LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving

📬 Primary contact: Tianyu Li ( litianyu@opendrivelab.com )

arXiv | Blog TODO | Slides TODO

Highlights

🔥 We advocate Lane Segment as a map learning paradigm that seamlessly incorporates both map 🛣️ geometry and 🕸️ topology information.

🏁 Lane Segment and OpenLane-V2 Map Element Bucket will serve as a main track in the CVPR 2024 Autonomous Driving Challenge. For further details, please stay tuned!

News

[2023/12] LaneSegNet paper is available on arXiv. Code is also released!

Overall pipeline of LaneSegNet

Model Zoo
Prerequisites
Installation
Prepare Dataset
Train and Evaluate
License and Citation

Model Zoo

Model	Epoch	mAP	TOP_lsls	Memory	Config	Download
LaneSegNet	24	33.5	25.4	9.4G	config	model/log

Prerequisites

Linux
Python 3.8.x
NVIDIA GPU + CUDA 11.1
PyTorch 1.9.1

Installation

We recommend using conda to run the code.

conda create -n lanesegnet python=3.8 -y
conda activate lanesegnet

# (optional) If you have CUDA installed on your computer, skip this step.
conda install cudatoolkit=11.1.1 -c conda-forge

pip install torch==1.9.1+cu111 torchvision==0.10.1+cu111 -f https://download.pytorch.org/whl/torch_stable.html

Install mm-series packages.

pip install mmcv-full==1.5.2 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.9.0/index.html
pip install mmdet==2.26.0
pip install mmsegmentation==0.29.1
pip install mmdet3d==1.0.0rc6

Install other required packages.

pip install -r requirements.txt

Prepare Dataset

Following OpenLane-V2 repo to download the Image and the Map Element Bucket data. Run following script to collect data for this repo.

cd LaneSegNet
mkdir data

ln -s {Path to OpenLane-V2 repo}/data/OpenLane-V2 ./data/
python ./tools/data_process.py

After setup, the hierarchy of folder data is described below:

data/OpenLane-V2
├── train
|   └── ...
├── val
|   └── ...
├── test
|   └── ...
├── data_dict_subset_A_train_lanesegment.pkl
├── data_dict_subset_A_val_lanesegment.pkl
├── ...

Train and Evaluate

Train

We recommend using 8 GPUs for training. If a different number of GPUs is utilized, you can enhance performance by configuring the --autoscale-lr option. The training logs will be saved to work_dirs/lanesegnet.

cd LaneSegNet
mkdir -p work_dirs/lanesegnet

./tools/dist_train.sh 8 [--autoscale-lr]

Evaluate

You can set --show to visualize the results.

./tools/dist_test.sh 8 [--show]

License and Citation

All assets and code are under the Apache 2.0 license unless specified otherwise.

If this work is helpful for your research, please consider citing the following BibTeX entry.

@article{li2023lanesegnet,
  title={LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving},
  author={Li, Tianyu and Jia, Peijin and Wang, Bangjun and Chen, Li and Jiang, Kun and Yan, Junchi and Li, Hongyang},
  journal={arXiv preprint arXiv:2312.16108},
  year={2023}
}

@inproceedings{wang2023openlanev2,
  title={OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping}, 
  author={Wang, Huijie and Li, Tianyu and Li, Yang and Chen, Li and Sima, Chonghao and Liu, Zhenbo and Wang, Bangjun and Jia, Peijin and Wang, Yuting and Jiang, Shengyin and Wen, Feng and Xu, Hang and Luo, Ping and Yan, Junchi and Zhang, Wei and Li, Hongyang},
  booktitle={NeurIPS},
  year={2023}
}

Related resources

We acknowledge all the open-source contributors for the following projects to make this work possible:

Shaohu-Li / LaneSegNet