基于遥感影像敏感目标的隐写嵌入与图像恢复方法及装置
By combining global binary union masking, distortion-free cropping, and neural network decoder, the problems of multi-target management and concealment in the technology of hiding sensitive targets in remote sensing images are solved, and the recovery of sensitive targets with high fidelity and security is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XIAMEN UNIV OF TECH
- Filing Date
- 2026-05-07
- Publication Date
- 2026-07-17
AI Technical Summary
Existing remote sensing image sensitive target hiding technologies suffer from problems such as complex multi-target management logic, limited embedding capacity, insufficient concealment of frequency domain watermarking algorithms, irreversible distortion of micro-texture caused by scaling operations, and low security of key management mechanisms.
A steganalysis embedding and image restoration method based on remote sensing imagery is adopted. By generating a global binary union mask, distortion-free cropping, secret map management, neural network decoder and joint loss optimization, the method can achieve efficient hiding and accurate restoration of sensitive targets.
It achieves high-fidelity restoration of sensitive targets, excellent visual concealment, multi-target synchronous management, lightweight security, and scene-level in-situ accurate restoration, thereby improving the concealment and security of remote sensing images.
Smart Images
Figure CN122156015B_ABST