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

Question about the alignment-method #148

Closed
sdrdis opened this issue Jul 25, 2016 · 1 comment
Closed

Question about the alignment-method #148

sdrdis opened this issue Jul 25, 2016 · 1 comment

Comments

@sdrdis
Copy link

sdrdis commented Jul 25, 2016

Hi,

I have one question about the alignment-method parameter of stereo. When I read the section B.1 of the documentation, it is written:

When alignment-method is set to affineepipolar, stereo will attempt to pre-align [...] such that pairs of conjugate epipolar lines become collinear and parallel to one of the image axes.

I plan to use a home made stereo vision algorithm, but would like to benefit from the preprocessing step of stereo. However, I need to make sure that the epipolar lines are horizontal and not vertical. Therefore, is there a way to know, after the preprocessing step, which axis (vertical or horizontal) the epipolar lines are parallel to? Or is there a way to force these lines to be horizontal?

Thanks,

@oleg-alexandrov
Copy link
Member

I honestly don't remember now which direction the epipolar lines end up pointing. What you can do, is run disparitydebug on the obtained D.tif that comes from stereo. If affineepipolar alignment was successful, the obtained disparity in D.tif will be mostly horizontal or mostly vertical. And it will answer your question. If you want to force the lines to be horizontal (if they are not), I suggest you look at our source code in the location where epipolar alignment happens, in AffineEpipolar.cc.

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