Hyperspectral Intelligent Classification Method Based on Prototype Learning Mechanism and Multidimensional Residual Network

Abstract

The invention belongs to the technical field of image processing, and discloses a hyperspectral intelligent classification method based on a prototype learning mechanism and a multidimensional residual network. First, a multidimensional residual network suitable for hyperspectral image features is constructed to extract spectral and spatial features of hyperspectral images; second, a class prediction function based on a prototype learning mechanism is constructed to replace the softmax classifier used in traditional deep learning ; Then construct a new prototype distance loss function, replace the traditional softmax cross-entropy loss function, and complete the optimization update of the multidimensional residual network parameters. The present invention introduces a multi-dimensional residual network, discards the traditional softmax classifier and softmax cross-entropy loss function, constructs and applies a category prediction function and a prototype distance loss function based on a prototype learning mechanism, and has high precision for hyperspectral image classification problems, and the training process The convergence speed is fast, and the robustness of the trained classification model is high.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a hyperspectral intelligent classification method based on a prototype learning mechanism and a multidimensional residual network in the technical field of hyperspectral image classification. The invention can be used to classify and identify different substances in hyperspectral images, and can play an important role in geological exploration, crop growth, camouflage revealing and the like. Background technique [0002] Hyperspectral imaging technology is a new technology gradually developed in the 1980s. It is a multi-dimensional information acquisition technology that combines traditional two-dimensional imaging technology and one-dimensional spectral detection technology. Hyperspectral images have extremely high spectral resolution and information richness, and can reflect the diagnostic spectral characteristics of target objects in more detail and accurately. ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the shortcomings of the above-mentioned existing deep learning hyperspectral classification technology that relies on softmax classifiers and softmax cross-entropy loss functions: the features learned by the classification model are not highly scalable, and the intra-class differences may be greater than the inter-class differences , the depth model is not robust, the classification accuracy is low, and the convergence speed of the training process is slow. A hyperspectral intelligent classification method based on a prototype learning mechanism and a multidimensional residual network is proposed.

Images