A Comprehensive Multi-Modal Anti-UAV Dataset for Modern Miniature Drone Threats is a paper by Shenghai Yuan, Yizhuo Yang, Thien Hoang Nguyen, Thien-Minh Nguyen, Jianfei Yang, Fen Liu, Jianping Li, Han Wang, and Lihua Xie.

In light of the increasing challenges of small unmanned aerial vehicles (UAVs) capable of carrying harmful payloads or causing damage autonomously, the authors introduce MMAUD: a comprehensive Multi-Modal Anti-UAV Dataset. Addressing a crucial gap in current threat detection methods, MMAUD focuses on drone detection, UAV-type classification, and trajectory estimation. What sets MMAUD apart is its integration of diverse sensory inputs, including stereo vision, various Lidars, Radars, and audio arrays, offering superior overhead aerial detection compared to datasets based on specific viewpoints using thermal and RGB. Additionally, MMAUD provides precise Leica-generated ground truth data, enhancing credibility and facilitating confident algorithm and model refinement, a feature unparalleled in other datasets. Since many existing studies do not disclose their datasets, MMAUD emerges as an invaluable resource for developing accurate and efficient solutions. Our proposed modalities are cost-effective and highly adaptable, empowering users to explore and implement innovative UAV threat detection tools. By incorporating ambient sounds from heavy machinery, our dataset closely mirrors real-world scenarios, capturing the exact challenges encountered during close-range vehicular operations. We anticipate that MMAUD will significantly advance UAV threat detection, classification, trajectory estimation capabilities, and more. Our dataset, codes, and designs will be accessible at https://github.com/ntuaris/MMAUD.

Publication Date– 2024

A Comprehensive Multi-Modal Anti-UAV Dataset for Modern Miniature Drone Threats contains the following major sections:

  • Introduction
  • Related Work
  • Sensor Setup
  • Dataset Characteristics
  • Dataset Format
  • Sensor Calibration
  • Evaluation and Benchmark
  • Issues and Challenges
  • Conclusion

C-UAS Hub does not own this content and provides a link for users at the bottom of the page to access the document in its original location. This allows the author(s) or organizations to track important metrics related to their work. All credit goes to its rightful owner(s).

Post Image Credit- envatoelements by  seventyfourimages