Multi-Class Concrete Defect Classification Using Guided Semantic–Spatial Fusion and Squeeze–Excitation Enhanced DenseNet Model

Concrete materials are vulnerable to various sorts of structural defects. Reliable measurement and quantification of concrete defects are crucial for ensuring safety and effective maintenance. Deep learning is commonly utilized to detect and classify concrete defects efficiently. However, most available studies do not study multi-class defect identification. This study aims to develop a multi-class concrete defect detection framework to enhance concrete classification accuracy while enabling reliable defect localization. To achieve this, a new image-based non-destructive measurement dataset comprising 2029 images of concrete defects, categorized into five categories, has been compiled. For defect identification, the DenseNet201 model is modified by adding a guided semantic-spatial fusion module with a squeeze-and-excitation architecture, which enhances feature representation and introduces attention mechanisms to the model, enabling it to detect and track defect regions. Experiments are conducted on the collected dataset, and various scenarios and comparisons are performed to verify the proposed model. Results reveal the superiority of the proposed architecture with an accuracy enhancement of 5.6% compared to the original DenseNet201. A graphical user interface is also designed to integrate the trained model into a practical measurement instrument, enabling users to interact with the backend model and detect various defects from intact cases.