Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for automatically identifying loss fault of cutout cock handle of train

An automatic identification and door handle technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve problems such as low efficiency of manual detection and misjudgment

Inactive Publication Date: 2016-03-09
HUBEI UNIV OF TECH
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide an automatic identification method for the loss of the train truncation plug door handle, which solves the problems of low efficiency of manual detection and misjudgment

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
  • Method for automatically identifying loss fault of cutout cock handle of train
  • Method for automatically identifying loss fault of cutout cock handle of train
  • Method for automatically identifying loss fault of cutout cock handle of train

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The present invention will be described in detail below in combination with specific embodiments.

[0026] The steps of the automatic identification method for the loss of the train truncation plug door handle in the present invention are as follows: figure 1 Shown:

[0027] Step 1: The outdoor image acquisition equipment of the train fault trackside image detection system captures the dynamic image of the braking device at the bottom of the passing train in real time, and transmits it to the train inspection station through the optical fiber network.

[0028] Step 2: Preprocess the original image collected by the train fault trackside image detection system, and apply Gaussian filtering to eliminate the influence of the shooting environment on the original image.

[0029] Specifically, the Gaussian smoothing filter is a kind of linear smoothing filter, and has a good elimination effect on noises that obey or approximately obey a normal distribution. The principle is ...

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 present invention discloses a method for automatically identifying a loss fault of a cutout cock handle of a train, comprising the steps of: preprocessing an image acquired by a railway freight car operating fault dynamic image detection system to eliminate influence of a shooting environment on an original image, and performing image segmentation processing for the de-noised image; setting ROIs (Regions of Interest) at corresponding positions of a detection image, using a handle variable-step-size quick matching method based on Hu invariant moment matching values to calculate a matching value of a template image and an ROI image, comparing the matching value with a predetermined coarse positioning threshold to determine whether the corresponding position is a precise matching candidate point, and storing the position into a precise matching preselection point sequence if the position is the precise matching candidate point; for non-precise matching candidate points of which the matching values are less than the coarse positioning threshold, calculating the next horizontal matching step size according to the matching values; and judging whether the cutout cock handle is lost through a final matching result. The method of the present invention has the beneficial effect that the method can accurately, quickly and automatically detect and judge whether the cutout cock handle of the train is lost.

Description

technical field [0001] The invention belongs to the technical field of image analysis and processing, and relates to an automatic identification method for a fault that a train cut-off plug door handle is lost. Background technique [0002] For a long time, my country's train technical inspection (referred to as "train inspection") has always relied on the manual inspection of train inspectors to complete. Affected by human subjective factors such as eyesight, fatigue and external environment such as climate and light, the detection efficiency is low and there are certain misjudgments. In 2014, my country's railway freight volume was as high as 3.81 billion tons, ranking first in the world, and the large-scale and high-density freight transportation also put forward higher requirements for train fault detection. Therefore, TFDS (Trouble of moving Freight car Detection System, dynamic image detection system for truck running faults) is gradually applied to some domestic rail...

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): G06K9/32G06K9/62
CPCG06V10/25G06V10/751
Inventor 赵大兴孙国栋杨林杰王博王璜张杨梅术正艾成汉林松靖马超
Owner HUBEI UNIV OF TECH