基于多源遥感图像多级协同融合的舰船识别算法

doi:10.12305/j.issn.1001-506X.2024.02.05

摘要/Abstract

摘要：

针对极化合成孔径雷达(polarimetric synthetic aperture radar, PolSAR)图像存在斑点噪声严重、可视性差、直接影响目标识别精度的问题, 提出一种基于多源遥感图像多级协同融合的舰船识别算法。通过采用多级协同融合方式, 丰富图像的特征量, 提高舰船识别精度。所提方法首先进行多源遥感数据的像素级融合, 然后在上一步基础上进行特征级融合, 最终得到新的目标特征。所提方法充分发挥了不同频段的PolSAR与多光谱图像的信息互补优势，不仅保留了多频段PolSAR对目标的极化散射特征, 也保留了多光谱数据的空-谱信息。所提方法在可视性与检测精度上表现都较为出色，与传统的单一遥感数据相比, 识别精度至少提高了5.12%。

关键词: 极化合成孔径雷达, 图像融合, 多光谱, 舰船检测

Abstract:

The problem of serious speckle noise and poor visibility in polarimetric synthetic aperture radar (PolSAR) directly affect the accuracy of target recognition. A ship recognition algorithm based on the multi-level cooperative fusion of multi-source remote sensing images is proposed. The method of multi-level cooperative fusion is adopted to enrich the image features and improve the accuracy of ship recognition. Firstly, the multi-source remote sensing data is fused at the pixel level. Then, the feature-level fusion is carried out on the basis of the previous step. Finally, new target features are obtained. This method gives full play to the information complementarity advantage of PolSAR and multispectral images in different frequency bands. This method retains the polarization scattering characteristics of the target in different frequency bands of PolSAR. Meantime, the spectral-spatial information of multispectral data is also retained. Compared with the traditional single remote sensing data, the proposed method performs better in visibility and detection accuracy. The recognition accuracy of the proposed method is improved by 5.12% at least.

Key words: polarimetric synthetic aperture radar (PolSAR), image fusion, multispectral, ship detection

中图分类号:

TP701

张亚丽, 冯伟, 全英汇, 邢孟道. 基于多源遥感图像多级协同融合的舰船识别算法[J]. 系统工程与电子技术, 2024, 46(2): 407-418.

Yali ZHANG, Wei FENG, Yinghui QUAN, Mengdao XING. Ship recognition algorithm based on multi-level collaborative fusion of multi-source remote sensing images[J]. Systems Engineering and Electronics, 2024, 46(2): 407-418.

