This study presents an innovative approach to traffic sign and lane detection for autonomous vehicles utilizing the Semi-Supervised Learning Algorithm (SSLA). As the demand for safe and reliable autonomous driving systems continues to grow, the ability to accurately interpret traffic signs and lane markings becomes paramount. The proposed SSLA framework combines both labeled and unlabeled data to enhance the learning process, significantly reducing the reliance on extensive labeled datasets while improving detection accuracy. By employing advanced computer vision techniques and deep learning architectures, our system effectively identifies and classifies various traffic signs and lane markings in diverse environmental conditions. Experimental results demonstrate that the SSLA-based model outperforms traditional supervised learning methods, achieving higher precision and recall rates. This research highlights the potential of semi-supervised learning in advancing autonomous driving technologies, paving the way for safer navigation and improved decision-making capabilities in complex driving scenarios. Ultimately, the findings contribute to the development of more robust and adaptive autonomous systems, enhancing road safety and efficiency in transportation.

Lane Detection, Traffic Signal detection, Self-Driving Cars