Space spectrum full convolution hyperspectral image classification method based on superpixel sample expansion

Abstract

The invention discloses a space-spectrum full-convolution hyperspectral image classification method based on superpixel sample expansion. The method comprises the following steps: inputting a hyperspectral image; obtaining a training set and a test set; performing principal component analysis and dimension reduction on the hyperspectral image; performing entropy rate segmentation on the dimensionreduction result; generating a pseudo label sample; updating the training set; performing data preprocessing on the hyperspectral image; inputting the data into a convolutional neural network; training a convolutional neural network, and classifying the hyperspectral images; repeating the above operations and performing voting; and outputting a high spectral classification result. According to themethod, the entropy rate super-pixel segmentation result is used for expanding the pseudo-label sample, the prior characteristics of the hyperspectral image are fully used, the number of samples is increased, the problems of network overfitting and low network convergence speed are solved, and the classification accuracy of the hyperspectral image under the condition of scarcity of marked samplesis improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for classifying hyperspectral images with spatial spectrum full convolution based on superpixel sample expansion. Background technique [0002] With the advancement of science and technology, hyperspectral remote sensing technology has been greatly developed. Hyperspectral data can be represented as a hyperspectral data cube, which is a three-dimensional data structure. Hyperspectral data can be regarded as a three-dimensional image, and one-dimensional spectral information is added to the ordinary two-dimensional image. Its spatial image describes the two-dimensional spatial characteristics of the earth's surface, and its spectral dimension reveals the spectral curve characteristics of each pixel in the image, thus realizing the organic fusion of remote sensing data spatial dimension and spectral dimension information. Hyperspectral remote sensing...

AI Technical Summary

Problems solved by technology

However, since the training of convolutional neural networks requires a large number of labeled samples as training samples, and the cost of hyperspectral image labeling is very expensive, how to solve the problem of small samples is currently a hot direction.

Images