A large crack detection dataset of 2446 manually labeled images is established to cover a wide range of noise and to evaluate the performance of end-to-end deep convolutional networks in detecting cracking. Five state-of-the-art end-to-end deep computer vision architectures for semantic segmentation are trained and evaluated, including Fully Convolutional Network (FCN), Global Convolutional Network (GCN), Pyramid Scene Parsing Network (PSPNet), UPerNet, and DeepLabv3+. For the backbones, the VGG, ResNet, and DenseNet are adopted. Based on the comparison of test set metrics, DeepLabv3+ with the ResNet101 backbone achieved the highest IoU of 0.6298, the highest recall of 0.6834, and the highest F1 score of 0.7732. The influence of database choice and image noise on crack detection performance is reported. Based on the comparison of predicted images, UperNet with ResNet101 backbone shows the highest performance for images with shadings, while DeepLabv3+ with ResNet101 backbone shows the best performance for images with blemishes. The research outcome can provide reference for the application of fast and accurate detection of cracks in civil engineering.

中文翻译：

---

用于裂缝语义分割的深度卷积神经网络

建立了一个包含 2446 张手动标记图像的大型裂纹检测数据集，以覆盖广泛的噪声并评估端到端深度卷积网络在检测裂纹方面的性能。训练和评估了五种最先进的用于语义分割的端到端深度计算机视觉架构，包括全卷积网络 (FCN)、全局卷积网络 (GCN)、金字塔场景解析网络 (PSPNet)、UPerNet、和 DeepLabv3+。对于主干，采用 VGG、ResNet 和 DenseNet。基于测试集指标的比较，DeepLabv3+ 与 ResNet101 主干实现了最高 IoU 0.6298，最高召回率 0.6834，最高 F1 得分 0.7732。报告了数据库选择和图像噪声对裂纹检测性能的影响。根据预测图像的比较，带有 ResNet101 主干的 UperNet 对带有阴影的图像表现出最高的性能，而带有 ResNet101 主干的 DeepLabv3+ 对带有瑕疵的图像表现出最好的性能。研究成果可为快速准确检测土木工程裂缝的应用提供参考。