A bridge crack detection method based on tensor voting

Abstract

The invention discloses a bridge crack detection method based on tensor voting, which mainly solves the problem of false detection of concrete bridge cracks detected based on tensor voting in the prior art. According to the implementation scheme, the method comprises using a computer to read an original bridge image and preprocess the original bridge image; calculating an image gradient based on aSobel operator, and extracting a symbiotic edge and an initial crack seed point of the concrete crack; constructing a rod tensor table and a ball tensor table, and enhancing an initial crack seed point based on a tensor voting method; carrying out non-maximum and small connected domain inhibition on the enhanced seed points to obtain accurate crack seed points; extracting accurate crack seed point crack position, number and length information by using a Prim algorithm; and obtaining crack width information through the accurate crack seed points and the crack symbiotic edges and storing the crack width information to a computer terminal. According to the method, the concrete bridge crack can be detected with high accuracy and real-time performance, and the method can be used for obtainingthe information such as the position, the width, the length and the number of the bridge concrete crack.

Description

technical field [0001] The invention belongs to the technical field of testing, and in particular relates to a method for detecting bridge cracks, which can be used to acquire information such as the position, width, length and quantity of bridge concrete cracks. technical background [0002] The important indicators to measure the degree of bridge concrete disease include data information such as the length, width, and quantity of cracks. The methods for detecting the position, width, and length of bridge concrete cracks include: manual measurement, infrared analysis, and image processing analysis. in: [0003] The manual measurement method is to manually use a vernier caliper to measure the crack width. This method has poor measurement accuracy, low efficiency, and certain dangers. [0004] The infrared analysis method uses infrared rays to detect the width of the crack. This method has the advantages of high detection accuracy and fast detection speed. However, the instr...

AI Technical Summary

Problems solved by technology

However, the Sobel operator has the disadvantages of high time complexity and poor real-time performance in the process of obtaining image edge information, and this method does not take into account the many interferences that exist in practical applications.

Therefore, in practical applications, the accuracy and real-time performance of the detection results are difficult to guarantee.

[0009] To sum up, many methods of detecting concrete cracks using image processing technology have been proposed at home and abroad. Most of them have a large deviation between the detected crack position and the actual position, and the algorithm complexity is high, the anti-interference ability is poor, and the real-time performance and accuracy are poor. Low disadvantages that affect engineering applications

Images