图/表 9

图1

图2

图3

图4

表1

表2

图5

图6

表3

参考文献 46

1	ZHANG T W , ZHANG X L , LIU C , et al. Balance learning for ship detection from synthetic aperture radar remote sensing imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 182, 190- 207. doi: 10.1016/j.isprsjprs.2021.10.010
2	FENG W , QUAN Y H , DAUPHIN G , et al. Semi-supervised rotation forest based on ensemble margin theory for the classification of hyperspectral image with limited training data[J]. Information Sciences, 2021, 575, 611- 638. doi: 10.1016/j.ins.2021.06.059
3	HAN Y Q , YANG X Y , PU T , et al. Fine-grained recognition for oriented ship against complex scenes in optical remote sensing images[J]. IEEE Trans. on Geoscience and Remote Sensing, 2021, 60, 5612318.
4	ZHU C R , ZHOU H , WANG R S , et al. A novel hierarchical method of ship detection from spaceborne optical image based on shape and texture features[J]. IEEE Trans. on Geoscience and Remote Sensing, 2010, 48 (9): 3446- 3456. doi: 10.1109/TGRS.2010.2046330
5	LIN K, LI W M, LIU H Y, et al. Different levels multi-source remote sensing image fusion[C]//Proc. of the IEEE International Conference on Signal, Information and Data Processing, 2019.
6	CAO Y C , WU Y , LI M , et al. DFAF-Net: a dual-frequency PolSAR image classification network based on frequency-aware attention and adaptive feature fusion[J]. IEEE Trans. on Geoscience and Remote Sensing, 2022, 60, 5224318.
7	ZHAO L L , YANG J , LI P X , et al. Damage assessment in urban areas using post-earthquake airborne PolSAR imagery[J]. International Journal of Remote Sensing, 2013, 34 (24): 8952- 8966. doi: 10.1080/01431161.2013.860566
8	MARINO A . A notch filter for ship detection with polarimetric SAR data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2013, 6 (3): 1219- 1232. doi: 10.1109/JSTARS.2013.2247741
9	WANG Y, YANG J, LI J W. Similarity-intensity joint PolSAR speckle filtering[C]//Proc. of the CIE International Conference on Radar, 2016.
10	HAN Y , CAI Y Z , CAO Y , et al. A new image fusion performance metric based on visual information fidelity[J]. Information Fusion, 2013, 14 (2): 127- 135. doi: 10.1016/j.inffus.2011.08.002
11	WANG J, CHEN J Q, WANG Q W. Fusion of PolSAR and multispectral satellite images: a new insight for image fusion[C]// Proc. of the IEEE International Conference on Computational Electromagnetics, 2020: 83-84.
12	HU P F, WANG H C, FAN J P. Comparison of research on methods of multi-source remote sensing image fusion[C]//Proc. of the International Conference on Remote Sensing, Environment and Transportation Engineering, 2011: 3938-3941.
13	ZOU B , LI H L , ZHANG L M . Multilevel information fusion-based change detection for multiangle PolSAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 19, 4005805.
14	PAL S K , MAJUMDAR T J , BHATTACHARYA A K . ERS-2 SAR and IRS-1C LISS Ⅲ data fusion: a PCA approach to improve remote sensing based geological interpretation[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2007, 61 (5): 281- 297. doi: 10.1016/j.isprsjprs.2006.10.001
15	WANG Z J , ZIOU D , ARMENAKIS C , et al. A comparative analysis of image fusion methods[J]. IEEE Trans. on Geoscience and Remote Sensing, 2005, 43 (6): 1391- 1402. doi: 10.1109/TGRS.2005.846874
16	NENCINI F , GARZELLI A , BARONTI S , et al. Remote sensing image fusion using the curvelet transform[J]. Information Fusion, 2007, 8 (2): 143- 156. doi: 10.1016/j.inffus.2006.02.001
17	GARZELLI A . Wavelet-based fusion of optical and SAR image data over urban area[J]. International Archives of Photogrammetry Remote Sensing and Spatial Information Sciences, 2002, 34 (3/B): 59- 62.
18	HUANG B , LI Y , HAN X Y , et al. Cloud removal from optical satellite imagery with SAR imagery using sparse representation[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12 (5): 1046- 1050. doi: 10.1109/LGRS.2014.2377476
19	WU W F , SHAO Z F , HUANG X , et al. Quantifying the sensitivity of SAR and optical images three-level fusions in land cover classification to registration errors[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 112, 102868. doi: 10.1016/j.jag.2022.102868
20	ZHAI W , SHEN H F , HUANG C L , et al. Fusion of polarimetric and texture information for urban building extraction from fully polarimetric SAR imagery[J]. Remote Sensing Letters, 2016, 7 (1): 31- 40. doi: 10.1080/2150704X.2015.1101179
21	苏瑞雪, 汤玉奇. 光学-极化SAR影像特征融合与分类[J]. 测绘与空间地理信息, 2019, 42 (6): 51- 55.
	SU R X , TANG Y Q . Feature fusion and classification of optical-PolSAR images[J]. Geomatics & Spatial Information Technology, 2019, 42 (6): 51- 55.
22	万剑华, 臧金霞, 刘善伟, 等. 一种全极化高分SAR与中分光学影像融合方法[J]. 热带海洋学报, 2017, 36 (2): 79- 85.
	WAN J H , ZANG J X , LIU S W , et al. A fusion method of high-resolution full polarimetric SAR and moderate-resolution optical image[J]. Journal of Tropical Oceanography, 2017, 36 (2): 79- 85.
