Skip to content

[TIP 2024] Pytorch implementation of the paper 'CoBEV: Elevating Roadside 3D Object Detection with Depth and Height Complementarity'

License

Notifications You must be signed in to change notification settings

MasterHow/CoBEV

Repository files navigation

CoBEV: Elevating roadside 3d object detection with depth and height complementarity

Hao Shi · Chengshan Pang · Jiaming Zhang · Kailun Yang · Yuhao Wu · Huajian Ni · Yining Lin · Rainer Stiefelhagen · Kaiwei Wang

IEEE T-IP 2024

Logo




PyTorch Lightning
Paper PDF

CoBEV (Complementary-BEV) is a new end-to-end monocular 3D object detector that integrates geometry-centric depth and semantic-centric height cues to construct robust BEV representations for roadside perception. CoBEV outperforms BEVHeight with a margin of 3.80% / 7.92% /6.09% across Vehicle, Pedestrian and Cyclist on DAIR-V2X-I. In scenarios where camera parameters are directly perturbed by noise affecting focal length, roll, and pitch, CoBEV exhibits an enhanced detection capability, surpassing BEVHeight by an average of 3.93%. Our goal is to enhance the perception range of intelligent vehicles and improve the responsiveness of the overall transportation system by constructing robust features within a unified BEV space.

Memo

  • Release the pretrained models

Table of Contents
  1. Getting Started
  2. Model Zoo
  3. Acknowledgment
  4. Citation

Getting Started

Train CoBEV with 8 GPUs

python [EXP_PATH] --amp_backend native -b 8 --gpus 8

Eval CoBEV with 8 GPUs

python [EXP_PATH] --ckpt_path [CKPT_PATH] -e -b 8 --gpus 8

Model Zoo

The pretrained models can be found via the following links:

Acknowledgment

This project is developed based on the code of the following projects.

Citation

If our work is helpful to you, please consider citing us by using the following BibTeX entry:

@article{shi2024cobev,
  title={Cobev: Elevating roadside 3d object detection with depth and height complementarity},
  author={Shi, Hao and Pang, Chengshan and Zhang, Jiaming and Yang, Kailun and Wu, Yuhao and Ni, Huajian and Lin, Yining and Stiefelhagen, Rainer and Wang, Kaiwei},
  journal={IEEE Transactions on Image Processing},
  year={2024},
  publisher={IEEE}
}

About

[TIP 2024] Pytorch implementation of the paper 'CoBEV: Elevating Roadside 3D Object Detection with Depth and Height Complementarity'

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published