Image-based crack detection method and system, computer device and storage medium
A detection method and image technology, applied in the field of image processing, can solve the problems of inaccurate crack measurement length and low efficiency, and achieve the effects of low quantization error rate, high detection efficiency, efficient and accurate detection
Pending Publication Date: 2022-03-11
GUANGZHOU UNIVERSITY
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In view of at least one technical problem in the above-mentioned crack detection related technologies, such as low efficiency and inaccurate crack measurement length, the purpose of the present invention is to provide an image-based crack detection method, system, computer device and storage medium
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0046] In this example, refer to figure 1 , the image-based crack detection method includes the following steps:
[0047] S1. Obtain an image to be detected;
[0048] S2. Establish a PANet model;
[0049] S3. Input the image to be detected to the PANet model;
[0050] S4.PANet model processes the image to be detected, and outputs crack pixels and background pixels;
[0051] S5. The crack pixels are processed by the A* algorithm, and the crack length is output.
[0052] In step S1, the cracked concrete, metal, plastic, wood or tunnel lining surface may be photographed in advance or on-site to obtain an image to be detected.
[0053] In step S2, the structure of the established PANet model is as follows figure 2 shown. refer to figure 2 , the PANet model includes a backbone unit composed of a ResNet-101 network, a region extraction network RPN, an ROI alignment layer, an adaptive feature pool AFP, a mask branch, and a semantic branch FCF. The backbone unit, region extr...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an image-based crack detection method and system, a computer device and a storage medium, and the method comprises the steps: inputting a to-be-detected image into a PANet model, processing the to-be-detected image through the PANet model, outputting a crack pixel and a background pixel, processing the crack pixel through an A * algorithm, and carrying out the processing of the background pixel through an A * algorithm; outputting the crack length and the like. According to the method, the crack length is detected by performing image analysis on the to-be-detected image, so that the method has relatively high detection efficiency; according to the method, the PANet model is expanded by using the A * algorithm, inaccuracy caused by crack discontinuity, image skeletonization and the like can be reduced, crack features are separated from the to-be-detected image, and the A * algorithm has a relatively low length and width quantization error rate, so that the length and width of the crack in the to-be-detected image can be accurately analyzed and obtained; therefore, efficient and accurate crack detection is realized. The method is widely applied to the technical field of image processing.
Description
technical field [0001] The invention relates to the technical field of image processing, in particular to an image-based crack detection method, system, computer device and storage medium. Background technique [0002] Crack detection is required in fields such as construction engineering. The task of crack detection is not only to find cracks, but also to care about the length of cracks and other data. In the current crack detection related technologies, crack detection is mainly performed by instruments such as flaw detectors. The instrument operation process is complicated, and it may need to use toxic penetrants and other materials to assist the detection process, so the efficiency is low and it is dangerous. In terms of detecting crack length data, the current crack detection related technologies generally use the length measurement method to determine the size of the flaw according to the flaw wave height and the moving distance of the probe. In the length measurement...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/194G06T7/62G06T7/155G06V10/25G06V10/44G06V10/764G06V10/80G06V10/82G06K9/62G06N3/04
CPCG06T7/194G06T7/62G06T7/155G06T2207/20084G06T2207/20104G06T2207/20112G06N3/045G06F18/2415G06F18/253
Inventor 蔡长青刘爽
Owner GUANGZHOU UNIVERSITY