Dimension reducing and sorting method of hyperspectral imagery based on blocking low rank tensor analysis

Abstract

The invention belongs to the technical field of remote sensing image processing and particularly relates to a dimension reducing and sorting method of a hyperspectral imagery based on blocking low rank tensor analysis. According to the dimension reducing and sorting method of the hyperspectral imagery based on the blocking low rank tensor analysis, a blocking idea is introduced into a dimension reducing method of the hyperspectral imagery based on the low rank tensor analysis according to three-dimensional data structures, spectral characteristics and correlated characteristics of local spaces of the hyperspectral imagery, the problems that integral spatial correlation of the imagery is weaker and negative effects of configuration of dimension-reduced subspace dimension on a dimension reducing effect are overcome, finally a novel dimension reducing method capable of greatly improving total sorting precision of the imagery is realized, and the novel dimension reducing method is a blocking low rank tensor analysis method. An algorithm presents well applicability on various different hyperspectral data (including simulation data and actual data sets). The dimension reducing and sorting method of the hyperspectral imagery based on the blocking low rank tensor analysis has important application values in high-precision terrain classification aspects based on the hyperspectral imagery.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a block-based tensor analysis theory and a method for solving the problem of dimensionality reduction and classification of hyperspectral remote sensing data. Background technique [0002] Remote sensing is a new comprehensive technology developed in the 1960s. It is closely related to science and technology such as space, electron optics, computer, and geography. It is one of the most powerful technical means for studying the earth's resources and environment. In recent years, with the development of hyperspectral imaging technology, hyperspectral remote sensing has become a rapidly developing branch of remote sensing. As a multi-dimensional information acquisition technology, it combines imaging technology and spectral technology to simultaneously acquire information in tens to hundreds of very narrow and continuous spectral intervals of the ...

AI Technical Summary

Problems solved by technology

Moreover, the classification accuracy of LRTA after dimensionality reduction is greatly affected by the subspace, and the existing subspace estimation methods (such as Hysime, AIC, MDL [4-10]) are not reliable, and often cannot find out the performance of LRTA to achieve optimal optimal subspace

Images