YOLO-AMC：一种改进的带有注意力机制的YOLO架构用于建筑裂缝检测
YOLO-AMC: An Improved YOLO Architecture with Attention Mechanisms for Building Crack Detection
AI总结：
提出YOLO-AMC，在YOLOv11中移除C2PSA并引入GAM、Res-CBAM、SA等注意力机制，增强裂缝检测性能，在测试集上mAP@0.5达0.9917，速度110.95 FPS，兼顾精度与部署效率。
摘要：
裂缝检测在基础设施检查和结构健康监测（SHM）中起着重要作用。然而，裂缝通常表现为薄、低对比度的结构，且容易受到背景噪声的影响，给现有目标检测模型带来了挑战。本研究提出了一种改进的基于YOLO的架构，集成了注意力机制，称为YOLO-AMC（用于裂缝检测的YOLO注意力机制），以增强自动裂缝检测性能。基于YOLOv11，移除了原始的C2PSA模块，并在Neck的多尺度特征融合层中引入了多种注意力机制，包括全局注意力机制（GAM）、残差卷积块注意力模块（Res-CBAM）和Shuffle Attention（SA），以加强跨尺度特征整合。实验结果表明，YOLO-AMC在多个评估指标上始终优于基线模型YOLOv11n和YOLOv8n。在评估的注意力模块中，GAM取得了最佳检测性能，在测试数据集上获得了mAP@0.5 = 0.9917和mAP@0.5:0.95 = 0.9506，高于YOLOv11（0.9833 / 0.9112）和YOLOv8（0.9707 / 0.8921）。此外，在保持7.6 GFLOPs计算复杂度的同时，所提出的模型在NVIDIA RTX 4090平台上达到了110.95 FPS，在Raspberry Pi 5边缘设备上约为5 FPS，展示了准确性与部署效率之间的良好权衡。本研究的实现代码可在GitHub上获取，网址为：https://this https URL。
英文摘要：
Crack detection plays an important role in infrastructure inspection and Structural Health Monitoring (SHM). However, cracks typically appear as thin, low-contrast structures and are easily affected by background noise, posing challenges for existing object detection models. This study proposes an improved YOLO-based architecture with integrated attention mechanisms, termed YOLO-AMC (YOLO with Attention Mechanisms for Crack Detection), to enhance automated crack detection performance. Based on YOLOv11, the original C2PSA module is removed, and multiple attention mechanisms, including Global Attention Mechanism (GAM), Residual Convolutional Block Attention Module (Res-CBAM), and Shuffle Attention (SA), are introduced into the multi-scale feature fusion layers of the Neck to strengthen cross-scale feature integration. Experimental results demonstrate that YOLO-AMC consistently outperforms baseline models YOLOv11n and YOLOv8n across multiple evaluation metrics. Among the evaluated attention modules, GAM achieves the best detection performance, obtaining mAP@0.5 = 0.9917 and mAP@0.5:0.95 = 0.9506 on the test dataset, which are higher than those of YOLOv11 (0.9833 / 0.9112) and YOLOv8 (0.9707 / 0.8921). Furthermore, while maintaining a computational complexity of 7.6 GFLOPs, the proposed model achieves 110.95 FPS on an NVIDIA RTX 4090 platform and approximately 5 FPS on a Raspberry Pi 5 edge device, demonstrating a favorable trade-off between accuracy and deployment efficiency. The implementation code for this study is available on GitHub at https://github.com/CY-Tsai24/YOLO-AMC.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
