Real-time lane detection for autonomous vehicles using YOLOV5 Segmentation Model

The increasing prominence of autonomous vehicles underscores the critical need for precise and prompt lane detection to ensure safe and reliable transportation. This paper aims to enhance autonomous vehicle performance by developing an advanced real-time lane detection system using the YOLOV5 Segmentation Large Model. The methodology utilises LabelMe for dataset annotation and employs rigorous pre-processing techniques such as resizing, augmentation, noise addition, greyscale conversion, enhanced exploration size, and image rotation. YOLOv5 architecture is extensively employed for in-lane instance segmentation. The proposed model achieves high performance with a pixel accuracy of 89%, a processing speed of 48 frames per second, and mAP@0.5 scores of 0.885 for the bounding box and 0.731 for the mask. These results demonstrate the model's effectiveness in various conditions. This paper introduces an innovative approach to autonomous vehicle lane detection, leveraging the YOLOV5 Segmentation Large Model for unparalleled precision and recall rates. This paper makes a significant contribution to the advancement of autonomous vehicle technology, emphasising the critical role of reliable and timely lane detection in strengthening the dependability and safety of transportation systems.