Positioning method and system based on components beside rail

A positioning method and positioning system technology, applied in computer parts, neural learning methods, character and pattern recognition, etc., can solve the problems of slow operation speed and large amount of data, so as to improve the calculation speed, solve the demand and reduce the algorithm. The effect of complexity

Pending Publication Date: 2021-07-27
BEIJING MININGLAMP SOFTWARE SYST CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The embodiment of the present application provides a positioning method and system based on railside components to at least solve the problems of large data volume and slow calculation speed in related technologies

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
  • Positioning method and system based on components beside rail
  • Positioning method and system based on components beside rail
  • Positioning method and system based on components beside rail

Examples

Experimental program
Comparison scheme
Effect test

example 2

[0132] S601. Select a reference target and label the result.

[0133] Such as Figure 7 As shown, using the center part of the wheel set in the trackside picture as the reference target, its coordinate example: 856,385,1488,1050

[0134] Annotate the data set, an example of the labeling result:

[0135] 916,418,985,507,0

[0136] 1221,434,1289,528,0

[0137] 1327,706,1399,797,0

[0138] 1189,997,1254,1075,0

[0139] 920,989,983,1064,0

[0140] 795,690,866,776,0

[0141] 1293,332,1690,708,4

[0142] 786,416,1406,1075,8

[0143] S602, designing a deep learning regression network.

[0144] Train deep learning regression networks with labeled datasets. Figure 9 Design diagrams for deep learning regression networks, for examples of results see Figure 9 shown.

[0145] S603. Train a location prediction model, and use the location prediction model to perform prediction.

[0146] Forecast results such as Figure 10 , 11 as shown, Figure 10 It is a schematic diagram ...

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 relates to a positioning method and system based on components beside a rail. The method comprises the following steps: marking relative positions of all components beside a to-be-detected rail; selecting a part in a picture under a conventional condition as a reference target, marking absolute coordinates of the reference target and a to-be-positioned target in the picture according to the relative position, and taking the absolute coordinates as a training set; according to a deep learning regression algorithm, based on the training set, utilizing a neural network to fit a mathematical relationship between the to-be-positioned target and the reference target; based on the mathematical relationship, training according to deep learning and establishing a positioning prediction model; and according to the absolute position of the reference target, obtaining the absolute position of the to-be-positioned target by using the positioning prediction model. By marking the positions of all types of components beside the rail, fitting the mathematical relationship between the reference target and the target to be positioned by using the regression network, and establishing the positioning prediction model for all specific types, the demand of data is greatly solved, the algorithm complexity is reduced, and the calculation speed is improved.

Description

technical field [0001] The present application relates to the technical field of rail data processing, in particular to a positioning method and system based on railside components. Background technique [0002] Rail maintenance and inspection is a very important task in the daily operation of rail tracks. In the past, maintenance workers relied on the naked eye to observe the key components of the train one by one after the train was put into storage to check whether there is a failure or a precursor to failure. [0003] With the development of digital technology, information technology and computer technology, the maintenance method has gradually changed from on-site naked eye observation to using a line-scan camera to take pictures of both sides of the train when the train enters the warehouse, upload it to the computer, and then the maintenance workers will check it on the computer. . [0004] Of course, it is still troublesome to drag and drop the whole picture. Theref...

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): G06K9/20G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V10/22G06N3/045G06F18/214
Inventor 邱琼文
Owner BEIJING MININGLAMP SOFTWARE SYST CO LTD
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