Aircraft Detection and Registration Number Recognition System with YOLO and OCR

Recently, large airports are promoting a smart airport business that introduces robots and IoT using artificial intelligence and big data, which are major technologies in the fourth industrial era. Various artificial intelligence technologies are applied not only to customer convenience but also to airport security and control, and in particular, video monitoring and analysis technologies such as missing children are introduced through intelligent CCTV. In this paper, we propose a system for recognizing aircraft detection and registration number (tail number) taking off and landing on the runway using YOLO, a deep learning object detection model, and character recognition technology (OCR). It acquires aircraft data through cameras installed on the ground and learns it with the fastest YOLO model among deep learning object detection models to automatically detect aircraft in the airport and its registration number area. And the registration number recognized the result detected by YOLO using the OCR algorithm through the image preprocessing process. This study conducted data acquisition and real-time detection tests at Taean Airfield (RKTA) at Hanseo University in Korea, and real-time aircraft detection was more than 90% and registration number recognition was more than 80%. Through this system, information on the direction, location, model, and registration number of the aircraft can be acquired, confirming its utility as an automatic ground monitoring system for small airports in the future.