Abstract This paper proposes an automatic crack detection, localization, and quantification method using the integration of a faster region proposal convolutional neural network (Faster R-CNN) algorithm to detect crack regions. The regions were located using various bounding boxes and a modified tubularity flow field (TuFF) algorithm to segment the crack pixels from the detected crack regions. A modified distance transform method (DTM) was used to measure crack thickness and length in terms of pixel measurement. To validate the proposed method, 100 images were taken in different places with complex backgrounds containing different angles and distances between the camera and the objects. The results obtained from the Faster-R-CNN-based crack damage detection had a 95% average precision. The pixel-level segmentation performance of the modified TuFF algorithm exhibited an authentic outcome, with 83% intersection over union. Finally, the modified DTM algorithm provided 93% accuracy with respect to crack length and thickness with a 2.6 pixel root mean square error.

中文翻译：

---

使用深度学习跨复杂背景的混合像素级混凝土裂缝分割和量化

摘要 本文提出了一种自动裂纹检测、定位和量化方法，该方法使用更快的区域提议卷积神经网络（Faster R-CNN）算法的集成来检测裂纹区域。使用各种边界框和改进的管状流场 (TuFF) 算法定位区域，以从检测到的裂缝区域分割裂缝像素。改进的距离变换方法 (DTM) 用于根据像素测量来测量裂纹厚度和长度。为了验证所提出的方法，在具有复杂背景的不同地方拍摄了 100 张图像，其中包含不同角度和相机与物体之间的距离。从基于 Faster-R-CNN 的裂纹损伤检测中获得的结果具有 95% 的平均精度。修改后的 TuFF 算法的像素级分割性能表现出真实的结果，83% 的交集超过并集。最后，改进的 DTM 算法在裂纹长度和厚度方面提供了 93% 的准确度，误差为 2.6 像素均方根。