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

Confused about the training data called img_kps #12

Open
zuixiaosanlang opened this issue Jul 16, 2020 · 1 comment
Open

Confused about the training data called img_kps #12

zuixiaosanlang opened this issue Jul 16, 2020 · 1 comment

Comments

@zuixiaosanlang
Copy link

Hello,
I am confused about the data format img_kpts/<img_idx>.bin.
If i get a keypoint detect by SIFT,how can i get the values as:
affine = (-0.25711258, 0.52153266, -0.58181703, -0.78229898, -0.38566887, -0.53048758)
What laws are there between affine[0], affine[1], affine[3], affine[4] ?

Why the affine transformation matrix in <img_idx>.bin is not like this:
affine_mat[0, 0] = m_cos
affine_mat[1, 0] = m_sin
affine_mat[2, 0] = ptf[0]
affine_mat[0, 1] = -m_sin
affine_mat[1, 1] = m_cos
affine_mat[2, 1] = ptf[1]

i read the article GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints,but still confused,

Thanks a lot for your help.

@luoqianchina
Copy link

luoqianchina commented Oct 13, 2020

Same question. Besides, in the article GeoDesc, equation(1) there is a σ' [-(kσ/2)sin(θ) (kσ'/2)cos(θ) y]. Is that correct? What does it mean? Or it should be σ? Thanks.

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