Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Dust removal and noise reduction neural network method for monitoring image under mine

A technology of neural network and neural network model, which is applied in the field of neural network for dust removal and noise reduction of underground monitoring images, can solve the problems of inability to remove dust and noise of monitoring images, and low definition of monitoring images, and achieve good portability and real-time performance, reduce model complexity, and reduce the effect of model parameters

Inactive Publication Date: 2020-04-21
XI AN JIAOTONG UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the large amount of dust in the mine and the complex environment, the surveillance images obtained by the surveillance equipment are of low resolution. The traditional physical dust removal methods for surveillance images, including keeping the equipment dry and improving the current of the main board, are not suitable for this situation and cannot be used for monitoring. Effectively deal with the problem of image dust removal and noise reduction

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
  • Dust removal and noise reduction neural network method for monitoring image under mine
  • Dust removal and noise reduction neural network method for monitoring image under mine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0018] Its model is as figure 1 As shown, it includes three VGG modules and a 1×1 convolutional layer, where each VGG module includes a convolutional layer and a pooling layer, and the convolutional layer and the pooling layer are sequentially from the input layer to the 1×1 Convolutional output layer permutations. According to the direction from input to output, the VGG modules are named as VGG module 1, VGG module 2 and VGG module 3.

[0019] The specific implementation plan is as follows:

[0020] Step 1: Design the specific parameters of the neural network model. The present invention mainly adopts VGG module to carry out model design, and each VGG module includes a convolutional layer and a pooling layer, and to different VGG modules, specific parameters are as follows:

[0021] (1) In VGG module 1, the shape of the convolutional layer is 64×3×11×11,...

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 dust removal and noise reduction neural network method for a monitoring image under a mine. The method comprises the steps of data image processing, neural network model design, loss function selection and optimization algorithm selection and model training. A final test result can reach about 24 FPS by configuring a computer environment, the requirement for real-time processing of monitoring images under a mine can be met, and the model file can also be stored in a development board, used for an embedded platform and has good portability. According to the invention,the images with dust and low definition collected in the mine are processed to obtain the dedusting images, so that the monitoring quality of the monitoring system is improved, and the defects in theprior art are overcome.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a neural network method for dust removal and noise reduction of underground monitoring images. Background technique [0002] Mine monitoring equipment is mainly used to detect parameters such as mine gas concentration, humidity, temperature, etc., to prevent explosions caused by excessive gas concentration. However, due to the large amount of dust in the mine and the complex environment, the surveillance images obtained by the surveillance equipment are of low resolution. The traditional physical dust removal methods for surveillance images, including keeping the equipment dry and improving the current of the main board, are not suitable for this situation and cannot be used for monitoring. Effectively deal with the problem of image dust removal and noise reduction. Contents of the invention [0003] In order to overcome the above-mentioned deficiencies in the ...

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): G06K9/00G06K9/40G06T5/00G06N3/04G06N3/08
CPCG06N3/08G06V20/36G06V20/52G06V10/30G06N3/045G06T5/70
Inventor 朱爱斌安德麟屠尧
Owner XI AN JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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