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

Unmixing method of chnmf remote sensing image based on information entropy

A remote sensing image and information entropy technology, applied in the field of CHNMF remote sensing image unmixing based on information entropy, can solve the problem of not considering the physical information of remote sensing data, and achieve a good unmixing effect

Active Publication Date: 2021-10-08
CHINA UNIV OF GEOSCIENCES (WUHAN)
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] However, the above optimization algorithms only consider the spectral information and spatial information of remote sensing data, and most of them introduce L 1 , L 2 The constraints of equal norms are used to optimize the algorithm, and the physical information of remote sensing data is not considered

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
  • Unmixing method of chnmf remote sensing image based on information entropy
  • Unmixing method of chnmf remote sensing image based on information entropy
  • Unmixing method of chnmf remote sensing image based on information entropy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] Embodiment 1. In this embodiment, synthetic data is used to verify the effectiveness of the CHNMF algorithm, and compared with the traditional NMF algorithm and CNMF algorithm. The initial value is obtained randomly. And the regularization parameter of CHNMF also refers to the empirical value of CNMF. Three kinds of ground features, Carnallite, Chert and Andradite, were still selected as the experimental results, and the experimental results were the average results of 25 experiments.

[0072] Such as figure 2 As shown, the comparison between the three kinds of endmember abundance maps unmixed by the three algorithms of NMF, CNMF and CHNMF and the real endmember abundance map, the local areas circled by white rectangles in the table, from top to It is getting closer and closer to the reference result, that is to say, the endmember abundance map unmixed by CHNMF is the closest to the real endmember abundance map.

[0073] Table 1 shows the comparison of the SAD value...

Embodiment 2

[0076] Embodiment 2. In this embodiment, the data used is part of the data of Cuprite in Nevada, USA. Through real data experiments, the unmixing of the three algorithms of NMF, CNMF and HCNMF is further compared and analyzed. The abundance map is represented by The result of the tetracorder operation is used as a reference. For the spectral curve of the end member, the spectral curve of the end member is extracted from the original data on the ENVI4.8 platform as a reference result, and hematite, chalcedony and brilliance are selected. The three typical features of pyroxene are used as reference results, such as image 3 As shown in Table 2, the abundance maps, SAD values ​​and RMSE values ​​of the three endmembers after the unmixing of the three algorithms are given in turn.

[0077] From the abundance map, for hematite, the area circled by the white box in the second column in the table, from top to bottom, the color is getting closer to black, which is closer to the refere...

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 present invention provides a CHNMF remote sensing image unmixing method based on information entropy, comprising: S1, establishing an NMF-based remote sensing image unmixing algorithm for the current remote sensing image; S2, establishing a current remote sensing image based on the NMF-based remote sensing image unmixing algorithm Smoothness Constrained CNMF Remote Sensing Image Unmixing Algorithm to obtain L 2 Norm; S3. Obtain the information entropy of the current remote sensing image; S4. For the NMF-based remote sensing image unmixing algorithm, use the L obtained in S2 2 The norm is used as a regularization function to constrain the endmember spectral matrix M, and the information entropy obtained in S3 is used as a regularization function to constrain the abundance matrix S to establish a CHNMF remote sensing image unmixing method based on information entropy. Compared with the traditional algorithm, the invention has better unmixing effect.

Description

technical field [0001] The invention relates to a CHNMF remote sensing image unmixing method based on information entropy. Background technique [0002] Remote sensing technology is a new technology that intersects multiple disciplines such as detection and information detection. As the research and development of imaging spectrometers continues to make new breakthroughs, image analysis technology is getting more and more in-depth, and the research and development of remote sensing technology has set off an upsurge, which has won the favor of the majority of scientific researchers and occupies a place in various fields. [0003] The prototype of remote sensing technology is the imaging spectrometer research and development program, which was first formulated and proposed by the Jet Propulsion Lab (JPL) of the California Institute of Technology. The world's first generation of high-resolution aerial imaging spectrometer - AIS-1 was born in the United States in 1983. The sec...

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): G06T5/00
CPCG06T5/00G06T2207/10032G06T5/70
Inventor 李杏梅刘晓杰王心宇
Owner CHINA UNIV OF GEOSCIENCES (WUHAN)