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

Hyperspectral mixed pixel unmixing method based on reconstruction error approximation method

A technology of mixing pixels and reconstructing errors, which is applied in the direction of instruments, character and pattern recognition, scene recognition, etc., can solve the problems of inability to guarantee the accuracy of the target loss function and the growth of reconstruction errors, so as to improve accuracy and overcome nonlinearity Effect

Inactive Publication Date: 2019-08-09
HUZHOU TEACHERS COLLEGE
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But based on L 2 The target loss function of the norm, because of the influence of outliers, the reconstruction error increases quadratically with the outliers
Worse still, in the L-based 2 Sparse constraints are imposed on the objective function of the norm, and the square-fold increase error caused by outliers will be passed to the sparse item
Therefore, only considering Gaussian noise and ignoring outlier interference cannot guarantee the accuracy of the constructed target loss function

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
  • Hyperspectral mixed pixel unmixing method based on reconstruction error approximation method
  • Hyperspectral mixed pixel unmixing method based on reconstruction error approximation method
  • Hyperspectral mixed pixel unmixing method based on reconstruction error approximation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] A kind of construction method of the mixed pixel unmixing model based on correlation entropy induction measure of the present invention, comprises the following steps successively:

[0040] a) Calculate the number of end members included in the mixed pixel matrix Y according to the virtual dimension method.

[0041] b) Initialize the endmember matrix U and the abundance matrix V. Set the value of q to be greater than 0 and less than 2.

[0042] c) According to the unmixing model based on the sparsity-constrained correlation entropy-induced metric,

[0043]

[0044] Iterate over related variables. in Refers to the mixed pixel matrix including various noises, nonlinearities and abnormal points, Represents the endmember matrix extracted from the mixed pixel matrix Y containing various noises, nonlinearities and outliers, represents the corresponding endmember abundance matrix.

[0045] c1) by U=U*[|(E-Y)V T |-(E-Y)V T ] / (2UVV T ), iteratively calculate the e...

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 construction method of a mixed pixel demixing model based on a correlation entropy induction measurement criterion. The method comprises the following steps of providing a sparse constraint reconstruction error approximation method unmixing model; deriving an unmixing result of the proposed model by adopting semi-quadratic minimization and a conjugate function theory; andquantitatively comparing and evaluating the unmixing performance of mixed pixels of the proposed model by using a multiplication iteration rule. According to the method, the influence of noise, nonlinearity and abnormal points on the hyperspectral image mixed pixel unmixing is overcome by constructing the mixed pixel unmixing model based on the correlation entropy induction measurement criterion;the model effectively overcomes the influence of various interferences in a hyperspectral image on demixing according to the characteristics that the correlation entropy induction measurement is insensitive to the abnormal points, and the nonlinear problem can be solved, so that a reconstruction error is accurately approximated, a guarantee is provided for improving the demixing performance of the mixed pixels, theoretical derivation is carried out on a proposed model, and the feasibility and the superiority of the mixed pixel demixing based on a correlation entropy induction measurement model are proved.

Description

[0001] 【Technical field】 [0002] The present invention relates to the technical field of hyperspectral mixed pixel unmixing model, in particular to the technical field of the construction method of mixed pixel unmixing model based on error approximation. [0003] 【Background technique】 [0004] The hyperspectral image is restricted by factors such as terrain changes and sensor resolution during the capture process, which leads to the generation of mixed pixels in the hyperspectral image. Unmixing mixed pixels of hyperspectral images is an important part of hyperspectral image analysis and processing. In addition, hyperspectral images are also affected by factors such as bad weather, illumination changes, and surface distribution during the imaging process. These factors make hyperspectral images include a lot of noise, nonlinearity, and abnormal points. In order to solve the influence of Gaussian noise, the traditional unmixing algorithm uses L 2 Norm constructs the objectiv...

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): G06K9/00
CPCG06V20/194G06V20/13
Inventor 李春芝陈晓华
Owner HUZHOU TEACHERS COLLEGE
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