23	童莹萍, 全英汇, 冯伟, 等. 基于空谱信息协同与Gram-Schmidt变换的多源遥感图像融合方法[J]. 系统工程与电子技术, 2022, 44 (7): 2074- 2083.
	TONG Y P , QUAN Y H , FENG W , et al. Multi-source remote sensing image fusion method based on spatial-spectrum information collaboration and Gram-Schmidt transform[J]. Systems Engineering and Electronics, 2022, 44 (7): 2074- 2083.
24	LIN Y Y , ZHANG H S , LIN H , et al. Incorporating synthetic aperture radar and optical images to investigate the annual dynamics of anthropogenic impervious surface at large scale[J]. Remote Sensing of Environment, 2020, 242, 111757. doi: 10.1016/j.rse.2020.111757
25	DU P J , SAMAT A , WASKE B , et al. Random forest and rotation forest for fully polarized SAR image classification using polarimetric and spatial features[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 105, 38- 53. doi: 10.1016/j.isprsjprs.2015.03.002
26	WANG X Y, FENG J L, CAO Z J, et al. Polarimetric-spatial classification of PolSAR images based on composite kernel feature fusion[C]//Proc. of the IEEE Radar Conference, 2017: 1455-1459.
27	李国梁. 基于深度学习的红外与可见光图像融合算法研究[D]. 北京: 北京交通大学, 2021.
	LI G L. Research on infrared and visible image fusion algorithm based on deep learning[D]. Beijing: Beijing Jiaotong University, 2021.
28	SHAO Z F , FU H Y , FU P , et al. Mapping urban impervious surface by fusing optical and SAR data at the decision level[J]. Remote Sensing, 2016, 8 (11): 945. doi: 10.3390/rs8110945
29	DU P J , ZHANG W , XIA J S . Hyperspectral remote sensing image classification based on decision level fusion[J]. Chinese Optics Letters, 2011, 9 (3): 031002. doi: 10.3788/COL201109.031002
30	HU B X , LI Q , HALL G B . A decision-level fusion approach to tree species classification from multi-source remotely sensed data[J]. ISPRS Open Journal of Photogrammetry and Remote Sensing, 2021, 1, 100002. doi: 10.1016/j.ophoto.2021.100002
31	FENG W , DAUPHIN G , HUANG W , et al. Dynamic synthetic minority over-sampling technique-based rotation forest for the classification of imbalanced hyperspectral data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12 (7): 2159- 2169. doi: 10.1109/JSTARS.2019.2922297
32	FENG W , DAUPHIN G , HUANG W , et al. New margin-based subsampling iterative technique in modified random forests for classification[J]. Knowledge-Based Systems, 2019, 182, 104845. doi: 10.1016/j.knosys.2019.07.016
33	KASAPOGLU N G, ANFINSEN S N, ELTOFT T. Fusion of optical and multifrequency PolSAR data for forest classification[C]// Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2012: 3355-3358.
34	LI T, ZHANG J P, ZHAO H L, et al. Classification-oriented hyperspectral and PolSAR images synergic processing[C]//Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2013: 1035-1038.
35	李齐贤. 基于无人机图像与激光融合的铁路运行环境异常识别方法研究[D]. 北京: 北京交通大学, 2021.
	LI Q X. Research on recognition method of railway operation environment abnormality based on UAV image and laser fusion[D]. Beijing: Beijing Jiaotong University, 2021.
36	ZOU B, CAI H J, MOON W M, et al. Target detection based on L-and C-band PolSAR data[C]//Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2011: 397-400.
37	ZYL J J V. An overview of the analysis of multi-frequency polarimetric SAR data[C]//Proc. of the 6th European Conference on Synthetic Aperture Radar, 2006.
38	LABEN C A, BROWER B V. Process for enhancing the spatial resolution of multispectral imagery using pan-sharpening[P]. U.S. : Patent 6011875, 2000-01-04.
39	WEI W , XU S Z , ZHANG L Y , et al. Boosting hyperspectral image classification with unsupervised feature learning[J]. IEEE Trans. on Geoscience and Remote Sensing, 2021, 60, 5502315.
40	QU G H , ZHANG D L , YAN P F . Information measure for performance of image fusion[J]. Electronics Letters, 2002, 38 (7): 313- 315. doi: 10.1049/el:20020212
41	张小利, 李雄飞, 李军. 融合图像质量评价指标的相关性分析及性能评估[J]. 自动化学报, 2014, 40 (2): 306- 315.
	ZHANG X L , LI X F , LI J . Validation and correlation analysis of metrics for evaluating performance of image fusion[J]. Acta Automatica Sinica, 2014, 40 (2): 306- 315.
42	ESKICIOGLU A M , FISHER P S . Image quality measures and their performance[J]. IEEE Trans. on Communications, 1995, 43 (12): 2959- 2965. doi: 10.1109/26.477498
43	HAN Z Z , TANG X M , GAO X M , et al. Image fusion and image quality assessment of fused images[J]. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2013, doi: 10.5194/isprsarchives-XL-7-W1-33-2013
44	XYDEAS C S , PETROVIC V . Objective image fusion perfor-mance measure[J]. Military Technical Courier, 2000, 36 (4): 308- 309.
45	ASLANTAS V , BENDES E . A new image quality metric for image fusion: the sum of the correlations of differences[J]. AEU-international Journal of Electronics and Communications, 2015, 69 (12): 1890- 1896.
46	SHEIKH H R , BOVIK A C . Image information and visual quality[J]. IEEE Trans. on Image Processing, 2006, 15 (2): 430- 444. doi: 10.1109/TIP.2005.859378

