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

Michael Bezick; Majid Sahin

cs.CVMar 9, 2026

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

Authors: Michael Bezick, Majid Sahin

Organizations: Johns Hopkins University APL

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.

Figures & tables

Figure 1: (a) Far distance drone test at 300m using the Navitar 100mm F2.8 lens. (b) Direct sunlight test demonstrating the wide dynamic range of event based vision. (c) Multi-drone test - both identified correctly. (d)-(e) Handheld shaky-cam examples. Algorithm is able to accurately isolate the drone from the background, while keeping latency to real-time speeds despite large event throughput. (f)-(h) Angle of elevation experiment at $0^{\circ}$ , $10^{\circ}$ , and $90^{\circ}$ respectively. At $0^{\circ}$ , drone is barely visible (due to pose and possibly the focus of lens) and not identified, but at $10^{\circ}$ , drone is accurately identified, showing a limitation of DDHF. At $90^{\circ}$ angle of elevation, the drone is most easily identified. (i) Power spectrum of pixel where two overlapping rotor paths projected onto. (j) Typical power spectrum of a single-rotor pixel.

Figure 2: Visualization of one frame, comparing the spectra of a drone pixel versus a car wheel pixel. Both spectral flatness and harmonic comb scores from DDHF are able to distinguish between the spectrum of a spinning tire versus a spinning rotor.

Figure 3: Demonstration of the interpretable tuning capabilities of DDHF. For row (a) , the default hyperparameters obtained from the Bayesian optimization were used. For row (b) , $\tau_{sf}$ was tuned from $0.89$ to $0.5$ . For row (c) , $\tau_{\mathrm{comb}}$ was tuned from $1.5$ to $6$ . In both tuning cases, the bounding box becomes far more selective, filtering out the power spectra of the moving cars and effectively isolating the drone. Interestingly, only the inner parts of the drone rotor at this pose appear to be identified.

Condition	Detection Ours			Detection YOLO			Latency (ms) Ours			Latency (ms) YOLO			n
	P	R	F1	P	R	F1	Median	IQR	p95	Median	IQR	p95
Stationary - 10 m	$99.58$	$99.58$	99.58	99.79	98.98	99.38	2.30	$0.65$	$4.10$	11.91	1.17	15.24	$979$
Slow - 10 m	$97.18$	$96.57$	96.87	92.60	97.13	94.81	2.60	$1.06$	$5.06$	12.44	1.18	16.67	$350$
Fast - 10 m	$100.00$	$93.24$	$96.46$	97.26	98.61	97.93	3.01	$1.84$	$7.49$	12.07	0.74	13.45	$77$
Multi-Drone - 15 m	$93.63$	$93.53$	93.58	100.00	5.47	10.37	1.85	$0.46$	$3.48$	11.57	1.17	14.69	$448$
Direct Sunlight	$100.00$	$99.42$	99.71	100.00	96.53	98.24	2.29	$0.31$	$2.80$	13.22	1.26	16.78	$173$

Table 1: Head-to-head detection and latency at IoU=0.5. Our method is shown to almost always achieve far higher average detection scores and significantly lower latencies. As each frame at 30 fps corresponds to 33.33 milliseconds, latencies are comfortably below this budget, indicating our method is likely sufficient for real-time operation on the tested hardware. Latency is measured in milliseconds per frame, and inference is performed on an NVIDIA L40-8Q GPU.

n

= number of frames tested. We also report metric averages, weighted by number of frames per experiment.

Panel of Figure 4 — Figure 4: Performance versus angle of elevation. (a) Accuracy measured by F1-score; (b) inference latency.

Parameter	Symbol	BO Range	Final Value
Spectral flatness threshold	$\tau_{sf}$	$[0.3,0.98]$	0.89
Comb SNR threshold	$\tau_{\mathrm{comb}}$	$[1.5,6.0]$	1.5
# comb harmonics	$M$	$[4,16]$	4
Harmonic half-bandwidth	$\Delta k$	$[0,4]$	3
Min. matched harmonics	$h_{\min}$	$[2,8]$	4
Minimum passes / window	$n_{\min}$	$[2,10]$	6

Table 2: Bayesian optimization search space and results. All hyperparameters saw Uniform priors, and we use a GP with the expected improvement (EI) acquisition function.

