语义引导的星载多角度SAR三维重建方法

doi:10.12305/j.issn.1001-506X.2026.02.06

摘要/Abstract

摘要：

面向舰船目标结构复杂性及散射特性导致的星载合成孔径雷达影像三维重构精度较低问题，提出一种语义引导的多角度合成孔径雷达三维重建技术。通过推导本质矩阵模型，弥补基础矩阵在表达目标与投影点间关系上的局限性。此外，采用多层次的拉普拉斯高斯Blob探测算法来辨识合成孔径雷达图像中的显著特征点，并选用归一化互相关算法来执行图像配准，有效应对旁瓣干扰。在完成图像分割与特征提取后，借助提取到的语义信息，系统剔除错误重构点，从而强化舰船目标的三维重建质量。实验结果显示，所得舰船结构解析的相对误差在4%以下，验证了所提方法的有效性。

关键词: 多角度合成孔径雷达, 语义信息, 舰船目标, 图像匹配

Abstract:

To address the problem of low three-dimensional （3D） reconstruction accuracy of ship targets caused by their complex structure and scattering characteristics in spaceborne synthetic aperture radar （SAR） images, a semantic-assisted multi-view SAR 3D reconstruction technology is proposed. This technology overcomes the limitation of the fundamental matrix in expressing the relationship between targets and projection points by deriving an intrinsic matrix model. Additionally, a multi-level Laplacian Gaussian Blob detection algorithm is adopted to identify significant feature points in SAR images, and the normalized cross-correlation algorithm is used to perform image registration, effectively addressing the interference from side lobes. After completing image segmentation and feature extraction, the extracted semantic information is used to systematically eliminate incorrect reconstruction points, thereby enhancing the quality of ship target 3D reconstruction. Experimental results show that the relative error of obtained ship structure result is under 4%, which demonstrates the effectiveness of the proposed method.

Key words: multi-view synthetic aperture radar (SAR), semantic information, ship target, image matching

中图分类号:

TN 957.52

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.

Xueying YANG, Gaopeng LI, Yun ZHANG. Semantic information-assisted 3D reconstruction method for satellite-borne multi-view SAR[J]. Systems Engineering and Electronics, 2026, 48(2): 430-446.

