Autonomous driving paper index
Detection and Instance Segmentation of Road Markings and Lane Lines Using YOLOv11-SEG for ADAS and Autonomous Driving
One-line summary
This paper presents YOLOv11-SEG, an enhanced deep learning model tailored for real-time detection and instance segmentation of road markings and lane lines, crucial for Advanced Driver Assistance Systems (ADAS) and autonomous vehicles.
Engineering notes
Key topics: autonomous driving, autonomous vehicle, instance segmentation, adas, deployment. See the paper for implementation details and experimental results.
Chinese explanation / 中文解读
中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。
Original abstract
This paper presents YOLOv11-SEG, an enhanced deep learning model tailored for real-time detection and instance segmentation of road markings and lane lines, crucial for Advanced Driver Assistance Systems (ADAS) and autonomous vehicles. The architecture introduces a novel C3k2 module for refined feature extraction and a C2PSA attention mechanism to enhance spatial focus, enabling accurate detection of small or occluded markings. The model was trained on a custom dataset covering ten traffic-relevant classes, including lane boundaries and directional arrows. Evaluation results show strong performance with a precision of 94.3%, recall of 88%, and mAP@0.5 of 93% for detection. Qualitative results and F1-confidence analysis further confirm the model’s robustness across varied conditions. YOLOv11-SEG offers a balanced trade-off between accuracy and efficiency, making it highly suitable for embedded deployment in real-time ADAS applications.
Links and sources
Need this topic turned into a technical roadmap?
Full Self Driving can prepare a custom autonomous driving literature review, code map, dataset map, and B2B technology assessment.
Request B2B research
Comments