Multi-scale sar target detection method and system based on phase consistency constraint

CN122157004APending Publication Date: 2026-06-05SOUTHWEST JIAOTONG UNIV +1
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SOUTHWEST JIAOTONG UNIV
Filing Date
2026-01-08
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Existing technologies for target detection in SAR images suffer from problems such as inconsistent phase response during multi-scale feature transfer, insufficient utilization of polarization information, and fixed feature fusion methods, resulting in insufficient accuracy and robustness in small target detection.

Method used

A multi-scale SAR target detection method based on phase consistency constraints is adopted. By introducing a multi-scale feature extraction network with phase consistency constraints and combining it with a polarization-enhanced attention mechanism, attention weights are generated using the polarization covariance matrix to perform multi-scale feature enhancement, and target detection results are output through multiple detection heads.

Benefits of technology

It significantly improves the detection accuracy and robustness of small targets in SAR images, reduces the false alarm rate and missed detection rate, and is suitable for practical application scenarios such as military reconnaissance, maritime surveillance, and port security.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122157004A_ABST
    Figure CN122157004A_ABST
Patent Text Reader

Abstract

The application relates to the technical field of radar remote sensing and target detection, and particularly relates to a multi-scale SAR target detection method and system based on phase consistency constraint, which comprises the following steps: acquiring a SAR image, wherein the SAR image contains multi-polarization channel information; performing feature extraction on the SAR image through a multi-scale feature extraction network to obtain multi-scale features, and introducing a phase consistency constraint in the feature extraction process; enhancing the multi-scale features by using a polarization-enhanced attention mechanism; processing the enhanced multi-scale features through multiple detection heads to output a target detection result. The application aims to provide a multi-scale SAR target detection method and system based on phase consistency constraint, so as to solve the problems of phase response inconsistency in the multi-scale feature transmission process, insufficient utilization of polarization information, fixed feature fusion mode and the like in the prior art, thereby improving the detection accuracy and robustness of targets in a SAR image, especially small targets.
Need to check novelty before this filing date? Find Prior Art