AI-Based Structural Health Monitoring Using Computer Vision and Sensor Fusion

Abstract

Structural Health Monitoring (SHM) has become an essential component of modern infrastructure management, enabling the continuous assessment of structural integrity, safety, and serviceability of critical assets such as bridges, buildings, tunnels, dams, and industrial facilities. Traditional inspection methods are often labor-intensive, subjective, costly, and incapable of providing real-time condition assessment. Recent advances in Artificial Intelligence (AI), Computer Vision (CV), and sensor technologies have created new opportunities for automated and intelligent monitoring systems capable of detecting structural anomalies with high accuracy and reliability. AI-driven computer vision techniques facilitate the identification of cracks, corrosion, spalling, deformation, and surface deterioration from visual data, while sensor fusion integrates information from heterogeneous sensing modalities including accelerometers, strain gauges, vibration sensors, acoustic emission sensors, and environmental sensors. The combined utilization of computer vision and sensor fusion enhances detection accuracy, reduces uncertainty, improves fault localization, and enables predictive maintenance strategies. This paper presents a comprehensive review of AI-based structural health monitoring frameworks that leverage computer vision and sensor fusion techniques. The study examines recent developments, methodologies, applications, challenges, and future research directions while highlighting the role of intelligent monitoring systems in improving infrastructure resilience, operational efficiency, and long-term sustainability.