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

Method for enhancing distinguishability cooperated with space-optical spectrum information of high optical spectrum image

A hyperspectral image and spectral information technology, which is applied in the field of hyperspectral image information to improve spatial resolution, can solve the problem of not being able to make full use of spatial information and spectral information image resolution, and achieve the goal of improving spatial resolution and breaking through image acquisition methods The effect of limiting and making up for the lack of hardware

Inactive Publication Date: 2009-07-15
HARBIN INST OF TECH
View PDF5 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 solve the problem that the existing hyperspectral image processing technology cannot make full use of spatial information and spectral information to improve the image resolution, and then propose a space-spectral information of hyperspectral image to jointly improve the resolution Methods

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
  • Method for enhancing distinguishability cooperated with space-optical spectrum information of high optical spectrum image
  • Method for enhancing distinguishability cooperated with space-optical spectrum information of high optical spectrum image
  • Method for enhancing distinguishability cooperated with space-optical spectrum information of high optical spectrum image

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0023] Specific implementation mode one: combine figure 1 Describe this embodiment, the steps of this embodiment are as follows:

[0024] Step 1: Input hyperspectral image data: read in hyperspectral image data according to the data format, and simultaneously input the hyperspectral image data into the spatial information extraction module in step A and the spectral information extraction module in step B of the computer to perform information extraction;

[0025] Step 2: This step includes step A and step B,

[0026] Step A: Spatial information extraction: Feature band selection and spatial local analysis and judgment are performed through the spatial information module;

[0027] Step A1: Feature band selection: feature band selection is to extract or select feature bands with large amount of information in the hyperspectral image data;

[0028] Step A2: Spatial local analysis and judgment: use the differential operator edge detection algorithm to extract the edge informat...

specific Embodiment approach 2

[0034] Specific embodiment two: the difference between this embodiment and specific embodiment one is that the method used in the feature band selection in step A one has principal component transformation to extract feature bands or select feature bands based on the principle of maximum information entropy; other composition and connection methods are the same as The specific embodiment one is the same.

specific Embodiment approach 3

[0035] Specific implementation mode three: combination figure 2 Describe this embodiment, the difference between this embodiment and specific embodiment 1 is that the spatial local analysis and judgment in step A 2 is to analyze the hyperspectral image of each characteristic spectrum segment, where x i，j is the pixel to be processed in the single-band hyperspectral image, W is the local window centered on the pixel, and a 3×3 window is used as an example to illustrate:

[0036] W = x i - 1 , j - 1 , x i - ...

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 method for synergistically improving resolution with spatial-spectral information of hyperspectral images, which relates to a method for improving spatial resolution by utilizing hyperspectral image information. It solves the problem that the existing hyperspectral image processing cannot make full use of spatial information and spectral information to improve image resolution. The steps of the present invention are: 1. Input hyperspectral image data; A. Spatial information extraction; A1. Feature band selection; A2. Spatial local analysis and judgment; B. Spectral information extraction; B1. Spectral endmember extraction; B. 2. Decomposition of mixed pixels; C. Space-spectrum collaborative super-resolution; D. Hyperspectral image with improved resolution. The present invention breaks through the spatial resolution limit of image acquisition; utilizes support vector machine unmixing and local spatial correlation to carry out spatial-spectral information collaboration technology to improve the spatial resolution of hyperspectral images, which can greatly improve the detection and positioning capabilities of targets, Break through the limitations of image acquisition methods and make up for the lack of hardware.

Description

technical field [0001] The invention relates to a method for improving spatial resolution by using hyperspectral image information. Background technique [0002] Spatial resolution is simply a measure of the imaging system's ability to distinguish image details, and it is also an indicator of the subtlety of objects in the image. It represents the detail level of scene information and is one of the important indicators for evaluating sensor performance and remote sensing information. An important basis for the shape and size of ground objects. The spatial resolution of the remote sensing image is directly related to the imaging optical system. If the resolution is low, there will be more mixed pixels in the remote sensing image, which will seriously affect the analysis and understanding of the image. In terms of detection and identification, it is very unfavorable. [0003] Spectral resolution refers to the fineness of the discrete sampling of the surface object spectrum b...

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): G01S17/89G01S7/48G01J3/28
Inventor 张钧萍张晔谷延锋邹斌王立国陈浩
Owner HARBIN INST OF TECH
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