A fast identification method for tunnel cracks based on deep learning
A technology of deep learning and identification method, applied in the field of underground engineering, can solve the problem that the length and width information of cracks cannot be directly obtained, and achieve the effect of high precision, robustness and accuracy, and simplify the detection process.
Active Publication Date: 2021-12-28
SHANGHAI TONGYAN CIVIL ENGINEERING TECHNOLOGY CORP LTD
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] Aiming at the problem that the current crack detection method based on deep learning cannot directly obtain the length and width information of cracks, the present invention provides a fast identification method for tunnel cracks based on deep learning, which is used for tunnel crack detection to improve the efficiency of tunnel crack detection. efficiency
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
[0047] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0048] According to attached figure 1 , the present invention is a method for quickly identifying tunnel cracks based on deep learning, characterized in that the method for quickly identifying tunnel cracks includes the following steps:
[0049] S1. Create a deep learning image training set.
[0050] The specific operation of the step S1 is as follows:
[0051] (1) Collect tunnel images. The single-channel tunnel image is obtained by shooting the tunnel surface with mobile detection equipment, and its resolution is generally required to be no less than 2 million pixels, and the image definition is required to be high enough, and the minimum width of the crack in the image is not less than 1 pixel;
[0052] (2) Through manual screening of tunnel images, 50,000 images of cracks and 50,000 images of non-cracks were selected, and the image size was adjusted, a...
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 present invention is a fast recognition method for tunnel cracks based on deep learning, which mainly solves the problem that the current crack detection method based on deep learning cannot directly obtain the length and width information of cracks. The present invention includes steps: S1, creating a deep learning image training set ; S2. Train the deep convolutional neural network model; S3. Use the trained convolutional neural network model to detect the image to be detected and output the predicted label image; S4. Output the detection result according to the predicted label image, including the image category and the coordinates of the crack information and the pixel-level width and length values of cracks; S5, output the disease record results according to the detection results, if there are cracks in the image to be detected, record the image name, the coordinate information of the cracks, and the actual width and length of the cracks; if If there is no crack in the image to be detected, it will not be recorded.
Description
technical field [0001] The invention relates to a method for quickly identifying tunnel cracks, and discloses a method for quickly identifying tunnel cracks based on deep learning, which is applied to the field of underground engineering. Background technique [0002] With the advancement of science and technology and the development of society, the construction scale of tunnel projects is increasing day by day, which greatly facilitates people's travel and life, such as subway tunnels, railway tunnels, road tunnels, etc., and most of the completed tunnel projects have entered the maintenance and repair stage , therefore, as the number of tunnels continues to increase, the operation status and disease detection of tunnel structures become particularly important. During the operation of the tunnel, due to the vibration of the vehicle, the disturbance of the surrounding load, and the change of the surrounding rock pressure, cracks will appear on the surface of the tunnel. The ...
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 Patents(China)
IPC IPC(8): G06K9/20G06K9/34G06N3/04G06N3/08
CPCG06N3/08G06V10/22G06V10/267G06N3/045
Inventor 刘学增刘新根朱爱玺刘海波
Owner SHANGHAI TONGYAN CIVIL ENGINEERING TECHNOLOGY CORP LTD