ITU-T Recommendations

Transportation tunnels are susceptible to various defects and disasters over their operational lifespan, which can compromise structural safety and operational efficiency. Traditional manual inspection methods often face challenges in terms of safety, accuracy and cost-effectiveness. The integration of robotic systems with advanced artificial intelligence (AI) technologies, particularly computer vision and computer audition, presents a transformative approach to enhance the intelligence and analytical capabilities of a tunnel inspection.
Recommendation ITU-T F.748.75 specifies the requirements and framework for computer vision and audition-based transportation tunnel inspection robotic systems. It provides a layered reference framework comprising a device layer, network layer, service and application support layer, and an application layer, supported by cross-layer management and security capabilities. Furthermore, it specifies functional requirements for the system components, including the use and development of AI models for visual and acoustic data analysis to support intelligent, efficient and comprehensive tunnel inspections.