A hyperspectral remote sensing image anomaly target detection method based on hierarchical robust discriminative learning
CN116402798BActive Publication Date: 2026-07-24CHONGQING UNIV OF POSTS & TELECOMM
View PDF 2 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHONGQING UNIV OF POSTS & TELECOMM
- Filing Date
- 2023-04-11
- Publication Date
- 2026-07-24
AI Technical Summary
Technical Problem
Background and anomalous targets are difficult to separate in hyperspectral remote sensing images, especially in cases of mixed noise and deep mixing. Existing methods are ineffective in detecting and separating background and anomalous targets.
Method used
A hierarchical robust discriminative learning method is adopted, which gradually separates the background and abnormal targets by introducing structurally irrelevant learning, mixed noise suppression and hierarchical discriminative learning, thereby enhancing the model's discrimination ability and noise suppression ability.
Benefits of technology
It improves the separability and detection capability of background and anomalous targets, and enhances the performance of anomalous target detection in complex environments.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116402798B_ABST
Abstract
The application provides a layered robust discriminant learning method for hyperspectral remote sensing image anomaly detection. 1，1 The application effectively depicts the complex mixed noise introduced in the process of acquiring the hyperspectral remote sensing image in a real scene through the l norm and the Frobenius norm, and improves the anti-noise performance of the anomaly target detection model. In order to more accurately separate the deeply mixed background and anomaly target, obtain a robust and more powerful anomaly target detection model, and design a layered detection idea, the background and anomaly target components in the deeply mixed hyperspectral remote sensing image are gradually separated. The application can not only improve the distinguishability between the background and the anomaly target, but also has very strong noise suppression performance and detection robustness.
Need to check novelty before this filing date? Find Prior Art