Abstract
Abstract The field of aircraft type recognition has a broad range of applications. This technology serves as a valuable tool for airlines and airports in the scheduling and maintenance of aircraft. Furthermore, it provides crucial support to aviation regulatory authorities in their efforts to ensure safety in aviation. However, the task of recognizing aircraft types in real-world scenarios presents a significant challenge due to the subtle differences between various aircraft. Moreover, practical applications need real-time detection of aircraft type. To address these issues, this paper introduces the YOLOv8 object detector and investigates the performance of five different versions of YOLOv8 in the context of aircraft type recognition, to identify the most suitable model for this task. Experimental results on the Military Aircraft Detection Dataset demonstrate that the YOLOv8l model outperforms the others, achieving the highest performance with a COCO AP score of 84.2.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
