article · Applied Artificial Intelligence
The growing use of drones creates airspace safety risks when they are deployed maliciously, driving the need for intelligent anti-drone systems that can accurately recognise airborne threats. Distinguishing drones from other flying objects, particularly birds, remains a significant operational challenge. To address this, an Identification Friend or Foe model classifies aerial targets by categorising birds as friends and drones as foes. The approach integrates artificial intelligence and computer vision techniques, incorporating transfer learning and data augmentation. It also evaluates how depth affects classification performance across eight different deep learning models. Among the tested architectures, EfficientNetB6 demonstrated the highest effectiveness, achieving 98.12 percent accuracy, 98.184 percent precision, a 98.115 percent F1 score, and an area under the curve of 99.85 percent, confirming the practical feasibility of automated aerial target classification.
Security systems often struggle to tell the difference between harmless birds and malicious unmanned aerial vehicles. By using deep learning to accurately separate birds from drones, anti-drone platforms can reduce false alarms and improve threat detection, helping to safeguard critical airspace, public venues, and sensitive infrastructure from unauthorized drone activity without misidentifying natural wildlife.
This work enables enhanced optical target recognition for automated anti-drone surveillance systems. Potential end users include airspace authorities, defence operators, and commercial security firms guarding private or public infrastructure. Based on the abstract, the technology is at the applied and tested experimental stage, having demonstrated computational viability across multiple neural network architectures but not yet showing operational deployment in field-tested tracking hardware.
AI-generated from the published abstract. Always read the original work before citing.
Recently, the growing use of drones has paved the way for limitless applications in all the domains. However, their malicious exploitations have affected the airspace safety, making them double-edged weapons. Therefore, intelligent anti-drone systems capable of recognizing and neutralizing airborne targets become highly required. In the existing literature, most of the attention has been centered on recognizing drones as unique airborne target, whereas the real challenge is to distinguish between drones and non-drone targets. To address this issue, this study develops an Identification Friend or Foe (IFF) model able to classify the aerial targets in foe or friend categories by determining whether the aerial target is a drone or bird, respectively. To achieve this objective, artificial intelligence and computer vision approaches have been combined through transfer learning, data augmentation and other techniques in our model. Another contribution of this work is the study of the impact of depth on the classification performance, which is demonstrated through our experiments. A comparison is performed based on eight models, where EfficientNetB6 shows the best results with 98.12% accuracy, 98.184% precision, 98.115% F1 score and 99.85% Area Under Curve (AUC). The computational results demonstrate the practicality of the developed model.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1080/08839514.2024.2318672
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
