search

alexsax / 2D-3D-Semantics

The data skeleton from Joint 2D-3D-Semantic Data for Indoor Scene Understanding
http://3dsemantics.stanford.edu
Apache License 2.0
464 stars 67 forks source link

Rotations in the pose files #31

Closed onatsahin closed 5 years ago

onatsahin commented 5 years ago

Hi,

My goal is to create range images from the point clouds using PCL. For that, I use the camera poses. However, the resulting range images are not showing where the corresponding RGB images do. Camera's location seems to be correct, but its pose is different. The closed issue https://github.com/alexsax/2D-3D-Semantics/issues/26 does what I want to do with the mesh, but I can't recreate this behavior with point clouds. I inferred that the Euler angles are given as radians. When creating the range images, I had to change the yaw angle by 90 or 180 degrees in the trials I made to make the camera look at where the corresponding rgb image shows. Even then, the resulting image does not perfectly align with the RGB image like it does in the closed issue I mentioned. What might be the issue? I am doing my experiments on Area 3, and I took the point cloud from the S3DIS dataset instead of the .mat file.

brokenCandy commented 4 years ago

@onatsahin can I know how you generated images using camera poses and have you used python ?

onatsahin commented 4 years ago

@brokenCandy For creating the range images, I used PCL's RangeImagePlanar class. This class has a member function called createFromPointCloudWithFixedSize, which uses camera information and pose to create a range image from the point cloud. These are all available in the C++ version of PCL. PCL also has a python version with less functionality, but I'm not sure if the things I used are available there.