基于改进的深度学习网络的SAR图像瞬时海岸线自动提取算法

doi:10.12305/j.issn.1001-506X.2021.08.11

摘要/Abstract

摘要：

针对目前合成孔径雷达(synthetic aperture radar, SAR)在对大尺度瞬时海岸线提取方面的图像解译过程中, 仍然存在精度低与自动化水平差的问题, 提出一种基于深度学习网络的瞬时海岸线自动提取算法。首先, 将SAR图像进行Lee滤波增强来抑制相干斑。其次, 通过升级残差网络为主干网络，分4级提取海水目标的特征。然后, 将4级特征经过全局卷积网络、密集连接网络和解码器网络配合，充分提取目标的本质特征, 并通过上采样产生海水分割结果。最后, 利用Sobel算子分离出海岸线并和原SAR图像融合以便清晰查看结果。通过与全卷积网络与细化网络的海岸线提取实验结果进行对比, 证明所提算法对海岸线的提取更加准确, 能够减少虚警和漏警, 具有更好的性能。

关键词: 海岸线提取, 合成孔径雷达图像阴影水体提取, 深度学习, 编码解码网络

Abstract:

Aiming at the problems of low accuracy and automation in the process of image interpretation of large-scale instantaneous coastline extraction by synthetic aperture radar (SAR), a instantaneous coastline automatic extraction algorithm based on deep learning network is proposed. Firstly, the enhancing Lee filter is used to suppressing speckle noise for SAR image. Secondly, the features of seawater targets are extracted in four levels by upgrading the residueal network as the backbone network. Then, the four levels of features pass through global convolutional network, dense connection network and decoder network to extract the essential features. The sea water segmentation results are obtained by the upsampling process. Finally, the results can be clearly viewed by separating the coastline using Sobel operator and fusing it with the original SAR image. Compared with the coastline extraction experimental results of full convolutional network and refinement network, the experimental results show that the proposed algorithm has less false alarm and miss alarm results, and the accuracy extraction of the obtained coastline results, which has better performance.

Key words: coastline extraction, synthetic aperture radar (SAR) image shadow water extraction, deep learning, coding and decoding network

中图分类号:

TP753

王彬, 王国宇. 基于改进的深度学习网络的SAR图像瞬时海岸线自动提取算法[J]. 系统工程与电子技术, 2021, 43(8): 2108-2115.

Bin WANG, Guoyu WANG. Instantaneous coastline automatic extraction algorithm for SAR images based on improved deep learning network[J]. Systems Engineering and Electronics, 2021, 43(8): 2108-2115.

