Railway tool detection method, system and device and storage medium

A detection method and tool technology, applied in neural learning methods, image data processing, image enhancement, etc., can solve problems such as occlusion, uneven illumination, complex background, etc., to avoid sample imbalance and over-fitting, improve Detection accuracy, solve the effect of complex background

Pending Publication Date: 2020-09-25
WUHAN INSTITUTE OF TECHNOLOGY +1
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a detection method, system, device and storage medium for railway machinery and tools, which can effectively solve the problem of complex background, uneven illuminatio

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
  • Railway tool detection method, system and device and storage medium
  • Railway tool detection method, system and device and storage medium
  • Railway tool detection method, system and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Embodiment one, as figure 1 Shown, a kind of detection method of railway tool, comprises the following steps:

[0032] S1: Obtain multiple machine tool images, and make a data set based on all machine tool images;

[0033] S2: Construct a deep convolutional neural network, use the data set and the deep convolutional neural network to construct a reflection image extraction network, obtain a feature detection network according to the deep convolutional neural network and the reflection image extraction network, and obtain a feature detection network according to the described deep convolutional neural network. The deep convolutional neural network, the reflected image extraction network and the feature detection network obtain an initial detection network model;

[0034] S3: Using the data set to train the initial detection network model to obtain a target detection network model;

[0035] S4: Detect the image of the tool to be detected according to the target detectio...

Embodiment 2

[0096] Embodiment two, such as Figure 10 As shown, a detection system of a railway machine tool is applied to the detection method of a railway machine tool in Embodiment 1, including a data set acquisition module, a network model building module, a training module and a detection module;

[0097] The data set acquisition module is used to acquire a plurality of machine tool images, and make a data set according to all machine tool images;

[0098] The network model construction module is used to construct a deep convolutional neural network, using the data set and the deep convolutional neural network to construct a reflection image extraction network, and according to the deep convolutional neural network and the reflection image extraction network A feature detection network is obtained, and an initial detection network model is obtained according to the deep convolutional neural network, the reflected image extraction network and the feature detection network;

[0099] T...

Embodiment 3

[0126] Embodiment 3. Based on Embodiment 1 and Embodiment 2, this embodiment also discloses a detection device for a railway machine tool, including a processor, a memory, and a computer stored in the memory and operable on the processor. A computer program that, when running, implements the figure 1 The specific steps from S1 to S4 are shown.

[0127] Through the computer program stored in the memory and running on the processor, the detection of the railway machine tool of the present invention is realized, which effectively solves the problems of complex background, uneven illumination, large difference in target scale, complex shape, and occlusion, etc. To a certain extent, it avoids the problems of sample imbalance and over-fitting, automatically detects the position and category of the machine tool in the image, quickly and accurately detects the target of the railway machine tool, realizes the automatic inventory of the railway machine tool, and greatly improves the Th...

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 relates to a railway tool detection method, system and device and a storage medium, and the method comprises the steps: obtaining a plurality of tool images, and making a data set according to all tool images; constructing a deep convolutional neural network, constructing a reflection image extraction network by using the data set and the deep convolutional neural network, obtaininga feature detection network according to the deep convolutional neural network and the reflection image extraction network, and obtaining an initial detection network model according to the deep convolutional neural network, the reflection image extraction network and the feature detection network; training the initial detection network model by using the data set to obtain a target detection network model; and detecting the to-be-detected tool image according to the target detection network model to obtain a detection result. According to the method, the problems of complex background, unevenillumination, large target scale difference, complex form, shielding and the like can be effectively solved, rapid and accurate target detection is carried out on the railway tools, and the automaticcounting of the railway tools is realized.

Description

technical field [0001] The invention relates to the technical field of railway operation and maintenance and target detection, in particular to a detection method, system, device and storage medium for railway machinery and tools. Background technique [0002] Railways are an important part of the transportation system. In order to ensure the safe operation of railways, railway departments usually carry out operation and maintenance work at night, and a large number of tools and tools are often lost during the operation and maintenance process. So far, the detection method of industrial tools adopted is to take pictures of the industrial tools collected and returned by workers, and to find lost industrial tools through manual comparison and analysis. This method requires workers to carry out cumbersome and repeated inspection work, which greatly wastes human and financial resources. Therefore, the automatic counting of railway tools and tools can be realized by analyzing t...

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): G06T7/70G06N3/04G06N3/08
CPCG06T7/70G06N3/08G06T2207/30164G06N3/045
Inventor 陈灯杨瑾王司恺魏巍张彦铎吴云韬周华兵刘玮段功豪卢涛于宝成鞠剑平唐剑隐徐文霞彭丽王逸文
Owner WUHAN INSTITUTE OF TECHNOLOGY
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