<![CDATA[Maritime surveillance complexity has increased due to expanding vessel activities, security challenges, and the demand for accurate real-time maritime domain awareness. This research aims to develop an AI-powered integrated surveillance framework combining shore-based radar, Automatic Identification System (AIS), and Unmanned Aerial Vehicle (UAV) computer vision for automated vessel tracking in Koarmada I operations. The study employs a mixed-methods technological development approach involving multi-source maritime data integration, artificial intelligence modeling, performance evaluation, and expert validation. The findings reveal that the integrated AI framework improves vessel detection accuracy, identification reliability, and tracking continuity compared with individual surveillance approaches. Radar contributes extensive spatial detection, AIS enhances vessel identification, and UAV computer vision provides visual verification capabilities. The integrated model demonstrates significant potential for reducing information gaps and strengthening maritime situational awareness. The research concludes that AI-driven sensor fusion represents an effective strategy for advancing naval surveillance systems by transforming fragmented maritime data into actionable operational intelligence. The proposed framework contributes to maritime security technology development and provides a foundation for future autonomous surveillance applications within complex operational environments. Future implementation requires broader datasets, adaptive algorithms, and extensive operational testing to ensure robustness across diverse maritime conditions and support sustainable defense information system transformation.]]>
