A Real-time Concrete Crack Detection and Segmentation Model Based on YOLOv11

Abstract: Accelerated aging of transportation infrastructure in the rapidly developing Yangtze River Delta region necessitates efficient concrete crack detection, as crack deterioration critically compromises structural integrity and regional economic growth. To overcome the limitations of inefficient manual inspection and the suboptimal performance of existing deep learning models, particularly for small-target crack detection within complex backgrounds, this paper proposes YOLOv11-KW-TA-FP, a multi-task concrete crack detection and segmentation model based on the YOLOv11n architecture. The proposed model integrates a three-stage optimization framework: (1) Embedding dynamic KernelWarehouse convolution (KWConv) within the backbone network to enhance feature representation through a dynamic kernel sharing mechanism; (2) Incorporating a triple attention mechanism (TA) into the feature pyramid to strengthen channel-spatial interaction modeling; and (3) Designing an FP-IoU loss function to facilitate adaptive bounding box regression penalization. Experimental validation demonstrates that the enhanced model achieves significant performance improvements over the baseline, attaining 91.3% precision, 76.6% recall, and 86.4% mAP@50. Ablation studies confirm the synergistic efficacy of the proposed modules. Furthermore, robustness tests indicate stable performance under conditions of data scarcity and noise interference. This research delivers an efficient computer vision solution for automated infrastructure inspection, exhibiting substantial practical engineering value.