ASUMOT: Motion-Consistency-Based Asynchronous UAV Detection and Tracking with Event Cameras

2026-07-13

AI Summary

This work addresses the challenges of tracking long-range, low-altitude unmanned aerial vehicles (UAVs) using event cameras, where the resulting event streams are sparse, noisy, and fragmented, leading existing asynchronous tracking methods to suffer from trajectory duplication and identity instability. To overcome these limitations, the authors propose ASUMOT, a novel framework that introduces motion consistency modeling directly on raw event streams. ASUMOT represents UAVs as clusters of spatially coherent event blobs whose motions are locally consistent, enabling end-to-end asynchronous detection and tracking with stable identities through lightweight multi-task verification and clustering. The study also introduces ES-UAV, a high-precision, event-level UAV dataset. Experimental results demonstrate that ASUMOT significantly improves tracking accuracy and efficiency while preserving the inherent advantages of asynchronous processing.

Abstract

Event cameras offer microsecond-level temporal resolution and high dynamic range for low-altitude UAV perception. However, long-range UAVs often produce sparse, fragmented, and noise-contaminated event responses, where one semantic target may appear as multiple spatially separated blobs. Direct blob-level asynchronous tracking therefore suffers from duplicate trajectories and unstable identities. We propose ASUMOT, a motion-consistency-based asynchronous UAV detection and tracking framework operating directly on raw events. ASUMOT models each UAV as a set of motion-consistent event blobs. A local motion-consistency estimator triggers reliable candidates, a lightweight multi-task verifier provides UAV confidence and motion-direction cues, and motion-consistency clustering aggregates fragmented blobs into identity-consistent UAV tracks. We also introduce ES-UAV, a high-definition event-level UAV benchmark with dense semantic annotations. Experiments on public UAV tracking data and ES-UAV show that ASUMOT improves the accuracy--efficiency trade-off while preserving asynchronous event processing. Code and Dataset will be released.

Problem

• event cameras
• UAV detection and tracking
• motion consistency
• asynchronous tracking
• sparse events

Innovation

• event camera
• motion consistency
• asynchronous tracking
• UAV detection
• blob clustering