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

A Hyperspectral Mixed Pixel Decomposition Method Based on Abundance and Sparse Constraints

A technology of mixed pixel decomposition and sparse constraints, applied in instrumentation, scene recognition, calculation, etc., can solve problems such as ignoring abundance and sparsity, and achieve the effect of improving accuracy

Active Publication Date: 2022-06-28
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the abundance sparsity is ignored in the PCHA algorithm of the main convex hull prototype analysis, a hyperspectral mixed pixel decomposition method based on the abundance sparsity constraint is proposed

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 Hyperspectral Mixed Pixel Decomposition Method Based on Abundance and Sparse Constraints
  • A Hyperspectral Mixed Pixel Decomposition Method Based on Abundance and Sparse Constraints
  • A Hyperspectral Mixed Pixel Decomposition Method Based on Abundance and Sparse Constraints

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The key invention of the present invention is the hyperspectral mixed pixel decomposition method based on the abundance-sparse prototype analysis, which mainly improves the problem that the main convex hull prototype analysis algorithm ignores the abundance-sparse characteristics, and improves the accuracy of the hyperspectral mixed pixel decomposition . combine figure 1 , the specific embodiment of the present invention will be described in further detail.

[0045] 1. A hyperspectral mixed pixel decomposition method based on abundance sparse constraints, characterized in that it comprises the following steps:

[0046] (1) Input hyperspectral image R with size L×M×N mixed , transform it into a two-dimensional L×n image matrix R, where L is the total number of bands, n is the total number of pixels, and its size is:

[0047] n=M×N

[0048] where M is the image R mixed The number of rows, N is the number of columns of the image;

[0049] (2) Construct the objective ...

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

In order to improve the accuracy of hyperspectral mixed pixel decomposition, a hyperspectral mixed pixel decomposition method based on abundance and sparse constraints is proposed to solve the problem that the abundance sparsity is ignored in PCHA, the main convex hull prototype analysis algorithm. This method combines the matrix decomposition form of the original algorithm, on the basis of the original objective function, adding the abundance l 1 ‑norm sparse constraint regularization term; then, the coefficient matrix and abundance matrix are optimized and solved by projected gradient and alternating direction multiplier method respectively; finally, endmembers and abundance are obtained according to the solution results. This method can realize endmember extraction and abundance estimation at the same time, has lower data fitting error, and the solved abundance is closer to the actual situation in the physical sense.

Description

technical field [0001] The invention belongs to the technical field of hyperspectral mixed pixel decomposition, in particular to a hyperspectral mixed pixel decomposition algorithm based on abundance and sparse constraints. Background technique [0002] Due to the limited spatial resolution of hyperspectral images, complex and diverse natural features, and the mixing effect in the image acquisition process, there are widely mixed pixels in hyperspectral remote sensing images, resulting in low accuracy and poor effect of hyperspectral classification, which restricts hyperspectral classification. Development and application of remote sensing technology. Endmember extraction and abundance estimation in spectral unmixing technology are the key technologies to solve the problem of mixed pixels. Among them, the endmember extraction can identify the potential characteristics in the image and extract the object categories that make up the image, and the abundance estimation can obt...

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): G06V20/13G06V10/77
CPCG06F18/2136
Inventor 许明明杨志如叶传龙刘善伟
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)