现代雷达2025，Vol.47Issue(10)：77-84,8.DOI:10.16592/j.cnki.1004-7859.2025042801
面向空中目标识别的分布式多视角ISAR图像融合方法
A Distributed Multi-view ISAR Image Fusion Method for Air Target Recognition
摘要
Abstract
In the task of high-precision radar-based aerial target recognition,single-view inverse synthetic aperture radar(ISAR)is susceptible to azimuth variations,partial occlusions,and noise interference.These factors often hinder the representation of a tar-get's complete structure,leading to reduced recognition accuracy.To address this issue,this paper proposes an aerial target recog-nition method based on multi-view ISAR image fusion.The method employs a shared feature extraction network to extract semantic features from multi-view ISAR images and utilizes a Transformer encoder to model global dependencies across different viewpoints.Additionally,a dynamic gating fusion module is introduced to adaptively weight and fuse discriminative features from various ISAR viewpoints.L1 regularization is applied to constrain the viewpoint weights of ISAR images,effectively enhancing the network's a-bility to suppress redundant views.The proposed method is validated through electromagnetic scattering simulations on six types of aerial aircraft targets.Experimental results demonstrate that,compared to traditional single-view methods,the proposed ap-proach improves recognition accuracy by approximately 15%and 20%under high and low signal-to-noise ratio(SNR)condi-tions,respectively.关键词
逆合成孔径雷达/目标识别/Transformer编码器/多视角图像融合Key words
inverse synthetic aperture radar/target recognition/Transformer encoder/multi-view image fusion分类
信息技术与安全科学引用本文复制引用
李双侨,韦顺军,文彦博,王谋,师君,张晓玲,崔国龙..面向空中目标识别的分布式多视角ISAR图像融合方法[J].现代雷达,2025,47(10):77-84,8.基金项目
国家自然科学基金资助项目(62271108,62371104,62401119) （62271108,62371104,62401119）
四川省自然科学基金资助项目(20252ZNSFSC0526) （20252ZNSFSC0526）
