LiDAR health monitoring of transport infrastructure: automatic damage detection using classification of point clouds

Health monitoring of transport infrastructure is crucial for efficient management and safety, particularly in the wake of recent global bridge collapses. This is the case of italy, where aligning with European guidelines, specific protocols for bridge assessment and monitoring were issued. While traditional visual inspections are accurate, they suffer from low repeatability and high costs. Recent advancements in Non-Destructive Testing (NDT), especially LiDAR technologies, offer promising solutions. This study focuses on utilizing Terrestrial Laser Scanner (TLS) point clouds for automated defect identification, emphasizing signal amplitude for enhanced accuracy. By clustering point clouds and integrating signal amplitude, structural anomalies like cracks and corrosion can be precisely identified. Experimental results demonstrate the effectiveness of this approach in reducing inspection time and streamlining the workflow, paving the way for more efficient monitoring of transport infrastructure.