Tucker decomposition-based spectral tensor dimension reduction and classification method

Abstract

The invention discloses a Tucker decomposition-based spectral tensor dimension reduction and classification method. The method comprises the steps of constructing a three-order tensor by taking factors influencing a spectral feature of a ground object as intra-class factors and taking the intra-class factors, classes and pixel spectrums as modes respectively, and performing low-rank tensor decomposition-based dimension reduction on the three-order tensor; performing low-rank tensor decomposition on the three-order tensor to obtain a nuclear tensor Z, a class space matrix Uclass, an intra-class factor space matrix Uwithin-class and a pixel spectral matrix Upixels; and performing classification on unclassified test hyperspectral images d by adopting a supervised classifier. According to the method, the hyperspectral images can be classified after model building, and adjustment does not need to be carried out; for other tensor modeling methods, the best classification effect can be achieved by repeated setting and adjustment of parameters; and all pixel spectrums in a class are mapped to a same coefficient vector, so that the influence of various factors is reduced to minimum, the classification precision is improved, and a result is stable.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a spectral tensor dimension reduction and classification method based on Tucker decomposition. Background technique [0002] Hyperspectral images provide a detailed and rich description of the spectral characteristics of ground objects, greatly improving the classification ability of ground objects, and have been widely used in geological exploration and earth resource investigation, urban remote sensing and planning management, environmental and disaster monitoring, precision agriculture, surveying and mapping and archaeology. [0003] However, hyperspectral images are composed of a large number of band data, and these bands constitute a high-dimensional feature space, and its processing requires a huge amount of calculation, causing a "data disaster". To solve this problem, the most effective way is dimensionality reduction. Principal Compo...

AI Technical Summary

Problems solved by technology

However, this method only simply models the hyperspectral cube as a third-order tensor, without considering the real reason that affects the accuracy of hyperspectral classification: the spectral characteristics of ground objects are affected by various factors such as illumination, mixing, atmospheric scattering, and atmospheric radiation.

Images