Technology Category
Intelligent Robots: Multimodal Perception & Sensor FusionComputer Vision: Remote Sensing / Geospatial AIPlanning, Routing, and Scheduling: Activity and Plan Recognition
Enhancing Maritime Domain Awareness on Inland Waterways: A YOLO-Based Fusion of Satellite and AIS for Vessel Characterization
🤖 AI Summary
To address maritime perception bottlenecks in inland waterways—particularly the difficulty in identifying “dark ships” and verifying navigational compliance due to inadequate AIS coverage and unreliable AIS data—this paper proposes the first satellite imagery–AIS fusion framework specifically designed for inland river environments. Innovatively, YOLOv11 is adapted for multi-attribute, fine-grained vessel parsing, jointly detecting vessel type, barge coverage status, operational mode, heading, and fleet size on high-resolution satellite imagery (5,973 sq. mi.) over the Mississippi River Basin, annotated with 4,550 samples. Experimental results show a vessel classification F1-score of 95.8%, operational state classification F1-score of 99.4%, heading estimation accuracy of 93.8%, barge count MAE of 2.4, and cross-regional transfer accuracy up to 98%. The framework significantly enhances geographical robustness and fine-grained maritime situational awareness.
Technology Category
Application Category
📝 Abstract
Maritime Domain Awareness (MDA) for inland waterways remains challenged by cooperative system vulnerabilities. This paper presents a novel framework that fuses high-resolution satellite imagery with vessel trajectory data from the Automatic Identification System (AIS). This work addresses the limitations of AIS-based monitoring by leveraging non-cooperative satellite imagery and implementing a fusion approach that links visual detections with AIS data to identify dark vessels, validate cooperative traffic, and support advanced MDA. The You Only Look Once (YOLO) v11 object detection model is used to detect and characterize vessels and barges by vessel type, barge cover, operational status, barge count, and direction of travel. An annotated data set of 4,550 instances was developed from $5{,}973~mathrm{mi}^2$ of Lower Mississippi River imagery. Evaluation on a held-out test set demonstrated vessel classification (tugboat, crane barge, bulk carrier, cargo ship, and hopper barge) with an F1 score of 95.8%; barge cover (covered or uncovered) detection yielded an F1 score of 91.6%; operational status (staged or in motion) classification reached an F1 score of 99.4%. Directionality (upstream, downstream) yielded 93.8% accuracy. The barge count estimation resulted in a mean absolute error (MAE) of 2.4 barges. Spatial transferability analysis across geographically disjoint river segments showed accuracy was maintained as high as 98%. These results underscore the viability of integrating non-cooperative satellite sensing with AIS fusion. This approach enables near-real-time fleet inventories, supports anomaly detection, and generates high-quality data for inland waterway surveillance. Future work will expand annotated datasets, incorporate temporal tracking, and explore multi-modal deep learning to further enhance operational scalability.
Problem
Research questions and friction points this paper is trying to address.
Fusing satellite imagery with AIS data to detect dark vessels
Addressing vulnerabilities in cooperative inland waterway monitoring systems
Enhancing vessel characterization through object detection and data fusion
Innovation
Methods, ideas, or system contributions that make the work stand out.
Fuses satellite imagery with AIS data
Uses YOLO v11 for vessel detection
Links visual detections with AIS tracking
🔎 Similar Papers
No similar papers found.
