This paper presents the development of a real-time traffic sign and pedestrian detection system based on the YOLO (You Only Look Once) object detection architecture. In the context of intelligent transportation systems and autonomous driving technologies, fast and accurate object detection is essential for ensuring road safety and supporting advanced driver assistance systems (ADAS). The study investigates the performance of modern YOLO-based models, particularly YOLOv5 and YOLOv8, in detecting traffic signs and pedestrians under real-time conditions. The methodology includes dataset preparation, annotation, model training, optimization, and evaluation using metrics such as mAP, precision, recall, and FPS (frames per second). Experimental results demonstrate that YOLO-based models achieve high detection accuracy while maintaining real-time processing speed, making them suitable for practical deployment in smart transportation systems. Keywords: YOLO, real-time detection, traffic sign recognition, pedestrian detection, computer vision, deep learning, intelligent transportation systems