Radar and Acoustic Sensor Fusion using a Transformer Encoder for Robust Drone Detection and Classification

TL;DR

This paper presents a multi-modal drone detection system combining radar and acoustic sensors with a transformer encoder, achieving robust and accurate classification in outdoor environments.

Contribution

It introduces a novel fusion approach using raw acoustic signals and a transformer encoder, reducing parameters and enhancing detection performance.

Findings

Outperforms state-of-the-art methods in outdoor tests

Uses raw acoustic signals without feature extraction

Demonstrates robustness across weather conditions

Abstract

The use of drones in a wide range of applications is steadily increasing. However, this has also raised critical security concerns such as unauthorized drone intrusions into restricted zones. Therefore, robust and accurate drone detection and classification mechanisms are required despite significant challenges due to small size of drones, low-altitude flight, and environmental noise. In this letter, we propose a multi-modal approach combining radar and acoustic sensing for detecting and classifying drones. We employ radar due to its long-range capabilities, and robustness to different weather conditions. We utilize raw acoustic signals without converting them to other domains such as spectrograms or Mel-frequency cepstral coefficients. This enables us to use fewer number of parameters compared to the stateof-the-art approaches. Furthermore, we explore the effectiveness of the transformer encoder architecture in fusing these sensors. Experimental results obtained in outdoor settings verify the superior performance of the proposed approach compared to the state-of-the-art methods.