基于散射拓扑增强的双流SAR飞机检测网络

doi:10.12305/j.issn.1001-506X.2026.06.07

系统工程与电子技术 ›› 2026, Vol. 48 ›› Issue (6): 1848-1858.doi: 10.12305/j.issn.1001-506X.2026.06.07

基于散射拓扑增强的双流SAR飞机检测网络

赵巍山¹^,²^,³(), 尤思洋¹^,²^,³(), 黄丽佳¹^,²^,³^,*(), 周光尧¹^,²^,³()

1. 中国科学院空天信息创新研究院，北京 100094
2. 中国科学院空间信息处理与应用系统技术重点实验室，北京 100190
3. 中国科学院大学电子电气与通信工程学院，北京 100049

收稿日期:2025-04-08 修回日期:2025-05-29 接受日期:2025-06-10 出版日期:2026-06-25 发布日期:2026-02-13
通讯作者: 黄丽佳 E-mail:Zhaoweishan22@mails.ucas.ac.cn;yousiyang23@mails.ucas.ac.cn;iecas8huanglijia@163.com;zhougy@aircas.ac.cn
作者简介:赵巍山（1999—），男，硕士研究生，主要研究方向为合成孔径雷达典型目标检测
尤思洋（2001—），男，博士研究生，主要研究方向为合成孔径雷达信号处理、深空目标监测
周光尧（1984—），男，高级工程师，博士研究生，主要研究方向为雷达信号和信息处理、图像处理
基金资助:
中国科学院青年促进会优秀会员项目（Y2023036）资助课题

Dual-stream SAR aircraft detection network enhanced by scattering topology

Weishan ZHAO¹^,²^,³(), Siyang YOU¹^,²^,³(), Lijia HUANG¹^,²^,³^,*(), Guangyao ZHOU¹^,²^,³()

1. Aerospace Information Research Institute，Chinese Academy of Sciences，Beijing 100094，China
2. Key Laboratory of Technology in Geo-Spatial Information Processing and Application System，Chinese Academy of Sciences，Beijing 100190，China
3. School of Electronic，Electrical and Communication Engineering，University of Chinese Academy of Sciences，Beijing 100049，China

Received:2025-04-08 Revised:2025-05-29 Accepted:2025-06-10 Online:2026-06-25 Published:2026-02-13
Contact: Lijia HUANG E-mail:Zhaoweishan22@mails.ucas.ac.cn;yousiyang23@mails.ucas.ac.cn;iecas8huanglijia@163.com;zhougy@aircas.ac.cn

摘要/Abstract

摘要：

为解决合成孔径雷达图像中飞机目标部件特征离散引发虚警、成像角度差异性导致特征失稳的问题，提出基于散射拓扑增强的双流合成孔径雷达飞机目标检测网络。首先通过基于图卷积的层次拓扑特征提取模块，实现对目标散射点的空间建模，增强其结构关联性。在此基础上，引入精细化层次特征调节模块，使用多层次拓扑信息对不同感受野视觉特征进行调节与增强，提升模型对目标几何表征的感知能力。最后在合成孔径雷达飞机检测数据集上进行实验验证，所提网络相较于基线方法mAP提升2.8%，整体mAP达到67.0%。在多种复杂场景下均优于其他同类方法，具备较强的鲁棒性和泛化能力。

关键词: 飞机目标, 目标检测, 散射拓扑, 合成孔径雷达

Abstract:

To address false alarms caused by the discrete characteristics of aircraft target components in synthetic aperture radar （SAR） images and feature instability due to imaging angle differences, this paper proposes a dual-stream SAR aircraft target detection network based on scattering topology enhancement. First, a hierarchical topological feature extraction module （HTFEM） based on graph convolution is introduced to achieve spatial modeling of target scattering points, enhancing their structural correlation. On this basis, a refined hierarchical feature adjustment module （RHFAM） is incorporated, utilizing multi-level topological information to adjust and enhance visual features at different receptive fields, thereby improving the model’s perception of target geometric representation. Finally, experiments are conducted on the SAR Aircraft Detection Dataset （SADD）, with a 2.8% mAP gain over the baseline, achieving an overall mAP of 67.0%. The proposed approach outperforms other similar methods in various complex scenarios, exhibiting strong robustness and generalization capability.

