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

about extrinsic parameter for stereo cameras #111

Open
jaehwan-pi opened this issue Sep 7, 2023 · 1 comment
Open

about extrinsic parameter for stereo cameras #111

jaehwan-pi opened this issue Sep 7, 2023 · 1 comment

Comments

@jaehwan-pi
Copy link

Thank you for your wonderful work.
As I'm testing your code with stereo camera setup,
I found that scale errors are quite big even if I'm using stereo images.
For example when I test with EuRoC dataset, scale error values are around 1.1 for all sequences.

According to an issue(#102),
It seems like your code does not consider stereo camera extrinsic value.

When I change the parameter https://github.com/princeton-vl/DROID-SLAM/blob/main/droid_slam/geom/projective_ops.py#L105
to stereo camera extrinsic value, provided by EuRoC calibration file,
it seems like scale errors are reduced quite much.

So these are my questions.

  1. Changing the parameter above, is it a right way to consider stereo camera setup?
  2. If so, why your code have fixed the parameter to be [-0.1, 0.0, 0.0, 0.0, 0.0, 0.0, 1.0] ?
@dani808-max
Copy link

could you help me how to run this code in google colab?

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