General integrated hyperspectral image mixed pixel demixing frame

Abstract

The invention discloses a general integrated mixed pixel demixing framework model. A model solving method is provided. A hyperspectral image is divided into a plurality of sub-blocks; a proper overlapped area is reserved in adjacent areas of the sub-block; therefore, the problems of end member variation and non-linear non-uniform distribution are solved; the problem of abnormal noise is solved through sparse constraint reconstruction errors, the three problems of nonlinearity, end member variation and abnormal points are integrated into the same unmixing framework to be solved through a correlation entropy induction measurement criterion, and the unmixing performance of the proposed model mixed pixels is quantitatively evaluated through a Lagrangian function method and a KKT condition. Theinfluence of non-linearity, end member variation bars and abnormal points on hyperspectral image mixed pixel unmixing is overcome by constructing a universal integrated mixed pixel unmixing frameworkmodel. According to the characteristics of nonlinearity and end member variation heterogeneous distribution, and abnormal points including abnormal end members and abnormal noise, the model effectively simulates Gaussian mixture distribution, abandons sparse distribution of abnormal noise, and improves the unmixing performance of mixed pixels. And theoretical derivation is carried out on the proposed model, so that the feasibility and superiority of mixed pixel demixing based on a general integrated framework are proved.

Description

[0001] 【Technical field】 [0002] The present invention relates to the technical field of solving three challenging problems in the hyperspectral mixed pixel unmixing problem, especially the technical field of the construction method of the mixed pixel unmixing model based on a general integration framework. [0003] 【Background technique】 [0004] Hyperspectral image imaging is limited by complex physical conditions. In addition to noise, the image also includes nonlinearity, variable endmembers, and abnormal points. Non-linearity, variable endmembers and outliers are the three major challenges in the process of mixed pixel unmixing. These three challenging issues intersect and jointly affect the accuracy of unmixing results. The complex formation mechanism of the three problems of nonlinearity, variable endmembers and outliers makes it difficult to accurately characterize, so it is difficult to consider these three problems simultaneously in the unmixing model. Since hypers...

AI Technical Summary

Problems solved by technology

These three challenging issues intersect and jointly affect the accuracy of unmixing results

The complex formation mechanism of the three problems of nonlinearity, variable endmembers and outliers makes it difficult to accurately characterize, so it is difficult to consider these three problems simultaneously in the unmixing model

Since hyperspectral unmixing is an ill-posed problem, only one or two of the above challenging problems can be solved, and accurate unmixing results cannot be obtained.

Images