Crack detection method based on improved encoding and decoding network model

A network model and detection method technology, applied in biological neural network models, neural learning methods, character and pattern recognition, etc. problem, to achieve the effect of improving the detection effect

Pending Publication Date: 2021-04-23
CHANGZHOU UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is: in order to overcome the deficiencies in the prior art, the present invention provides a crack detection method based on an im

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
  • Crack detection method based on improved encoding and decoding network model
  • Crack detection method based on improved encoding and decoding network model
  • Crack detection method based on improved encoding and decoding network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention is described in further detail now in conjunction with accompanying drawing. These drawings are all simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, so they only show the configurations related to the present invention.

[0042] A crack detection method based on an improved codec network model. Firstly, the crack image data set is collected for marking, and then the number of data sets is multiplied by data enhancement to reduce the risk of overfitting. Finally, the test data is sent to the improved codec network model. Conduct experiments to get results; in terms of network improvement: speed up network training by replacing the backbone network with a pre-trained ResNet34.

[0043] The specific plan is as follows:

[0044] 1. Data preprocessing, such as figure 1 shown.

[0045] S1. Data acquisition: Choose to use smart phones and other devices to capture crack images on br...

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 crack detection method based on an improved coding and decoding network model, and the method comprises the steps: transmitting a data set after data preprocessing to an encoder for feature extraction, enabling the model to employ an encoder decoder structure, enabling a trunk network to be ResNet34 pre-trained in ImageNet, adding cascaded dual-core cavity convolution to an intermediate layer of the encoder, so that more cracks in the underlying semantic information and spatial structure information are retained and merged in the jump connection stage, the multi-core pooling module is introduced in the decoder stage to obtain crack information of different sizes and fuse the crack information, compared with information obtained through a single pooling layer, the information obtained through the method is more global, and fine cracks in a picture can be effectively detected. Experiments are carried out on different data sets, comparison experiments are carried out with other mainstream algorithm models at the same time, results show that the method provided by the invention has high precision in effect, and the defects of a traditional method are overcome.

Description

technical field [0001] The invention relates to the technical field of safety monitoring image processing, in particular to a crack detection method based on an improved codec network model. Background technique [0002] Concrete surface crack detection is an important part of concrete building structure health monitoring. If cracks appear on the surface of the building and continue to extend, it will lead to structural failure in the long run, resulting in serious economic losses and casualties. The process of manual detection of cracks is time-consuming and laborious, and there are certain subjective judgment factors that affect the detection accuracy. It is also difficult to achieve manual detection of high-rise buildings, bridges and other structures. Therefore, the method of automatic detection of concrete cracks based on image processing technology has become a hot spot of current research. [0003] With the rapid development of information technology, researchers pr...

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
IPC IPC(8): G06T7/00G06T3/40G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06T7/0004G06T3/4007G06N3/08G06T2207/20081G06T2207/30132G06V10/44G06N3/045G06F18/241
Inventor 徐守坤杨秋媛李宁石林庄丽华王雨生
Owner CHANGZHOU UNIV
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