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

Correction method of non-uniform illumination images of online detection of conveyor belt faults

A lighting correction and image correction technology, which is applied in image analysis, image data processing, instruments, etc., can solve problems such as uneven illumination of images, influence on fault detection, missed or false detection of faults, etc., and achieve simple and reliable completion of the correction method Effect

Pending Publication Date: 2018-01-19
TIANJIN POLYTECHNIC UNIV +1
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the technical problems of uneven illumination, poor image quality, and influence on fault detection in images collected by online detection of conveyor belt faults, and to provide a non-uniform on-line detection of faults on conveyor belts. Illumination Image Correction Method

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
  • Correction method of non-uniform illumination images of online detection of conveyor belt faults
  • Correction method of non-uniform illumination images of online detection of conveyor belt faults
  • Correction method of non-uniform illumination images of online detection of conveyor belt faults

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The specific implementation of the present invention will be described in detail below in conjunction with the accompanying drawings and examples.

[0017] The overall operation process of the method proposed by the present invention is as attached figure 1 As shown, the specific implementation is generally divided into two stages, which are respectively the stage of obtaining correction coefficients and the stage of correction application. First, in the stage of obtaining the correction coefficient, calculate the non-uniform illumination correction coefficient c j ; Then in the correction application stage, realize the non-uniform illumination image correction of the conveyor belt fault on-line detection.

[0018] The operation process of obtaining the correction coefficient stage is as follows:

[0019] Step 1, use a line scan camera with a resolution of M to collect running images of the conveyor belt, one row of images at a time, and the collected images are digit...

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 correction method of non-uniform illumination images of online detection of conveyor belt faults, and belongs to the field of fault detection. The method solves technical problems that illumination of the collected images is not uniform, image quality is poor, fault detection is impacted and missed detection or false detection of the faults is liable to be caused due to factors of conveyor belt surface geometry, light source lighting differences, light source placement positions, complex on-site environments and the like in online detection of the conveyor belt faults. According to the method, a linear-array camera is used to collect the conveyor belt running images, images, which does not contain the faults, of successive multiple rows are selected to calculate amean value of column vectors, then an illumination distribution curve fitting function and column illumination evaluation values are calculated, then a target value of non-uniform illumination correction and non-uniform illumination correction coefficients are calculated, and finally, non-uniform illumination correction is completed. The method of the invention is simple and fast, is suitable forfast correction of the non-uniform illumination images detected online by adopting the linear-array camera, and facilitates highly efficient and reliable completion of online detection of the conveyor belt faults.

Description

technical field [0001] The invention relates to a non-uniform illumination image correction method for on-line detection of conveyor belt faults, in particular to a correction method for non-uniform illumination images in the on-line detection of conveyor belt faults based on machine vision, and belongs to the field of fault detection. Background technique [0002] On-line detection of conveyor belt deviation, surface damage and longitudinal tear faults based on machine vision technology can avoid safety accidents, ensure safe production, and avoid loss of equipment, property and personnel safety. In the online detection of conveyor belt faults based on machine vision, the installation space of the lighting source and line array camera in the image acquisition system is limited by the conveyor structure, and the installation space is narrow. In order to meet the requirements of conveyor belt detection, according to the detected conveyor belt width, it is necessary to use sin...

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): G06T7/00
Inventor 苗长云高瑞李现国李杰仲为亮张立东
Owner TIANJIN POLYTECHNIC 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