Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

CNN-deep-learning-based bridge-crack detecting and positioning method

A technology of deep learning and positioning method, which is applied in the field of image processing and computer vision, can solve problems such as crack detection and positioning in color images, and achieve good generalization ability, strong adaptability, and fast processing speed

Active Publication Date: 2017-06-30
SHAANXI NORMAL UNIV
View PDF5 Cites 60 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that traditional image processing algorithms cannot directly detect and locate cracks in color images, the present invention provides a bridge crack detection and positioning method based on CNN deep learning

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
  • CNN-deep-learning-based bridge-crack detecting and positioning method
  • CNN-deep-learning-based bridge-crack detecting and positioning method
  • CNN-deep-learning-based bridge-crack detecting and positioning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] The main task of the invention is to detect and locate bridge cracks for pictures of bridge cracks with colors, different background textures and different materials. combine Figure 1-Figure 2 , a bridge crack detection and positioning method based on CNN deep learning method, comprising the following steps:

[0058] The first step is to use the camera sensor to collect a certain number of bridge crack pictures, and normalize all the pictures to 1024*1024 resolution pictures;

[0059] In the second step, use a fixed-size window of W*H to slide on the bridge crack image without overlapping, and at the same time, use the small slice of the bridge crack image covered by the sliding window as a ROI region of interest. Among them, the small slice image containing the bridge background is called the bridge background surfel, and the small slice containing the bridge crack is called the bridge crack surfel. The specific process is shown in the following formula:

[0060] im...

Embodiment 2

[0086] Refer below Figure 1-Figure 4 , using specific data to describe the present invention in detail:

[0087] The first step is to use image acquisition equipment to collect five kinds of bridge crack pictures with different background textures and different materials. The total number of collected pictures is 2000, and all pictures are normalized into pictures with a resolution of 1024*1024;

[0088] In the second step, the 2000 pictures are divided into 2 data sets, artificial amplification data set and test data set, each data set has 1000 pictures;

[0089] The third step is to use a W*H fixed-size window to slide non-overlapping 1000 pictures in the artificially amplified data set, and at the same time, use the small slice of the bridge crack picture covered by the sliding window as a ROI region of interest. Among them, the small slice image containing the bridge background is called the bridge background surfel, and the small slice containing the bridge crack is cal...

Embodiment 3

[0107] This embodiment discloses a method for constructing a DBCC classification model based on CNN deep learning, comprising the following steps:

[0108] (1) Convolute and sum the input original picture with all the convolution kernels in the first convolutional layer in a convolutional manner to obtain the feature map of the first convolutional layer;

[0109] (2) Add a Relu activation function after the first convolutional layer;

[0110] (3) After the first convolutional layer, add a local response value normalization layer for picture brightness correction, and the local response value normalization layer improves the recognition effect of the network;

[0111] (4) Downsample the feature map of the first convolutional layer in the first pooling layer, reduce the resolution and select excellent features as the feature map of the first pooling layer;

[0112] (5) On the second convolutional layer, the feature map of the first pooling layer and all the convolution kernels ...

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 CNN-deep-learning-based bridge-crack detecting and positioning method, comprising: first, using the window sliding algorithm to cut a bridge image into smaller bridge crack surface element images and bridge crack background element images; and at the same time, based on the CNN-based DBCC classification model, identifying the bridge crack background element images and the bridge crack surface element images; then, in combination with the window sliding algorithm, performing bridge crack detecting and positioning on the entire bridge crack image; and finally, speeding up the algorithm through the search strategy of combining the image pyramid and ROI. Compared with the traditional crack detecting and positioning method, not only the bridge crack detecting and positioning method of the invention achieves a better detection effect and a stronger generalization ability, but also the method is performed directly based on color images, an impossible situation for the traditional crack detecting and positioning method.

Description

technical field [0001] The invention belongs to the fields of image processing and computer vision, and in particular relates to a bridge crack detection and positioning method based on CNN deep learning. Background technique [0002] As the hub of traffic systems such as roads, highways, and railways, bridges need to be regularly evaluated for their health status, and bridge cracks, as one of the most important bridge diseases, seriously affect the safe operation of bridges, and more serious ones will occur. Bridge crash accident. Therefore, it is very important to effectively detect and locate bridge cracks. [0003] In recent years, many scholars have carried out research on crack detection methods, but at present the main research is based on traditional image processing algorithms for crack detection. For example, the patent document whose publication number is CN103528527A discloses an automatic measurement method of crack size based on region selection, which is bas...

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): G06T7/00G06N3/04G06N3/08
CPCG06N3/08G06T7/0002G06T2207/10024G06T2207/20021G06T2207/20081G06N3/045
Inventor 李良福马卫飞李丽张玉霞
Owner SHAANXI NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com