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

2026-07-16

AI Summary

This work addresses the challenges of air-to-air UAV tracking under low-light, overexposed, and high-speed conditions, where conventional frame-based cameras suffer from limited dynamic range and existing event-based methods rely heavily on GPU resources and large-scale training data, hindering deployment on resource-constrained platforms. To bridge this gap, the authors introduce AE-UAV—the first air-to-air event camera tracking benchmark, comprising 178 sequences with continuous-time cubic B-spline annotations—and propose FSFT, a lightweight, training-free frequency-domain tracking method. By integrating frequency-domain template matching, search region prediction, and detection-driven drift correction, FSFT achieves real-time performance at 420 FPS on a CPU alone, attaining 93.97% of the accuracy of state-of-the-art GPU-based methods while offering a 5.32× speedup and demonstrating strong generalization across temporal resolutions.

Abstract

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.

Problem

• air-to-air UAV tracking
• event-based vision
• real-time tracking
• resource-constrained platforms
• tracking benchmark

Innovation

• event-based vision
• air-to-air UAV tracking
• frequency-domain tracking
• lightweight tracker
• real-time CPU processing