Automatic Road Subsurface Distress Recognition from Ground Penetrating Radar Images using Deep Learning-based Cross-verification

arXiv:2507.11081v3 Announce Type: replace-cross Abstract: Ground penetrating radar (GPR) has become a rapid and non-destructive solution for road subsurface distress (RSD) detection. However, recognizing RSD from GPR images is labor-intensive and heavily relies on the expertise of inspectors. Deep learning-based automatic RSD recognition, though ameliorating the burden of data processing, suffers from insufficient capability to recognize defects. In this study, a novel cross-verification strateg