Convolutional neural networks (CNNs) have gained growing interest in recent years for their advantages in detecting cracks on concrete bridge components. Class imbalance is a fundamental problem in crack segmentation, resulting in unsatisfactory segmentation for tiny cracks. Besides, limited by the local receptive field, CNNs often cannot integrate local features with global dependencies, thus significantly affecting the detection accuracy of tiny cracks across the entire image. To solve those problems in segmenting tiny cracks, a multiscale feature fusion network with attention mechanisms named “Tiny-Crack-Net” (TCN) is proposed. The modified residual network was used to capture the local features of tiny cracks. The dual attention module was then incorporated into the architecture to better separate the tiny cracks from the background. Also, a multiscale fusion operation was implemented to preserve the edge details of tiny cracks. Finally, a joint learning loss of the cross-entropy and similarity was proposed to alleviate the poor convergence induced by the severe class imbalance of the pixels representing tiny cracks. The capability of the network in segmenting tiny cracks was remarkably enhanced by the aforementioned arrangements, and the “Tiny-Crack-Net” achieved a Dice similarity coefficient of 87.96% on an open-source data set, which was at least 5.84% higher than those of the six cutting-edge networks. The effectiveness and robustness of the “Tiny-Crack-Net” were validated with field test results, which showed that the intersection over union (IOU) for cracks with a width of 0.05 mm or wider reaches 91.44%.

中文翻译：

---

Tiny-Crack-Net：具有注意力机制的多尺度特征融合网络，用于分割微小裂缝

近年来，卷积神经网络 (CNN) 因其在检测混凝土桥梁构件裂缝方面的优势而受到越来越多的关注。类不平衡是裂缝分割中的一个基本问题，导致对微小裂缝的分割效果不理想。此外，受限于局部感受野，CNN 往往无法将局部特征与全局依赖相结合，从而显着影响整个图像中微小裂缝的检测精度。为了解决分割微小裂缝中的这些问题，提出了一种具有注意力机制的多尺度特征融合网络，称为“Tiny-Crack-Net”（TCN）。修改后的残差网络用于捕捉微小裂缝的局部特征。然后将双重注意力模块合并到架构中，以更好地将微小裂缝与背景分开。还，实施了多尺度融合操作以保留微小裂缝的边缘细节。最后，提出了交叉熵和相似性的联合学习损失，以缓解由代表微小裂缝的像素的严重类别不平衡引起的收敛性差。通过上述安排，网络对微小裂缝的分割能力显着增强，“Tiny-Crack-Net”在开源数据集上实现了 87.96% 的 Dice 相似系数，至少高于 5.84%。六个尖端网络的那些。现场测试结果验证了“Tiny-Crack-Net”的有效性和鲁棒性，结果表明宽度为0.05 mm或更宽的裂缝的交集（IOU）达到91.44%。