Inspection System for Bridge Surface Defects in Cold Regions Based on Parameter Sharing and Feature Enhancement

Abstract

To address the scarcity of bridge defect data in the harsh environments of cold regions, as well as the parameter redundancy and edge platform deployment challenges of existing algorithms, this paper proposes an intelligent inspection system for bridge surface defects in cold regions based on parameter sharing and feature enhancement. The system first constructs a large-scale dataset called CRBD (Cold-Region Bridge Defect), which contains 10,129 high-resolution images and finely classifies defects into four standardized categories: Crack, Spalling, Patch, and Seepage. Subsequently, a lightweight detection network called BridgeNet is designed. Its core parameter sharing and feature enhancement detection head stabilizes training via group normalization, significantly reduces the parameter count through cross-scale global sharing and structural reparameterization, and improves bounding-box regression accuracy by incorporating a distribution focal loss mechanism. On this basis, an airborne real-time image processing and intelligent perception pipeline is constructed, which establishes the complete workflow for autonomous unmanned aerial vehicle inspections. The experimental results demonstrate that with a lightweight architecture of only 2.26 M parameters and a model size of 4.98 M, BridgeNet achieves a mean Average Precision of 61.4% and an F1 Score of 60.9%. Furthermore, it exhibits excellent real-time inference speed on heterogeneous edge mobile platforms and maintains robust overall perception stability under various extreme physical disturbances.