Traffic signs are essential for the safety of autonomous vehicles, aiding in speed regulation, stops, and lane management to prevent accidents and improve navigation. Traffic sign detection is crucial for road safety, particularly in autonomous driving systems, where accurate and timely recognition is key. The challenge lies in detecting signs under diverse conditions, including varying lighting, weather, and occlusions. The proposed model uses a deep learning model, YOLOv8, for real-time traffic sign detection. By leveraging the processing capabilities of the NVIDIA Jetson Nano, the model delivers fast and precise object detection with low latency. The proposed approach offers an efficient solution for real-time traffic sign recognition, enhancing the safety and effectiveness of modern transportation systems. The performance metrics of proposed system i.e., precision, recall, mAP are 99.8%, 95%, 90.5%.
Traffic Sign Detection on Jetson Nano Using YOLOV8 Deep Learning Model
Lect. Notes in Networks, Syst.
International Conference on Information Systems and Management Science ; 2025 ; Malta, Malta February 22, 2025 - February 23, 2025
AI Technologies for Information Systems and Management Science ; Kapitel : 28 ; 297-311
07.08.2025
15 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Traffic Sign Detection Using YOLOv8
IEEE | 2024
|Traffic sign detection and identification method based on YOLOv8
Europäisches Patentamt | 2023
|