open_vins
open_vins copied to clipboard
An open source platform for visual-inertial navigation research.
Hello, I have encountered the "classic" drift in a simulation environment using your code. After some modification, i managed to have it initialize correctly and depending on the way the...
Thanks for this wonderful project! I have used OpenVins on Hilti SLAM challenge dataset 2021 with mono mode, but the pose goes to infinity quickly. here is the website [Hilti...
This color of trajectory of a feature with too long track length on the display image will be white current now. This problem is caused by the property of integer...
Hi I am trying to build on ROS-1 Noetic (Ubuntu 20.04) and getting the following error for the ov_init package ``` errors
Thanks for the project! I'm facing some trouble running it. I'm getting very serious drifts in odometry when running on the [subt](https://github.com/osrf/subt) simulator(ignition gazebo). https://user-images.githubusercontent.com/12036454/179759456-e7f908fb-fdaa-4122-89d7-2a0b7ea85c90.mp4 Here's how my configs look...
The odometry with high frequency IMU (greater than 400hz) can be slow since the state is re-integrated from the previous update timestep. More ideally we should cache the result of...
I've played with the dynamic initializer a little bit and got quite confused with the MLE process. What i don't understand is the derivation of the theta_error's jacobian with respect...
Hi This issue is an extension of #61 and #49. Based on the suggestion provided in these two issues, we performed a coordinate transformation between OpenVins' global frame of reference...
when I see the code **UpdaterZeroVelocity.cpp**, and I found the follow measurement noise may be false, noise should be proportional to dt^2 ? https://github.com/rpng/open_vins/blob/cd866b5ba58f1b59f0d6983c0a379753d25d1308/ov_msckf/src/update/UpdaterZeroVelocity.cpp#L165