YOLOv8-Based Traffic Sign Detection for Autonomous Vehicles in Diverse Environments

Autonomous driving systems depend critically on traffic sign detection to allow vehicles to real-time comprehend and react to road signs. The efficiency of the YOLOv8 model at spotting several traffic signals under different environmental settings is investigated in this work. With an anchor-free detection head and improved multi-scale feature extraction, YOLOv8's sophisticated architecture presents gains over past iterations in both accuracy and inference time. The model was trained and tested using a large dataset including augmented samples mimicking various weather and illumination environments. Maintaining real-time processing rates at 35 FPS, the results show that YOLOv8 achieves a mean Average Precision (mAP) of 95.3%, a precision of 96.1%, and a recall of 94.7%. These results highlight the fit of YOLOv8 for real-time traffic signal detection systems, hence advancing autonomous car safety and efficiency. Future research seeks to improve model resilience against poor weather and investigate edge device deployment efficiencies against occlusion issues.