Bridge surface crack identification method based on image technology

Abstract

The invention relates to a bridge surface crack identification method based on an image technology. The method comprises the following steps: acquiring image information of a bridge surface; three single-pixel width curves of the upper edge, the skeleton and the lower edge of the crack and three-dimensional coordinates of pixel points are obtained through pretreatment; respectively fitting curvilinear functions of the curves of the upper edge, the skeleton and the lower edge of the crack by adopting a three-point interpolation method, solving the crack width in the normal direction of pixel points on the skeleton curve and the second derivative of the curves of the upper edge and the lower edge of the crack, and respectively calculating the variance of the crack width and the second derivative; and multiplying by a corresponding weight coefficient and then adding to construct an authenticity discrimination coefficient, and identifying the authenticity of the crack on the surface of the bridge by setting an authenticity discrimination coefficient threshold value. According to the algorithm, the crack width change value and the edge curve concavity and convexity are used as main characteristic values for distinguishing the authenticity of the crack, the discrimination coefficient is constructed for authenticity identification, the calculation efficiency and the identification accuracy are high, and an effective guarantee is provided for quantitative evaluation of bridge surface concrete crack detection.

Description

technical field [0001] The invention belongs to the technical field of bridge crack detection, and relates to a bridge surface crack recognition method based on image technology. Background technique [0002] In the field of bridge inspection, cracks are the most common disease when assessing the technical condition of bridges. At present, most of the crack detection adopts manual detection, that is, manually identifying the authenticity of cracks, recording the position and direction of cracks, and measuring the width and length of cracks, which is labor-intensive and time-consuming, and the detection efficiency is low. [0003] With the development of detection robot platforms such as drones and image processing technology, attempts have been made to use detection robot platforms to take photos of cracks, and then use image processing technology to analyze and obtain crack information. In the bridge inspection, we often encounter cobwebs, sundries, rain, stains, artificia...

AI Technical Summary

Problems solved by technology

Different from manual inspection of cracks, inspection robots cannot discriminate cracks on the spot like inspectors, and can only "faithfully" take photos according to instructions

Therefore, the use of image technology to identify the authenticity of cracks on photos of attachments or traces on the bridge surface is a key prerequisite for analyzing and obtaining crack-related information. At present, there is no research on the authenticity identification method of bridge surface cracks based on image technology in China.

Images