Ship identification system and method for optical remote sensing images
By collaborative modeling of the visual global clustering scanning branch and the local shape adaptation branch, combined with the wavelet attention enhancement fusion module, the problem of feature extraction of ships with large aspect ratios in optical remote sensing images is solved, achieving more accurate global feature extraction and local structure preservation, and improving the overall performance of ship identification.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHANGCHUN INST OF OPTICS FINE MECHANICS & PHYSICS CHINESE ACAD OF SCI
- Filing Date
- 2026-04-15
- Publication Date
- 2026-06-05
AI Technical Summary
Existing feature extraction networks based on CNN, Transformer, and Mamba are difficult to effectively extract global and local features of ship targets with large aspect ratios in optical remote sensing images, and they also suffer from noise interference and high computational complexity.
A visual global clustering scanning branch is used to construct a structure-aware sequence, and a local shape adaptation branch is used to collaboratively model local textures and slender structures. Combined with a wavelet attention enhancement fusion module, adaptive weighting and spatial-frequency domain fusion are performed to achieve differentiated enhancement and complementary fusion of global semantics and local structure.
It significantly improves the feature extraction capability for ships with large aspect ratios, enhances the accuracy of ship identification and overall characterization, and can effectively capture global features and local details.
Smart Images

Figure CN122156998A_ABST