Key words: aircraft target, target detection, scattering topology, synthetic aperture radar （SAR）

中图分类号:

TP 753

赵巍山, 尤思洋, 黄丽佳, 周光尧. 基于散射拓扑增强的双流SAR飞机检测网络[J]. 系统工程与电子技术, 2026, 48(6): 1848-1858.

Weishan ZHAO, Siyang YOU, Lijia HUANG, Guangyao ZHOU. Dual-stream SAR aircraft detection network enhanced by scattering topology[J]. Systems Engineering and Electronics, 2026, 48(6): 1848-1858.

图/表 12

图1

表1

图2

表2

图3

表3

图4

图5

图6

图7

表4

图8

参考文献 33

1	ROHLING H. Radar CFAR thresholding in clutter and multiple target situations[J]. IEEE Trans. on Aerospace and Electronic Systems, 1983 (4): 608- 621.
2	HE C, TU M X, LIU X L, et al. Mixture statistical distribution based multiple component model for target detection in high resolution SAR imagery[J]. ISPRS International Journal of Geo-Information, 2017, 6 (11): 336. doi: 10.3390/ijgi6110336
3	ZHAO Y, ZHAO L J, LI C Y, et al. Pyramid attention dilated network for aircraft detection in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 18 (4): 662- 666.
4	LUO R, CHEN L F, XING J, et al. A fast aircraft detection method for SAR images based on efficient bidirectional path aggregated attention network[J]. Remote Sensing, 2021, 13 (15): 2940. doi: 10.3390/rs13152940
5	CHEN J H, ZHANG B, WANG C. Backscattering feature analysis and recognition of civilian aircraft in TerraSAR-X images[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 12 (4): 796- 800.
6	WANG D, SONG Y P, CHEN L P, et al. Attributed scattering center guided network based on omnidirectional sub-aperture division for SAR target detection[J]. IEEE Trans. on Geoscience and Remote Sensing, 2025, 63, 5207415.
7	吕艺璇, 王智睿, 王佩瑾, 等. 基于散射信息和元学习的 SAR 图像飞机目标识别[J]. 雷达学报, 2022, 11 (4): 652- 665. doi: 10.12000/JR22044
	LYU Y X, WANG Z R, WANG P J, et al. Scattering information and meta-learning based SAR images interpretation for aircraft target recognition[J]. Journal of Radars, 2022, 11 (4): 652- 665. doi: 10.12000/JR22044
8	SUN X, LV Y X, WANG Z R, et al. SCAN: scattering characteristics analysis network for few-shot aircraft classification in high-resolution SAR images[J]. IEEE Trans. on Geoscience and Remote Sensing, 2022, 60, 5226517.
9	KANG Y Z, WANG Z R, ZUO H Y, et al. ST-Net: scattering topology network for aircraft classification in high-resolution SAR images[J]. IEEE Trans. on Geoscience and Remote Sensing, 2023, 61, 5202117.
10	ZHAO C X, ZHANG S Q, LUO R, et al. Scattering features spatial-structural association network for aircraft recognition in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2023, 20, 4006505.
11	PAN Z X, QIU X L, HUANG Z L, et al. Airplane recognition in TerraSAR-X images via scatter cluster extraction and reweighted sparse representation[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 14 (1): 112- 116.
12	HUANG B C, ZHANG T, QUAN S N, et al. Scattering enhancement and feature fusion network for aircraft detection in SAR images[J]. IEEE Trans. on Circuits and Systems for Video Technology, 2024, 35 (2): 1936- 1950.
13	GUO Q, WANG H P, XU F. Aircraft detection in high-resolution SAR images using scattering feature information [C]//Proc. of the 6th Asia-Pacific Conference on Synthetic Aperture Radar, 2019.
14	ZHOU J, XIAO C, PENG B, et al. DiffDet4SAR: diffusion-based aircraft target detection network for SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2024, 21, 4007905.
15	CHAI B S, NIE X, ZHOU Q F, et al. Enhanced cascade R-CNN for multi-scale object detection in dense scenes from SAR images[J]. IEEE Sensors Journal, 2024, 24 (12): 20143- 20153. doi: 10.1109/JSEN.2024.3393750
16	HARRIS C, STEPHENS M. A combined corner and edge detector[C]//Proc. of the Alvey Vision Conference, 1988, 15(50): 10-5244.