图/表 25

图1

图2

图3

表1

图4

图5

图6

图7

图8

图9

图10

表2

图11

图12

图13

表3

表4

图14

表5

图15

图16

图17

表6

图18

图19

参考文献 38

1	CHEN X, DONG Z, ZHANG Z H, et al. Very high resolution synthetic aperture radar systems and imaging: a review[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17, 7104- 7123. doi: 10.1109/JSTARS.2024.3374429
2	WANG Y X, QIU X L, WEN X J. High-resolution SAR imaging characteristics for multiple scattering of rotating targets[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17, 9974- 9988. doi: 10.1109/JSTARS.2024.3382038
3	WU C J, TEBALDINI S, MANZONI M, et al. Evaluating phase histograms for remote sensing of forested areas using L-band SAR: theoretical modeling and experimental results[J]. IEEE Trans. on Geoscience and Remote Sensing, 2024, 62 doi: 10.1109/tgrs.2024.3425494
4	WANG Y Y, ZHANG X L, ZHOU L M, et al. Linear array SAR imaging and autofocus approach [C]//Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2019: 2316−2319.
5	YUE X Y, LIN Y, TENG F, et al. Multi-angular SAR scattering anisotropy analysis based on low-rank matrix decomposition[C]//Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2021: 3420−3423.
6	李高鹏, 徐乾坤, 涂尚坦, 等. 一种本质矩阵变换的多角度SAR三维重建方法[J/OL]. 哈尔滨工业大学学报, 2024: 1−10 [2024-10-24]. http://link.cnki.net/urlid/23.1235.T.20231214.0953.005.
	LI G P, XU Q K, TU S T, et al. Multi-view SAR 3D reconstruction method based on essential matrix transformation[J]. Journal of Harbin Institute of Technology, 2024: 1−10 [2024-10-24]. http://link.cnki.net/urlid/23.1235.T.20231214.0953.005.
7	CURLANDER J C. Location of spaceborne SAR imagery[J]. IEEE Trans. on Geoscience and Remote Sensing, 1982, GE-20(3): 359−364.
8	杨正得, 谢亚楠, 周星里. 具有解析解的星载SAR图像目标定位方法[J]. 电子测量技术, 2010, 033 (6): 59- 61. doi: 10.3969/j.issn.1002-7300.2010.06.017
	YANG Z D, XIE Y N, ZHOU X L. Method to target location of spaceborne SAR imagery with analysis solution[J]. Electronic Measurement Technology, 2010, 033 (6): 59- 61. doi: 10.3969/j.issn.1002-7300.2010.06.017
9	CHEN L P, AN D X, HUANG X T. A 3-D reconstruction strategy of vehicle outline based on single-pass single-polarization CSAR data[J]. IEEE Trans. on Image Processing, 2020, 26 (11): 5545- 5554.
10	ZHANG J Q, SUO Z Y, LI Z F, et al. DEM generation using circular SAR data based on low-rank and sparse matrix decomposition[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15 (5): 724- 728. doi: 10.1109/LGRS.2018.2809905
11	SHAO M X, ZHANG Z, LI J, et al. TADCG: a novel gridless tomographic SAR imaging approach based on the alternate descent conditional gradient algorithm with robustness and efficiency[J]. IEEE Trans. on Geoscience and Remote Sensing, 2024, 62 doi: 10.1109/tgrs.2023.3345454
12	ZHANG H Q, LIN Y, FENG S S, et al. 3-D target reconstruction using C-band circular SAR imagery based on background constraints [C]//Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2021: 2923−2926.
13	ZHANG X M, LI W C, HUANG C, et al. Three dimensional surface reconstruction with multistatic SAR[C]//Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2021: 5207−5210.
14	郭伟, 杨涵西, 李煜, 等. 语义增强与高阶强交互的SAR图像舰船检测[J]. 遥感信息, 2024, 39 (3): 32- 39. doi: 10.20091/j.cnki.1000-3177.2024.03.005
	GUO W, YANG H X, LI Y, et al. Semantic enhancement and high-order strong interaction for ship detection in SAR images[J]. Remote Sensing Information, 2024, 39 (3): 32- 39. doi: 10.20091/j.cnki.1000-3177.2024.03.005
15	周佳新. 基于语义信息的图像/点云配准与三维重建[D]. 深圳: 中国科学院深圳先进技术研究院, 2020.
	ZHOU J X. Image/point cloud registration and 3D reconstruction based on semantic information[D]. Shenzhen: Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, 2020.
16	MA Z K, YANG J, CHAO J G, et al. A lightweight real-time semantic segmentation network for equipment images in space capsule[C]// Proc. of the International Workshop on Electronic Communication and Artificial Intelligence, 2020: 20−25.
17	LUO Y T, QIU X L, DONG Q, et al. A robust stereo positioning solution for multiview spaceborne SAR images based on the range-Doppler model[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19 doi: 10.1109/lgrs.2020.3048731
18	仇晓兰, 焦泽坤, 杨振礼, 等. 微波视觉三维SAR关键技术及实验系统初步进展[J]. 雷达学报, 2022, 22 (1): 1- 19. doi: 10.12000/JR22027
	QIU X L, JIAO Z K, YANG Z L et al. Key technology and preliminary progress of microwave vision 3D SAR experimental system[J]. Journal of Radars, 2022, 22 (1): 1- 19. doi: 10.12000/JR22027
19	LUO Y T, QIU X L, CHENG Y. A geometric auto-calibration method for multiview UAV-borne FMCW SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2024, 21 doi: 10.1109/lgrs.2024.3350903
20	HAN N, WU J C, FANG X Z, et al. Projective double reconstructions based dictionary learning algorithm for cross domain recognition[J]. IEEE Trans. on Image Processing, 2020, 29, 9220- 9233. doi: 10.1109/TIP.2020.3024728
21	SUN Z C, SUN H R, AN D Y, et al. Trajectory optimization for maneuvering platform bistatic SAR with geosynchronous illuminator[J]. IEEE Trans. on Geoscience and Remote Sensing, 2024, 62 doi: 10.1109/tgrs.2024.3358303
22	KANEMOTO D, HIROSE T. EEG measurements with compressed sensing utilizing EEG signals as the basis matrix[C]// Proc. of IEEE International Symposium on Circuits and Systems, 2023.
23	WU Y F, QI X Y, HUANG L J, et al. Enhanced BP algorithm combined with semantic segmentation and subaperture for improving agricultural scene image quality in GEO SAR. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025, 18: 3043−3056.
24	ZHANG Y, REN H, LU Z, et al. Focusing of highly squinted bistatic SAR with MEO transmitter and high maneuvering platform receiver in curved trajectory[J]. IEEE Trans. on Geoscience and Remote Sensing, 2024, 62 doi: 10.1109/tgrs.2024.3493614
25	REN H, ZHENG L, LI G P, et al. A high-resolution spotlight imaging algorithm via modified second-order space-variant wavefront curvature correction for MEO/HM-BiSAR[J]. Remote Sensing, 2024, 16, 4768. doi: 10.3390/rs16244768
26	LIU W K, LI H, ZHANG J S. On the role of scene coordinate system in focusing of GEO SAR data with fast time-domain algorithm[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025, 18, 2355- 2369. doi: 10.1109/JSTARS.2024.3517665
27	MATAR J, RODRIGUEZ M, KRIEGER G, et al. MEO SAR: system concepts and analysis[J]. IEEE Trans. on Geoscience and Remote Sensing, 2020, 58 (2): 1313- 1324.
28	ISLAM A, ASIKUZZAMAN M, KHYAM M O, et al. Stereo vision-based 3-D positioning and tracking[J]. IEEE Access, 2020, 8, 138771- 138787.
29	SATHYA S, MADHUMATHI R, MANJULA D, et al. Performance evaluation of Blob detection techniques using image processing[C]// Proc. of the International Conference on Sustainable Expert Systems, 2024: 1101−1106.
30	ELBOHER E, WERMAN M. Asymmetric correlation: a noise robust similarity measure for template matching[J]. IEEE Trans. on Image Processing, 2013, 22 (8): 3062- 3073.
31	LI D, LIANG Q H, LIU H Q, et al. A novel multidimensional domain deep learning network for SAR ship detection[J]. IEEE Trans. on Geoscience and Remote Sensing, 2022, 60
32	YU J M, ZHOU G Y, ZHOU S B, et al. A fast and lightweight detection network for multi-scale SAR ship detection under complex backgrounds[J]. Remote Sensing, 2022, 14 (1): 31.
33	JIANG M Z, YANG X Z, DONG Z Y, et al. Ship classification based on superstructure scattering features in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13 (5): 616- 620. doi: 10.1109/LGRS.2016.2514482
34	IERVOLINO P, GUIDA R. A novel ship detector based on the generalized-likelihood ratio test for SAR imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10 (8): 3616- 3630. doi: 10.1109/JSTARS.2017.2692820
35	WANG X L, CHEN C X, PAN Z, et al. Superpixel-based LCM detector for faint ships hidden in strong noise background SAR imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16 (3): 417- 421. doi: 10.1109/LGRS.2018.2873637
36	SUN K, LI Y Y, LI C, et al. A two-step ship target detection method in high-resolution SAR image based on coarse-to-fine mechanism[C]//Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2020: 5207−5210.
37	WANG X, ZHANG S N, ZHAO H C, et al. Analyze of ship’s micro-Doppler characteristics based on hough transform [C]//Proc. of the IEEE International Conference on Signal and Image Processing, 2020: 644−648.
38	张琳. 基于RD反投影的圆周SAR典型目标三维点云重建方法研究[D]. 北京: 北方工业大学, 2023.
	ZHANG L. Research on 3D point cloud reconstruction method of circular SAR typical target based on RD back projection[D]. Beijing: North China University of Technology, 2023.

