Hyperspectral image classification method based on cross-grouping space-spectral feature enhancement network

Abstract

The invention discloses a hyperspectral image classification method based on a cross-grouping space-spectral feature enhancement network, comprising: 1) spectral feature cross-grouping; 2) multi-channel grouping spectral feature extraction; 3) spatial feature cross-grouping; 4) grouping space Feature extraction; 5) Spectral-spatial channel information interaction; 6) Hyperspectral image pixel classification. This method uses spectral-spatial feature information to perform cross-grouping and feature extraction operations on spectral features and spatial features, which can effectively reduce the correlation between adjacent spectra. The obtained features are enhanced, information interaction and fusion of spatial features and spectral features are performed, and the fused features are used for classification, which can improve the network classification performance.

Description

technical field [0001] The invention relates to the technical field of intelligent image processing, in particular to a hyperspectral image classification method based on a cross-grouping spectral-spatial feature enhancement and fusion network. Background technique [0002] Hyperspectral remote sensing images (HSI for short) have the characteristics of spatial information and spectral information at the same time, which makes them have great application value in research fields such as ground object classification, target segmentation and recognition, and dynamic target tracking. At present, it has been widely used in agricultural testing, mineral exploration, safety monitoring and environmental science and other fields. The classification research of hyperspectral remote sensing images is one of the important means of hyperspectral image information extraction, and it is the basis of hyperspectral research technology. [0003] In the traditional machine learning hyperspect...

AI Technical Summary

Problems solved by technology

First of all, due to the large number of spectral bands and large amount of data in hyperspectral images, directly using the original hyperspectral data blocks as the input of the model is prone to the curse of dimensionality; second, the computational complexity of 3D CNN is higher than that of 2D CNN. The model is prone to overfitting problems and cannot extract deeper features; finally, these methods do not take into account the strong correlation between adjacent spectra of hyperspectral images when extracting spectral features, ignoring the processing of spectral dimensions

Images