Chen Xiyin, Shi Yonghua, Pang Junjie
School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510640, China.
Sensors (Basel). 2025 Apr 22;25(9):2642. doi: 10.3390/s25092642.
Crack segmentation is essential for structural health monitoring and infrastructure maintenance, playing a crucial role in early damage detection and safety risk reduction. Traditional methods, including digital image processing techniques have limitations in complex environments. Deep learning-based methods have shown potential, but still face challenges, such as poor generalization with limited samples, insufficient extraction of fine-grained features, feature loss during upsampling, and inadequate capture of crack edge details. This study proposes SECrackSeg, a high-accuracy crack segmentation network that integrates an improved UNet architecture, Segment Anything Model 2 (SAM2), MI-Upsampling, and an Edge-Aware Attention mechanism. The key innovations include: (1) using a SAM2 S-Adapter with a frozen backbone to enhance generalization in low-data scenarios; (2) employing a Multi-Scale Dilated Convolution (MSDC) module to promote multi-scale feature fusion; (3) introducing MI-Upsampling to reduce feature loss during upsampling; and (4) implementing an Edge-Aware Attention mechanism to improve crack edge segmentation precision. Additionally, a custom loss function incorporating weighted binary cross-entropy and weighted IoU loss is utilized to emphasize challenging pixels. This function also applies Multi-Granularity Supervision by optimizing segmentation outputs at three different resolution levels, ensuring better feature consistency and improved model robustness across varying image scales. Experimental results show that SECrackSeg achieves higher precision, recall, F1-score, and mIoU scores on the CFD, Crack500, and DeepCrack datasets compared to state-of-the-art models, demonstrating its excellent performance in fine-grained feature recognition, edge segmentation, and robustness.
裂缝分割对于结构健康监测和基础设施维护至关重要，在早期损伤检测和降低安全风险方面发挥着关键作用。包括数字图像处理技术在内的传统方法在复杂环境中存在局限性。基于深度学习的方法已显示出潜力，但仍面临挑战，例如样本有限时泛化能力差、细粒度特征提取不足、上采样过程中的特征丢失以及裂缝边缘细节捕捉不充分。本研究提出了SECrackSeg，这是一种高精度裂缝分割网络，它集成了改进的UNet架构、Segment Anything Model 2（SAM2）、MI - 上采样和边缘感知注意力机制。关键创新点包括：（1）使用带有冻结主干的SAM2 S - Adapter以增强低数据场景下的泛化能力；（2）采用多尺度扩张卷积（MSDC）模块促进多尺度特征融合；（3）引入MI - 上采样以减少上采样过程中的特征丢失；（4）实现边缘感知注意力机制以提高裂缝边缘分割精度。此外，还使用了一种结合加权二元交叉熵和加权交并比损失的自定义损失函数来强调具有挑战性的像素。该函数还通过在三个不同分辨率级别优化分割输出应用多粒度监督，确保在不同图像尺度上具有更好的特征一致性和更高的模型鲁棒性。实验结果表明，与现有模型相比，SECrackSeg在CFD、Crack500和DeepCrack数据集上实现了更高的精度、召回率、F1分数和平均交并比分数，证明了其在细粒度特征识别、边缘分割和鲁棒性方面的优异性能。
