Please refer to the OpenCOOD repository for setup and installation.
Install bbx NMS calculation CUDA version:
python3 opencood/utils/setup.py build_ext --inplace
Setup:
python3 setup.py develop --user
Install spconv:
e.g.
pip3 install spconv-cu113
python3 opencood/tools/train.py --hypes_yaml opencood/hypes_yaml/point_pillar_spatialcooper.yaml
Before you run the following command, first make sure the validation_dir
in config.yaml under your checkpoint folder.
- Testing dataset path:
opv2v_data_dumping/test
. - Culver City dataset path:
opv2v_data_dumping/test_culver_city
.
python3 opencood/tools/inference.py --model_dir opencood/logs/point_pillar_spatialcooper/ --fusion_method intermediate
Single Vehicle Perception v.s. Cooperative Perception
Cooperative perception for vehicle and pedestrian detection
- Xu, R., Xiang, H., Xia, X., Han, X., Li, J. and Ma, J., 2022, May. Opv2v: An open benchmark dataset and fusion pipeline for perception with vehicle-to-vehicle communication. In 2022 International Conference on Robotics and Automation (ICRA) (pp. 2583-2589). IEEE.