FRED: The Florence RGB-Event Drone Dataset

TL;DR

FRED is a comprehensive multimodal dataset combining RGB and event streams, designed to improve drone detection, tracking, and trajectory prediction under challenging conditions, addressing limitations of existing benchmarks.

Contribution

The paper introduces FRED, a novel drone dataset with high temporal resolution multimodal data, enabling advanced research in drone perception and tracking.

Findings

Over 7 hours of annotated drone trajectories

Includes diverse scenarios like rain and low light

Provides standardized evaluation protocols

Abstract

Small, fast, and lightweight drones present significant challenges for traditional RGB cameras due to their limitations in capturing fast-moving objects, especially under challenging lighting conditions. Event cameras offer an ideal solution, providing high temporal definition and dynamic range, yet existing benchmarks often lack fine temporal resolution or drone-specific motion patterns, hindering progress in these areas. This paper introduces the Florence RGB-Event Drone dataset (FRED), a novel multimodal dataset specifically designed for drone detection, tracking, and trajectory forecasting, combining RGB video and event streams. FRED features more than 7 hours of densely annotated drone trajectories, using 5 different drone models and including challenging scenarios such as rain and adverse lighting conditions. We provide detailed evaluation protocols and standard metrics for each task, facilitating reproducible benchmarking. The authors hope FRED will advance research in high-speed drone perception and multimodal spatiotemporal understanding.