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

which dataset did you use? could you provide the link? #2

Open
YiChenCityU opened this issue Sep 19, 2017 · 8 comments
Open

which dataset did you use? could you provide the link? #2

YiChenCityU opened this issue Sep 19, 2017 · 8 comments

Comments

@YiChenCityU
Copy link

which dataset did you use? could you provide the link?
Thanks.

@alexwu-bayarea
Copy link
Collaborator

I used Kitti Odometry dateset: http://www.cvlibs.net/datasets/kitti/eval_odometry.php

@marvis
Copy link

marvis commented Sep 27, 2017

Hi @JiatianWu. Is there big difference between grayscale images and color images when running the results? Thanks!

@alexwu-bayarea
Copy link
Collaborator

Not exactly. Stereo DSO transforms color image to grayscale.

@taiping-z
Copy link

taiping-z commented Nov 30, 2017

Hi, @JiatianWu.

How to calc disparity in Calibration File for the KITTI datasets, could you please provide a simple example or a link?

Thanks!

@ouerkakaChango
Copy link

@taiping-z
try this for KITTI 00:
718.856 718.856 607.1928 185.2157 0
1241 376
crop
640 480
0.3861448
(The so called 'disparity' is baseline,I found the parameter in ORB-SLAM2's yaml,and divide 1000)

@alexwu-bayarea
Copy link
Collaborator

Yes the disparity is actually baseline of the stereo camera. Already update it. Sorry for the ambiguity.

@taiping-z
Copy link

@ouerkakaChango, @JiatianWu,
Thanks a lot.

@ganleiboy
Copy link

@ouerkakaChango Thanks a lot. I have made camera.txt, but i don't kown why dividing 1000 is needed. Could you explain it in detail, please?

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

6 participants