Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Example of slam and imu fusion? #5

Open
antithing opened this issue Dec 6, 2022 · 3 comments
Open

Example of slam and imu fusion? #5

antithing opened this issue Dec 6, 2022 · 3 comments

Comments

@antithing
Copy link

Hi, thanks for making this code available. I am looking to implement inertial fusion into a slam algorithm, is there any examples here that do that?

Thanks!

@jeff-delaune
Copy link
Member

Hi,

Yes, there's a ROS implementation available here:

https://github.com/jpl-x/x_vio_ros

And a technical report about this implementation here:

https://arxiv.org/abs/2103.15215

@antithing
Copy link
Author

Thank you! I need to run without ROS so I will attempt to modify the code. The matchesptr object, is that the 2d features, as pixel location?

@jeff-delaune
Copy link
Member

jeff-delaune commented Dec 19, 2022

Yes, the matches_ptr includes the feature matches from to the current images in pixel coordinates (+ a placeholder for the 3D coordinates for debugging purposes). For more details, the import code is located in line 339 at https://github.com/jpl-x/x/blob/master/src/x/vio/vio.cpp

Please note the match_ptr is only used if you decide to use an external feature tracker (or simulation) that sends data in this format. If you use the image callback instead, xVIO will run its own feature tracker.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants