A method and device for space-spectrum classification of hyperspectral images taking into account the importance of spectra

Abstract

The invention discloses a hyperspectral image spatial spectrum classification method and device considering the importance of spectrum. For a given hyperspectral remote sensing image with hundreds of spectral bands, the importance of spectral features is calculated through random forest; the spectral weight feature can be customized The kernel function uses the extracted spectral feature weights to model the relative role of each spectral band in the classification, giving greater weight to the bands that are more beneficial to the identification of feature categories, and increasing the spectral discrimination ability of features; in the conditional random field Construct spectral unary potential energy and spatial binary potential energy under a unified framework, consider spectral feature weight in spectral unary potential energy, integrate spectral weight kernel function to improve the ability to distinguish different spectral features in nonlinear space, and model through spatial binary potential energy Spatial correlation of ground objects. The beneficial effects of implementing the present invention are: the influence of unimportant bands on classification is reduced, the distinguishability of categories is improved, and the classification effect is improved.

Description

technical field [0001] The invention belongs to the field of hyperspectral remote sensing image processing, and in particular relates to a hyperspectral image spatial spectrum classification method and device taking into account the importance of the spectrum. Background technique [0002] Hyperspectral remote sensing images have the unique advantages of high spectral resolution and map-spectrum integration, which can provide diagnostic spectral features of different ground objects, and are an important data source for classification and recognition of ground objects. In recent years, with the rapid development of hyperspectral technology, hyperspectral remote sensing images with high spatial resolution (double high remote sensing images) have begun to emerge, such as the domestic Tiangong-1 satellite, aviation ROSIS, CASI, and drones. The spatial resolution of hyperspectral imagery has reached meter level, or even submeter level. This kind of hyperspectral image with high ...

AI Technical Summary

Problems solved by technology

However, the current spatial spectral classification method based on spatial context information, represented by the random field model, focuses on the modeling of spatial information, and lacks a learning mechanism for sensitive spectral information of ground objects, so it is difficult to use spatial information to suppress classification noise while maintaining local classification. Details

Images