Supercharge Your Innovation With Domain-Expert AI Agents!

A video image encoding and decoding method for mine intelligent monitoring

An encoding and decoding method and video image technology, applied in the field of intelligent monitoring and image processing, can solve problems such as poor real-time performance, and achieve the effect of improving performance and real-time performance.

Active Publication Date: 2020-08-04
CHINA UNIV OF MINING & TECH (BEIJING)
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention mainly solves the problem of poor real-time performance when traditional compressed sensing methods are reconstructed, and proposes a video image encoding and decoding method for mine intelligent monitoring

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 video image encoding and decoding method for mine intelligent monitoring
  • A video image encoding and decoding method for mine intelligent monitoring
  • A video image encoding and decoding method for mine intelligent monitoring

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The present invention will be described in detail below with reference to the drawings and specific embodiments.

[0054] Reference figure 1 , Is the implementation flow chart of the video image coding and decoding method used for mine intelligent monitoring. First, the existing mine image monitoring system is used to collect 35,000 images of the underground scene with 1000 pixels×1000 pixels. Randomly select 30,000 images to generate the training set, and the remaining 5,000 images to generate the test set.

[0055] Set the training batch size to 64 images / batch, and set the maximum number of iterations to 20000. Input the training set into the encoder network and the decoder network for training. When the average mean square error between the reconstructed image and the original image obtained on the training set is less than 0.001 or reaches the maximum number of iterations, the training is considered complete, otherwise the training continues. The following formula giv...

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 video image coding and decoding method for intelligent mine monitoring. The method adopts a machine vision-based convolutional neural network algorithm and achieves coding and decoding functions on mine video images. The method comprises the following steps: 1, images are acquired by mine video image acquisition equipment, and a training set and a test set are made accordingly; 2, a coder network and a decoder network of the mine video images are constructed, wherein the coder network comprises a downsampling layer, and the decoder network comprises upsampling layers,a two-branch convolution layer, standardization layers, non-linear activation layers and a depth transform layer; 3, the networks are trained; and 4, coding and decoding of the mine video images arecompleted by means of the trained networks. According to the method, the problem that the coding, decoding and signal reconstruction time of a mine video monitoring system is too long is solved, and the performance of the intelligent mine video monitoring system is improved.

Description

Technical field [0001] The invention belongs to the signal coding and decoding technology in the field of intelligent monitoring and image processing, and particularly relates to a video image coding and decoding method used for mine intelligent monitoring. Background technique [0002] Realizing the low-person or even unmanned operation of the underground working face is one of the most important goals of safe mining and smart mine construction. Research on the optimization method and key technologies of the mine smart video monitoring system is helpful to promote the development of mine smart and safe mining technology and smart mine construction Has a very important meaning. The image compression method in the traditional video surveillance system uses the classic Nyquist sampling theorem to solve the problem of video image signal acquisition, encoding and decoding. However, the data volume of the mine video image signal is large, and the traditional compression method not 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 Patents(China)
IPC IPC(8): H04N19/132H04N19/42H04N19/44H04N7/18
CPCH04N7/18H04N19/132H04N19/42H04N19/44
Inventor 张帆徐志超
Owner CHINA UNIV OF MINING & TECH (BEIJING)
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com