Collaborative generative adversarial network and spatial-spectral joint approach for hyperspectral image classification

Abstract

The invention discloses a hyperspectral image classification method based on collaborative generative confrontation network and space-spectrum union, the steps of which are as follows: input hyperspectral image; obtain sample set; generate training samples and test samples; build multi-scale discriminator; construct cooperative relationship ; Build a collaborative generative confrontation network; training samples generate initial values ​​through a multi-scale discriminator; the generator generates samples; the multi-scale discriminator classifies; constructs the loss function of the generator and the multi-scale discriminator; to classify hyperspectral images. The present invention utilizes the collaborative generation confrontation network built to extract the spatial-spectral joint features of pixels, and at the same time generate more realistic samples, increase the number of samples, alleviate the problems of network over-fitting and slow network convergence, and improve the accuracy of hyperspectral image classification. accuracy.

Description

technical field [0001] The present invention belongs to the technical field of image processing, and further relates to a hyperspectral image classification method in the technical field of image classification through collaborative generative confrontation network and space-spectrum union. The invention can detect and recognize underwater obstacles and land tanks and warships in the collected hyperspectral images, and can analyze the types of crops in the hyperspectral images. Background technique [0002] Hyperspectral images can obtain approximately continuous spectral information of target ground objects in a large number of bands such as ultraviolet, visible light, near-infrared and mid-infrared, and describe the spatial distribution relationship of ground objects in the form of images, so as to establish "map-spectrum integration" data , can realize accurate identification and detail extraction of ground objects, and provide favorable conditions for understanding the o...

AI Technical Summary

Problems solved by technology

Although this method does not need to solve the complex global energy optimization problem, it can extract the non-local spatial information of the hyperspectral image to optimize the classification. For the problem of large and small differences in the spatial characteristics of different pixels, only extracting the spatial characteristics of the hyperspectral image will lead to a large number of misclassifications, resulting in low classification accuracy

Although this method makes full use of the characteristics of "integration of space and spectrum" and "double high resolution" of hyperspectral data, the disadvantage of this method is that when using convolutional neural network training, the network parameters are many The network training time is long, and the number of samples is too small relative to the number of network parameters, resulting in over-fitting of the network, resulting in low classification accuracy

Images