Lidar Toolbox Interface for OpenPCDet Library

Detect objects from point clouds using voxel R-CNN object detector from OpenPCDet

Lidar Toolbox™ Interface for OpenPCDet Library enables you to detect objects from point clouds using pretrained Voxel R-CNN [1] models and training models using your own data.

Using the support package, you can:

• Configure a Voxel R-CNN object detection using voxelRCNNObjectDetector object.
• Load pretrained models trained on KITTI and PandaSet data sets using the object detector.
• Train a custom Voxel R-CNN model using the trainVoxelRCNNObjectDetector function.

Please refer to the documentation for examples to help get started with workflows such as training and transfer learning a pretrained Voxel R-CNN model on custom dataset.

To learn more about OpenPCDet library, visit the OpenPCDet GitHub® repository.

References

[1] Deng J, Shi S, Li P, Zhou W, Zhang Y, Li H. Voxel r-cnn: Towards high performance voxel-based 3d object detection. InProceedings of the AAAI conference on artificial intelligence 2021 May 18 (Vol. 35, No. 2, pp. 1201-1209).