External thread detection method based on machine vision and real-time detection system

A real-time detection and detection method technology, applied in the direction of instruments, measuring devices, image data processing, etc., can solve the problems of Hough transformation with large calculation amount and small linear parameter range, and achieve reduced calculation amount, good adaptability, and low positioning requirements Effect

Inactive Publication Date: 2020-12-29
上海红马饲料有限公司
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The unique globality and robustness of the Hough transform is used to improve the reliability of the detection process; and the characteristics of the external thread, that is, the small range of parameters of the straight line constituting the profile of the external thread, solve the problem of the large amount of calculation of the Hough transform , can be used as an image processing method for machine vision real-time automatic detection devices to measure the external thread and judge its screwability, and provide real-time measurement data for production process control

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
  • External thread detection method based on machine vision and real-time detection system
  • External thread detection method based on machine vision and real-time detection system
  • External thread detection method based on machine vision and real-time detection system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] The present embodiment is a machine vision-based external thread detection method, wherein only one Hough transform accumulation is performed, and the main steps include:

[0052] S1. Use parallel light pipe backlight and camera to obtain thread image, the thread axis is horizontal, but does not require a fixed direction, it can be realized by a simpler device, the camera is vertical, and the obtained image is partially as follows image 3 shown;

[0053] S1.1 Use the machine vision grid calibration plate to calibrate the image system: place the appropriate size grid plate in the corresponding horizontal position of the thread axis, and adjust the vertical and horizontal axes of the grid plate to coincide with the visual field axis;

[0054] S1.2 Obtain the image, and re-adjust the position of the grid plate if necessary; perform edge detection, statistical grayscale, and binarization; use high-resolution Hough transform to obtain straight line information, and calculat...

Embodiment 2

[0083] This embodiment is a case where two advanced Hough transform accumulations are performed. The main steps are similar to those of the first embodiment, and only the key steps of the advanced accumulation will be described below. More advanced accumulations can be made if necessary, but with diminishing marginal benefits.

[0084] The calculation is carried out according to the first embodiment, but the accumulation matrix with lower resolution is used to reduce the calculation amount. A lower resolution image can also be used at the same time to further reduce the amount of computation, but the effect is not as pronounced as reducing the resolution of the accumulation matrix. The resolution of the parameter ρ is taken as 1 pixel, the size of the θ accumulation matrix is ​​0.2 degrees (respectively reduced by 10 times and 4 times), and when the accumulation range of θ is relaxed to 16 degrees, the cumulative matrix size becomes 2472*80, compared to In case 1, the cumula...

Embodiment 3

[0088] Corresponding to the first embodiment, this embodiment is a real-time detection system for external threads based on machine vision, including an image preprocessing and calibration module, which calibrates image size and distortion; a system learning and screwability judgment standard generation module; real-time detection module, obtain external thread size information and judge its screwability; test report and process control chart generation module.

[0089] The specific functions of the modules in this embodiment correspond to the method steps in the first embodiment, and are not repeated here.

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 an external thread detection method based on machine vision and a real-time detection system. The external thread detection method comprises the following steps that S1, an image is calibrated by using a standard grating; S2, a judgment standard of the thread screwing-in property is determined by using the thread tolerance requirement and system learning data; S3, linear detection is carried out by utilizing a rapid Hough transformation algorithm designed for external thread detection; and S4, a measurement report and a process control statistical chart are generated. Benefited from the globality and robustness of Hough transformation, the detection method and the real-time detection system have low requirements on image quality and positioning of a detected piece,have good adaptability and high detection reliability; various detected piece sizes and tolerance requirements are met through calibration steps and advanced Hough transformation; and through technical means such as table look-up method calculation, cumulative range reduction, cumulative array resolution advancement, the calculation amount is reduced, and real-time detection and process control can be realized.

Description

technical field [0001] The present application relates to the field of external thread detection, and in particular, to a machine vision-based external thread detection method and real-time detection system. Background technique [0002] Various equipments in the feed industry often need to work in dust environment and vibration environment, and various bolt connections are the guarantee of equipment safety and reliability. Various equipment housings generally have multiple internally threaded holes for compactly fixing other parts with screws. Since these important connections have many tightening torque requirements and require automated assembly, high requirements are placed on the quality of the screws used. If the external thread of the screw has quality defects, firstly, it may not meet the torque requirements and needs to be reworked, and it is more likely that the internal thread on the shell will be damaged and the expensive shell will be scrapped. These screws pl...

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): G01B11/24G01B11/00G06T7/00G06T7/13G06T7/136G06T7/80
CPCG01B11/2425G01B11/002G06T7/0004G06T7/13G06T7/136G06T7/80G06T2207/10004G06T2207/20081G06T2207/30164
Inventor 杨华廷朱林
Owner 上海红马饲料有限公司
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