Papers by Keyword: Crack Inspection

Abstract: The desire to ensure safety of the infrastructure such as bridge, dam, and tunnel while reducing maintenance time and costs in the civil engineering applications emerged. Image processing techniques may well represent a next step in the development of smart monitoring of crack. In this paper, a method to inspect the surface crack in a concrete structure using 2D image has been proposed. The standardized crack specimen which has different crack widths was manufactured and the crack images were taken at the object distance from 5 to 60 m with 5 m step. The characteristics of the several edge operators such as Sobel, Prewitt, Robert, Canny and LoG to recognize the crack were analyzed according to the object distance.

Abstract: Crack inspection of bridges is indispensable to maintain the public traffic safety. It is conventionally carried out by specialists through visual inspection manually. Considering the efficiency and security, digital image processing technique is used to inspect the bridges. After analyzing many representative images of cracks, this paper presents the particular region feature, gray value feature and contour feature of cracks on the bridges’ surface and obtains hundreds of cracks’ feature values. We select some representative data to identify cracks from images according to these cracks’ feature values. The software has been developed to distinguish whether cracks exist in an image, and to extract automatically the existent cracks by means of MATLAB. We present experimental results obtained to prove these methods.