Multi-source remote sensing data classification method

Through the multi-source remote sensing data classification method, the frequency feature decomposition and homofrequency feature fusion module are used, combined with the frequency modulation layer and attention layer, global and local features are extracted, and the problem that single-source data cannot capture complex features is solved, achieving more accurate classification results.

CN119649135APending Publication Date: 2025-03-18NANJING UNIV OF INFORMATION SCI & TECH
2 Cites 4 Cited by

Patent Information

Application Number
CN202411798370.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-09
Publication Date
2025-03-18

AI Technical Summary

Technical Problem

In the prior art, the use of single-source remote sensing data cannot fully capture complex land features, resulting in inaccurate classification results.

Method used

The multi-source remote sensing data classification method is adopted to obtain multiple types of remote sensing data, extract shallow features, and use the frequency feature decomposition module and the same-frequency feature fusion module to combine the frequency modulation layer and attention layer to extract global and local features, and finally weight it in the spectral dimension to obtain deep features and prediction classification results.

Benefits of technology

Through the feature fusion and deep learning technology of multi-source data, complex land features can be captured more comprehensively, and the accuracy of classification results can be improved, especially under low training samples, which show higher classification accuracy.

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

Abstract

The invention provides a multi-source remote sensing data classification method, which belongs to the field of hyperspectral image processing in the field of remote sensing, and comprises the following steps: acquiring remote sensing data of various target objects; extracting shallow layer features of each kind of remote sensing data; obtaining a plurality of frequency characteristics of each kind of remote sensing data; fusing the same frequency features of all remote sensing data to obtain a plurality of same frequency fusion features; splicing the plurality of same-frequency fusion features to obtain a multi-source fusion feature; enabling the multi-source fusion features to sequentially pass through a frequency modulation layer and an attention layer which are superposed to obtain fused global features and local features; and weighting the global features and the local features in the spectral dimension to obtain a prediction classification result of the target object. According to the method, directional frequency characteristic decomposition and fusion of the multi-source data are realized, the multi-source fusion characteristics are extracted based on the multi-source remote sensing data to serve as the basis of classification, more comprehensive information is provided for classification of target objects, complex ground object characteristics can be fully captured, and the classification result is more accurate.
Need to check novelty before this filing date? Find Prior Art