A Method of Panchromatic Remote Sensing Image Compression Based on Sample Binary Tree Dictionary Learning

A remote sensing image, dictionary learning technology, applied in the field of signal processing, can solve the problems of texture information cannot be effectively represented, complex structure, etc., to achieve the effect of improving PSNR index and subjective visual evaluation

Active Publication Date: 2019-07-23
XIDIAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to address the deficiencies in the prior art above, and propose a panchromatic remote sensing image compression method based on sample binary tree dictionary learning, which is used to solve the problem of complex texture information in existing panchromatic remote sensing image compression methods. Technical issues that can be effectively represented

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 Method of Panchromatic Remote Sensing Image Compression Based on Sample Binary Tree Dictionary Learning
  • A Method of Panchromatic Remote Sensing Image Compression Based on Sample Binary Tree Dictionary Learning
  • A Method of Panchromatic Remote Sensing Image Compression Based on Sample Binary Tree Dictionary Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0040] refer to figure 1 , a full-color remote sensing image compression method based on sample binary tree dictionary learning, including the following steps:

[0041] Step 1. Randomly select 100,000 non-smooth image blocks with a size of 16×16 from one or more full-color training images, and pull each image block into a column vector, and then arrange these column vectors into a matrix to obtain sample set Among them, y i The column vector drawn for the i-th image block, i=1,2,...,100000;

[0042] Step 2. Establish a three-layer sample binary tree with the same number of leaf nodes and layers, and obtain three training sample sets:

[0043] 2a) Define the image block complexity function BC(X):

[0044]

[0045] Among them, X is containing 4 sub-image blocks x s image block, s is the sub-image block x s The serial number o...

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 provides a panchromatic remote sensing image compressing method based on sample binary tree dictionary learning, which is used to solve the technical problem that the complex texture information existing in the existing panchromatic remote sensing image compressing method cannot be expressed effectively. The implementation steps are as follows: through an image sample complexity evaluation function, distinguishing the simple sample from the complex sample in the image; preprocessing the trained images and the to-be-compressed images o obtain a sample set Y and a sample set T; through the sample set Y and sample set T, establishing a training sample binary tree and a testing sample binary tree to complete the division of samples of different complexities; using the samples of different complexities on the binary tree leaf nodes to train dictionaries of different scales; performing sparse encoding to the sample sets of different complexities on the testing sample binary tree leaf nodes in the corresponding dictionary and obtaining a coefficient matrix; and obtaining a binary coding stream coefficient matrix after quantized coding of the coefficient matrix. The compressed reconstructed image of the invention has a high PSNR index and achieves high subjective visual evaluation.

Description

technical field [0001] The invention belongs to the technical field of signal processing, and relates to a remote sensing image compression method, in particular to a panchromatic remote sensing image compression method based on sample binary tree dictionary learning, which can be used for panchromatic image storage and transmission with high spatial resolution, while not Compromise data availability. Background technique [0002] Remote sensing images are divided into panchromatic remote sensing images and multispectral remote sensing images according to the spectral dimension. Multispectral remote sensing images have low spatial resolution, high spectral resolution, and multiple spectral bands, while panchromatic remote sensing images have high spatial resolution and spectral The resolution is low, and there is only one spectral band. Especially with the development of remote sensing technology in recent years, the resolution of panchromatic remote sensing images has been ...

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): G06T9/40H04N19/124H04N19/176H04N19/85H04N19/96
CPCG06T9/40H04N19/124H04N19/176H04N19/85H04N19/96
Inventor 杨淑媛马文萍焦李成刘林瓒段韵章王敏刘志吕文聪黄震宇刘振孟丽珠
Owner XIDIAN 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