Unlock instant, AI-driven research and patent intelligence for your innovation.

Building surface crack detection method based on U-Net

A surface crack and detection method technology, applied in the field of detection, can solve problems such as false detection and difficulty in ensuring data, and achieve the effect of improving segmentation accuracy, ensuring robustness and invariance, and powerful real-time data enhancement

Inactive Publication Date: 2019-07-26
FUZHOU UNIV
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For ordinary sensory systems, such as fiber optic sensor systems, it is difficult to ensure that the data obtained by numerous sensors represent actual structural defects, because noisy signals or sensory system failures may lead to false detections

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Building surface crack detection method based on U-Net
  • Building surface crack detection method based on U-Net
  • Building surface crack detection method based on U-Net

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The technical solution of the present invention will be specifically described below in conjunction with the accompanying drawings.

[0029] The present invention first constructs a small data set. A total of 30 raw images containing different types of cracks were obtained under various conditions to enhance the adaptability of the neural network. After annotating the original images, they are cropped into small patch images with a resolution of 512×512 pixels for training, validation and testing processes. Utilizes the improved U-net's powerful network architecture to detect cracks on building surfaces. The input image size of our network is 512×512 pixels, and the output is a mask image showing each pixel class. Using the sliding window technique, the model can handle images of larger size. The proposed method without post-processing achieves acceptable accuracy in various complex backgrounds, and outperforms traditional edge detection methods.

[0030] Concrete t...

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

No PUM Login to View More

Abstract

The invention relates to a building surface crack detection method based on U-Net. Firstly, using a camera and an unmanned aerial vehicle for collecting 30 original images containing cracks; marking acrack area in each original image and storing annotations as grayscale image label files; preprocessing the images, selecting 200 images as a data set, and randomly dividing the data set into a training set, a verification set and a test set according to a proportion; adopting a data enhancement method to process a manufactured data set, and then sending the data set to a U-net network for training, after 30 rounds of iterative training, the accuracy of the U-net model on the test set is 99.56%; and finally carrying out crack detection by using the trained model. The method can adapt to crackdetection under different conditions, the complexity of arranging a large number of sensors is omitted, cracks can be automatically and accurately recognized and detected, and the method plays an important role in improving the accuracy and efficiency of building surface crack detection.

Description

technical field [0001] The invention belongs to the field of detection methods, in particular to a method for detecting cracks on the surface of buildings based on U-Net. Background technique [0002] Building damage will not only increase the maintenance period, materials, labor, and cost, but also affect the overall operational efficiency of civil infrastructure and cause safety hazards. A large part of these damages are manifested as cracks or damage on the surface. On the one hand, it is easy to cause accidents. On the other hand, it indicates that there are hidden dangers in the structure. If measures are not taken in time, it may cause extremely serious consequences. The solution to this is to establish various laws and regulations, study structural non-destructive testing technology, determine whether the safety and durability of the structure meet the requirements of use, and on this basis, timely take reinforcement, reinforcement and other treatment measures to impr...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00
CPCG06T7/0004G06T2207/20081G06T2207/20084G06T2207/30132
Inventor 吴丽君宋春歌陈志聪纪金树周海芳程树英林培杰段博曦
Owner FUZHOU UNIV