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

Dam crack image data enhancement method based on deep convolution generative adversarial network

An image data, depth convolution technology, applied in image enhancement, image data processing, image analysis and other directions, can solve the problem of insignificant enhancement effect, unable to meet the requirements of category and data volume, low image quality, etc., to increase the feature The number of graph channels, the effect of mitigating performance degradation, and simplifying the network structure

Active Publication Date: 2020-04-03
HOHAI UNIV +3
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Common data enhancement methods include flipping, rotating, zooming, cropping, translating, random data erasure, etc., but the enhancement effect is not obvious, and the quality of the enhanced image is not high, which cannot meet the requirements of the training sample category in the dam crack image recognition technology. and data volume requirements

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
  • Dam crack image data enhancement method based on deep convolution generative adversarial network
  • Dam crack image data enhancement method based on deep convolution generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In the following, the present invention will be further clarified with reference to specific examples. It should be understood that these examples are only used to illustrate the present invention and not to limit the scope of the present invention. After reading the present invention, those skilled in the art will understand various equivalent forms of the present invention. All the modifications fall within the scope defined by the appended claims of this application.

[0026] On the basis of the basic data enhancement operation on the dam crack image data, the real crack image data of the dam is used as input, and an image generator (DGM) based on the deep convolution generation counter network is used to generate the dam crack image. The structure is like figure 1 As shown, an image discriminator (DDM) based on a deep convolution generation confrontation network is used to judge the quality of the image generated by the DGM. The discriminator structure is as follows fi...

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 dam crack image data enhancement method based on a deep convolution generative adversarial network, and the method comprises the steps: (1), taking dam real crack image dataas the input, and generating a dam crack image; (2) judging the dam crack image generated in the step (1). According to the invention, on the basis of basic data enhancement operation, an image generator (DGM) based on a deep convolution generative adversarial network is used to generate the crack image, an image discriminator (DDM) based on a deep convolution generative adversarial network is used for discriminating the quality of a generated image, and a new dam crack sample data set is generated according to original small sample dam crack data, thereby meeting the requirements for the typeand data size of a training sample in the dam crack image recognition technology.

Description

Technical field [0001] The invention belongs to the technical field of engineering safety monitoring, and particularly relates to a method for enhancing dam crack image data based on a deep convolution generation counter network. Background technique [0002] During long-term operation, hydraulic structures are affected by various factors such as light, water flow impact, and temperature changes, and are prone to functional degradation and surface cracks. These problems may affect the normal operation of the dam. Dam crack detection is an important way to discover hidden dangers of dam safety in time. Traditional dam crack image recognition mainly relies on human vision, but the efficiency and accuracy of crack detection and recognition will decrease during long-term work. With the development of digital image processing technology, the traditional manual method of detecting image cracks has been gradually replaced by machine vision-based crack detection methods, becoming one of...

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): G06T5/00
CPCG06T5/00G06T2207/10004G06T2207/20081G06T2207/20084
Inventor 程杨堃李艳伟毛莺池许后磊葛恒于青坤字林吕昂晋良军陈亚军
Owner HOHAI 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