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

Can we plot the GT trajectory in the GUI? #13

Closed
alik-git opened this issue Mar 7, 2024 · 1 comment
Closed

Can we plot the GT trajectory in the GUI? #13

alik-git opened this issue Mar 7, 2024 · 1 comment

Comments

@alik-git
Copy link
Contributor

alik-git commented Mar 7, 2024

Hey guys congrats on the great work.

I think it would be quite helpful to plot the GT trajectory as well in the GUI to allow for comparison. I can take a look at doing it myself, but I'm still familiarizing myself with the code, so if you could give me your thoughts on what my options are for implementing this at a high level that would be great.

if you already have the code for doing that, please point me to it, thank you!

@muskie82
Copy link
Owner

muskie82 commented Mar 8, 2024

Hi,

Thank you.
For RGB-D case, you can quickly add GT pose frustum in GUI with a few lines of code. Insert the following code after this line.

name = "gt_{}".format( keyframe.uid)
frustum = self.add_camera(keyframe, name=name, color=[1, 0, 0], gt=True)

This will display the GT poses as red frustums in the GUI.

gt_vis

Note that "GT pose" referred to here means the GT relative pose against the first frame.
Thus, these GT poses looks slightly different from the one in ATE evaluation plot, which performs whole trajectory alignment between GT/estimated trajectory.

Also, please keep in mind that this visualization might not be meaningful for monocular cases because the scale is not adjusted.

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