SAR image target detection method based on global-local attention and multi-scale fusion enhancement

The SAR image target detection method enhanced by global-local attention and multi-scale fusion solves the problems of noise interference and small target detection in SAR images, and achieves high robustness and high accuracy in target detection, especially for the accurate localization of rotating targets.

CN122336581APending Publication Date: 2026-07-03HANGZHOU DIANZI UNIV
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HANGZHOU DIANZI UNIV
Filing Date
2026-04-17
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

SAR image target detection suffers from problems such as severe speckle noise interference, low signal-to-noise ratio, small targets being easily obscured by background clutter, and inaccurate positioning of rotating targets, which are difficult to solve effectively with existing technologies.

Method used

A SAR image target detection method based on global-local attention and multi-scale fusion enhancement is adopted, including a continuous denoising attention network, a SAR sensing multi-scale difference fusion module, and a weighted IoU loss function. Through global-local feature fusion and multi-scale feature enhancement, noise is suppressed, and the detection capability of small targets and the positioning accuracy of rotating targets are improved.

Benefits of technology

It significantly improves the robustness and accuracy of target detection in SAR images, reduces noise interference, enhances the detection capability of small-scale targets and targets with complex backgrounds, and improves the localization accuracy of rotating targets and the convergence speed of the model.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122336581A_ABST
    Figure CN122336581A_ABST
Patent Text Reader

Abstract

The application relates to the technical field of remote sensing image processing, and discloses a SAR image target detection method based on global-local attention and multi-scale fusion enhancement, which comprises the following steps: acquiring a SAR image, inputting the SAR image into a continuous denoising attention network to perform speckle noise suppression processing, obtaining a denoised image, inputting the denoised image into a backbone network of YOLOv10 to extract a multi-scale feature map, inputting the multi-scale feature map extracted by the backbone network into a neck network, using an SAR perception multi-scale difference fusion module in the neck network to perform multi-scale feature difference extraction and fusion enhancement, obtaining an enhanced feature, using a weighted IoU loss function as a bounding box regression loss to optimize a predicted bounding box, and outputting a target detection result. The application can comprehensively improve the robustness and accuracy of image target detection, reduce the interference of speckle noise on subsequent detection, significantly enhance the model detection capability, and effectively improve the positioning accuracy of a rotating target and the convergence speed of the model.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Remote sensing image ultra-small target detection method based on improved YOLO

    CN121837953A