Hyperspectral image classification method based on flat hybrid convolutional neural network

Abstract

The invention relates to the technical field of hyperspectral image processing, in particular to a hyperspectral image classification method based on a flat hybrid convolutional neural network. According to the method provided by the invention, convolution of multiple dimensions is utilized; three-dimensional convolution is introduced into the first several layers of the primary neural network model; according to the method, spatial-spectral features are extracted and expressed, the latter several layers are connected with a two-dimensional convolution layer, and learned features are further integrated, so that the defects of large space occupation, time consumption and slow convergence of single three-dimensional convolution are avoided, and more effective features can be learned than single two-dimensional convolution; according to the method, pooling of various types is combined for sampling, learned effective features are utilized and reserved as much as possible while feature dimension acceleration training is reduced, model parameters are greatly reduced, the over-fitting phenomenon is relieved, the feature learning capacity can be kept under the condition of few training samples, and a good classification effect is obtained.

Description

technical field [0001] The present application relates to the technical field of hyperspectral image processing, in particular to a hyperspectral image classification method based on a flat hybrid convolutional neural network. Background technique [0002] Thanks to the development and maturity of remote sensing technology, hyperspectral image technology has also developed rapidly in recent years. The rich spectral information in hyperspectral images plays an important role in agriculture, military, geological exploration, environmental monitoring and other fields. The classification technology of hyperspectral images has always been one of the application directions that has attracted much attention. Its purpose is to accurately determine the category of surface objects corresponding to each pixel in hyperspectral images. However, in practical applications, due to the huge amount of spectral data and the strong information correlation between bands, it is very challenging ...

AI Technical Summary

Problems solved by technology

[0005] This application provides a hyperspectral image classification method based on a flat hybrid convolutional neural network to solve the problem of limited learned features and poor classification results when there are few training samples

Images