You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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!
The text was updated successfully, but these errors were encountered:
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.
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!
The text was updated successfully, but these errors were encountered: