Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MMAUD: A Comprehensive Multi-Modal Anti-UAV Dataset for Modern Miniature Drone Threats

Shenghai Yuan, Yizhuo Yang, Thien Hoang Nguyen, Thien-Minh Nguyen, Jianfei Yang, Fen Liu, Jianping Li, Han Wang, Lihua Xie

TL;DR

This work tackles the need for accurate detection, classification, and trajectory estimation of small UAV threats in real-world settings. It proposes MMAUD, a comprehensive multi-modal Anti-UAV dataset that fuses stereo vision, LiDAR, radar, and audio, with Leica Nova MS60 ground truth to achieve millimeter-level accuracy. The dataset supports aerial overhead detection and UAV-type classification, providing data in rosbag and filesystem formats and offering open-source code for replication. Results on 2D detection and 3D pose estimation demonstrate the value of multi-modal fusion, while the paper discusses practical constraints such as sensor synchronization and regulatory restrictions, highlighting MMAUD's potential to enable robust benchmarking and development of real-world anti-UAV systems.

Abstract

In response to the evolving challenges posed by small unmanned aerial vehicles (UAVs), which possess the potential to transport harmful payloads or independently cause damage, we introduce MMAUD: a comprehensive Multi-Modal Anti-UAV Dataset. MMAUD addresses a critical gap in contemporary threat detection methodologies by focusing on drone detection, UAV-type classification, and trajectory estimation. MMAUD stands out by combining diverse sensory inputs, including stereo vision, various Lidars, Radars, and audio arrays. It offers a unique overhead aerial detection vital for addressing real-world scenarios with higher fidelity than datasets captured on specific vantage points using thermal and RGB. Additionally, MMAUD provides accurate Leica-generated ground truth data, enhancing credibility and enabling confident refinement of algorithms and models, which has never been seen in other datasets. Most existing works do not disclose their datasets, making MMAUD an invaluable resource for developing accurate and efficient solutions. Our proposed modalities are cost-effective and highly adaptable, allowing users to experiment and implement new UAV threat detection tools. Our dataset closely simulates real-world scenarios by incorporating ambient heavy machinery sounds. This approach enhances the dataset's applicability, capturing the exact challenges faced during proximate vehicular operations. It is expected that MMAUD can play a pivotal role in advancing UAV threat detection, classification, trajectory estimation capabilities, and beyond. Our dataset, codes, and designs will be available in https://github.com/ntu-aris/MMAUD.

MMAUD: A Comprehensive Multi-Modal Anti-UAV Dataset for Modern Miniature Drone Threats

TL;DR

This work tackles the need for accurate detection, classification, and trajectory estimation of small UAV threats in real-world settings. It proposes MMAUD, a comprehensive multi-modal Anti-UAV dataset that fuses stereo vision, LiDAR, radar, and audio, with Leica Nova MS60 ground truth to achieve millimeter-level accuracy. The dataset supports aerial overhead detection and UAV-type classification, providing data in rosbag and filesystem formats and offering open-source code for replication. Results on 2D detection and 3D pose estimation demonstrate the value of multi-modal fusion, while the paper discusses practical constraints such as sensor synchronization and regulatory restrictions, highlighting MMAUD's potential to enable robust benchmarking and development of real-world anti-UAV systems.

Abstract

In response to the evolving challenges posed by small unmanned aerial vehicles (UAVs), which possess the potential to transport harmful payloads or independently cause damage, we introduce MMAUD: a comprehensive Multi-Modal Anti-UAV Dataset. MMAUD addresses a critical gap in contemporary threat detection methodologies by focusing on drone detection, UAV-type classification, and trajectory estimation. MMAUD stands out by combining diverse sensory inputs, including stereo vision, various Lidars, Radars, and audio arrays. It offers a unique overhead aerial detection vital for addressing real-world scenarios with higher fidelity than datasets captured on specific vantage points using thermal and RGB. Additionally, MMAUD provides accurate Leica-generated ground truth data, enhancing credibility and enabling confident refinement of algorithms and models, which has never been seen in other datasets. Most existing works do not disclose their datasets, making MMAUD an invaluable resource for developing accurate and efficient solutions. Our proposed modalities are cost-effective and highly adaptable, allowing users to experiment and implement new UAV threat detection tools. Our dataset closely simulates real-world scenarios by incorporating ambient heavy machinery sounds. This approach enhances the dataset's applicability, capturing the exact challenges faced during proximate vehicular operations. It is expected that MMAUD can play a pivotal role in advancing UAV threat detection, classification, trajectory estimation capabilities, and beyond. Our dataset, codes, and designs will be available in https://github.com/ntu-aris/MMAUD.
Paper Structure (19 sections, 5 figures, 4 tables)

This paper contains 19 sections, 5 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Sensor Setup
  4. Stereo Cameras
  5. Conic 3D LIDAR
  6. Peripheral 3D LIDAR
  7. Audio Array
  8. Millimeter Wave Radar
  9. Ground Truth
  10. Dataset Characteristics
  11. Dataset Format
  12. Sensor Calibration
  13. Evaluation and Benchmark
  14. Issues and Challenges
  15. Limited Geographic Coverage
  16. ...and 4 more sections

Figures (5)

  • Figure 1: System Overview.
  • Figure 2: List of UAV being collected and their characteristics. Notes: The RCS is approximated based on the size projection.
  • Figure 3: Visualization of the Visual, LIDAR and RADAR data.
  • Figure 4: The visual detection results encompass both successful and unsuccessful cases when employing YoloX. Drones that are white, smaller in size, or located at a greater distance are less likely to be detected.
  • Figure 5: Precision-recall curve of visual detection result.