Bridge Crack Detection and Recognition Algorithm Based on the Improved YOLOv8n Model

本文针对我国桥梁数量众多、维护需求迫切的背景，提出了一种改进的YOLOv8n模型，以提升桥梁裂缝检测的准确性和效率。通过引入全局注意力机制(GAM)，研究成功增强了模型从复杂背景中提取显著特征的能力，结合Wise-IOU损失函数，优化了对难以检测样本的关注度。实验结果表明，改进后的YOLOv8n在精确度、平均精度均值(mAP)和F1分数上较原始模型分别提升了2.4、1.1和1.3个百分点，尽管召回率略有下降，但整体性能仍优于当前主流检测模型。本文的贡献在于通过技术创新，提高了桥梁裂缝的自动化检测能力，填补了传统人工检测方法的效率和主观性缺陷，为桥梁维护提供了更为高效、可靠的解决方案。未来，模型的进一步优化及在更广泛的实际应用中的验证，将是提升桥梁安全性和耐久性的关键。This study addresses the urgent maintenance needs of the numerous bridges in China by proposing an improved YOLOv8n model to enhance the accuracy and efficiency of bridge crack detection. By incorporating a Global Attention Mechanism (GAM), the research successfully enhances the model’s ability to extract salient features from complex backgrounds. Additionally, the Wise-IOU loss function optimizes the model’s focus on hard-to-detect samples. Experimental results indicate that the improved YOLOv8n achieves increases of 2.4, 1.1, and 1.3 percentage points in accuracy, mean average precision (mAP), and F1 score, respectively, compared to the original model. Although the recall rate slightly declined, the overall performance remains superior to current mainstream detection models. The contribution of this research lies in the technological innovation that improves the automation capability of bridge crack detection, addressing the efficiency and subjectivity deficiencies of traditional manual inspection methods, thus providing a more efficient and reliable solution for bridge maintenance. Future work will focus on further optimizing the model and validating it in a broader range of practical applications, which will be key to enhancing bridge safety and durability.