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

A laser spectrum image compression method and system based on deep learning network

A deep learning network and spectral image technology, applied in the field of laser spectral image compression, can solve the problems of low compression efficiency, no redundant steps to eliminate, and poor coding gain status, and achieve the effect of compression and residual value reduction.

Active Publication Date: 2021-10-22
SHAANXI SCI TECH UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method does not eliminate redundant steps, and the image compression efficiency is not high
The latter uses a linear weighting algorithm to improve the prediction accuracy of the image coding block, and uses the distortion optimization method to select the optimal coding block size. The experimental results show that this method can achieve the compression of the laser spectrum image, but the coding gain is not good. The problem
In the above methods, there are problems of low compression efficiency and poor coding gain state, which will affect the performance of the compression 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
  • A laser spectrum image compression method and system based on deep learning network
  • A laser spectrum image compression method and system based on deep learning network
  • A laser spectrum image compression method and system based on deep learning network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] see figure 1 The laser spectrum image compression method based on the deep learning network provided in this embodiment includes the following steps:

[0035] Step 101: Acquire the laser spectrum image to be compressed;

[0036] Step 102: using the DPCM prediction algorithm to eliminate the redundancy between the spectra of the laser spectral image to be compressed to obtain the first spectral image;

[0037] Step 103: using the SPIHT algorithm to eliminate spatial redundancy in the first spectral image to obtain a second spectral image;

[0038] Step 104: Using the trained convolutional neural network to compress the second spectral image to obtain a compressed image.

[0039] Wherein, before step 104, the convolutional neural network needs to be trained to obtain a trained convolutional neural network. In the training of convolutional neural network, the second spectral image is used as input, and multiple convolutional layers and nonlinear activation layers are su...

Embodiment 2

[0091] see Figure 5 , the deep learning network-based laser spectral image compression system provided in this embodiment includes:

[0092] The laser spectrum image acquisition module 501 to be compressed is used to acquire the laser spectrum image to be compressed;

[0093] The inter-spectral redundancy elimination module 502 is used to eliminate the inter-spectral redundancy of the laser spectral image to be compressed by using the DPCM prediction algorithm to obtain the first spectral image;

[0094] A spatial redundancy elimination module 503, configured to eliminate spatial redundancy in the first spectral image by using the SPIHT algorithm to obtain a second spectral image;

[0095] The convolutional neural network training module 504 is configured to train the convolutional neural network to obtain a trained convolutional neural network.

[0096] An image compression module 505, configured to compress the second spectral image by using a trained convolutional neural...

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 laser spectrum image compression method and system based on a deep learning network. The method includes: acquiring a laser spectrum image to be compressed; using a DPCM prediction algorithm to eliminate spectral redundancy of the laser spectrum image to be compressed to obtain a first spectral image; using an SPIHT algorithm to eliminate spatial redundancy in the first spectral image , to obtain a second spectral image; using a trained convolutional neural network to compress the second spectral image to obtain a compressed image. Compared with the traditional method, the coding gain state of the method provided by the invention is better, and the image compression efficiency is higher, the laser spectrum image can be effectively compressed, and the method has higher application value.

Description

technical field [0001] The invention relates to the technical field of image compression, in particular to a laser spectrum image compression method and system based on a deep learning network. Background technique [0002] Laser spectral image compression technology, as the key technology of remote sensing data storage and transmission, from the perspective of information theory, most compression technologies complete the purpose of image compression by eliminating data redundancy, but different types of data, the data redundancy The rest of the properties are also different. It is generally believed that laser spectral image data contains two kinds of redundancy, inter-spectral redundancy and spatial redundancy. The research on laser spectral image compression is generally to extend the two-dimensional transformation and compression method to three-dimensional data, and then eliminate the redundancy between spectra while eliminating the two-dimensional space redundancy. ...

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): H04N19/50H04N19/182G06N3/04G06N3/08
CPCH04N19/50H04N19/182G06N3/08G06N3/045
Inventor 蒋媛
Owner SHAANXI SCI TECH 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