17	ZHANG Z W, CUI P, ZHU W W. Deep learning on graphs: a survey[J]. IEEE Trans. on Knowledge and Data Engineering, 2020, 34 (1): 249- 270.
18	KE Q Y, WU Y M, ZHAO W C, et al. SFG-Net: a scattering feature guidance network for oriented aircraft detection in SAR images[J]. Remote Sensing, 2025, 17 (7): 1193. doi: 10.3390/rs17071193
19	郭倩, 王海鹏, 徐丰. SAR图像飞机目标检测识别进展[J]. 雷达学报, 2020, 9 (3): 497- 513. doi: 10.12000/JR20020
	GUO Q, WANG H P, XU F. Research progress on aircraft detection and recognition in SAR imagery[J]. Journal of Radars, 2020, 9 (3): 497- 513. doi: 10.12000/JR20020
20	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017: 6000–6010.
21	ZHANG P, XU H, TIAN T, et al. SEFEPNet: scale expansion and feature enhancement pyramid network for SAR aircraft detection with small sample dataset[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15, 3365- 3375. doi: 10.1109/JSTARS.2022.3169339
22	WERNINGHAUS R, BUCKREUSS S. The TerraSAR-X mission and system design[J]. IEEE Trans. on Geoscience and Remote Sensing, 2009, 48 (2): 606- 614.
23	HUMAYUN M F, NASIR F A, BHATTI F A, et al. YOLO-OSD: optimized ship detection and localization in multiresolution SAR satellite images using a hybrid data-model centric approach[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17, 5345- 5363. doi: 10.1109/JSTARS.2024.3365807
24	WANG Z X, HOU G Y, XIN Z H, et al. Detection of SAR image multiscale ship targets in complex inshore scenes based on improved Yolov5[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17, 5804- 5823. doi: 10.1109/JSTARS.2024.3370722
25	TANG H D, GAO S, LI S, et al. A lightweight SAR image ship detection method based on improved convolution and Yolov7[J]. Remote Sensing, 2024, 16 (3): 486. doi: 10.3390/rs16030486
26	ROSS T Y, DOLLÁR G. Focal loss for dense object detection[C]//Proc. of the IEEE Conference on Computer Vision And Pattern Recognition, 2017: 2980−2988.
27	ZHANG Y, JIA Y N, TANG Y. Accurate detection of arbitrary ship directions using SAR based on RTMDET[J]. Remote Sensing Letters, 2025, 16 (2): 156- 169. doi: 10.1080/2150704X.2024.2440666
28	REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
29	LIN H, LIU J, LI X Y, et al. DCEA: DETR With concentrated deformable attention for end-to-end ship detection in SAR images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17, 17292- 17307. doi: 10.1109/JSTARS.2024.3461723
30	HE K, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN[C]//Proc. of the IEEE International Conference on Computer Vision, 2017: 2961−2969.
31	MENG Q B, WU Y M, SUO Y X, et al. STC-Net: scattering topology cue-based network for aircraft detection in SAR images[J]. IEEE Trans. on Geoscience and Remote Sensing, 2025, 63, 5201816.
32	PAN D, GAO X, DAI W, et al. SRT-Net: scattering region topology network for oriented ship detection in large-scale SAR images[J]. IEEE Trans. on Geoscience and Remote Sensing, 2024, 62, 520231.
33	DAI Y M, ZOU M R, LI Y X, et al. DenoDet: attention as deformable multi-subspace feature denoising for target detection in SAR images[J]. IEEE Trans. on Aerospace and Electronic Systems, 2025, 61 (2): 4729- 4743. doi: 10.1109/TAES.2024.3507786

参数名称	设定值	说明
角点响应阈值	0.2	过滤低质量角点
角点最大数量	100	限制角点数量
最小欧几里德距离	10	限制角点间距离

方法	AP@[IoU=0.5:0.95]			mAP
方法	小型目标	中型目标	大型目标	mAP
YoloX	0.487	0.605	0.420	0.517
Yolov5	0.605	0.708	0.574	0.631
Yolov7	0.618	0.706	0.532	0.638
RetinaNet	0.614	0.771	0.553	0.647
Faster-RCNN	0.628	0.769	0.564	0.663
Grid-RCNN	0.511	0.655	0.476	0.548
DETR	0.605	0.735	0.572	0.520
Mask-RCNN	0.628	0.782	0.546	0.666
RTMDet（基线）	0.615	0.732	0.570	0.642
所提方法	0.639	0.788	0.575	0.670

