Awesome-Lane-Detection

This repository contains content related to 2D and 3D lane detection, as well as video lane detection. Continual improvements are being made to this repository. If you come across any relevant papers that should be included, please don't hesitate to open an issue.

Table of Contents

• Awesome-Lane-Detection
  • Table of Contents
  • Activities
  • 2D Lane Detection
    • Segmentation-Based: Traditional Semantic Segmentation.
    • Segmentation-Based: Grid Semantic Segmentation.
    • Segmentation-Based: Instance Segmentation.
    • Detection-Based: Keypoints Detection.
    • Detection-Based: Parametric Curve Detection.
    • Detection-Based: Line-Proposal&Line-Anchor Detection.
  • 3D Lane Detection
    • Mono Deteciton?
    • Mutli-View Detection?
    • Mapless Driving
  • Video Lane Detection
    • Segmentation-Based
    • Detection-Based
  • Lane Detection toolkit
    • MMDetection-Based
    • PPaddleDetection-Based
    • Pure Pytorch
  • Datasets
  • Survey
  • Articles

Activities

2D Lane Detection

Segmentation-Based: Traditional Semantic Segmentation.

(Arxiv 1712) SCNN: Spatial as Deep: Spatial CNN for Traffic Scene Understanding. Xingang Pan et al. AAAI 2018. Code

(Arxiv 2008) RESA: Recurrent Feature-Shift Aggregator for Lane Detection. Tu Zheng et al. AAAI 2021. Code

Segmentation-Based: Grid Semantic Segmentation.

(Arxiv 2004) UFLD: Ultra Fast Structure-Aware Deep Lane Detection. Zequn Qin et al. ECCV 2020Code

(Arxiv 2105) CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution. Lizhe Liu et al. ICCV 2021. Code

(Arxiv 2203) Laneformer: Object-aware Row-Column Transformers for Lane Detection. Jianhua Han et al. AAAI 2022.

(Arxiv 2206) UFLDv2: Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal Classification. Zequn Qin et al. TPAMI 2022. Code

(Arxiv xxxx) CondLSTR: Generating Dynamic Kernels via Transformers for Lane Detection. Ziye Chen et al. ICCV 2023. Code

Segmentation-Based: Instance Segmentation.

(Arxiv 1817) LaneNet: Real-Time Lane Detection Networks for Autonomous Driving. Ze Wang et al. Code

(Arxiv 2103) LaneAF: Robust Multi-Lane Detection with Affinity Fields. Hala Abualsaud et al. LRA 2021. Code

(Arxiv 2105) CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution. Lizhe Liu et al. ICCV 2021. Code

Detection-Based: Keypoints Detection.

(Arxiv 2002) PINet: Key Points Estimation and Point Instance Segmentation Approach for Lane Detection. TITS 2021. Code

(Arxiv 2105) FOLOLane: Focus on Local: Detecting Lane Marker from Bottom Up via Key Point. Zhan Qu et al. CVPR 2021.

(Arxiv 2204) GANet: A Keypoint-based Global Association Network for Lane Detection. Jinsheng Wang et al. CVPR 2022. Code

Detection-Based: Parametric Curve Detection.

(Arxiv 2004) PolyLaneNet: Lane Estimation via Deep Polynomial Regression. Lucas Tabelini et al. ICPR 2021. Code

(Arxiv 2011) LSTR: End-to-End Lane Shape Prediction With Transformers. Ruijin Liu et al. WACV 2021. Code

(Arxiv 2203) BézierLaneNet: Rethinking Efficient Lane Detection via Curve Modeling. Zhengyang Feng et al. CVPR 2022. Code

(Arxiv 2301) BSNet: Lane Detection via Draw B-spline Curves Nearby. Haoxin Chen et al.

Detection-Based: Line-Proposal&Line-Anchor Detection.

(Arxiv xxxx) Line-CNN: End-to-End Traffic Line Detection With Line Proposal Unit. Xiang Li et al. T-ITS2020.

(Arxiv 2010) LaneATT: Keep Your Eyes on the Lane: Real-Time Attention-Guided Lane Detection. Lucas Tabelini et al. CVPR2021. Code

(Arxiv 2105) SGNet: Structure guided lane detection. Jinming Su et al. IJCAI 2021. Code

(Arxiv 2203) CLRNet: Cross Layer Refinement Network for Lane Detection. Tu Zheng et al. CVPR2022. Code

(Arxiv 2301) BSNet: Lane Detection via Draw B-spline Curves Nearby. Haoxin Chen et al.

(Arxiv 2305) O2Former: End-to-End Lane Detection with One-to-Several Transformer. Kunyang Zhou et al. Code

(Arxiv 2308) ADNet: Lane Shape Prediction via Anchor Decomposition. Lingyu Xiao et al. ICCV 2023. Code

3D Lane Detection

Mono Deteciton?

Mutli-View Detection?

Mapless Driving

Video Lane Detection

Segmentation-Based

Detection-Based

Lane Detection toolkit

MMDetection-Based

MMLaneDet: It is an open-source lane detection toolbox based on MMDetection.

Features: 1. Supports multi-gpu training; 2. Inherits from mmdet's trainer; 3. Self-implemented data enhancement auxiliary albumentation

PPaddleDetection-Based

PPlanedet: A Toolkit for lane detection based on PaddlePaddle.

Features: 1. Supports multi-gpu training; 2. Using trainer from the PaddlePaddle framework; 3. Self-implemented data enhancement auxiliary albumentation

Pure Pytorch

PytorchAutoDrive: It is a pure Python framework includes semantic segmentation models, lane detection models based on PyTorch. Here we provide full stack supports from research (model training, testing, fair benchmarking by simply writing configs) to application (visualization, model deployment).

Features: 1. Supports distributed training; 2. Self-implemented trainer; 3. Self-implemented data enhancement

lanedet: It is an open-source lane detection toolbox based on PyTorch that aims to pull together a wide variety of state-of-the-art lane detection models. Developers can reproduce these SOTA methods and build their own methods.

Features: 1. mmdet format; 2. Self-implemented trainer; 3. Self-implemented data enhancement

Datasets

Survey

Articles