参数类型	值
偏心率	0.003
近地点幅角/（°）	90
轨道高度/km	1 000
轨道倾角/（°）	6
升交点赤经/（°）	98
载频/GHz	10
带宽/MHz	400
脉冲重频/Hz	1 000
采样率/MHz	500
合成孔径时间/s	30

参数	参数值（角度1，角度2）
下视角/（°）	60.8, 26.1
斜视角/（°）	8.6, 35.3
雷达相对成像平面高度/km	577.2, 707.9
雷达与目标距离/km	1196.4, 965.6
雷达相对速度/（m/s）	7499.4, 7732.3
脉冲重复频率/Hz	2000
载频/GHz	10
带宽/MHz	400
采样频率/MHz	500
数据方位向跨度/（°）	26.7

误差项	误差值/（像素/个）
X坐标平均匹配误差	1.6618
Y坐标平均匹配误差	−1.2946
最小匹配误差	0.7549
最大匹配误差	12.7394
平均匹配误差	1.6798

误差项	误差值/（像素/个）
X坐标平均匹配误差	−0.6619
Y坐标平均匹配误差	−0.2870
最小匹配误差	0.5197
最大匹配误差	2.3085
平均匹配误差	0.7256

误差项	误差值
误差项	RD BP	所提算法
最小估计误差	0.3085	0.2125
最大估计误差	9.7319	4.7326
平均估计误差	3.3504	0.3025