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

The question #1

Open
YiruWangYuri opened this issue Jan 21, 2018 · 3 comments
Open

The question #1

YiruWangYuri opened this issue Jan 21, 2018 · 3 comments

Comments

@YiruWangYuri
Copy link

YiruWangYuri commented Jan 21, 2018

No description provided.

@YiruWangYuri
Copy link
Author

YiruWangYuri commented Jan 21, 2018

I couldn't find the "segmentation_error" in the 51 line of homo_eval.m and fundal_eval.m. Hence i could not run this demo successfully. Was there anybody else met this question?

@trungtpham
Copy link
Owner

Hi Yiru, I have just added segmentation_error function. Please check it out.

Cheers,
Trung

@YiruWangYuri
Copy link
Author

Hi Trung, thank you so much for your prompt reply! I have run the fundamental demo successfully. And I also have a question about the model_type. In fact, most of the robust model fitting algorithms provided the code with some model types such as “fundamental" and "homography". However, there are also other remaining model types: line, plane, circle, two-view motion segmentation, etc.. Hence, I am not clear how to compare with the state of the art in these remaining model types. Actually, it is just lack of some "fit_XXX.m" when we fit XXX model. Meanwhile, it seems that most of the authors did not provide all the model_types mentioned in the paper. As a freshman in this field, I wonder know whether there is no need for providing all codes in every model_types. The users could code these part by themselves or find them among Peter Kovesi and Andrew Zisserman's MATLAB functions?
Thank you very much!

Best regards,
Yiru

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