A classification method, device and storage device for hyperspectral remote sensing images

Abstract

The invention provides a classification method, device and storage device of hyperspectral remote sensing images, a classification method of hyperspectral remote sensing images, by performing dimensionality reduction processing on high-dimensional hyperspectral remote sensing images, combined with sample data to classify deep forests Model training, and then through the trained deep forest classification model to achieve the purpose of accurate and fast classification of hyperspectral remote sensing images; a classification device and storage device for hyperspectral remote sensing images, used to realize a hyperspectral remote sensing image Classification. The beneficial effects of the present invention are: by using the deep forest algorithm to classify hyperspectral remote sensing images, the classification accuracy and classification speed of the deep forest classification model are improved, and the method provided by the present invention involves few parameters, is easy to adjust, and greatly improves Classification effect and practicality of hyperspectral remote sensing images.

Description

technical field [0001] The invention relates to the field of hyperspectral remote sensing image classification, in particular to a hyperspectral remote sensing image classification method, device and storage device. Background technique [0002] Hyperspectral remote sensing images have the characteristics of numerous bands, high spectral resolution, high dimensionality, and huge data volume. Because they can accurately reflect the spatial information and spectral information of ground objects, they have been widely used in geological exploration, resource investigation, urban planning, Environmental disaster monitoring and other fields have been widely used and researched by various countries. [0003] In the process of hyperspectral remote sensing image classification, traditional classification methods include support vector machine classification, artificial neural network classification and decision tree classification. Due to the limited spatial resolution of remote se...

AI Technical Summary

Problems solved by technology

However, these methods not only rely on a large number of training samples, but also have problems such as complex structure, troublesome parameter adjustment, and weak robustness.

Images