Real-Time Drone Detection in Event Cameras via Per-Pixel Frequency Analysis

TL;DR

This paper introduces a real-time drone detection method using event cameras and per-pixel frequency analysis with NDFT, outperforming YOLO in accuracy and latency by identifying rotor frequency signatures.

Contribution

The paper presents a novel analytical framework, DDHF, for UAV detection that leverages non-uniform Fourier analysis of event camera data, enabling fast, accurate localization without deep learning.

Findings

DDHF achieves 90.89% F1 score and 2.39ms latency.

Compared to YOLO, DDHF is faster and more accurate.

Method is easily tunable and interpretable.

Abstract

Detecting fast-moving objects, such as unmanned aerial vehicle (UAV), from event camera data is challenging due to the sparse, asynchronous nature of the input. Traditional Discrete Fourier Transforms (DFT) are effective at identifying periodic signals, such as spinning rotors, but they assume uniformly sampled data, which event cameras do not provide. We propose a novel per-pixel temporal analysis framework using the Non-uniform Discrete Fourier Transform (NDFT), which we call Drone Detection via Harmonic Fingerprinting (DDHF). Our method uses purely analytical techniques that identify the frequency signature of drone rotors, as characterized by frequency combs in their power spectra, enabling a tunable and generalizable algorithm that achieves accurate real-time localization of UAV. We compare against a YOLO detector under equivalent conditions, demonstrating improvement in accuracy and latency across a difficult array of drone speeds, distances, and scenarios. DDHF achieves an average localization F1 score of 90.89% and average latency of 2.39ms per frame, while YOLO achieves an F1 score of 66.74% and requires 12.40ms per frame. Through utilization of purely analytic techniques, DDHF is quickly tuned on small data, easily interpretable, and achieves competitive accuracies and latencies to deep learning alternatives.