Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Motor train unit train side foreign matter detection method

A foreign object detection and EMU technology, applied in the field of image processing, can solve the problems of low detection efficiency and accuracy, and achieve the effect of ensuring gray balance, improving detection efficiency, accuracy and efficiency

Inactive Publication Date: 2021-01-29
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF11 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to propose a method for detecting foreign matter on the side of the EMU train in view of the problem of low detection efficiency and accuracy when manually detecting whether there is foreign matter on the side skirt of the EMU train 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
  • Motor train unit train side foreign matter detection method
  • Motor train unit train side foreign matter detection method
  • Motor train unit train side foreign matter detection method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0029] Specific implementation mode one: refer to figure 1 and figure 2 This embodiment is specifically described. A method for detecting foreign matter on the side of an EMU train described in this embodiment includes the following steps:

[0030] Step 1: Obtain a two-dimensional image of the train;

[0031] Step 2: Capture the image of the side skirt area of ​​the train:

[0032] Step 3: Carry out grayscale normalization processing on the image of the side skirt plate area of ​​the train;

[0033] Step 4: Carry out background modeling according to the fixed features of the train side skirt area image;

[0034] Step 5: performing differential matching on the normalized image of the side skirt area of ​​the train and the background model corresponding to the image of the side skirt area of ​​the train;

[0035] Step 6: Perform morphological processing on the image after differential matching:

[0036] Step 7: Set the area threshold, the length, width threshold and aspect...

specific Embodiment approach 2

[0046] Embodiment 2: This embodiment is a further improvement to Embodiment 1. The difference between this embodiment and Embodiment 1 is that the specific steps of step 3 are:

[0047] According to the fixed characteristics of the train side skirt area image and the pixel value of the two-dimensional image of the train, the high pixel value ratio threshold R of the image is obtained H0 And image low pixel value ratio threshold R L0 , and then divide the pixel values ​​into 255 levels. The size of the currently selected side skirt image is W×H, where W is the width of the image, and H is the height of the image. The pixel value of a certain point in the image is normalized by grayscale The transformed value is Y, where the threshold for high pixel values ​​is Y H0 =W×H×R H0 , the threshold for low pixel values ​​is Y L0 =W×H×R L0 , the value of Y is obtained by the following formula:

[0048]

[0049] Definition of image grayscale normalization

[0050] Gray level nor...

specific Embodiment approach 3

[0055] Specific embodiment three: this embodiment is a further improvement to specific embodiment two, and the difference between this embodiment and specific embodiment two is that the step of background modeling in the step four is: first, the train side skirt plate area image It is divided into upper, middle and lower parts, and the background image is modeled according to the image characteristics of the three parts on different cars.

[0056] background modeling

[0057] According to the inherent component characteristics of the side skirt image of the EMU, the side image is divided into upper, middle and lower areas, and the background modeling is carried out for the images of different cars, which can effectively avoid various covers and bolts and The impact of the grille ensures the accuracy and efficiency of foreign object detection. See the process for details figure 2 .

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 motor train unit train side foreign matter detection method, relates to the technical field of image processing, and aims to solve the problems of low detection efficiency and low accuracy when whether foreign matters exist on a side apron board of a motor train unit train or not is manually detected in the prior art. The method comprises the steps: 1 obtaining the two-dimension image of a train; 2, intercepting an area image of the position of the side apron board of the train; step 3, carrying out gray normalization processing on the area image; 4, carrying out morphological processing on the image after gray normalization, and carrying out background modeling according to fixed features of the apron board; 5, performing difference matching on different apron board images and background models corresponding to the apron board images; 6, carrying out morphological processing on the image after difference matching; and 7, an area threshold value, a length threshold value, a width threshold value, and a length-width ratio threshold value of the contour being set, and whether a foreign matter exists being determined by comparing the image after morphologicalprocessing with the threshold values.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image processing method for side foreign object detection based on gray scale normalization of features of side parts of an EMU train. Background technique [0002] The side skirts of EMU trains are easy to attach foreign objects such as bottles and plastic bags during the operation of the train. If they are not found and cleaned in time, it will endanger the driving safety. Manual inspection of images is used for fault detection. Due to the operation of EMUs The density is high, the inspection time is short, and the inspectors are prone to fatigue and omissions during the work process, resulting in missed inspections and wrong inspections, affecting driving safety, and using manual inspections, the detection efficiency and accuracy are low. Contents of the invention [0003] The object of the present invention is to propose a method for detecting foreign matter on ...

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): G06T7/00G06T7/62G06T5/30G06K9/32G06K9/46B61K9/00
CPCG06T7/0002G06T7/62G06T5/30B61K9/00G06V10/25G06V10/56
Inventor 邓艳
Owner HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL 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
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