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

Heuristic multi-way line repairing method based on pattern recognition and optimal distribution

An optimal allocation and pattern recognition technology, applied in the fields of artificial intelligence, computer vision, and crack extraction, it can solve problems such as poor timeliness and reliability, impact of crack detection, and severe labor detection consumption, so as to improve accuracy and connection accuracy. rate and improve the connection accuracy

Pending Publication Date: 2020-11-27
ZHENGZHOU UNIVERSITY OF AERONAUTICS
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The background of cracks is complex and diverse. General manpower detection is not only expensive but also has poor timeliness and reliability. Therefore, the technology of automatic crack detection by computer has become one of the research hotspots in this technical field.
Existing crack detection is easily affected by factors such as light and shadow, and crack extraction is usually multiple intermittent curves, which has a great impact on crack detection

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
  • Heuristic multi-way line repairing method based on pattern recognition and optimal distribution
  • Heuristic multi-way line repairing method based on pattern recognition and optimal distribution
  • Heuristic multi-way line repairing method based on pattern recognition and optimal distribution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] A heuristic polyline patching method based on pattern recognition and optimal allocation:

[0047] Crack identification and measurement is to extract the main fracture line and bifurcation line from the captured image, and measure the cosine similarity of the fracture image.

[0048] Step 1: Collect crack images, perform semantic extraction on crack images, extract cracks in crack images, and obtain binary images of trunk cracks and bifurcation line cracks.

[0049] Firstly, crack extraction is performed on the crack image, and finally a binary image is obtained. The crack extraction method is a common technology, and there is no restriction in this step, and the crack extraction can also be performed based on the DNN convolutional neural network. The present invention takes the semantic segmentation DNN as an example: the label is manually marked, and the trunk and bifurcation lines are marked for the multi-line crack image, which is represented by a pixel value of 1,...

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 heuristic multi-branch line repairing method based on pattern recognition and optimal distribution, and the method comprises the steps: carrying out the semantic extraction of a crack image, extracting a crack in the crack image, and obtaining a trunk crack binary image and a branch line crack binary image; performing connected domain analysis on the trunk crack binary image and the bifurcation line crack binary image, and performing crack subgraph cutting operation and affinity measurement on all connected domains in the trunk crack binary image and all connected domains in the bifurcation line crack binary image respectively; and calculating the connection affinity of the to-be-analyzed crack subgraph and the to-be-connected crack subgraph, and connecting the two crack subgraphs of which the connection affinity is greater than a set threshold with the nearest crack endpoint in the crack image. According to the invention, the accuracy of crack connection is improved.

Description

technical field [0001] The invention relates to the technical fields of computer vision, artificial intelligence and crack extraction, in particular to a heuristic multi-prong repair method based on pattern recognition and optimal distribution. Background technique [0002] The background of cracks is complex and diverse, and general manpower detection is not only costly but also poor in timeliness and reliability. Therefore, the technology of automatically detecting cracks by computer has become one of the research hotspots in this technical field. Existing crack detection is easily affected by factors such as light and shadow, and crack extraction is usually multiple intermittent curves, which has a great impact on crack detection. For the fracture interruption phenomenon detected by the previous method, a method is needed to repair it, so as to reduce its influence on the fracture analysis. Contents of the invention [0003] The object of the present invention is to 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): G06K9/00G06K9/34G06K9/46G06K9/62G06N3/04
CPCG06V20/00G06V10/267G06V10/40G06N3/045G06F18/22G06F18/214Y02P90/30
Inventor 廖歆王乐乐王战伟
Owner ZHENGZHOU UNIVERSITY OF AERONAUTICS
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