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

Deep learning-based circle detection method and application thereof

A technology of deep learning and circle detection, which is applied in the field of image processing, can solve the problems of small amount of data and low precision, and achieve the effect of improving precision, high precision and stable performance

Pending Publication Date: 2022-01-28
YIJIAHE TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Purpose of the invention: Aiming at the above-mentioned deficiencies, the present invention proposes a circle detection method based on deep learning and its application, and designs a new algorithm flow to solve the influence of problems such as illumination, less data volume, and low precision

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
  • Deep learning-based circle detection method and application thereof
  • Deep learning-based circle detection method and application thereof
  • Deep learning-based circle detection method and application thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0048] figure 1 Be the flow chart of the present invention, as figure 1 As shown, the circle detection method based on deep learning of the present invention comprises the following steps:

[0049] (1) Design feature labeling rules:

[0050] The existing model segmentation scheme is to extract the entire area of ​​the circle. This paper abandons this extraction method and only extracts the circle outline. The data features acquired by this method are relatively concentrated, and there are few features that need to be learned, which can better apply to the amount of data. Less model training; when marking, use continuous line segments to mark the circular outline of the collected original image to obtain image samples, and set the line width to 7pixel;

[0051] (2), build deep learning model, and adopt step (1) to obtain image sample to train...

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 deep learning-based circle detection method and application thereof. The method comprises the following steps: (1) marking a circle contour on an original image as an image sample; (2) constructing a deep learning model and performing training by utilizing the image sample obtained in the step (1) to obtain an image segmentation model; and (3) segmenting an image to be detected by using the image segmentation model obtained in the step (2) to obtain a corresponding circle contour, and performing circle fitting on the circle contour to obtain a final circle. According to the method, on the basis of arc segmentation, the least square fitting and ransac algorithm screening are combined, fitting errors can be effectively avoided, the judgment condition of screening is searching for the maximum coverage area of a fitting circle, the precision is high, and the performance is stable.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a circle detection method based on deep learning and its application. Background technique [0002] In order to realize the intelligent operation robot to carry out grounding knife switch and handcart operation on the KYN28 high-voltage switchgear of the substation, the robot needs to be equipped with a self-designed mobile platform as the actuator. The actuator is equipped with a circular telescopic rod as the contact piece. When the telescopic rod needs to be aimed at the circular switch of the grounding knife switch or handcart, it is necessary to measure the distance between the center of the target circle and the center of the telescopic rod. [0003] In the past, circle detection methods were mostly based on binary image processing. The main problem faced by this type of method is the influence of illumination. When the illumination changes greatly, the performance...

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): G06T7/11G06T7/12G06T7/66
CPCG06T7/11G06T7/12G06T7/66G06T2207/20081G06T2207/20084G06T2207/20061
Inventor 王卓毛成林项导
Owner YIJIAHE TECH CO LTD
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