Self-coding hyperspectral anomaly detection method based on local and global double-branch cooperation

Through multi-directional mask convolution and local-global dual-branch collaborative model, the interference of abnormal pixels is destroyed, the background reconstruction capability is enhanced, the problems of missed detection and false alarm in hyperspectral anomaly detection are solved, and more efficient detection effect is achieved.

CN120635699APending Publication Date: 2025-09-12XIDIAN UNIV
0 Cites 4 Cited by

Patent Information

Application Number
CN202510719396.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-30
Publication Date
2025-09-12

AI Technical Summary

Technical Problem

In existing hyperspectral anomaly detection methods, abnormal pixel interference leads to poor detection results, some abnormal samples are reconstructed and missed, and insufficient background sample reconstruction leads to a high false alarm rate.

Method used

A multi-directional mask convolution module is designed to destroy the spatial correlation of anomalies. The local and global dual-branch collaborative model is combined with the attention-driven multi-scale grouped convolution and cascaded spatial spectral attention module to enhance the reconstruction ability of background samples and suppress anomaly reconstruction.

Benefits of technology

The results of hyperspectral anomaly detection are significantly improved, the missed detection rate and false alarm rate in anomaly detection are reduced, and the detection accuracy is improved.

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

Abstract

The invention provides a self-encoding hyperspectral anomaly detection method based on local and global dual-branch cooperation, and mainly solves the problem that the detection effect is poor due to the fact that an existing method is interfered by abnormal pixels. Comprising the following steps: 1) acquiring an original hyperspectral image; 2) constructing a self-encoding hyperspectral anomaly detection model comprising an encoder, a multi-direction mask convolution MDMC module which destroys anomaly spatial correlation along each direction, an attention-driven multi-scale grouping convolution AMGC module, a cascade type spatial spectrum attention CSSA module and a reconstruction module, wherein the self-encoding hyperspectral anomaly detection model comprises the encoder, the multi-direction mask convolution MDMC module, the attention-driven multi-scale grouping convolution AMGC module, the cascade type spatial spectrum attention CSSA module and the reconstruction module; 3) using an L1 norm and a spectral angular distance LSAD as a joint loss function, and guiding the model training to converge; and 4) inputting the original hyperspectral image into the trained final detection model to obtain a reconstructed hyperspectral image, and calculating to obtain an anomaly detection result. According to the method, the background reconstruction capability of the model can be improved, the reconstruction of the model on the anomaly is remarkably weakened, and the hyperspectral anomaly detection performance is effectively improved.
Need to check novelty before this filing date? Find Prior Art