Multi-Modal Graph Neural Network-Inspired Vessel Identification and Tracking for UAV-Based Maritime Surveillance

Key points

• To address these problems, this paper proposes an airborne multi-modal graph learning-driven framework, termed AMGT, for vessel identification and tracking in UAV-assisted maritime IoT.1
• To detect small and oriented vessels, we develop a mixed-modality MAir-YOLOv8-OBB detector, followed by the MAir-SORT algorithm for stable vessel tracking.1
• We further design a graph learning-driven association network to model temporal dynamics and spatial dependencies among vessels and between vessels and UAVs.1
• A motion-aware coordinate unification (MCU) strategy is also introduced to reduce nonlinear misalignment caused by UAV motion.1

Sources (1)

• [1]Multi-Modal Graph Neural Network-Inspired Vessel Identification and Tracking for UAV-Based Maritime Surveillance
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 08:37 AM

  The unmanned aerial vehicle (UAV)-based maritime surveillance is becoming an important part of maritime Internet of Things (IoT) and intelligent transportation systems.

  To address these problems, this paper proposes an airborne multi-modal graph learning-driven framework, termed AMGT, for vessel identification and tracking in UAV-assisted maritime IoT.

Extractive summary: sentences quoted from the sources.