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

Train positioning method and system based on improved FCM algorithm

A train positioning and algorithm technology, applied in the field of train positioning method and system based on improved FCM algorithm, can solve the problem of ignoring the different effects of classification results, and achieve the effect of improving recall rate and detection speed, and improving safety and reliability.

Inactive Publication Date: 2021-01-01
SOUTHWEST JIAOTONG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, the traditional FCM algorithm presupposes that the contribution of each dimension feature quantity of the sample to be analyzed to the classification is the same, ignoring the different influence of each feature quantity on the classification result

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
  • Train positioning method and system based on improved FCM algorithm
  • Train positioning method and system based on improved FCM algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] A train positioning method based on the improved FCM algorithm, such as figure 1 shown, including the following steps:

[0046] S1. Acquiring and preprocessing the orbital area pictures on the orbital path, specifically,

[0047] The orbital area pictures include orbital anchor point object pictures and orbital pictures at any position. Track anchor point objects refer to objects with independent characteristics on the track path, such as one or more combinations of spring bars, bolts, cables, spikes, and sleepers along the track; track pictures at any position are false positive point pictures, Featured objects in false positive images are misrecognized objects rather than actual pre-labeled ones.

[0048] In the orbital path, there are various combinations of orbital positioning point objects. It is necessary to identify the categories and calculate the respective quantities of these categories. Only when the category and quantity are the same as the positioning poi...

Embodiment 2

[0071] This embodiment provides a train positioning system applying the above method, such as figure 2 shown, including

[0072] The collection module is used to obtain and preprocess the orbital area pictures on the orbital path;

[0073] The training module is used to train the positioning point object recognition model according to the preprocessed track area picture, and utilizes the improved FCM algorithm to perform clustering optimization on the recognition model;

[0074] Recognition module, for utilizing the recognition model that training completes to recognize the category of the anchor point object and the quantity of the corresponding category in the track area picture collected during the train traveling process;

[0075] The positioning module is configured to determine the current absolute position of the train according to the identified absolute position information of the positioning point object.

[0076] Those skilled in the art should understand that th...

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 train positioning method and system based on an improved FCM algorithm, and the method comprises the steps of training a recognition model related to a positioning point object, and carrying out the positioning point object recognition of rail region image information collected in the advancing process of a train through the recognition model; and processing the image bythe computer so as to identify the positioning point object with independent characteristics, so that the absolute position information contained in the positioning point object is obtained, and the absolute positioning of the train is realized. Other equipment does not need to be added to the railway track, the method has the advantages of being simple in construction and reducing maintenance cost, the driving safety and reliability are improved, and the false alarm condition of the positioning point is improved.

Description

technical field [0001] The invention relates to the technical field of image recognition and positioning, in particular to a train positioning method and system based on an improved FCM algorithm. Background technique [0002] At present, the absolute positioning of trains in the field of rail transit mainly includes technical solutions such as beacon positioning, satellites, axle counting, and track circuits. Beacon positioning. A beacon is a physical sign installed along the line to reflect the absolute position of the line. The beacon is similar to a non-contact IC card. When the train passes by the position of the beacon, the electromagnetic wave emitted by the vehicle antenna stimulates the beacon to work and transmits Absolute position information to the train. Satellite positioning, including radio navigation systems such as Beidou / GPS, as the first high-tech application in navigation and positioning systems, satellites provide users with continuous high-precision th...

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): G06T7/73G06N3/08G06N3/04G06K9/62
CPCG06T7/73G06N3/08G06T2207/20081G06T2207/20084G06T2207/30256G06N3/045G06F18/23
Inventor 吴松荣李振伟徐睿衡熙丹刘洋康世豪张皓琰
Owner SOUTHWEST JIAOTONG 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

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