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

Embedded steel rail profile detection light bar extraction method

An extraction method and embedded technology, applied in the field of data processing, can solve the problems of low processing accuracy, poor robustness, low processing speed, etc., and achieve the effect of narrowing the search range, fast speed, and fast extraction.

Pending Publication Date: 2022-08-02
CHENGDU TANGYUAN ELECTRICAL APPLIANCE
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In order to overcome the defects in the above-mentioned prior art, the present invention discloses a method for extracting light strips based on embedded rail profile detection. The problem of poor stickiness

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
  • Embedded steel rail profile detection light bar extraction method
  • Embedded steel rail profile detection light bar extraction method
  • Embedded steel rail profile detection light bar extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] A method for extracting light strips based on embedded rail profile detection, comprising the following steps:

[0067] S1. Perform image scaling, dynamic threshold segmentation, and connected area screening (adaptive ROI) on the original image in turn to determine the target area on the original image;

[0068] S2. Perform selective mask smoothing, image binarization and center point extraction processing on the original image after the target area is determined, to obtain the center of the light bar of the target area.

[0069] In this embodiment, in step S1, the adaptive ROI method is used to determine the target area, which can remove the interference area to a limited extent, increase the accuracy of light strip extraction, narrow the search range during light strip extraction, and greatly improve the efficiency of the algorithm. In step S2, selective mask smoothing, image binarization and center point extraction are sequentially performed on the target area to ext...

Embodiment 2

[0072] This embodiment makes further improvements on the basis of Embodiment 1, such as figure 1 As shown, the step S1 includes the following steps:

[0073] S11. Image scaling: the original image is drawn at every 4 points in rows and columns, respectively, to obtain a scaled image reduced by 1 / 4.

[0074] S12. Dynamic threshold segmentation: perform large-scale smoothing on the scaled image to obtain a smooth image, and make a difference between the scaled image and the smoothed image to obtain a differential image; wherein, the smoothing scale is set to the width (pixel width) of the rail head area. The dynamic threshold segmentation data flow is as follows Figure 2-4 shown.

[0075] S13. Screening of connected areas: in the differential image, filter out the connected areas of the light bars.

[0076] S14. Determine the target area: in the filtered connected area of ​​the light bar, use geometric parameter information such as the length, width and area of ​​the minimum...

Embodiment 3

[0079] This embodiment makes further improvements on the basis of Embodiment 2, such as Figure 9 As shown, the step S2 includes the following steps:

[0080] S21. Selective mask smoothing: perform selective mask smoothing on the original image including the target area.

[0081] In this embodiment, the selective mask smoothing is an adaptive local smoothing filtering algorithm, which can obtain better image details.

[0082] The selective mask smoothing method is based on the template operation. Taking the 5*5 template window as an example, in the window, the center pixel is used as the basic point to make 4 pentagons, 4 quadrilaterals, and a square with a side length of 3 There are 9 masks in total, as follows:

[0083]

[0084] Calculate the mean and variance of each template according to the above 9 templates. The calculation method is as follows:

[0085]

[0086] Find the gray mean value under the mask with the smallest variance among the 9 templates as the fina...

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 embedded steel rail profile detection light bar extraction method, which relates to the technical field of data processing technology, and comprises the following steps: S1, sequentially carrying out image zooming, dynamic threshold segmentation and connected region screening processing on an original image, and determining a target region on the original image; the target area is determined in a self-adaptive ROI mode, interference areas can be removed in a limited mode, and the accuracy of light strip extraction is improved. And S2, sequentially performing selective mask smoothing, target area image binaryzation and central point extraction processing on the original image after the target area is determined to obtain a light stripe center of the target area. Wherein the purpose of selective mask smoothing is to obtain better image details; the target area image binarization processing aims to highlight the contour of the target; the purpose of central point extraction processing is to obtain the light stripe center of the target area, and through the processing, the light stripe center of the target area can be accurately extracted.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method for extracting light strips based on embedded rail profile detection. Background technique [0002] In the line structured light measurement system, the laser beam is projected vertically to the surface of the object to be measured, and the camera captures the laser fringe image from another angle, and obtains the laser cross-section data according to the triangulation method. The triangulation method requires that the contour line projected onto the surface of the object should be infinitely thin, that is, only one pixel wide. However, due to light scattering and the point-spreading effect of the imaging system, the projected image of the actual contour line on the image plane has a certain thickness and is in the shape of a light strip. Therefore, how to quickly and accurately extract the position of the center of the laser stripe and obtain the accurate spati...

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): G06T7/136G06T3/40G06T5/00G06T7/187
CPCG06T7/136G06T7/187G06T3/40G06T2207/10004G06T5/70
Inventor 周蕾王云龙
Owner CHENGDU TANGYUAN ELECTRICAL APPLIANCE
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