RFUAV: 1.3 TB of Raw RF Signal Data from 37 Distinct UAV Models

RFUAV contains 1.3 TB of raw radio-frequency (RF) signal data collected from 37 distinct unmanned aerial vehicle (UAV) models for detection and identification tasks. Developed by kitofrank and released in 2025, this benchmark provides high-volume signal data to address the limitations of smaller, less diverse drone signal repositories.

Use Cases

• Multi-class classification to identify specific drone models from 37 distinct categories
• Signal detection to distinguish UAV radio-frequency signatures from background noise
• Benchmarking deep learning models on 1.3 TB of high-volume RF signal data

Strengths

• 1.3 TB of raw frequency data
• Includes 37 distinct UAV models for high-granularity identification
• Apache 2.0 licensed for open research
• Linked to Arxiv publication 2503.09033 for methodology verification

Limitations

• Extremely high storage requirement of 1.3 TB may be prohibitive for some users
• Potential class imbalance across the 37 drone types
• Focus is restricted to RF signals, excluding multi-modal data like optical or thermal imagery

Provenance

Source

RFUAV: A Benchmark Dataset for Unmanned Aerial Vehicle Detection and Identification (Arxiv 2503.09033)

Collection Method

Sensor-based collection of radio frequency signals from 37 physical UAV units

Freshness

Last updated June 2025.