FRED: The Florence RGB-Event Drone Dataset

1 MICC (Media Integration and Communication Center), University of Florence, Italy
2 University of Siena, Italy
Fred Dataset Teaser Image

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.

Spatio-Temporal Synchronization

FRED dataset is spatio-temporally synchronized, meaning RGB and Event frames can be perfectly overlapped.

Detection

FRED has detection annotations for 7+ hours of drone footage, with more than 700,000 annotated frames per each modality.

Tracking

FRED presents challenging tasks such as tracking multiple drones within a scene.

Forecasting

Drone trajectory forecasting is also explored in FRED as a separate task, with a collection of complex drone motions given the multiple drone models and challenging scenarios.

Challenging Scenarios


Raining

Event Frame
RGB Frame

High dynamic ranges

Event Frame
RGB Frame

Night

Event Frame
RGB Frame

Indoor

Event Frame
RGB Frame

BibTeX

Under Review