3D Cascade RCNN
This is the implementation of 3D Cascade RCNN: High Quality Object Detection in Point Clouds.
We designed a 3D object detection model on point clouds by:
- Presenting a simple yet effective 3D cascade architecture
- Analyzing the sparsity of the point clouds and using point completeness score to re-weighting training samples. Following is detection results on Waymo Open Dataset.
Results on KITTI
| Easy Car | Moderate Car | Hard Car | |
|---|---|---|---|
| AP 11 | 90.05 | 86.02 | 79.27 |
| AP 40 | 93.20 | 86.19 | 83.48 |
Results on Waymo
| Overall Vehicle | 0-30m Vehicle | 30-50m Vehicle | 50m-Inf Vehicle | |
|---|---|---|---|---|
| LEVEL_1 mAP | 76.27 | 92.66 | 74.99 | 54.49 |
| LEVEL_2 mAP | 67.12 | 91.95 | 68.96 | 41.82 |
Installation
- Requirements. The code is tested on the following environment:
- Ubuntu 16.04 with 4 V100 GPUs
- Python 3.7
- Pytorch 1.7
- CUDA 10.1
- spconv 1.2.1
- Build extensions
python setup.py develop
Getting Started
Prepare for the data.
Please download the official KITTI dataset and generate data infos by following command:
python -m pcdet.datasets.kitti.kitti_dataset create_kitti_infos tools/cfgs/kitti_dataset.yaml
The folder should be like:
data
├── kitti
│ │── ImageSets
│ │── training
│ │ ├──calib & velodyne & label_2 & image_2
│ │── testing
│ │ ├──calib & velodyne & image_2
| |── kitti_dbinfos_train.pkl
| |── kitti_infos_train.pkl
| |── kitti_infos_val.pkl
Training and evaluation.
The configuration file is in tools/cfgs/3d_cascade_rcnn.yaml, and the training scripts is in tools/scripts.
cd tools
sh scripts/3d-cascade-rcnn.sh
Test a pre-trained model
The pre-trained KITTI model is at: model. Run with:
cd tools
sh scripts/3d-cascade-rcnn_test.sh
The evaluation results should be like:
2021-08-10 14:06:14,608 INFO Car [email protected], 0.70, 0.70:
bbox AP:97.9644, 90.1199, 89.7076
bev AP:90.6405, 89.0829, 88.4391
3d AP:90.0468, 86.0168, 79.2661
aos AP:97.91, 90.00, 89.48
Car [email protected], 0.70, 0.70:
bbox AP:99.1663, 95.8055, 93.3149
bev AP:96.3107, 92.4128, 89.9473
3d AP:93.1961, 86.1857, 83.4783
aos AP:99.13, 95.65, 93.03
Car [email protected], 0.50, 0.50:
bbox AP:97.9644, 90.1199, 89.7076
bev AP:98.0539, 97.1877, 89.7716
3d AP:97.9921, 90.1001, 89.7393
aos AP:97.91, 90.00, 89.48
Car [email protected], 0.50, 0.50:
bbox AP:99.1663, 95.8055, 93.3149
bev AP:99.1943, 97.8180, 95.5420
3d AP:99.1717, 95.8046, 95.4500
aos AP:99.13, 95.65, 93.03
Acknowledge
The code is built on OpenPCDet and Voxel R-CNN.
1 Dec 18, 2021
183 Dec 19, 2022
10 Dec 10, 2022
53 Jan 01, 2023
3 Aug 24, 2021
16 Dec 14, 2022
4 Feb 11, 2022
1 Dec 17, 2021
37 Jan 04, 2023
360 Jan 06, 2023
1.5k Dec 29, 2022
390 Dec 29, 2022
22 Apr 15, 2022
2.3k Jan 04, 2023
202 Dec 27, 2022
40 Dec 22, 2022
0 Oct 21, 2022
6 Sep 22, 2022
8 Sep 07, 2021