/simtrack

Exploring Simple 3D Multi-Object Tracking for Autonomous Driving (ICCV 2021)

Primary LanguagePythonOtherNOASSERTION

Exploring Simple 3D Multi-Object Tracking for Autonomous Driving

Chenxu Luo, Xiaodong Yang, Alan Yuille
Exploring Simple 3D Multi-Object Tracking for Autonomous Driving, ICCV 2021
[Paper] [Poster] [YouTube]

Getting Started

Installation

Please refer to INSTALL for the detail.

Data Preparation

python ./tools/create_data.py nuscenes_data_prep --root_path=NUSCENES_TRAINVAL_DATASET_ROOT --version="v1.0-trainval" --nsweeps=10

Training

python -m torch.distributed.launch --nproc_per_node=8 ./tools/train.py examples/point_pillars/configs/nusc_all_pp_centernet_tracking.py --work_dir SAVE_DIR

Test

In ./model_zoo we provide our trained (pillar based) model on nuScenes.
Note: We currently only support inference with a single GPU.

python ./tools/val_nusc_tracking.py examples/point_pillars/configs/nusc_all_pp_centernet_tracking.py --checkpoint CHECKPOINTFILE  --work_dir SAVE_DIR

Citation

Please cite the following paper if this repo helps your research:

@InProceedings{Luo_2021_ICCV,
    author    = {Luo, Chenxu and Yang, Xiaodong and Yuille, Alan},
    title     = {Exploring Simple 3D Multi-Object Tracking for Autonomous Driving},
    booktitle = {International Conference on Computer Vision (ICCV)},
    year      = {2021}
}

License

Copyright (C) 2021 QCraft. All rights reserved. Licensed under the CC BY-NC-SA 4.0 (Attribution-NonCommercial-ShareAlike 4.0 International). The code is released for academic research use only. For commercial use, please contact business@qcraft.ai.