Vehicle-mounted track inspection device and method based on deep learning

A technology of deep learning and track, applied in the field of vehicle-mounted track inspection devices based on deep learning, can solve the problems of low efficiency and low safety of manual inspection, and achieve improved maintenance efficiency, strong anti-interference, and high accuracy Effect

Active Publication Date: 2021-07-13
SHANGHAI ORIENTAL MARITIME ENG TECH CO LTD
View PDF12 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a vehicle-mounted track inspection device and method

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
  • Vehicle-mounted track inspection device and method based on deep learning
  • Vehicle-mounted track inspection device and method based on deep learning
  • Vehicle-mounted track inspection device and method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0044] A deep learning-based vehicle rail patrol apparatus and method proposed below will be further described below with reference to the accompanying drawings and specific examples. The advantages and features of the present invention will be more apparent from the following description and appended claims.

[0045] In this embodiment, for the problem of low-efficiency and high safety, it provides a deep learning-based car track inspection device, based on machine visual principles, and the image information will be obtained by the server through the image collection module. The detection model is detected, and the detected defect position and type are reported and the detected defect picture is saved to the database for manual review. The track inspection equipment has the characteristics of simple structure, high unit density, clear image, high accuracy, and strong anti-interference.

[0046] Specifically, please see figure 1 The depth learning-based car rail inspection device...

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 vehicle-mounted track inspection device and method, and aims to solve the problems of low efficiency, low safety and the like of traditional manual inspection and detect obtained image information through a detection model in a server through an image acquisition module on the basis of a machine vision principle. A report is generated according to the detected defect position and type, and the detected defect picture is stored in a database for manual rechecking. The vehicle-mounted track inspection device has the advantages of being simple in structure, high in unit density, clear in image, high in accuracy, high in anti-interference performance and the like; and according to the vehicle-mounted track inspection method, detection of different defects of a set of working image data is achieved within one time of skylight working time, such as fastener missing and fastener skewing, foreign matter invasion and track plate cracks. The collected images can be manually checked in the later period, so that field inspection of personnel is avoided, and the detection efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of track inspection, and in particular relates to a vehicle-mounted track inspection device and method based on deep learning. Background technique [0002] Compared with other transportation methods, railway transportation has large transportation volume, long transportation distance, high degree of safety, low transportation cost and is less affected by the climate environment. It plays an irreplaceable role in the comprehensive transportation network and contributes to the construction of the national economy. Provides reliable protection and strong support. In practice, the acceleration of the train's running speed and the heavy transport load have brought convenience to people, and at the same time, they have brought extremely severe tests to the safety of railway operation and the maintenance of rails. [0003] With the implementation of my country's railway speed-up strategy, there are higher require...

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): G06T7/00G06T7/11G06T7/73G06T1/20G06K9/62
CPCG06T7/0004G06T7/11G06T7/74G06T1/20G06T2207/20021G06T2207/20081G06T2207/20104G06T2207/30204G06F18/24G06F18/214
Inventor 徐树亮张余峰范信余天乐吴宴华张万鹏王昭利
Owner SHANGHAI ORIENTAL MARITIME ENG TECH 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