Acoustic Drone Package Delivery Detection

2026-02-10

AI Summary

This study addresses the security threat posed by unauthorized drones delivering contraband into restricted zones such as prisons, a challenge inadequately tackled by existing approaches that struggle to reliably detect the delivery event itself. The authors propose a novel acoustic-based detection method that relies solely on ground-deployed microphone arrays, achieving the first vision- and RF-free identification of drone delivery actions. By analyzing Mel-spectrograms with a deep neural network, the system simultaneously detects drone presence and estimates blade-pass frequency (BPF), leveraging abrupt temporal shifts in BPF to pinpoint the exact moment of payload release. Experimental results demonstrate an average absolute BPF estimation error of 16 Hz within 150 meters, a drone detection accuracy of 97%, and a delivery event recognition rate of 96% with an 8% false alarm rate, achieving effective detection up to 100 meters.

Technology Category

• Computer Vision: Object Detection & Categorization
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Security and Privacy: Large-scale security measurements
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

In recent years, the illicit use of unmanned aerial vehicles (UAVs) for deliveries in restricted area such as prisons became a significant security challenge. While numerous studies have focused on UAV detection or localization, little attention has been given to delivery events identification. This study presents the first acoustic package delivery detection algorithm using a ground-based microphone array. The proposed method estimates both the drone's propeller speed and the delivery event using solely acoustic features. A deep neural network detects the presence of a drone and estimates the propeller's rotation speed or blade passing frequency (BPF) from a mel spectrogram. The algorithm analyzes the BPFs to identify probable delivery moments based on sudden changes before and after a specific time. Results demonstrate a mean absolute error of the blade passing frequency estimator of 16 Hz when the drone is less than 150 meters away from the microphone array. The drone presence detection estimator has a accuracy of 97%. The delivery detection algorithm correctly identifies 96% of events with a false positive rate of 8%. This study shows that deliveries can be identified using acoustic signals up to a range of 100 meters.

Problem

• acoustic detection
• drone delivery
• UAV
• package delivery
• security challenge

Innovation

• acoustic detection
• drone delivery
• blade passing frequency
• deep neural network
• microphone array