Skip to content

Lane Detection Methods#

Overview#

This document describes some of the most common lane detection methods used in the autonomous driving industry. Lane detection is a crucial task in autonomous driving, as it is used to determine the boundaries of the road and the vehicle's position within the lane.

Methods#

This document covers the methods under two categories: lane detection methods and multitask detection methods.

Note

The results have been obtained using pre-trained models. Training the model with your own data will yield more successful results.

Lane Detection Methods#

CLRerNet#

This work introduce LaneIoU, which improves confidence score accuracy by considering local lane angles, and CLRerNet, a novel detector leveraging LaneIoU.

Method Backbone Dataset Confidence Campus Video Road Video
CLRerNet dla34 culane 0.4
CLRerNet dla34 culane 0.1
CLRerNet dla34 culane 0.01

CLRNet#

This work introduce Cross Layer Refinement Network (CLRNet) to fully utilize high-level semantic and low-level detailed features in lane detection. CLRNet detects lanes with high-level features and refines them with low-level details. Additionally, ROIGather technique and Line IoU loss significantly enhance localization accuracy, outperforming state-of-the-art methods.

Method Backbone Dataset Confidence Campus Video Road Video
CLRNet dla34 culane 0.2
CLRNet dla34 culane 0.1
CLRNet dla34 culane 0.01
CLRNet dla34 llamas 0.4
CLRNet dla34 llamas 0.2
CLRNet dla34 llamas 0.1
CLRNet resnet18 llamas 0.4
CLRNet resnet18 llamas 0.2
CLRNet resnet18 llamas 0.1
CLRNet resnet18 tusimple 0.2
CLRNet resnet18 tusimple 0.1
CLRNet resnet34 culane 0.1
CLRNet resnet34 culane 0.05
CLRNet resnet101 culane 0.2
CLRNet resnet101 culane 0.1

FENet#

This research introduces Focusing Sampling, Partial Field of View Evaluation, Enhanced FPN architecture, and Directional IoU Loss, addressing challenges in precise lane detection for autonomous driving. Experiments show that Focusing Sampling, which emphasizes distant details crucial for safety, significantly improves both benchmark and practical curved/distant lane recognition accuracy over uniform approaches.

Method Backbone Dataset Confidence Campus Video Road Video
FENet v1 dla34 culane 0.2
FENet v1 dla34 culane 0.1
FENet v1 dla34 culane 0.05
FENet v2 dla34 culane 0.2
FENet v2 dla34 culane 0.1
FENet v2 dla34 culane 0.05
FENet v2 dla34 llamas 0.4
FENet v2 dla34 llamas 0.2
FENet v2 dla34 llamas 0.1
FENet v2 dla34 llamas 0.05

Multitask Detection Methods#

YOLOPv2#

This work proposes an efficient multi-task learning network for autonomous driving, combining traffic object detection, drivable road area segmentation, and lane detection. YOLOPv2 model achieves new state-of-the-art performance in accuracy and speed on the BDD100K dataset, halving the inference time compared to previous benchmarks.

Method Campus Video Road Video
YOLOPv2

HybridNets#

This work introduces HybridNets, an end-to-end perception network for autonomous driving. It optimizes segmentation heads and box/class prediction networks using a weighted bidirectional feature network. HybridNets achieves good performance on BDD100K and Berkeley DeepDrive datasets, outperforming state-of-the-art methods.

Method Campus Video Road Video
HybridNets

TwinLiteNet#

This work introduces TwinLiteNet, a lightweight model designed for driveable area and lane line segmentation in autonomous driving.

Method Campus Video Road Video
Twinlitenet

Citation#

@article{honda2023clrernet,
title={CLRerNet: Improving Confidence of Lane Detection with LaneIoU},
author={Hiroto Honda and Yusuke Uchida},
journal={arXiv preprint arXiv:2305.08366},
year={2023},
}

@InProceedings{Zheng_2022_CVPR,
    author    = {Zheng, Tu and Huang, Yifei and Liu, Yang and Tang, Wenjian and Yang, Zheng and Cai, Deng and He, Xiaofei},
    title     = {CLRNet: Cross Layer Refinement Network for Lane Detection},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2022},
    pages     = {898-907}
}

@article{wang&zhong_2024fenet,
      title={FENet: Focusing Enhanced Network for Lane Detection},
      author={Liman Wang and Hanyang Zhong},
      year={2024},
      eprint={2312.17163},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{vu2022hybridnets,
      title={HybridNets: End-to-End Perception Network},
      author={Dat Vu and Bao Ngo and Hung Phan},
      year={2022},
      eprint={2203.09035},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@INPROCEEDINGS{10288646,
  author={Che, Quang-Huy and Nguyen, Dinh-Phuc and Pham, Minh-Quan and Lam, Duc-Khai},
  booktitle={2023 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)},
  title={TwinLiteNet: An Efficient and Lightweight Model for Driveable Area and Lane Segmentation in Self-Driving Cars},
  year={2023},
  volume={},
  number={},
  pages={1-6},
  doi={10.1109/MAPR59823.2023.10288646}
}