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.
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
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.
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.
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.
Smart Images

Figure CN122368952A_ABST