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.

CN122156998APending Publication Date: 2026-06-05CHANGCHUN INST OF OPTICS FINE MECHANICS & PHYSICS CHINESE ACAD OF SCI
View PDF 0 Cites 0 Cited by

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

Technical Problem

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.

Method used

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.

Benefits of technology

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.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122156998A_ABST
    Figure CN122156998A_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of deep learning, and more particularly to a ship identification system and method for optical remote sensing images, wherein the collected ship remote sensing images are processed by multiple global-local fusion modules, the output features enter the detection head, and the detection result of the ship is obtained; in each global-local fusion module, a structure perception sequence is constructed by a feature-guided local clustering strategy to maintain the spatial integrity of the local structure such as target texture and edge, thereby realizing more accurate extraction of global features; through collaborative modeling of conventional local texture and slender structure, the local feature extraction capability for large aspect ratio ship targets is significantly improved; the wavelet attention enhanced fusion branch realizes differentiated enhancement and complementary fusion of global semantics and local structure information through adaptive weighting and space-frequency domain fusion, and significantly improves the overall target representation capability.
Need to check novelty before this filing date? Find Prior Art