Automatic Recognition and Quantification of Multiple Defects in Highway Tunnels Using Vehicle-Mounted Multisensor...

With advances in computer vision and modern surveying technologies, intelligent inspection systems and automatic recognition methods are increasingly used in highway tunnel maintenance. However, existing mobile inspection methods still struggle to balance high-speed operation, fine-crack recognition, and comprehensive assessment of multiple defects. This study proposes an automatic recognition and quantitative assessment method for multiple visible defects in highway tunnels based on a vehicle-mounted multisensor inspection system. The system integrates high-resolution imaging, infrared illumination, 3D laser scanning, mileage positioning, and high-speed data storage, enabling continuous full-section data acquisition at speeds up to 80 km/h. A structural-feature-constrained mileage correction strategy is developed to reduce accumulated localization errors. For crack analysis, a multilevel framework combining two-stage CNN screening, cascaded segmentation, crack trajectory tracking, and subpixel edge extraction is established for crack recognition and 0.1 mm-level width measurement. Water leakage and spalling are extracted through visible-infrared image fusion and adaptive boundary refinement, while cross-sectional deformation is calculated using 3D tunnel axis reconstruction, point-cloud filtering, and cross-section fitting. Field tests and controlled experiments demonstrate that the system can rapidly identify, locate, and quantify multiple tunnel defects, providing a practical reference for intelligent tunnel inspection and maintenance.