Concrete crack width measuring method based on U-net CNN image recognition and pixel calibration

A technology of pixel calibration and crack width, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of low detection efficiency and difficulty in adapting to the large and complex monitoring data, and achieve simple structure, complete and clear crack identification process, Approach intelligent rigorous effect

Pending Publication Date: 2020-09-01
上海深物控智能科技有限公司
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is easily affected by human subjective factors such as the technology and experience of test professionals, and the detection efficiency is low, so it is difficult to adapt to the situation where there are many and complicated monitoring data for the health status assessment of modern bridge structures.

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
  • Concrete crack width measuring method based on U-net CNN image recognition and pixel calibration
  • Concrete crack width measuring method based on U-net CNN image recognition and pixel calibration
  • Concrete crack width measuring method based on U-net CNN image recognition and pixel calibration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] Take 100 crack photographs taken on the scene of a bridge survey in Jiangsu Province as an example below to illustrate the specific implementation process of the present invention.

[0068] (1) Check the photo properties to obtain the focal length parameters of each photo, and mark the photos in combination with the shooting distance parameters measured by the laser rangefinder during on-site shooting.

[0069] (2) Randomly divide the photos into a training set of 70 and a test set of 30. according to figure 2 The layer structure shown, constructs the U-net CNN network. It is divided into 9 layers, and each layer is composed of convolution layer, regularization layer, ReLU activation function, group pooling layer, deconvolution layer, and Softmax activation function. The convolution layer realizes feature extraction; the regularization layer limits the output of each layer to a fixed distribution, which speeds up the network training; the ReLU activation function rea...

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 discloses a concrete crack width measuring method based on U-net CNN image recognition and pixel calibration. The method comprises the following steps: using a single lens reflex and a laser range finder to obtain a plurality of pictures of concrete structure surface cracks with known shooting distances and focal lengths; training a U-net CNN network to realize automatic identification of cracks and extract crack forms; marking the crack width direction, and extracting the number of pixels in the crack width direction; carrying out an indoor target experiment, constructing a nonlinear model of the shooting distance, the focal length and the pixel actual size, and calibrating the pixel actual size; and calculating the crack width in combination with the pixel size in the crackwidth direction and the calibrated pixel actual size. Compared with the prior art, the method is novel, intelligent, efficient and accurate in width parameter identification.

Description

technical field [0001] The invention belongs to the field of concrete structure disease detection and monitoring, and is an image recognition-based method for accurately identifying the width of structural surface cracks. Specifically, it relates to crack width measurement based on U-net CNN image crack automatic recognition and SLR camera pixel size marking method. Background technique [0002] Bridge diseases mainly include various forms such as cracks, denudation, corrosion of steel bars, structural damage, and damage caused by uneven settlement of the foundation. Among them, cracks are undoubtedly the most common and common disease, and cracks can be divided into transverse cracks in the bottom plate, longitudinal cracks in the bottom plate, longitudinal cracks in the web, vertical cracks in the web, oblique cracks in the web, etc. according to the location and orientation of the cracks. The identification of cracks, the extraction and recording of morphological feature...

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): G06T7/80G06T7/13G06T7/11G06T7/00G06N3/08G06N3/04
CPCG06T7/97G06N3/08G06T7/80G06T7/11G06T7/13G06T7/0002G06T2207/30204G06N3/045
Inventor 钱辰
Owner 上海深物控智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap