改进YOLO检测裂缝，引入注意力机制提升精度与效率
YOLO-AMC: An Improved YOLO Architecture with Attention Mechanisms for Building Crack Detection
- 在颈部结构中加入多种注意力模块，增强多尺度特征融合
- 在测试集上达[email protected]=0.9917，优于YOLOv11和YOLOv8
- 模型轻量高效，可在边缘设备实时运行
裂缝检测在基础设施巡检与结构健康监测中至关重要。然而，裂缝通常呈细长、低对比度形态，易受背景噪声干扰，给现有目标检测模型带来挑战。本文提出一种基于YOLOv11改进的架构YOLO-AMC（用于裂缝检测的注意力机制YOLO），通过移除原始C2PSA模块，并在颈部多尺度特征融合层中引入全局注意力机制（GAM）、残差卷积块注意力模块（Res-CBAM）和混洗注意力（SA），以强化跨尺度特征整合能力。实验表明，YOLO-AMC在多个评估指标上持续优于基准模型YOLOv11n和YOLOv8n。其中，GAM表现最佳，在测试集上达到[email protected] = 0.9917，[email protected]:0.95 = 0.9506，显著高于YOLOv11（0.9833 / 0.9112）和YOLOv8（0.9707 / 0.8921）。尽管计算复杂度保持在7.6 GFLOPs，该模型在NVIDIA RTX 4090上实现110.95 FPS，在Raspberry Pi 5边缘设备上约达5 FPS，展现出精度与部署效率的良好平衡。代码已开源于GitHub。
原文摘要 · Abstract (English)
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 [email protected] = 0.9917 and [email protected]: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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。