Multi-line structured light self-calibration method and system for rail profile dynamic detection

A multi-line structured light and dynamic detection technology, applied in the direction of measuring devices, optical devices, instruments, etc., can solve the problem of low reliability of plane parameters, achieve the correction of distorted rail contours, improve robustness, and strong robustness Effect

Active Publication Date: 2018-12-07
湖南东映碳材料科技股份有限公司
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention provides a multi-line structured light self-calibration method and system in the dynamic detection of the rail profile,

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
  • Multi-line structured light self-calibration method and system for rail profile dynamic detection
  • Multi-line structured light self-calibration method and system for rail profile dynamic detection
  • Multi-line structured light self-calibration method and system for rail profile dynamic detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Please refer to figure 1 , the present invention provides a multi-line structured light self-calibration method in the dynamic detection of rail profile, comprising:

[0035] Step S1, obtaining the feature points on the multi-line structured light strip from the scene image of the rail according to the angle extraction algorithm;

[0036] Feature point extraction is performed on more than two rail profile light bars (ie, rail profile light bars) contained in the scene image, specifically, the Harris corner point extraction algorithm is used for feature point extraction. The internal parameters of the camera are determined by the Zhang Zhengyou calibration method.

[0037] Preferably, the step S1 includes:

[0038] Step S11, obtaining two rail profile light bars from the scene image;

[0039] see Figure 4 , the surface light source radiated by the line-structured light projector intersects the surface of the measured object and forms a light strip that can reflect i...

Embodiment 2

[0111] Please refer to Figure 7 , the embodiment of the present invention provides a multi-line structured light self-calibration system in the dynamic detection of rail profile, including:

[0112] The feature acquisition module 1 is used to obtain the feature points on the multi-line structured light strip according to the angle extraction algorithm from the scene image of the railroad track;

[0113] The projected profile module 2 is used to build a three-dimensional profile of the rail based on the feature points and the geometric shape of the rail itself in combination with the structured light visual model; and obtain the projected profile according to the three-dimensional profile of the rail;

[0114] The quantification module 3 is used to quantify the size and shape deviations of the projected profile and the standard profile on the three non-wearing areas of the rail jaw, the inner side of the rail head and the rail bottom, using a curve similarity measurement metho...

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 multi-line structured light self-calibration method and system for rail profile dynamic detection. The method comprises the following steps: obtaining the feature points on multi-line structured light strips from the scene image of a rail according to an angle extraction algorithm; establishing the three-dimensional profile of the rail according to the feature points andthe geometrical shape of rail through combination with the structured light visual model; obtaining the projection profile according to the three-dimensional profile of the rail; and quantifying the size and shape deviation of the projection profile and the standard profile in three non-abrasion areas of the rail jaw, the inner side of the rail head and the rail bottom by using the curve similarity measurement method; and iteratively optimizing the plane parameters of the multiline structured light according to the quantified deviation so as to realize self-calibration of the multiline structured light. According to the scheme, the problem that the structured light cannot be calibrated automatically and quickly online by relying on the calibration template can be solved so that the robustness of measurement profile reconstruction and auxiliary plane construction can be improved and correction of the distorted rail profile caused by multi-degree-of-freedom vibration can be facilitated.

Description

technical field [0001] The invention relates to the technical field of rail profile dynamic detection, in particular to a multi-line structured light self-calibration method in the rail profile dynamic detection. Background technique [0002] The speed of modern railway transportation is getting faster and faster, and the load is increasing. A reasonable and efficient line maintenance system is urgently needed to ensure the quality and safety of railway transportation. As the core component of the railway transportation system, the rail line needs to be monitored and maintained regularly, and the measurement of the cross-sectional shape of the rail is one of the key steps. The cross-sectional shape of the rail, that is, the profile, not only directly reflects the current degree of wear of the rail, but also provides a scientific and reasonable reference for the line maintenance system. Due to its high precision, strong real-time performance and low cost, structured light vi...

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): G01B11/25
CPCG01B11/2504
Inventor 李益李一鸣
Owner 湖南东映碳材料科技股份有限公司
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