Intelligent Recognition of GPR Road Hidden Defect Images Based on Feature Fusion and Attention Mechanism

Abstract

Ground penetrating radar (GPR) has emerged as a pivotal tool for nondestructive evaluation of subsurface road defects. However, conventional GPR image interpretation remains heavily reliant on subjective expertise, introducing inefficiencies and inaccuracies. This study introduces a comprehensive framework to address these limitations: 1) a DCGAN-based data augmentation strategy synthesizes high-fidelity GPR images to mitigate data scarcity while preserving defect morphology under complex backgrounds; 2) a novel multimodal chain and global attention network (MCGA-Net) is proposed, integrating multimodal chain feature fusion (MCFF) for hierarchical multiscale defect representation and global attention mechanism (GAM) for context-aware feature enhancement; and 3) MS Common Objects in Context (COCO) transfer learning fine-tunes the backbone network, accelerating convergence and improving generalization. Ablation and comparison experiments validate the framework’s efficacy. MCGA-Net achieves precision (92.8%), recall (92.5%), and mAP@50 (95.9%). In the detection of Gaussian noise ( $\sigma =25$ ), weak signals, and small targets, MCGA-Net maintains robustness and outperforms other models. This work establishes a new paradigm for automated GPR-based defect detection, balancing computational efficiency with high accuracy in complex subsurface environments.