Classification and detection of multiple UAVs using rational Gaussian wavelet neural networks

2026-05-25

AI Summary

This work addresses the challenge of low-cost, high-accuracy acoustic detection and classification of single and swarming unmanned aerial vehicles (UAVs) for civilian and military infrastructure protection. The authors propose an end-to-end method that integrates physical interpretability by embedding rational Gaussian wavelet transforms into a lightweight neural network, enabling adaptive feature extraction and joint detection–classification. This approach preserves model interpretability while enhancing performance and, to the best of the authors’ knowledge, represents the first acoustic sensing framework capable of perceiving UAV swarms. Evaluated in complex indoor and outdoor noisy environments, the method significantly outperforms conventional machine learning techniques. To promote reproducibility, the implementation code is publicly released.

Abstract

The detection of unmanned aerial vehicles (UAVs) is important for the protection of civilian and military infrastructure. In this paper we propose a cost effective UAV detection system using sound signals obtained from microphones. The recorded signals are passed through a signal processing pipeline which employs interpretable adaptive feature extractors using so-called rational Gaussian wavelets. These adaptive wavelet transformations are embedded into and trained together with an underlying small neural network which detects and classifies UAVs based on the obtained features. This leads to a physically interpretable machine learning algorithm that in addition to classifying UAVs is also capable of detecting UAV swarms. We demonstrate our results using data collected in indoor studio and noisy outdoor environments. We conclude that the proposed method outperforms traditional machine learning approaches for detecting and classifying single UAVs as well as drone swarms, while retaining a high degree of interpretability. Our implementation of the proposed methods is made publicly available for reproducibility.

Problem

• UAV detection
• drone swarm
• acoustic signal
• classification
• multiple UAVs

Innovation

• rational Gaussian wavelets
• interpretable machine learning
• UAV detection
• acoustic signal processing
• neural network