Structural surface crack detection method based on fusion of image features and Bayesian data

Abstract

The invention discloses a structural surface crack detection method based on fusion of image features and Bayesian data, which comprises the following specific steps: A, a metal member surface video image is collected and a detection image library is built; B, image texture features are calculated by localized binarization; C, two-step support vector machine image crack scanning and collection arecarried out; and D, Bayesian data fusion and decision making are carried out. By adopting video image detection, many areas that are difficult to reach by human beings can be acquired; a computer isadopted to recognize the surface crack of a structural member, thereby greatly reducing the heavy degree of interpretation and improving the crack detection rate; the correlation with the surface light intensity of the member is good, and in comparison with the previous grayscale map or other methods, the texture recognition effects can be improved; timely early warning can be carried out on a crack disease, and a structural disease can be detected early; on the premise of keeping a high scanning speed, a radial basis function support vector machine nerve network is used to maintain a high accuracy rate; and the crack recognition accuracy is improved.

Description

technical field [0001] The invention relates to a method for identifying cracks on the surface of a structure. Background technique [0002] Structural components such as steel structures are one of the important components in a large number of infrastructure fields. With the increase of operation time, due to the lack of sufficient regular inspection and subsequent maintenance, factors such as long-term use, overloading and material aging will inevitably lead to degradation Phenomenon. Structural aging problems such as cracks, fatigue, material embrittlement, wear, and corrosion will lead to functional loss and safety issues of the structure. In addition, structural components are more likely to be damaged in certain high temperature, high pressure, high radiation, acid-base environments. Therefore, the detection of structural components is an important task, which is conducive to slowing down component degradation and increasing structural safety. [0003] For structura...

AI Technical Summary

Problems solved by technology

Compared with manual inspection directly on site, this method has been improved and can reduce personnel risks. However, when judging cracks in video images by naked eyes, due to the low contrast of the surface of structural components and the cracks of structural components are generally small, In addition to real cracks on the surface of structural components, there are structures that are suspected of cracks such as scratches and welds, so it is difficult for inspectors to find early and small cracks

The surface brightness of different structural components is also very different, and the contrast between the crack and the surrounding area is not obvious. The grayscale image processing algorithm is not suitable for this problem. The existing image-based algorithm will have a higher accuracy when detecting cracks in structural components. False Positive and False Negative Rates

Images