实验	HTFEM	RHFAM	AP^s	AP^m	AP^l	mAP
1	−	−	0.615	0.732	0.570	0.642
2	√	−	0.622	0.748	0.569	0.654
3	−	√	0.629	0.772	0.573	0.660
4	√	√	0.639	0.788	0.575	0.670

卫星	中心坐标	模式	分辨率	波段	极化
TerraSAR-X	122.147/29.369	Spotlight	0.903545	X	HH

[1]	袁永康, 王君旭, 华煜明, 张磊. 地基雷达对月多普勒补偿成像方法[J]. 系统工程与电子技术, 2026, 48(6): 1859-1868.
[2]	张杰, 常天庆, 王晓卫, 郝文龙, 汤鑫. 基于可见光与红外特征融合的轻量化目标检测方法[J]. 系统工程与电子技术, 2026, 48(5): 1481-1491.
[3]	王新, 周生华, 张新勋, 南静怡, 孙世坤. 全极化MIMO雷达主瓣压制干扰抑制方法[J]. 系统工程与电子技术, 2026, 48(5): 1539-1550.
[4]	杨泽莹, 陈卓, 徐志明, 艾小锋, 吴其华, 王玲. 空间目标ISAR图像部件正向标记方法[J]. 系统工程与电子技术, 2026, 48(4): 1165-1173.
[5]	黄天佑, 林惠孚, 杨超, 赖涛, 王青松, 黄海风. SAR移频欺骗干扰距离主瓣展宽问题解决方法[J]. 系统工程与电子技术, 2026, 48(4): 1174-1185.
[6]	刘硕, 周宇, 张哲昊, 尚嵩, 程松. 时域多脉冲相关与聚类分析的抗同频干扰技术[J]. 系统工程与电子技术, 2026, 48(4): 1186-1194.
[7]	鲁明雨, 孟飞, 叶春茂, 李璋峰, 赵庆媛. 一种先验知识辅助的扩展目标检测方法[J]. 系统工程与电子技术, 2026, 48(4): 1209-1217.
[8]	胡继军, 韩伟, 张国玉, 李洋, 杨洁, 田甜. 基于行为识别网络的SAR工作模式识别方法[J]. 系统工程与电子技术, 2026, 48(4): 1218-1229.
[9]	程鲲, 雷洪涛, 吕志轩. 改进YOLOv8的轻量级无人机跟踪方法[J]. 系统工程与电子技术, 2026, 48(3): 737-750.
[10]	王威, 杨勇, 韩静雯. 基于相关性的雷达海面弱目标检测技术[J]. 系统工程与电子技术, 2026, 48(3): 787-794.
[11]	翟佳, 画麒嘉, 王梓权, 张子恺, 王睿琦, 刘金玲, 胡美琪, 武晨辉. 基于多级别融合的可见光和SAR图像联合识别[J]. 系统工程与电子技术, 2026, 48(3): 817-825.
[12]	李莹莹, 吴昊, 陈凤, 林郁卓越, 王雪莹, 冯鑫. 一种基于天线指向的大方位扫描滑聚模式星载SAR几何定位技术[J]. 系统工程与电子技术, 2026, 48(3): 846-858.
[13]	缪燕子, 赵志非, 吴巍. 基于代价敏感学习DBN-XGBoost的海面小目标检测方法研究[J]. 系统工程与电子技术, 2026, 48(2): 402-409.
[14]	杨雪莹, 李高鹏, 张云. 语义引导的星载多角度SAR三维重建方法[J]. 系统工程与电子技术, 2026, 48(2): 430-446.
[15]	陈凯, 赵永波, 刘仍莉, 邓海涛, 孙龙. 机载长合成孔径时间海面运动舰船高分辨SAR成像算法[J]. 系统工程与电子技术, 2026, 48(2): 456-465.

基于散射拓扑增强的双流SAR飞机检测网络

Dual-stream SAR aircraft detection network enhanced by scattering topology

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 33

相关文章 15

编辑推荐

Metrics

本文评价