Integration of UAV-Enabled Surveillance and GEOINT Fusion for Military Decision Support
Abstract
Border security operations increasingly require intelligence tools that can deliver rapid, reliable insight across difficult terrain and under real operational constraints. This study evaluates an integrated UAV-GEOINT framework that combines LiDAR, high-resolution RGB imagery, GIS-based spatial analysis, and AI-driven object detection to support decision-making in complex border environments. A proof-of-concept field trial conducted in southeastern Thailand assessed how the multi-sensor system performed during realistic surveillance tasks involving concealed personnel and vehicles. Results show that the platform generated accurate 3D terrain models, detected targets with strong reliability, and reduced intelligence delivery time compared with current workflows. While dense canopy and large LiDAR data volumes introduced certain limitations, the trial demonstrated that fusing UAV sensing with automated analytics can meaningfully enhance situational awareness and operational responsiveness. These findings highlight the potential of integrated UAV-GEOINT capabilities to strengthen surveillance effectiveness in regions where traditional methods face persistent challenges.