Hyperspectral classification method based on double-branch network

Abstract

A hyperspectral classification method based on the double-branch network provided by the invention firstly ensures that the number of different samples of input data is not constant and equal in eachiteration in the training process, and also ensures that each sample participating in the training is balanced in statistics through the method of data resampling. This not only effectively alleviatesthe sample imbalance problem in network learning, but also keeps the diversity of data. In order to extract the multi-scale features of the data, the invention uses the network structure of two branches to carry out semi-supervised learning through three training strategies, so that not only the training set is expanded, but also the classification accuracy is greatly improved; compared with other classification methods, the method greatly improves the classification precision through the ensemble learning strategy. The hyperspectral classification method based on the dual-branch network notonly is superior to other methods in performance, but also is superior to other methods in training efficiency.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a hyperspectral classification method based on a double-branch network. Background technique [0002] High-resolution hyperspectral images can not only display the geometric structure and spatial information of ground objects, but also contain rich spectral information. Therefore, hyperspectral images provide the basis for a wide range of applications, such as ground object recognition and classification, mineral exploration, precision agriculture, etc. For these applications, the most fundamental task is the classification of hyperspectral images. However, in the classification of hyperspectral images, there are still many challenges, such as, inter-class similarity, limited training data, sample imbalance, etc. [0003] To solve these problems, many researchers have proposed different solutions. Initially, Bigdeli et al. applied support vector machines (...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a hyperspectral classification method based on a dual-branch network, which solves the problem of poor classification ability of existing methods for classifying hyperspectral images

Images