Hyperspectral image compression method and device based on deep learning

A hyperspectral image and deep learning technology, applied in the field of hyperspectral image compression method and device based on deep learning, can solve the problems of poor compression effect of hyperspectral image, achieve the effect of improving the compression effect and reducing the number of bits

Inactive Publication Date: 2019-10-18
WUHAN UNIV
View PDF8 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In view of this, the present invention provides a hyperspectral image compression method and device based on deep learning to solve or at le

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
  • Hyperspectral image compression method and device based on deep learning
  • Hyperspectral image compression method and device based on deep learning
  • Hyperspectral image compression method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] The embodiment of the present invention provides a hyperspectral image compression method based on deep learning, please refer to figure 1 , the method includes:

[0051] Step S1: select a preset number of images as training images, and randomly crop the size of the training images to 32×32 as the training set, wherein the training images include ordinary images and hyperspectral images.

[0052] Specifically, the preset number can be set according to actual conditions. The training images selected by the present invention include ordinary images and hyperspectral images. In order to enable the network model of the present invention to compress the hyperspectral images, the present invention preprocesses the hyperspectral images and cuts the ordinary images and the hyperspectral images. together as the training set.

[0053] Step S2: Input the training set into the pre-built compressed network model, train the compressed network model, and obtain the trained compresse...

Embodiment 2

[0098] This embodiment provides a hyperspectral image compression device based on deep learning, please refer to Figure 6 , the device consists of:

[0099] The preprocessing module 201 is used to select a preset number of images as training images, and randomly crop the size of the training images to 32×32 as a training set, wherein the training images include ordinary images and hyperspectral images;

[0100] The model training module 202 is used to input the training set into the pre-built compressed network model, train the compressed network model, and obtain the trained compressed network model, wherein the trained compressed network model includes an encoding network, a quantization network and and decoding network;

[0101] The image compression module 203 is used to input the image to be compressed into the trained compression network model, extract the features of the image to be compressed through the encoding network to obtain the encoded feature map, and perform...

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 hyperspectral image compression method based on deep learning. The method comprises the following steps: firstly, selecting a training image, randomly cutting the size of thetraining image into a 32 * 32 size as a training set, and inputting the training set into a built compression network model for training to obtain a compression model comprising an encoding network,a quantization network and a decoding network; inputting an image to be compressed into a coding network, a coded feature map is obtained according to a calculation result of the coding network, theninputting the obtained feature map into a quantization network for quantization calculation to acquire code streams; finally inputting the quantized result into a decoding network, and acquiring a reconstructed image through calculation of a decoding network model. According to the invention,a hyperspectral image can be compressed, and the compression effect is improved.

Description

technical field [0001] The invention relates to the technical field of hyperspectral image compression, in particular to a hyperspectral image compression method and device based on deep learning. Background technique [0002] Compared with natural images, hyperspectral images contain two-dimensional spatial information and one-dimensional spectral information. Wherein, each spectral band corresponds to a two-dimensional image, and pixels at the same position in different bands form a spectral curve. Taking advantage of the differences in spectral curves of different ground features, hyperspectral images are widely used in various fields of the national economy. With the popularization of the application of high-resolution remote sensing imaging technology, how to effectively compress the challenges of the surge in transmission and storage data due to the significant improvement in the spectral and spatial resolution of remote sensing images is an urgent problem to be solve...

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): G06K9/62G06N3/04G06T9/00
CPCG06T9/008G06T9/00G06T2207/20081G06N3/045G06F18/214
Inventor 种衍文李浩南潘少明
Owner WUHAN UNIV
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