Hyperspectral Image Classification Method Based on Superpixel Sample Expansion and Generative Adversarial Network

Abstract

The present invention proposes a hyperspectral image classification method based on superpixel sample expansion and generative confrontation network, aiming to solve the problem of low classification accuracy caused by network overfitting when the number of labeled training samples is small. Its implementation is as follows: construct the initial training set and test set, and expand them to obtain the expanded training set and candidate test set; construct a generative confrontation network composed of a generator and a discriminator; use the generator to generate fake samples, and use the discriminator to obtain fake samples. The true and false prediction labels and category prediction labels of samples and expanded training sets; construct the loss function of the generator and the discriminator, and alternately train the generator and the discriminator; train the support vector machine; pass the candidate test set through the trained discriminator and discriminator The support vector machine is used to obtain the candidate label set; the maximum voting algorithm is used for the candidate label set to determine the category label of the test set. The invention effectively extracts the spatial features of the hyperspectral image, alleviates the problem of overfitting, improves the classification accuracy, and can be used to classify the hyperspectral image for ground objects.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to an image classification method, and further relates to a hyperspectral image classification method based on superpixel expansion and generation confrontation network. The invention can be used to classify the hyperspectral images. Background technique [0002] Compared with ordinary sensors, hyperspectral imaging spectrometers have more spectral channels and narrower wavelength ranges in a certain wavelength range. Due to the spectral overlap between bands, hyperspectral images have high spectral resolution. Combined with the spatial information of ground objects acquired by imaging spectrometers, hyperspectral images contain rich one-dimensional spectral information and two-dimensional spatial information at the same time. Hyperspectral image classification technology is one of the hotspots in the field of hyperspectral data applications. To avoid overfitting, the training...

AI Technical Summary

Problems solved by technology

However, the disadvantage of this method is that the number of executions of RGF is not easy to determine, so that the spectral-spatial information cannot be fully combined, and the classification accuracy is low.

Images