Hyperspectral remote sensing image classification method based on dense residual three-dimensional convolutional neural network

Abstract

The invention discloses a hyperspectral remote sensing image classification method based on a dense residual three-dimensional convolutional neural network. According to the method, original hyperspectral data are used as network input, three-dimensional spatial-spectral features of a hyperspectral remote sensing image are extracted through three-dimensional convolution, the hyperspectral image can be directly processed through three-dimensional convolution, preprocessing operations such as dimension reduction are not needed, and the spatial-spectral features of the hyperspectral image are extracted more sufficiently. The dense residual network is used to deepen the number of network layers and learn deeper spectral and spatial features, the residual network can effectively reduce the problem of gradient disappearance along with the increase of the network depth, and the structure can more effectively utilize the features and enhance the feature transfer between convolutional layers. The training time is shortened through an early stop method, classification prediction is carried out through a Soft-max classifier, and an initial classification result is obtained; and proposing a multi-label conditional random field optimization algorithm, and optimizing a classification result. The method improves the operation efficiency, and improves the classification accuracy of the remotesensing images.

Description

technical field [0001] The invention belongs to the field of remote sensing mapping and information engineering, and in particular relates to a hyperspectral remote sensing image classification method based on a dense residual three-dimensional convolutional neural network. Background technique [0002] With the development of hyperspectral remote sensing technology, new hyperspectral sensors can simultaneously collect continuous images of spectral features and spatial features, which contain rich ground object information. Remote sensing data not only reflects the spectral information of ground objects, but also contains the spatial distribution information of ground objects. Therefore, it has a wide range of applications in the fields of agriculture, environmental monitoring, urban planning, and military reconnaissance. The development and type changes of ground features are likely to cause changes in the value of remote sensing images. Therefore, the key to the classifica...

AI Technical Summary

Problems solved by technology

[0003] The remote sensing data not only contains the spectral information of the ground objects, but also contains the spatial distribution information of the ground objects. The amount of information contained is complex, which brings challenges to the classification of hyperspectral remote sensing images. The traditional hyperspectral remote sensing image classification methods only use image Spectral information, resulting in classification accuracy has been very unsatisfactory

Images