A Two-Dimensional Deep Network for RF-based Drone Detection and Identification Towards Secure Coverage Extension

TL;DR

This paper introduces a 2D deep learning approach using RF signal analysis with STFT and ResNet CNN to accurately detect and identify drones, enhancing security and coverage extension.

Contribution

It presents a novel combination of STFT feature extraction with a ResNet-based CNN for improved drone classification accuracy and convergence speed.

Findings

Higher accuracy than baseline models

Faster convergence during training

Balanced performance on raw and extended datasets

Abstract

As drones become increasingly prevalent in human life, they also raises security concerns such as unauthorized access and control, as well as collisions and interference with manned aircraft. Therefore, ensuring the ability to accurately detect and identify between different drones holds significant implications for coverage extension. Assisted by machine learning, radio frequency (RF) detection can recognize the type and flight mode of drones based on the sampled drone signals. In this paper, we first utilize Short-Time Fourier. Transform (STFT) to extract two-dimensional features from the raw signals, which contain both time-domain and frequency-domain information. Then, we employ a Convolutional Neural Network (CNN) built with ResNet structure to achieve multi-class classifications. Our experimental results show that the proposed ResNet-STFT can achieve higher accuracy and faster convergence on the extended dataset. Additionally, it exhibits balanced performance compared to other baselines on the raw dataset.