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

Pavement crack detection method based on pseudo twin dense connection attention mechanism

A technology of dense connections and detection methods, applied in neural learning methods, biological neural network models, image analysis, etc., can solve the problem of fewer detection models for mixed cracks

Active Publication Date: 2021-05-18
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there are relatively few studies on detection models for mixed fractures.

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
  • Pavement crack detection method based on pseudo twin dense connection attention mechanism
  • Pavement crack detection method based on pseudo twin dense connection attention mechanism
  • Pavement crack detection method based on pseudo twin dense connection attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] see Figure 1-Figure 3 , this embodiment provides a pavement crack detection method based on a pseudo-twin dense connection attention mechanism, including the following steps:

[0041] Step S1, obtaining a data set, and dividing the data set into a training set and a test set;

[0042] Specifically, in this implementation, first search open-source databases on GitHub.

[0043] The search keyword is set to "vement crack detection", and for the selection of the project, this embodiment selects two language-marked projects (Python, C++) as keywords, and the sorting mark is "most star".

[0044] Finally, five public datasets were collected, namely: Crack500, Crack200, CFD, AEL and GAPs384.

[0045] Step S2, preprocessing the pictures in the training set;

[0046] Specifically, since each data set has its own characteristics, data set preprocessing is required before use. Among them, Crack500 and Crack200 belong to the coarse crack data set, GAPs384 belongs to the fine c...

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 pavement crack detection method based on a pseudo twin dense connection attention mechanism. The pavement crack detection method comprises the following steps: S1, acquiring a data set; S2, preprocessing the pictures in the training set; s3, constructing a pseudo twin residual network; s4, designing a loss function of the pseudo twin residual network, training the pseudo twin residual network until the loss function converges, and storing the model; and S5, detecting the crack of the picture in the test by using the model obtained in the step S4. According to the method, a traditional Encoder-Decoder model is improved, so that a detection result under a mixed background, namely a mixed data set, can be effectively detected; and the loss function is optimized, so that the method is more suitable for a pavement crack background.

Description

technical field [0001] The invention relates to the field of image segmentation, in particular to a pavement crack detection method based on a pseudo twin densely connected attention mechanism. Background technique [0002] As the area of ​​the road surface increases year by year, the manpower and energy invested in the inspection and maintenance of the road surface are also increasing year by year. Not only will there be certain errors in the artificial detection of road surface cracks, but also the detection on the road surface will increase the danger of the inspection personnel. Therefore, an automated system is designed. A pavement crack detector is necessary. The purpose of automatic pavement crack detection is to output the detection results by inputting a pavement picture or video sequence. Although the traditional method can also realize automatic detection, the efficiency and detection accuracy of the traditional method have always been flawed, so most of the curre...

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): G06T7/00G06N3/04G06N3/08G06T7/194
CPCG06T7/0008G06T7/194G06N3/04G06N3/08G06T2207/30132
Inventor 王彩玲陈良全蒋国平
Owner NANJING UNIV OF POSTS & TELECOMM
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