南京航空航天大学学报（英文版）2025，Vol.42Issue(4)：477-486,10.DOI:10.16356/j.1005-1120.2025.04.004
弹载SAR图像晃动舰船识别
Recognition of Oscillatory Ships in Missile-Borne SAR
孙兵 1杨子悦 1植一航 1刘艳青 1门志荣1
作者信息
- 1. 北京航空航天大学电子信息工程学院,北京 100191,中国
- 折叠
摘要
Abstract
An end-to-end recognition strategy is proposed for oscillatory ships in missile-borne synthetic aperture radar(SAR),eliminating the need for image refocusing.Unlike conventional"focus-then-recognize"paradigm,the approach directly exploits oscillation-degraded SAR images for training and recognition,avoiding the unreliability of refocusing under complex imaging conditions.A multi-azimuth ship dataset under the"sea state five"condition is simulated,where ResNet-18 achieves a baseline accuracy of 66.66%,validating the feasibility of the end-to-end framework.By further incorporating a domain-adversarial neural network(DANN)to extract cross-azimuth invariant features,the recognition rate increases to 76.22%,demonstrating the potential of this strategy.The results indicate that,even with a non-optimal backbone,the end-to-end approach shows clear applicability in challenging scenarios,while offering a foundation for future performance gains with more advanced architectures.关键词
合成孔径雷达/晃动舰船识别/端到端/域自适应Key words
synthetic aperture radar(SAR)/oscillatory ship recognition/end-to-end/domain adaptation分类
信息技术与安全科学引用本文复制引用
孙兵,杨子悦,植一航,刘艳青,门志荣..弹载SAR图像晃动舰船识别[J].南京航空航天大学学报（英文版）,2025,42(4):477-486,10.
