Hyperspectral data dimensionality reduction method based on tensor distance patch alignment

Abstract

A hyperspectral data dimensionality reduction method based on tensor distance patch alignment belongs to a hyperspectral remote sensing image processing method. The hyperspectral data dimensionality reduction method aims at the tensor characteristic of the hyperspectral data. Firstly, the hyperspectral data is converted into a tensor form through a window area and maintains space information of every pixel; secondly, the tensor distance is introduced to construct a high-quality tensor distance neighbor graph containing determination information; thirdly, a globally optimal spectrum-space information is acquired according to a patch alignment framework expanded to tensor space; fourthly, solutions of tensor sub-space are obtained by using a iteration optimization method of the alternating least square algorithm; and lastly, categories of samples are discriminated on the basis of the tensor nearest neighbor method. The hyperspectral data dimensionality reduction method has the advantages that relatively high overall classification accuracy and the Kappa coefficient through effective utilization of the space area characteristic and the spectrum characteristic of the hyperspectral data, and the acquired classification effect picture is very clear and smooth with rich details; the dimensionality reduction framework can process 2-order data, 3-order data and data in higher orders.

Description

technical field [0001] The invention relates to a hyperspectral remote sensing image processing method, in particular to a hyperspectral data dimensionality reduction method based on tensor distance patch calibration. Background technique [0002] Hyperspectral image sensors are capable of collecting images containing hundreds of spectral bands per pixel. The data obtained by the hyperspectral image sensor is three-dimensional data, including two-dimensional spatial features (width and height) and one-dimensional spectral band information. For the analysis and processing of hyperspectral data, previous researchers have proved that the redundancy of inter-spectral correlation is very high, so the spectral bands in the data structure can be reduced without loss of important information for subsequent processing. Many bands. In order to reduce the redundancy between features, keep important discriminative information for subsequent classification processing and reduce computi...

AI Technical Summary

Problems solved by technology

[0005] Purpose of the present invention: To solve the problems and deficiencies in the above-mentioned prior art, a hyperspectral data dimensionality reduction method based on tensor distance patch calibration is proposed to solve the problem that the transformation of three-dimensional hyperspectral data into a one-dimensional vector will lead to the destruction of the internal structure of the data , the spatial characteristics of hyperspectral data are lost; too high dimension after vectorization will lead to the problem of "dimension disaster"

Images