Hyperspectral image classification method and system based on physical information neural network

By combining the joint training of the spectral spatial hybrid encoder and the PINN coordinate network, the problems of ignoring spectral physical priors and the scarcity of labeled samples in hyperspectral image classification are solved, and efficient and interpretable hybrid pixel processing and classification are achieved.

CN122244687BActive Publication Date: 2026-08-04XIDIAN UNIV
2 Cites 0 Cited by

Patent Information

Application Number
CN202610673146.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-05-15
Publication Date
2026-08-04
Estimated Expiration
2046-05-15

AI Technical Summary

Technical Problem

Existing hyperspectral image classification methods ignore spectral physical priors, resulting in poor interpretability, insufficient generalization ability when labeled samples are scarce, and difficulty in handling mixed pixel problems.

Method used

We employ a physical information neural network approach, combining a spectral spatial hybrid encoder and a PINN coordinate network. Through joint training using classification loss, physical constraint loss, spectral reconstruction loss, and endmember diversity loss, we extract data-driven features and physical features, which are then fused for classification.

Benefits of technology

It improves the interpretability and generalization ability of the model, enhances the ability to process mixed pixels, and achieves efficient hyperspectral image classification.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses a hyperspectral image classification method and system based on a physical information neural network, first acquires a hyperspectral image; constructs a spectrum-image hybrid encoder and a continuous coordinate mapping network, which are used for extracting a data-driven feature vector and a physical feature vector of the hyperspectral image; and trains and optimizes the spectrum-image hybrid encoder and the continuous coordinate mapping network; finally, inputting the hyperspectral image to be classified into the trained and optimized spectrum-image hybrid encoder and continuous coordinate mapping network, the data-driven feature vector and the physical feature vector are extracted respectively, and after the data-driven feature vector and the physical feature vector are fused, each category probability is output through a linear classifier, and the category with the maximum probability is taken as the final classification result, solving the problems that the existing classification methods ignore spectral physical prior, have poor interpretability, and have insufficient generalization ability when labeled samples are scarce.
Need to check novelty before this filing date? Find Prior Art