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

Bullet train stone sweeper loss fault image recognition method based on deep learning

A deep learning and image recognition technology, applied in the field of image recognition, can solve the problems of low detection efficiency and accuracy, achieve fast calculation speed, ensure accuracy, and improve detection efficiency

Inactive Publication Date: 2021-01-05
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a deep learning-based image recognition method for the missing fault image of the stone sweeper in order to solve the problem of low detection efficiency and accuracy of manual detection of the missing fault of the stone sweeper in the prior art

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
  • Bullet train stone sweeper loss fault image recognition method based on deep learning
  • Bullet train stone sweeper loss fault image recognition method based on deep learning
  • Bullet train stone sweeper loss fault image recognition method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0045] Specific implementation mode one: refer to figure 1 Specifically explaining this embodiment, a deep learning-based image recognition method for a lost fault image of a motor vehicle stone sweeper described in this embodiment includes the following steps:

[0046] Step 1: Obtain the moving car image;

[0047] Step 2: Roughly locate the stone sweeper component area in the acquired moving train image to form a sample data set;

[0048] Step 3: Carry out rectangular frame marking on the coarsely positioned train image, and form a marking information set;

[0049] Step 4: Extract the features of the sample data set and the tag information set, and use the extracted features to train the network;

[0050] Step 5: Use the trained network to judge the fault of the stone sweeper on the image to be tested.

[0051] 1. Create a sample data set

[0052] Build high-definition imaging equipment around the train track. When the train passes, the high-definition image of the train ...

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 bullet train stone sweeper loss fault image recognition method based on deep learning, relates to the technical field of image recognition, and aims to solve the problems oflow detection efficiency and low accuracy of manual detection of a stone sweeper loss fault in the prior art. The method comprises the following steps: 1, acquiring a bullet train image; 2, carrying out coarse positioning on a stone sweeper part area in the obtained bullet train image, and forming a sample data set; 3, carrying out rectangular frame marking on the bullet train image obtained aftercoarse positioning, and forming a marking information set; 4, performing feature extraction on the sample data set and the mark information set, and training the network by using the extracted features; and 5, performing stone sweeper fault judgment on an image to be detected by using the trained network. According to the invention, manual detection is replaced by an image automatic identification mode, and the detection efficiency and accuracy are improved.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a deep learning-based image recognition method for a lost fault image of a stone sweeper of a motor vehicle. Background technique [0002] The stone sweeper is used to eliminate some small obstacles that may appear on the rails during the operation of the train, so as to ensure the safety of the train. If the stone sweeper is lost or damaged, small stones on the rails may cause major accidents such as derailment of the train during the operation of the train. [0003] The failure of the stone sweeper loss of the bullet train is a kind of failure that endangers the safety of the train. In the previous fault detection, the fault detection was carried out by manually checking the image. Due to the high labor intensity of manual inspection, it may cause missed inspections and wrong inspections, which will affect driving safety, and the detection efficiency and accuracy are...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V20/584G06V2201/08G06N3/047G06N3/045
Inventor 于婷
Owner HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
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