Tractable Minacious Drones Aerial Recognition and Safe-Channel Neutralization Scheme for Mission Critical Operations

Abstract

As unmanned aerial vehicles (UAVs) are progressively deployed for logistics purposes, there is need for paradigm shift from mere drone detection to proactive identification of the conveyed objects and proper risk assessment from a far distance. This paper proposed a timely, efficient, accurate, and situation-aware (TEAS) mission critical operation approach for detecting, localizing, and neutralizing UAVs under 3 scenarios (sunny, cloudy, and evening) and different altitudes using vision-based deep learning model. Two manually generated datasets consisting of 7200 samples from 6 UAV models and 3600 samples from 9 conveyed objects were used for simulation purposes. The proposed model was compared with 7 state-of-the-art models based on selected performance metrics. The results shows that the proposed model achieved superior mean average precision of 99.5%, 100% sensitivity, 11.2% specificity, 21.5% G-mean, and 99.8% F1-score with a latency of 0.021s, and throughput of 16.4 Gbps, which is better than other models. The model also exhibited high efficiency with cost noise at 0.037, and high reliability with minimal detection error which makes it suitable for mission critical operation of proactive and situation-aware countering of drones.