ONCE-3DLanes

Project Page | Paper | Data

ONCE-3DLanes: Building Monocular 3D Lane Detection

Fan Yan1      Ming Nie1      Xinyue Cai2 Jianhua Han2    Hang Xu2

Zhen Yang2Chaoqiang Ye2Yanwei Fu1Michael Bi Mi2Li Zhang 1

1School of Data Science, Fudan University    2Huawei Noah's Ark Lab

Introduction

We present ONCE-3DLanes, a real-world autonomous driving dataset with lane layout annotation in 3D space. Conventional 2D lane detection from a monocular image yields poor performance of following planning and control tasks in autonomous driving due to the case of uneven road. Predicting the 3D lane layout is thus necessary and enables effective and safe driving. However, existing 3D lane detection datasets are either unpublished or synthesized from a simulated environment, severely hampering the development of this field. In this paper, we take steps towards addressing these issues. By exploiting the explicit relationship between point clouds and image pixels, a dataset annotation pipeline is designed to automatically generate high-quality 3D lane locations from 2D lane annotations in 211K road scenes. In addition, we present an extrinsic-free, anchor-free method, called SALAD, regressing the 3D coordinates of lanes in image view without converting the feature map into the bird's-eye view (BEV). To facilitate future research on 3D lane detection, we benchmark the dataset and provide a novel evaluation metric, performing extensive experiments of both existing approaches and our proposed method.

The aim of our work is to revive the interest of 3D lane detection in a real-world scenario. We believe our work can lead to the expected and unexpected innovations in both academia and industry.

More Details

You can refer to here to get more details of our dataset.

Install

  • python 3.6, pytorch 1.4, CUDA 10.2
git clone https://github.com/once-3dlanes/once_3dlanes_benchmark.git
conda create -n once3dlanes python=3.6.9
conda activate once3dlanes
pip install -r requirements.txt

Data Preparation

  • You can refer to here to download the official ONCE-3DLanes dataset.

  • The frame.json file of predicted 3D lanes should be organized like this:

{
  "lanes":[
    # One lane 
    {
      "points": [ 
        # The [x, y, z] coordinates of key points in the lane are listed as follows.
        [-2.475, 1.871, 31.082],
        [-2.547, 1.854, 28.394],        
        ...
      ],
      "score": 1,  #The value doesn't affect evaluation.
    },
    # Other lanes
    ...
  ]
}
  • The final data structure should be:
once_3dlanes_benchmark
├── ONCE_3DLanes
│   ├── train
│   │   │── sequence
│   │   │   │──cam01 
|   |   |   |	|──frame.json
|   |   |   |	|──...
│   ...
├── pred_dir
│   ├── sequence
│   │   │   │──cam01 
|   |   |   |	|──frame.json
|   |   |   |	|──...
│   ├── ...
├── ...
├── eval.py
├── eval.sh

Evaluation

You should refer to the eval.sh and change your rootgt_dir and pred_dir path.

Take the final data structure for example, the root = './once_3dlanes_benchmark', 'gt_dir = ONCE_3DLanes/train'and the pred_dir = 'pred_dir'.

bash eval.sh

Results

Citation

Please cite this paper in your publications if it helps your research:

@InProceedings{yan2022once,
  title={ONCE-3DLanes: Building Monocular 3D Lane Detection},
  author= {Yan, Fan and Nie, Ming and Cai, Xinyue and Han, Jianhua and Xu, Hang and Yang, Zhen and Ye, Chaoqiang and Fu, Yanwei and Bi Mi, Michael and Zhang, Li},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2022},
}