In response to rising security concerns with drones, our research overcomes the shortcomings of current systems by developing a novel YOLOv8-based technique for UAV detection in. Thorough testing yields better results than YOLOv7, YOLOv7-UAV, and SSD in terms of metrics, indicating flexibility and accuracy in various airborne conditions. Our approach successfully detects UAVs in real-world trials using a drone equipped with a camera, highlighting its practical applicability. The research provides an effective detection methodology that makes a substantial contribution to the advancement of aviation security. Especially, our model shows remarkable accuracy with a mean average precision (mAP) of 99.5%. These results highlight the urgency of adopting sophisticated systems like YOLOv8 in order to defend against possible dangers and counter evolving UAV threats. This work achieves an accuracy of 99.5%, recall of 99.9% and an F1 Score of 90%.
UAV Detection for Aerial Vehicles using YOLOv8
2024-02-23
1190036 byte
Conference paper
Electronic Resource
English
ITD-YOLOv8: An Infrared Target Detection Model Based on YOLOv8 for Unmanned Aerial Vehicles
DOAJ | 2024
|A Lightweight Real-Time Infrared Object Detection Model Based on YOLOv8 for Unmanned Aerial Vehicles
DOAJ | 2024
|