评价指标	PCA融合	所提融合算法
互信息	1.235 5	3.667 2
标准差	7.341 5	7.598 8
空间频率	0.099 4	0.107 0
相关系数	0.509 3	0.580 2
边缘信息保留	0.089 2	0.157 1
视觉信息保真度	0.439 9	1.131 2
差异相关和	0.592 5	0.714 1

评价指标	PCA融合	所提融合算法
互信息	1.520 4	3.048 2
标准差	8.772 2	8.808 7
空间频率	0.106 3	0.134 3
相关系数	0.688 0	0.731 8
边缘信息保留	0.169 6	0.185 1
视觉信息保真度	0.371 3	0.691 6
差异相关和	1.036 5	1.271 7

检测图像	区域1	区域2
Sentinel-2B	0.565 2	0.454 5
ALOS-PALSAR PolSAR	0.437 5	0.333 3
Gaofen-3 PolSAR	0.312 5	0.857 9
PCA融合图像	0.608 7	0.700 0
所提算法融合图像	0.956 5	0.909 1

[1]	王慧赢, 王春平, 付强, 韩子硕, 张冬冬. 基于图像特征的红外与低照度图像融合[J]. 系统工程与电子技术, 2023, 45(8): 2395-2404.
[2]	李海军, 孔繁程, 林云. 基于改进YOLOv5s的红外舰船检测算法[J]. 系统工程与电子技术, 2023, 45(8): 2415-2422.
[3]	王健, 何自豪, 刘洁, 杨珂. 基于梯度域导向滤波器和改进PCNN的图像融合算法[J]. 系统工程与电子技术, 2022, 44(8): 2381-2392.
[4]	张涛, 杨小冈, 卢瑞涛, 谢学立, 刘闯. 基于关键点的遥感图像舰船目标检测[J]. 系统工程与电子技术, 2022, 44(8): 2437-2447.
[5]	童莹萍, 全英汇, 冯伟, 邢孟道. 基于空谱信息协同与Gram-Schmidt变换的多源遥感图像融合方法[J]. 系统工程与电子技术, 2022, 44(7): 2074-2083.
[6]	陈冬, 句彦伟. 基于语义分割实现的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2022, 44(4): 1195-1201.
[7]	陈冬, 句彦伟. 基于改进型YOLOv3的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2021, 43(4): 937-943.
[8]	牛朝阳, 王建涛, 胡涛, 刘伟, 李润生. 极化合成孔径雷达有源干扰的干信比方程[J]. 系统工程与电子技术, 2021, 43(12): 3542-3551.
[9]	代晓康, 殷君君, 杨健. 基于Wishart距离和超像素的极化SAR图像车辆检测[J]. 系统工程与电子技术, 2021, 43(10): 2766-2774.
[10]	孙嘉赤, 邹焕新, 邓志鹏, 李美霖, 曹旭, 马倩. 基于级联卷积神经网络的港口多方向舰船检测与分类[J]. 系统工程与电子技术, 2020, 42(9): 1903-1910.
[11]	安影, 范训礼, 陈莉, 刘佩. 结合FABEMD和改进的显著性检测的图像融合[J]. 系统工程与电子技术, 2020, 42(2): 292-300.
[12]	徐国明, 袁宏武, 薛模根, 王峰. 全偏振参量低秩稀疏分解伪彩色图像融合[J]. 系统工程与电子技术, 2020, 42(11): 2450-2460.
[13]	韩萍, 周波, 卢斌, 韩宾宾. 环境特征与散射特性融合的PolSAR飞机目标检测[J]. 系统工程与电子技术, 2020, 42(10): 2231-2238.
[14]	韩萍, 贾锟, 卢晓光, 韩宾宾. PolSAR图像的改进非局部均值滤波算法[J]. 系统工程与电子技术, 2019, 41(5): 992-999.
[15]	宗静静, 邱天爽. 稀疏表示中稀疏系数的 l-1 范数的特性分析[J]. 系统工程与电子技术, 2019, 41(12): 2692-2696.