An Optimized YOLOv11 Framework for the Efficient Multi-Category Defect Detection of Concrete Surface
Zhuang Tian, Fan Yang, Lei Yang, Yunjie Wu, Jiaying Chen, Peng Qian
Abstract
Thoroughly and accurately identifying various defects on concrete surfaces is crucial to ensure structural safety and prolong service life. However, in actual engineering inspections, the varying shapes and complexities of concrete structural defects challenge the insufficient robustness and generalization of mainstream models, often leading to misdetections and under-detections, which ultimately jeopardize structural safety. To overcome the disadvantages above, an efficient concrete defect detection model called YOLOv11-EMC (efficient multi-category concrete defect detection) is proposed. Firstly, ordinary convolution is substituted with a modified deformable convolution to efficiently extract irregular defect features, and the model's robustness and generalization are significantly enhanced. Then, the C3k2module is integrated with a revised dynamic convolution module, which reduces unnecessary computations while enhancing flexibility and feature representation. Experiments show that, compared with Yolov11, Yolov11-EMC has improved precision, recall, mAP50, and F1 by 8.3%, 2.1%, 4.3%, and 3% respectively. Results of drone field tests show that Yolov11-EMC successfully lowers false and under-detections while simultaneously increasing detection accuracy, providing a superior methodology to tasks that require identifying tangible flaws in practical engineering applications.