Crack damage is commonly observed for civil structures and infrastructure in service. The recent years have witnessed an excessive utilization of deep learning models for realizing autonomous and machine-vision based crack detection. Given this trend, this paper recognizes two entwined challenges: the preparation of large-scale training data and the detection of simple crack damage amid complex scenes. To address them, a novel data augmentation technique is proposed considering crack characteristics in images for realizing deep transfer learning using very small datasets. Numerical experimentation is conducted based on two types of crack datasets (concrete structures and asphalt pavement), each of which has only tens of images containing complex scenes. When evaluating the performance, a sliding-window based rating scheme is proposed, which is much stricter than the conventional bounding-box based approach. Quantitative performance analysis shows the acceptable performance (e.g., an overall accuracy of 93.81%, an F-2 score of 74.4%, and a very high recall of 91% for the crack detection in concrete images). The result demonstrates the effectiveness of the proposed data augmentation method and the superior transferability if the transfer learning is carried out through a fully fine-tuned training process.

中文翻译：

---

用于小规模数据集裂纹损伤深度迁移学习的尺度空间数据增强

在使用中的土木结构和基础设施中，通常会观察到裂纹损坏。近年来，人们过度使用深度学习模型来实现自主和基于机器视觉的裂纹检测。鉴于这一趋势，本文认识到两个相互交织的挑战：大规模训练数据的准备和复杂场景中简单裂纹损伤的检测。为了解决这些问题，考虑到图像中的裂缝特征，提出了一种新的数据增强技术，以使用非常小的数据集实现深度迁移学习。数值实验基于两种类型的裂缝数据集（混凝土结构和沥青路面）进行，每个数据集只有几十张包含复杂场景的图像。在评估性能时，提出了基于滑动窗口的评级方案，这比传统的基于边界框的方法严格得多。定量性能分析显示了可接受的性能（例如，总体准确率为 93.81%，F-2 得分为 74.4%，混凝土图像裂缝检测的召回率为 91%）。如果通过完全微调的训练过程进行迁移学习，结果证明了所提出的数据增强方法的有效性和优越的可迁移性。