A two-stage highway lane line detection method and related device

By constructing a lane line topology refinement module using a two-stage detection method and graph neural network, the problem of missed detection in lane line detection in highway monitoring scenarios is solved, achieving high-precision and high-completeness lane line detection and improving the vehicle-level fine behavior analysis capability of intelligent transportation systems.

CN122368952APending Publication Date: 2026-07-10SOUTH CHINA UNIV OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SOUTH CHINA UNIV OF TECH
Filing Date
2026-03-26
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing lane detection technologies struggle to reliably and accurately extract complete lane line structures in highway monitoring scenarios, especially in complex topologies and occluded environments where they suffer from missed detections, impacting the vehicle-level fine-grained behavior analysis of intelligent transportation systems.

Method used

A two-stage detection method is adopted. First, a lane line detection network is used for preliminary detection. Then, a lane line topology relationship refinement module is constructed through graph neural network to enhance the confidence and positioning accuracy of lane lines. Finally, a sparse graph is constructed through multimodal similarity to recover missed detections caused by occlusion or scale changes.

Benefits of technology

It significantly improves the recall and topological integrity of lane line detection, enhances the accuracy and robustness of detection, and is suitable for intelligent transportation systems and autonomous driving perception.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122368952A_ABST
    Figure CN122368952A_ABST
Patent Text Reader

Abstract

This application provides a two-stage highway lane detection method and related equipment, belonging to the fields of computer vision and intelligent transportation technology. The method includes: a first stage, using a lane detection network to perform preliminary detection on the input image to obtain an initial set of lane lines; and a second stage, constructing a lane line topology refinement module. Using the initial lane lines as graph nodes, edge connections are constructed based on geometric attributes and visual features to form a lane line topology graph. Iterative message passing and feature aggregation are performed through a graph neural network to refine the initial detection results, enhancing the confidence and positioning accuracy of detected lane lines, and recovering missed lane lines based on topological relationship inference. This application can effectively improve the accuracy, completeness, and real-time performance of lane line detection in highway monitoring scenarios, and is suitable for lane-level fine-grained perception tasks in intelligent transportation systems.
Need to check novelty before this filing date? Find Prior Art