【车道线检测】车道线检测算法汇总

文章目录

• 零. 概述
• • 1. DataSet
  • 2. 车道线检测难点
  • 3. 数据增强
• 一、基于分割和辅助实例化信息的方法
• • 1. HDMapNet: An Online HD Map Construction and Evaluation Framework
  • 2. 3D-LaneNet: End-to-End 3D Multiple Lane Detection
  • 3. LaneAF: Robust Multi-Lane Detection with Affinity Fields
  • 4. Spatial As Deep: Spatial CNN for Traffic Scene Understanding
  • 5. RESA: Recurrent Feature-Shift Aggregator for Lane Detection
  • 6. LaneNet: Real-Time Lane Detection Networks for Autonomous Driving
  • 7. Learning Lightweight Lane Detection CNNs by Self Attention Distillation
  • 8. ONCE-3DLanes: Building Monocular 3D Lane Detection
  • 9. End-to-End Deep Learning of Lane Detection and Path Prediction for Real-Time Autonomous Driving
• 二、基于关键点的方法
• • 1. RCLane: Relay Chain Prediction for Lane Detection
  • 2. Focus on Local: Detecting Lane Marker from Bottom Up via Key Point
  • 3. Key Points Estimation and Point Instance Segmentation Approach for Lane Detection
  • 4. A Keypoint-based Global Association Network for Lane Detection
• 三、基于row-wise的方法
• • 1. Ultra Fast Structure-aware Deep Lane Detection
  • 2. CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution
  • 3. End-to-End Lane Marker Detection via Row-wise Classification
• 四、基于多项式回归的方法
• • 1. Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images
  • 2. Rethinking Efficient Lane Detection via Curve Modeling
  • 3. PolyLaneNet: Lane Estimation via Deep Polynomial Regression
  • 4. End-to-end Lane Shape Prediction with Transformers
• 五、基于anchor的方法
• • 1. PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark
  • 2. Line-CNN: End-to-End Traffic Line Detection With Line Proposal Unit
  • 3. (Lane-ATT)Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection
  • 4. 3D-LaneNet: End-to-End 3D Multiple Lane Detection
  • 5. Gen-LaneNet: A Generalized and Scalable Approach for 3D Lane Detection
  • 6. Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraints
  • 7. Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes
  • 8. CLRNet: Cross Layer Refinement Network for Lane Detection
• 六、直接输出实例的方法
• • 1. VectorMapNet: End-to-end Vectorized HD Map Learning
  • 2. Hierarchical Recurrent Attention Networks for Structured Online Maps
  • 3. DagMapper