The primary objective of maritime surveillance is to safeguard national and international rights and interests through reliable monitoring systems that enhance situational awareness and support maritime safety. Growing threats such as dense traffic, piracy, illegal fishing, unauthorized passages, intelligence gathering, smuggling, and oil spills demonstrate the critical importance of surveillance for both security and environmental sustainability.
Single-sensor information is insufficient for reliable detection and identification. The integration of heterogeneous data from multiple sensors—such as radar, optical systems, Automatic Identification System (AIS), and Synthetic Aperture Radar (SAR)—is essential to overcome individual limitations and improve overall awareness.
This review systematically examines multi-sensor fusion methods with emphasis on artificial intelligence-based approaches. Applications such as ship detection, recognition, tracking, and anomaly detection are analyzed within the framework of fusion processes. Using a structured literature review, the paper discusses current practices, technical and operational challenges, and future research directions. Both traditional techniques and modern artificial intelligence methods, including machine learning and deep learning, are evaluated. Key challenges include large-scale data handling, real-time processing, system complexity, heterogeneous data management, low-resolution issues, environmental variability, noise, and cyber vulnerabilities. This study provides a comprehensive reference for advancing maritime situational awareness through artificial intelligence-supported multi-sensor fusion.
If you have any questions about submitting your review, please email us at [email protected].