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

Non-negative sparse matrix-based WorldView-2 remote sensing panchromatic and multi-spectral image fusion method

A multi-spectral image, non-negative sparse technology, applied in the field of remote sensing panchromatic and multi-spectral image fusion, can solve the problem that the brightness component is not accurate enough, can not solve the problem of detail integration and spectral distortion, and achieve a reasonable extraction algorithm and improved Extraction accuracy, overall high quality results

Active Publication Date: 2016-12-07
NORTHWESTERN POLYTECHNICAL UNIV
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The existing fusion methods are aimed at traditional satellite remote sensing multispectral images. For ultra-high resolution remote sensing images, it is not the optimal image fusion method, and the existing brightness component extraction methods cannot solve the problem of detail fusion. and spectral distortion problems, making the extracted brightness components inaccurate

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
  • Non-negative sparse matrix-based WorldView-2 remote sensing panchromatic and multi-spectral image fusion method
  • Non-negative sparse matrix-based WorldView-2 remote sensing panchromatic and multi-spectral image fusion method
  • Non-negative sparse matrix-based WorldView-2 remote sensing panchromatic and multi-spectral image fusion method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

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

[0040] Step 1. Extract the I component using the non-negative matrix factorization (NMF) method

[0041] As a relatively mature data analysis method, non-negative matrix factorization has been widely used in image analysis, text clustering, data mining, speech processing, etc. Considering that the I component extracted from the multispectral image should be consistent with the spectral response of the panchromatic image as much as possible, the matrix V to be decomposed is composed of the panchromatic image and the eight-band multispectral image in the method of extracting the I component by NMF .

[0042] First, the panchromatic image Pan and the eight-band multispectral image X 1 ,X 2 ,...,X 8 Straighten by row to get P,M 1 , M 2 ,...,M 8 vector, and then compose the matrix V to be decomposed according to the formula (1), namely

[0043] V=[P,...

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 non-negative sparse matrix-based WorldView-2 (WV-2) remote sensing panchromatic and multi-spectral image fusion method, and relates to the field of image fusion. Multi-spectral images are subjected to brightness component extraction by using a non-negative matrix factorization (NMF) algorithm; and then the images are fused by using hyperspherical color space resolution merge (HCS) transformation to obtain a fused image. The fused image is improved in the aspects of detail injection and spectral preservation to a certain extent, and finally a high-quality fused result is obtained. An NMF method is adopted for I component extraction, so that the brightness component extraction precision is improved. Compared with a comparison algorithm, the method is more reasonable, so that the overall quality of the fused image of a WV-2 satellite is relatively high, the fused image is improved in the aspects of the detail injection and the spectral preservation to a certain extent, subjective evaluation and objective analysis results can reach consistency, the obtained fused image is better in visuality, and a picture is clearer. Compared with a traditional remote sensing panchromatic and multi-spectral image fusion method, the method provided by the invention is more advantageous.

Description

technical field [0001] The invention relates to the field of image fusion, in particular to a method for remote sensing panchromatic and multispectral image fusion. Background technique [0002] In recent years, the number of bands of new satellite remote sensing multispectral images has been increasing, and the resolution of images has also been rapidly improved. Take the WorldView-2 (WV-2) satellite as an example. The WV-2 satellite was launched in 2009 and can provide multi-spectral images with a resolution of 1.84 meters in 8 bands and panchromatic images with a resolution of 0.46 meters in a single band. Compared with traditional satellite images, it has the following characteristics: the number of bands increases, and the spectral division is finer; the spectral coverage of panchromatic images is narrowed, so that the spectral matching with multi-spectral bands has a large change. In remote sensing applications, images with both high spatial and high spectral resoluti...

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): G06T5/50
CPCG06T5/50
Inventor 何贵青董丹丹邢思远梁凡夏召强冯晓毅李会方谢红梅吴俊蒋晓悦
Owner NORTHWESTERN POLYTECHNICAL 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