing VIO approaches and seeing how a hybrid visual-inertial estimator is put together.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category