基于角度引导注意力的气动目标宽带PD识别方法

打开文本图片集

中图分类号：TN95 文献标志码：A DOI：10.12305/j.issn.1001-506X.2025.03.13

Angle-guided attention-based wideband PD recognition method for aerodynamic targets

LI Jiakuan，FENGBo，LIUHongliang，YEChunmao，YUJizhou* （Beijing InstituteofRadioMeasurement，BeijinglOo854，China）

Abstract：Inverse synthetic aperture radar（ISAR）images are vital tools for radar automatic target recognition. However，acquiring high-resolution ISAR images requires prolonged radar illumination，posing significant limitations in practical engineering applications.In contrast，wideband pulse Doppler（PD） images can effectively save radar resources byaccumulating images with short pulses.In this paper，the difference of modulation phenomena in images under diferent incident view angles is taken as the starting point，aiming to achieve higher recognition performance under limited resources，a convolutional neural network（CNN）with angle-guidedattntion is proposed.Firstly，throughahybridattention residual module，thenetwork focuses on thedifferences inthe image space，efectivelyenhancing therepresentationcapabilityoffine-grained target features. Subsequently，anangleguidedattentionmoduleisdesigned，embedding incident viewangle information into the network through angle encoding，establishing a coupling between target feature representation and pose，further improving recognition accuracy.Finally，the effctiveness of the proposed network is validated through the classification and recognition of measured wideband PD images of three types of aircraft.

Keywords：wideband pulse Doppler（PD） image；target recognition；attention mechanism；angle-guided

0 引言

目标的大小、结构和姿态，因此在精细化目标识别中扮演着重要的角色。（剩余17515字）