A Method for Image Recognition of Damaged Fault of Railway Wagon Bathtub

A technology for image recognition and railway wagons, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of fatigue, omission, and low detection efficiency of inspection personnel, and reduce the depth of the network and the number of convolution kernels , Improve the recognition speed, improve the effect of the segmentation effect

Active Publication Date: 2020-11-03
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF5 Cites 0 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 bathtub for railway wagons in view of the problems in the prior art that manual inspection of images is used for fault detection, because inspection personnel are prone to fatigue and omissions during work, resulting in low detection efficiency Image Recognition Method for Damaged Faults

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
  • A Method for Image Recognition of Damaged Fault of Railway Wagon Bathtub
  • A Method for Image Recognition of Damaged Fault of Railway Wagon Bathtub
  • A Method for Image Recognition of Damaged Fault of Railway Wagon Bathtub

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0042] Specific implementation mode one: refer to figure 1 and figure 2 Specifically explaining this embodiment, a method for image recognition of a damaged bathtub of a railway freight car described in this embodiment includes the following steps:

[0043] Step 1: Obtain the linear image of the passing truck, locate the bathtub area from the image, and perform cropping;

[0044] Step 2: Use the trained deep learning model to segment the image corresponding to the bathtub;

[0045] Step 3: According to the segmentation results of the deep learning model, the image processing method is used to further obtain the information of the segmented parts, and the bathtub damage is judged according to the prior knowledge.

[0046] 1. Image preprocessing

[0047] (1) Image collection

[0048] By building high-definition equipment around the truck tracks, high-definition line scan images of passing trucks are obtained. As truck components may be affected by rain, mud stains, oil sta...

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

An image recognition method for damaged bathtubs of railway freight cars, which relates to the technical field of freight train detection, aims at detecting faults by manually inspecting images in the prior art, because inspectors are prone to fatigue and omissions during the work process, resulting in For the problem of low detection efficiency, the present invention uses image processing and deep learning methods to automatically identify bathtub faults, and only needs to confirm the alarm results manually, which can effectively save labor costs and improve detection accuracy. The present invention applies deep learning algorithms to In the automatic identification of bathtub damage faults, the stability and accuracy of the overall algorithm are improved; since the background of the bathtub board is an ever-changing floor image, the FasterInception network is used to detect whether the image contains a bathtub, and then the U‑NET network is used to detect whether the image contains the bathtub. Subimage detection faults, reducing the impact of images that do not contain bathtubs on segmentation results.

Description

technical field [0001] The invention relates to the technical field of freight train detection, in particular to an image recognition method for a damaged bathtub of a railway freight train. Background technique [0002] The broken fault of the bathtub of the truck is a fault that endangers the driving safety. At present, manual inspection of images is mostly used for fault detection. As the inspectors are prone to fatigue and omissions during the work process, resulting in missed inspections and wrong inspections, affecting driving safety. The method of automatic image recognition can improve the detection efficiency and stability. In recent years, deep learning and artificial intelligence have continued to develop and mature in technology. Therefore, using deep learning to identify the damaged fault of the truck bathtub can effectively improve the detection accuracy. Contents of the invention [0003] The purpose of the present invention is to propose a bathtub for r...

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 Patents(China)
IPC IPC(8): G06T7/00G06T7/11G06T7/12G06T7/136
CPCG06T7/0004G06T7/11G06T7/12G06T7/136G06T2207/20081G06T2207/20084G06T2207/30164G06T2207/30204
Inventor 高恩颖
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
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