Blind hyperspectral unmixing model construction method based on Sinkhorn distance

Abstract

The invention discloses a blind hyperspectral unmixing model construction method based on Sinkhorn distance, and the method comprises the steps: replacing an Euclidean distance with an Earth Mover's Distance (EMD), and overcoming the noise influence; improving the EMD into a Sinkhorn distance through entropy regularization constraint, and modeling the relationship between different feature dimensions, so that the correlation between the features is ensured; and based on a manifold learning theory, introducing a graph regularization term to maintain a local geometric structure between data. According to the method, the problems that the traditional Euclidean distance is easily influenced by noise and correlation characteristics in an image space are ignored are solved by constructing the unmixing framework based on the Sinkhorn distance. According to the characteristic that the EMD is insensitive to the relation between the features of different dimensions, the model takes the Sinkhorn distance as the standard of error measurement, the features on different dimensions can be effectively modeled, and the correlation between the features is fully developed and utilized. The unmixing performance of the proposed model is quantitatively evaluated by adopting a Lagrange function method and a KKT condition, and the feasibility and superiority of the unmixing model are proved.

Description

【Technical field】 [0001] The invention relates to the technical field of processing mixed pixel decomposition problems in hyperspectral images, in particular to a method for constructing a blind hyperspectral unmixing model based on Sinkhorn distance. 【Background technique】 [0002] Hyperspectral blind unmixing is an important technique to solve the problem of mixed pixels. Among them, non-negative matrix factorization (NMF) lays the foundation for the development of unsupervised linear spectral unmixing by virtue of its clear physical meaning. Traditional NMF usually uses Euclidean distance as a similarity measure method. However, hyperspectral data is distributed in a nonlinear manifold, and a simple linear measure between two points cannot accurately represent the distance between data, and the objective function constructed based on this method ignores the image Correlation features in the space, affecting subsequent unmixing performance. In order to further dig out th...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problems in the prior art, and propose a method for constructing a blind hyperspectral unmixing model based on Sinkhorn distance, through which the unmixing model can overcome the problem that Euclidean distance is easily affected by noise, and can overcome The effect of ignoring the correlation between features on the performance of hyperspectral image mixture pixel decomposition

Images