Deep Learning Empowered Fast and Accurate Multiclass UAV Detection in Challenging Weather Conditions

Abstract

The emergence of Unmanned Aerial Vehicles (UAVs) raised multiple concerns, given their potentially malicious misuse in unlawful acts. Vision-based counter-UAV applications offer a reliable solution compared to acoustic and radio frequency-based solutions because of their high detection accuracy in diverse weather conditions. The existing solutions work well on trained datasets, but their accuracy is relatively low for real-time detection. In this paper, we model deep learning-empowered solutions to improve the multiclass UAV's classification performance using single-shot object detection algorithms (YOLOv5 and YOLOv7). They efficiently and correctly differentiate between multirotor, fixed-wing, and single-rotor UAVs in challenging weather conditions. Experiments show that the suggested technique is reliable with an overall best average-classification precision of 86.7\%, 88.5\% average recall, 91.8\% average mAP, and 58.4\% average-IoU.

Enhancing Mobile Acute Lymphoblastic Cancer Detection: Transfer Learning from YOLOv9 to TensorFlow for Real-Time Applications

“…Its advantages include speed, simplicity in setup, opensource availability, and compatibility with various frameworks [8]. Throughout its evolution, iterations like YOLOv2 [9], YOLOv3 [10], YOLOv4 [11], YOLOv5 [12], YOLOv6 [13], and YOLOv7 [14] have been introduced, reflecting enhancements in both speed and accuracy.…”