Leveraging AI and IoT for Enhanced Surveillance and Efficient Management of Water Dams

Abstract

Ensuring dam safety requires proactive monitoring of multiple critical risks, including floating debris, potential drowning incidents, and the gradual emergence of structural cracks. In response to these challenges, this work presents an integrated intelligent system based on computer vision and artificial intelligence, designed to detect and classify these hazards in real-time from visual data. The proposed system unifies three complementary detection modules within a single platform: floating object detection, drowning detection, and crack detection. Each module is built upon the YOLOv8 deep learning architecture and trained on dedicated, annotated datasets with tailored preprocessing and optimization techniques. This unified approach enables the system to automatically analyze surveillance imagery, generate accurate alerts, and support decision-making in dam management operations. The experimental results, obtained in a controlled environment, confirm the system’s effectiveness and robustness across all three detection tasks. This work lays the foundation for a future deployable solution to enhance dam safety through intelligent and autonomous monitoring. Keywords: Integrated intelligent system, dam safety, deep learning, YOLOv8, computer vision, floating object detection, drowning detection, crack detection, real-time monitoring.