Traffic sign detection is a vital component of Advanced Driver Assistance Systems (ADAS) and autonomous vehicles, where real-time and accurate recognition ensures road safety and efficient traffic management. This paper introduces an innovative approach using the YOLOv10, a state-of-the-art deep learning model renowned for its real-time object detection capabilities. The proposed method addresses the challenges of detecting traffic signs in diverse and complex environments, offering significant improvements in both accuracy and efficiency over traditional methods. YOLOv10 incorporates several innovations, including a dual consistent assignment system that eliminates the need for Non-Maximum Suppression (NMS), enhancing processing speed and reducing computational complexity. Additionally, the integration of a Compact Inverted Block (CIB) structure optimizes the model for deployment in resource-constrained environments, such as embedded systems in vehicles. Trained on a dataset of 23,428 traffic signs, YOLOv10 achieved a mean Average Precision (mAP@50) of 99.4%, demonstrating its ability to accurately detect and classify various traffic sign types even under challenging conditions. By leveraging advanced deep learning techniques, YOLOv10 provides a robust solution for real-time traffic sign detection, paving the way for safer and more efficient autonomous vehicles. The results highlight the model’s potential to significantly enhance the reliability and safety of autonomous driving systems.