unmannedlab / RELLIS-3D

RELLIS-3D: A Multi-modal Dataset for Off-Road Robotics
https://unmannedlab.github.io/research/RELLIS-3D
287 stars 49 forks source link

Semantic segmentation labels on stereo frames #23

Open yqsony opened 2 years ago

yqsony commented 2 years ago

I am interested in semantic segmentation using stereo cameras. If I understand correctly, the semantic annotation labels are on the monocular RGB camera (pylon), but not the left or right camera in the stereo set. Is there any way that I can project the semantic annotation labels on to the left camera of the stereo set?

maskjp commented 2 years ago

Hi, @yqsony,

Sorry for the late reply! We currently don't have the transformation between stereo and Balser cameras, so you can't project it on the camera. But we are working on it. We will provide it when we complete it. Appreciate your patience!

Best wishes!

Alt216 commented 2 years ago

Hi @maskjp , thanks for the awesome dataset! Is there any update on the transformation between stereo and Balser cameras?

maskjp commented 2 years ago

Hi, @yqsony , @Alt216 Sorry for the late reply. We recover the transformation using SFM. It's not perfect but might be usable. Here is the link I hope it helps!