Hyperspectral mixed pixel unmixing method based on reconstruction error approximation method

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...

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

Images