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

Can't achieve the same effect with my own data #70

Closed
GuoXiaoxiao1 opened this issue Jul 10, 2020 · 1 comment
Closed

Can't achieve the same effect with my own data #70

GuoXiaoxiao1 opened this issue Jul 10, 2020 · 1 comment

Comments

@GuoXiaoxiao1
Copy link

Hello, @niosus
I'm sorry to disturb you. After reading your code, I have some questions to ask.
First, when selecting different types of input files on the QT interface, although they are all 64 line data, the effects of KITTI bin files and scenario png files are very different. KITTI bin data results are obviously not good. Why is this?
Second, your paper said that it is also applicable to 16 line Lidar, but after I input the png files of 16 line Lidar, the segmentation effect is very poor and can hardly be used. Where is it that needs to be modified?

Looking forward to receiving your reply, thank you very much!

@niosus
Copy link
Member

niosus commented Jun 2, 2021

Without looking into your data, the only reason I can think if is that the angles between the beams are different for the different LiDARs. As for KITTI data, the actual data is pretty uncalibrated and does not produce nice range images, which is the reason for the failures that you see.

@niosus niosus closed this as completed Jun 2, 2021
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