Explore similar work

Mar 6, 2026

ODD-SEC: Onboard Drone Detection with a Spinning Event Camera

The rapid proliferation of drones requires balancing innovation with regulation. To address security and privacy concerns, techniques for drone detection have attracted significant attention.Passive solutions, such as frame camera-based systems, offer versatility and energy efficiency under typical conditions but are fundamentally constrained by their operational principles in scenarios involving fast-moving targets or adverse illumination.Inspired by biological vision, event cameras asynchronously detect per-pixel brightness changes, offering high dynamic range and microsecond-level responsiveness that make them uniquely suited for drone detection in conditions beyond the reach of conventional frame-based cameras.However, the design of most existing event-based solutions assumes a static camera, greatly limiting their applicability to moving carriers--such as quadrupedal robots or unmanned ground vehicles--during field operations.In this paper, we introduce a real-time drone detection system designed for deployment on moving carriers. The system utilizes a spinning event-based camera, providing a 360° horizontal field of view and enabling bearing estimation of detected drones. A key contribution is a novel image-like event representation that operates without motion compensation, coupled with a lightweight neural network architecture for efficient spatiotemporal learning. Implemented on an onboard Jetson Orin NX, the system can operate in real time. Outdoor experimental results validate reliable detection with a mean angular error below 2° under challenging conditions, underscoring its suitability for real-world surveillance applications. We will open-source our complete pipeline to support future research.

Kuan Dai, Hongxin Zhang, Sheng Zhong +1

Neuromorphic Automation and Intelligence Lab (NAIL) at School of Artificial Intelligence and Robotics, Hunan University, Changsha, China.

Aerial Object Detection Event-Based Object Detection Real-Time Object Detection Event-Based Vision

Ask PDF

Jul 12, 2026

End-to-End Real-Time Drone-Based Person Detection Framework Using Deep Learning

In recent years, Unmanned Aerial Vehicles (UAVs) or drones have gained rapid response in terms of security, search and rescue (SAR), border surveillance, etc. Existing monitoring frameworks often struggle to maintain detection consistency when targets undergo significant scale variations due to altitude changes, leading to critical information gaps. To address this issue, this work proposes an integrated real-time detection pipeline for detecting targets through the wireless live drone video feed. Build upon YOLOv8-nano architecture, extensive flight experiments were conducted to determine the detection performance across multiple flight altitudes. Trained on VisDrone2019 dataset, the results of YOLOv8-nano model achieves 57.4%, 41%, 44.8% and 20.3% in precision, recall, mAP and mAP50:95 respectively. While demonstrating on real environment, this analysis revealed that the algorithm achieves near-total detection reliability at altitudes between 16 and 25 meters with the detection frame rate consistently maintained above 41 FPS and reaching a peak of 50 FPS. However, the goal of this work is to enable real-time person detection from an aerial platform via wireless transmission. This approach effectively addresses the dual challenges of identifying targets at varying scales and ensuring near-to-accurate localization during aerial observation.

Payel Sarmah, Ayush Ranjan, Piyush Kaushik Bhattacharyya +2

Centre for Drone Technology Indian Institute of Technology Guwahati Guwahati, India · Dept. of CSE KIIT University Bhubaneswar, India · Drone LAB National Institute of Electronics and Information Technology Bhubaneswar, India

Object Detection Real-Time Object Detection Aerial Object Detection

Ask PDF

Jul 16, 2026

AE-UAV: An Air-to-Air Event-Based UAV Tracking Benchmark and a Real-Time Frequency-Domain Tracker

Air-to-air (A2A) unmanned aerial vehicle (UAV) tracking is fundamental to airborne remote sensing of low-altitude aerial targets. However, the deployment of continuous, real-time tracking systems on UAVs presents significant challenges. In A2A scenarios, traditional frame-based cameras suffer from severe performance degradation under low illumination, overexposure, and high-speed motion owing to their limited dynamic range and fixed temporal sampling. Although event cameras offer a promising alternative with microsecond temporal resolution and a high dynamic range, current research is bottlenecked by two primary issues: 1) the absence of dedicated A2A event-based datasets, and 2) the heavy reliance of existing trackers on GPU acceleration and extensive training data, rendering them impractical for resource-constrained UAVs. To bridge these gaps, we introduce AE-UAV, an air-to-air event-based UAV tracking benchmark. To the best of our knowledge, this is the first airborne-captured event camera dataset for A2A tracking, comprising 178 flight sequences with continuous-time cubic B-spline annotations. Furthermore, we propose the Fast-Slow Frequency-domain Tracking (FSFT) method. This lightweight, training-free framework seamlessly integrates frequency-domain template matching with search region prediction and detection-based drift correction. Extensive experiments demonstrate that FSFT operates at an ultra-fast 420 frames per second (FPS) on CPU-only hardware. It retains 93.97% of the accuracy of state-of-the-art GPU-dependent methods while delivering a 5.32-fold effective speedup and exhibiting superior temporal resolution generalization, thereby providing a highly efficient and robust solution for airborne remote sensing of aerial targets. The dataset and source code are available at https://github.com/MSP-xEN/AE-UAV.

Zixin Jiang, Bing He, Chaoran Xiong +3

Department of Electronic Engineering, Rocket Force University of Engineering, Xi’an 710025, China · Shanghai Key Laboratory of Navigation and Location Based Services, Shanghai Jiao Tong University, Shanghai 200240, China · State Key Laboratory of Submarine Geoscience, School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China

Event-Based Vision Visual Object Tracking UAV Remote Sensing

Ask PDF