Abstract

Cracks indicates the real time deformity in concrete structures. It is characterized as discontinuity in terms of shape and size of the concrete structures. To ensure the structural health and safety, crack detection is an important task. The traditional methods of crack detection include visual introspection, ultrasonic and hand-held testing of crack. These methods require a high human intervention along with an experienced and skilled inspector. Moreover, these methods are subjective and time-consuming process which fails to identify the crack of the complex concrete structures properly. To overcome these issues, a GrabCut with improved Sobel has been proposed for automatic crack detection from the concrete structures. The proposed method works as a two-step model where cracks regions are segmented in the first step and a precise crack assessment is performed in the second step. Furthermore, to improve the efficacy of Sobel, the mask is modified with the aid of local variance of the image instead of using conventional mask of the filter. For the experimentation study, the images of self-prepared concrete sample have been acquired. The effectiveness of the proposed method has been compared with respect to various pre-existing methods like Sobel, Prewitt, Robert, LoG, Zero Cross, and Canny. The comparative qualitative result exhibits that the proposed method surpasses the outcomes of the other pre-existing methods. Additionally, for easy implementation and application point of view a web tool of the proposed method has been developed. The web tool can be utilised by the civil infrastructure maintenance agency and construction engineers in the task of structure maintenance.

中文翻译：

---

在混凝土结构中使用图像处理技术的自动裂缝检测和网络工具

摘要

裂缝指示混凝土结构的实时变形。它的特点是混凝土结构的形状和尺寸不连续。为了保证结构的健康和安全，裂纹检测是一项重要的工作。传统的裂纹检测方法包括目视内省、超声波和手持式裂纹检测。这些方法需要大量的人工干预以及经验丰富且技术熟练的检查员。此外，这些方法是主观且耗时的过程，无法正确识别复杂混凝土结构的裂缝。为了克服这些问题，提出了采用改进的 Sobel 的 GrabCut，用于自动检测混凝土结构的裂缝。该方法采用两步模型，第一步对裂纹区域进行分割，第二步进行精确的裂纹评估。此外，为了提高Sobel的效率，借助图像的局部方差来修改掩模，而不是使用传统的滤波器掩模。为了进行实验研究，获取了自制混凝土样品的图像。所提出方法的有效性已与各种现有方法（如 Sobel、Prewitt、Robert、LoG、Zero Cross 和 Canny）进行了比较。比较定性结果表明，所提出的方法优于其他现有方法的结果。此外，为了便于实施和应用，我们开发了所提出方法的网络工具。土木基础设施维护机构和建筑工程师可以在结构维护任务中使用该网络工具。