qianguih / voxelnet

This is an unofficial inplementation of VoxelNet in TensorFlow.
646 stars 241 forks source link

How to draw 3D bounding box on 3d lidar data? #37

Open chowkamlee81 opened 5 years ago

chowkamlee81 commented 5 years ago

Kindly help in How to draw 3D bounding box on 3d lidar data using mayavi in voxelnet. Kindly help

hm2092 commented 5 years ago

You can refer this repo: https://github.com/skyhehe123/VoxelNet-pytorch/blob/bfd7be1ca6e5c5b39eece8a4c5fad3ad7b1f7c74/utils.py#L145

chowkamlee81 commented 5 years ago

In the above python code, code uses Camera to lidar coordinate to generate 3D BoBox on pointclouds. In my dataset i had only LIDAR dataset, no input images. Then how to draw plots on 3D LIDAR? Any help will be highly appreciated

hm2092 commented 5 years ago

The above code uses KITTI dataset in which the labels(x, y, z coordinates for bounding box centre) are given in camera coordinates. Thats why it is converted first to lidar coordinate system. If you directly have the corner points of the boxes you need to plot in lidar coordinate system, then you can use the plot3d function in mayavi to draw the box.