Multispectral image classification method based on dual-channel DCGAN and feature fusion

Abstract

The invention discloses a multispectral image classification method based on dual-channel deep convolutional generative adversarial network (DCGAN) and feature fusion. The method comprises steps of: inputting multispectral images; normalizing the image of each band of each multispectral image; obtaining a multispectral image matrix; obtaining a data set; creating a dual-channel DCGAN model; training a dual-channel DCGAN classification model; and classifying a test data set. The multispectral image classification method introduces the dual-channel DCGAN, combines the feature fusion, extracts avariety of multispectral high-level feature information in multiple directions, enhances the feature characterization ability, and improves the classification effect.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a multispectral image classification method based on a dual-channel generative confrontation network DCGAN (Deep Convolutional Generative Adversarial Networks) and feature fusion in the technical field of multispectral image classification. The invention can be used to classify ground objects including water areas, fields, cities and the like in multispectral images. Background technique [0002] Multispectral image is a kind of remote sensing image, which is obtained by repeatedly shooting the same target in multiple bands. The application value of multi-spectral images is more and more extensive, such as in the fields of aviation and aerospace ground detection, land surveying and mapping, disaster detection and so on. Image classification is an important direction in the research content of multispectral images. There are many traditional classification methods...

AI Technical Summary

Problems solved by technology

However, the shortcomings of this method are that the feature extraction design of this method relies on human experience, which is complex and time-consuming, and the combination of features is usually not suitable for scenes where the pixel contrast is not obvious.

However, the shortcomings of this method are that the calculation process is cumbersome, and the use of unsupervised clustering methods has the phenomenon of different spectra of the same object and the same spectrum of different objects, which affects the classification results.

Images