Implement a monocular VIO pipeline using GTSAM and the ImageProcessor class

ami-iit / kindyn-vio

Development on hold.

GNU Lesser General Public License v3.0

12 stars 1 forks source link

Implement a monocular VIO pipeline using GTSAM and the ImageProcessor class #27

Open prashanthr05 opened 2 years ago

prashanthr05 commented 2 years ago

We have implemented the ImageProcessor class in #10 and #11. We can make use of this along with GTSAM's IMU Preintegration methods to implement a VIO pipeline.

Reference project: https://github.com/ganlumomo/VisualInertialOdometry

prashanthr05 commented 2 years ago

See https://github.com/dic-iit/kindyn-vio/issues/6#issuecomment-893813610 for first steps.

prashanthr05 commented 2 years ago

[ ] Forster's IMU PreIntegration (CombineIMUFactor with Manifold Preintegration) + Aruco markers (BetweenFactor)
[ ] Forster's IMU PreIntegration (CombineIMUFactor with Manifold Preintegration) + Points Tracking (SmartProjectionFactor)
[ ] ...

Alternate method is to use (CombineIMUFactor with TangentSpace Preintegration) which is documented in gtsam/doc/ImuFactor.