M$^2$E-UAV: A Benchmark and Analysis for Onboard Motion-on-Motion Event-Based Tiny UAV Detection

TL;DR

This paper introduces M$^2$E-UAV, a novel dataset and benchmark for onboard tiny UAV detection using event cameras in motion-on-motion scenarios, highlighting the challenges and evaluating existing methods.

Contribution

It provides the first onboard UAV-view event-based dataset with synchronized data and labels, enabling evaluation of detection methods under realistic ego-motion conditions.

Findings

Existing baselines struggle with sparse target evidence and dense background events.

The benchmark includes over 100,000 samples across diverse scenes.

Code and data will be publicly available for further research.

Abstract

Tiny UAV detection from an onboard event camera is difficult when the observer and target move at the same time. In this motion-on-motion regime, ego-motion activates background edges across buildings, vegetation, and horizon structures, while the UAV may appear as a sparse event cluster. Unlike static- or ground-observer event-based UAV detection, onboard UAV-view detection breaks the clean-background assumption because sensor ego-motion can activate dense background events over the entire field of view. To explore this practical problem, we present M$^2$E-UAV, to the best of our knowledge, the first onboard UAV-view motion-on-motion event-based dataset and benchmark for tiny UAV detection, where both the sensing platform and the target UAV are moving. M$^2$E-UAV provides synchronized event streams and IMU measurements collected from an onboard sensing platform, together with event-level UAV foreground labels derived from temporally propagated 10 Hz bounding-box annotations. The processed benchmark contains 87,223 training samples and 21,395 validation samples across four scene families: sunny building-forest, sunny farm-village, sunset building-forest, and sunset farm-village. We define a train/validation split and an evaluation protocol for comparing representative existing baselines across event-frame, voxel-grid, and point-set representations, with optional IMU input. The benchmark results show that existing baselines remain limited under sparse tiny-target evidence and dense ego-motion-induced background events. Code and benchmark files will be released at https://github.com/Wickyan/M2E-UAV.