A Novel YOLOv10-DECA Model for Real-Time Detection of Concrete Cracks

The You Only Look Once (YOLO) series algorithms have been widely adopted in concrete crack detection, with attention mechanisms frequently being incorporated to enhance recognition accuracy and efficiency. However, existing research is confronted by two primary challenges: the suboptimal performance of attention mechanism modules and the lack of explanation regarding how these mechanisms influence the model’s decision-making process to improve accuracy. To address these issues, a novel Dynamic Efficient Channel Attention (DECA) module is proposed in this study, which is designed to enhance the performance of the YOLOv10 model in concrete crack detection, and the effectiveness of this module is visually demonstrated through the application of interpretable analysis algorithms. In this paper, a concrete dataset with a complex background is used. Experimental results indicate that the DECA module significantly improves the model’s accuracy in crack localization and the detection of discontinuous cracks, outperforming the existing Efficient Channel Attention (ECA). When compared to the similarly sized YOLOv10n model, the proposed YOLOv10-DECA model demonstrates improvements of 4.40%, 3.06%, 4.48%, and 5.56% in precision, recall, mAP50, and mAP50-95 metrics, respectively. Moreover, even when compared with the larger YOLOv10s model, these performance indicators are increased by 2.00%, 0.04%, 2.27%, and 1.12%, respectively. In terms of speed evaluation, owing to the lightweight design of the DECA module, the YOLOv10-DECA model achieves an inference speed of 78 frames per second, which is 2.5 times faster than YOLOv10s, thereby fully meeting the requirements for real-time detection. These results demonstrate that an optimized balance between accuracy and speed in concrete crack detection tasks has been achieved by the YOLOv10-DECA model. Consequently, this study provides valuable insights for future research and applications in this field.