LiDAR Annotation Semantic ROS Bag

unmannedlab / RELLIS-3D

RELLIS-3D: A Multi-modal Dataset for Off-Road Robotics

https://unmannedlab.github.io/research/RELLIS-3D

263 stars 47 forks source link

LiDAR Annotation Semantic ROS Bag #20

Open DLonng opened 2 years ago

DLonng commented 2 years ago

Hi, Thanks for providing this dataset.

I want to use

/os1_cloud_node/points
pylon_camera_node_label_color
/tf to build a semantic gridmap as a ground truth, but I don't know how to get such a bag.

Or, how to convert LiDAR Annotation SemanticKITTI Format to a ros bag file?

/semantic_label_color_cloud
/tf
odom, gps, imu ...

Thank for your replay. :)

maskjp commented 2 years ago

Hi, @DLonng,

Thank you so much for being so interested in our dataset.

Every LiDAR point cloud in the rosbag has a corresponding semantic label and pose.

You can read the semantic label and put the information in the ROS message like the intensity information in the point cloud message. You can take ouster lidar code as an example.

And use the pose file to register the point cloud. Or you can use other lidar-based slam algorithms to construct the map.

I hope this helps!

Best wishes!

DLonng commented 2 years ago

ok, thanks :)