Unlock instant, AI-driven research and patent intelligence for your innovation.

Hyper-spectral remote sensing image fusion method based on multi-scale geometric analysis and PCA transform

A hyperspectral remote sensing and hyperspectral image technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of band selection, low computing efficiency, too many dimensions, etc., and achieve good quality and facilitate extraction Effect

Inactive Publication Date: 2017-11-14
SHANGHAI OCEAN UNIV
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The large number of bands in hyperspectral images forms a massive amount of data, and the processing of hyperspectral images is faced with the problem of too many dimensions: difficulties such as band selection and low computational efficiency

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
  • Hyper-spectral remote sensing image fusion method based on multi-scale geometric analysis and PCA transform
  • Hyper-spectral remote sensing image fusion method based on multi-scale geometric analysis and PCA transform
  • Hyper-spectral remote sensing image fusion method based on multi-scale geometric analysis and PCA transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to make the present invention more comprehensible, it will be described in detail below in conjunction with specific embodiments and accompanying drawings. It should be understood that these examples are only illustrative of the invention.

[0039] combine figure 1 A hyperspectral remote sensing image fusion method based on multi-scale geometric analysis and PCA transformation provided by the present invention comprises the following steps:

[0040] Step 1: Hyperspectral image preprocessing and registration of N bands;

[0041] The hyperspectral image not only records the image information of the ground object, but also records the spectral information; each band of the hyperspectral image is imaged separately, and the imaging of these bands can be superimposed, as if after classification, each layer is imaged separately , each layer of surface features has the same radiation value, that is, spectral information.

[0042] Step 2: Carry out multi-scale geomet...

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 relates to a hyperspectral remote sensing image fusion method based on multi-scale geometric analysis and PCA transformation, which is characterized in that it includes the following steps: preprocessing and registering hyperspectral images of N bands; Perform multi-scale geometric analysis transformation on hyperspectral images to obtain multi-scale geometric analysis coefficient Cj(i) and geometric flow Gj(i) of hyperspectral images in each band; use PCA transformation to analyze multi-scale geometric analysis of hyperspectral images in N bands The coefficients and geometric flow are obtained to obtain their respective principal components; the multi-scale geometric analysis inverse transformation is carried out, and the new fusion image is reconstructed. The quality of the remote sensing image obtained by the method of the invention is better, and it is also more conducive to subsequent processing such as extraction and classification of the remote sensing image.

Description

technical field [0001] The invention relates to a fusion method of hyperspectral remote sensing images. Background technique [0002] Remote sensing is to use any object to have different electromagnetic wave reflection or radiation characteristics, obtain target information by obtaining electromagnetic waves reflected or radiated by ground targets, and process the obtained information to achieve target positioning, identification, qualitative or quantitative description etc. Remote sensing science is a comprehensive science. It is based on space information science, electronic information science, optics, computer science, biology, chemistry and other disciplines. Through the observation of space objects, it provides information for human activities such as national economy and scientific research. Abundant mass remote sensing image data. [0003] The multi-scale geometric analysis transform is a two-dimensional wavelet transform based on the edge. By defining the geometr...

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 Applications(China)
IPC IPC(8): G06T5/50
CPCG06T5/50G06T2207/10036G06T2207/20064G06T2207/20221
Inventor 朱卫东刘宇宸邱振戈栾奎峰沈蔚
Owner SHANGHAI OCEAN UNIV