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

Pointer type instrument automatic reading method based on radial gray scale

A technology for automatic reading and instrumentation, which is applied in the direction of instruments, biological neural network models, character and pattern recognition, etc., and can solve problems such as poor instrument reading results

Pending Publication Date: 2020-11-17
宁波中国科学院信息技术应用研究院 +1
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the existing angle-based reading methods rely on accurate dial center positioning and pointer line detection, which are not effective for meter readings with nonlinear ranges and non-vertical shooting.

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
  • Pointer type instrument automatic reading method based on radial gray scale
  • Pointer type instrument automatic reading method based on radial gray scale
  • Pointer type instrument automatic reading method based on radial gray scale

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0077] The following embodiment is an automatic reading method for radial grayscale statistics of a single-pointer instrument, and the complete flow chart of the method is as follows: figure 1 shown.

[0078] Step A, build an improved Unet dial scale line segmentation deep neural network, collect instrument images to make a data set and train the network, input the trained instrument image into the network to obtain the scale line segmentation results;

[0079] Step B, calculating the center coordinates of the dial and the distance from the scale to the center of the circle according to the scale segmentation results;

[0080] Step C, use yolov3 to detect the dial scale number category and position, and then determine the scale number by the mean-shift clustering method;

[0081] Step D, performing radial grayscale statistics on the instrument scale image, digital detection result image, and pointer thresholded image respectively, to obtain respective radial grayscale statist...

Embodiment 2

[0084] In this embodiment, on the basis of Embodiment 1, the specific process of the step A is as follows:

[0085] Step A1. Obtain the front single-channel image of the meter, normalize the resolution to 560*580, mark the meter scale pixels as 255, and mark the non-meter scale pixels as 0, a total of 25 images, including the instrument training image with the shell Such as figure 2 As shown in (a), the scale labeling results are as follows figure 2 As shown in (c); only the instrument training image of the dial is shown as figure 2 As shown in (b), the scale labeling results are as follows figure 2 as shown in (d);

[0086] Step A2, such as image 3As shown, a scale segmentation network with cross-layer connections is constructed, with a total of 9 layers. The first layer consists of two ordinary convolution layers and a pooling layer. The 2-4 layers use the residual module whose activation function is LeakyReLU as convolution. Unit, in which the slope of the negativ...

Embodiment 3

[0089] In this embodiment, on the basis of Embodiment 1, the specific process of the step B is as follows:

[0090] Step B1. Set a threshold of 0.5 in the scale segmentation probability map. Pixels higher than the threshold are reserved as scale pixels. After thresholding, a scale binary image is obtained, and all connected domains C in the scale binary image are marked in turn. i ,, remove the noise connected domain whose connected domain area is less than 5;

[0091] Step B2, fitting all the pixel points in each connected domain to a straight line l i , find any two fitting straight lines l i and l j Intersecting intersection point coordinates D ij (x ij ,y ij ), respectively calculate the mean value μ of the horizontal and vertical coordinates of the intersection point x , μ y with variance σ x , σ y ;

[0092] Step B3. Transform the abscissa and ordinate samples of the intersection point into a standard normal distribution, and keep the abscissa X' at the sample ...

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 pointer type instrument automatic reading method based on radial gray scale. The method comprises the following steps: constructing and training a dial scale segmentation convolutional neural network; calculating the circle center and the scale radius of the instrument; positioning and identifying dial scale numbers; respectively counting the sum of gray values of pixel points in the radius direction of the scale segmentation image, the scale reading image and the pointer threshold segmentation image; and calculating the indexing value of each section of scale sectionby section according to a statistical result to finish automatic reading. The invention can meet the reading requirements of various pointer instruments, and can achieve the high-precision and high-robustness automatic instrument reading method based on the strategy of radial gray scale statistics.

Description

technical field [0001] The invention belongs to the field of industrial computer vision, and in particular relates to an automatic reading method of a pointer instrument based on radial gray scale statistics. Background technique [0002] Pointer instruments are widely used in production and life because of their simple structure, low cost and anti-electronic interference. However, because its value is difficult to obtain through electronic sensors, many scenarios such as instrument quality inspection and factory instrument inspection often require manual reading of the instrument representation. However, manual instrument readings are time-consuming and labor-intensive, increasing labor costs. Repeated readings for a long time can easily cause visual fatigue and lead to reading errors. Frequent manual inspections of equipment in some factories can also easily increase the safety hazards of equipment and personnel. Designing a set of high-precision, fully automatic instrume...

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): G06K9/34G06K9/46G06K9/62G06N3/04
CPCG06V10/267G06V10/507G06V2201/02G06N3/045G06F18/2321G06F18/214
Inventor 刘博文陈春燕黄晁袁敏杰潘意杰查兴兴杨子江赵忆胡波
Owner 宁波中国科学院信息技术应用研究院
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