图/表 13

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

表1

参考文献 32

1	吴一全, 刘忠林. 遥感影像的海岸线自动提取方法研究进展[J]. 遥感学报, 2019, 23 (4): 582- 602.
	WU Y Q , LIU Z L . Research progress on automatic coastline extraction from remote sensing images[J]. Journal of Remote Sensing, 2019, 23 (4): 582- 602.
2	马小峰, 赵冬至, 邢小罡, 等. 海岸线卫星遥感提取方法研究[J]. 海洋环境科学, 2007, (2): 185- 189. doi: 10.3969/j.issn.1007-6336.2007.02.022
	MA X F , ZHAO D Z , XING X G , et al. Study on satellite remote sensing extraction method of coastline[J]. Journal of Marine Environmental Science, 2007, (2): 185- 189. doi: 10.3969/j.issn.1007-6336.2007.02.022
3	FERRETTI A , MONTIGUARNIERI A . InSAR principles: guidelines for SAR interferometry processing and interpretation[M]. Paris: the European Space Agency Publications, 2007.
4	CHENG J H , GAO G , KU X S , et al. Automatic road network extraction of high resolution SAR image based on MRF[J]. Journal of Systems Engineering, 2012, 34 (7): 1377- 1381.
5	GB 12327-1998. 海道测量规范[S]. 北京: 国家质量技术监督局, 2004.
	GB 12327-1998. Specification for hydrographic surveys[S]. Beijing: State Administration of Quality and Technical Supervision, 2004.
6	LIU C , YANG J , YIN J J , et al. Coastline detection in SAR images using a hierarchical level set segmentation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9 (11): 4908- 4920. doi: 10.1109/JSTARS.2016.2613279
7	WANG D L , YANG Y . Kernel estimation for optimal threshold SAR image coastline extraction[J]. Journal of Radar Science and Technology, 2019, 17 (3): 310- 318.
8	SUI H G, XU C. Automatic extraction of water in high-resolution SAR images based on multi-scale level set method and Otsu algorithm[C]// Proc. of the International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012.
9	LI Z M , LUO Y Z , MAN W , et al. Study on extraction and change of Fujian coastline based on remote sensing and GIS[J]. Journal of Applied Oceanography, 2017, 36 (1): 125- 134.
10	蒋科迪, 殷勇, 范开桂, 等. 基于Canny算子的南通江海岸线研究[J]. 测绘通报, 2019, (10): 83- 88.
	JIANG K D , YIN Y , FAN K G , et al. Research on the coastline of Nantong river based on Canny operator[J]. Bulletin of Surveying and Mapping, 2019, (10): 83- 88.
11	ALONSO M T , LOPEZ-MARTINEZ C , MALLORQUI J J , et al. Edge enhancement algorithm based on the wavelet transform for automatic edge detection in SAR images[J]. IEEE Trans.on Geoscience and Remote Sensing, 2011, 49 (1): 222- 235. doi: 10.1109/TGRS.2010.2052814
12	QIAO X Q , WANG Q , ZHAN C , et al. Automatic shoreline extraction of the yellow river delta based on multi-spectral data[J]. Journal of Oceanography, 2016, 38 (7): 59- 71.
13	TOCHAMNANVITA T , MUTTITANON W . Investigation of coastline changes in three provinces of Thailand using remote sensing[J]. International Archives of the Photogrammetry Remote Sensing, 2014, 8 (5): 1079- 1083.
14	朱长明, 张新, 骆剑承, 等. 基于样本自动选择与SVM结合的海岸线遥感自动提取[J]. 国土资源遥感, 2013, 25 (2): 69- 74.
	ZHU C M , ZHANG X , LUO J C , et al. Coastline remote sensing automatic extraction based on automatic sample selection and SVM[J]. Journal of Remote Sensing of Land and resources, 2013, 25 (2): 69- 74.
15	CHEN L F , CUI X L , LI Z H , et al. A new deep learning algorithm for SAR scene classification based on spatial statistical modeling and features re-calibration[J]. Sensors, 2019, 19 (11): 2479. doi: 10.3390/s19112479
16	CHEN L F , WENG T , XING J , et al. A new deep learning network for automatic bridge detection from sar images based on balanced and attention mechanism[J]. Remote Sensing, 2020, 12 (3): 441- 459. doi: 10.3390/rs12030441
17	KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[C]//Proc. of the International Conference on Neural Information Processing Systems, 2012.
18	CHEN L F , TAN S Y , PAN Z H , et al. A new framework for automatic airports extraction from SAR images using multi-level dual attention mechanism[J]. Remote Sensing, 2020, 12 (3): 560- 584. doi: 10.3390/rs12030560
19	SHELHAMER E , LONG J , DARRELL T . Fully convolutional networks for semantic segmentation[J]. IEEE Trans.on Pattern Analysis & Machine Intelligence, 2017, 39 (4): 640- 651.
20	CHEN L C , PAPANDREOU G , KOKKINOS I , et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Trans.on Pattern Analysis & Machine Intelligence, 2016, 40 (4): 834- 848.
21	ZHENG S, JAYASUMANA S, ROMERA-PAREDES B, et al. Conditional random fields as recurrent neural networks[C]//Proc. of the IEEE International Conference on Computer Vision, 2016.
22	CHEN L C, PAPANDREOU G, SCHROFF F, et al. Rethinking atrous convolution for semantic image segmentation[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017.
23	LIN G, MILAN A, SHEN C, et al. RefineNet: multi-path refinement networks for high-resolution semantic segmentation[C]// Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017.
24	PENG C, ZHANG X Y, YU G, et al. Large kernel matters-improve semantic segmentation by global convolutional network[C]// Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017.
25	LANG F K , YANG J , LI D R . An adaptive enhanced Lee speckle filter for polarimetric SAR image[J]. Bulletin of Surveying and Mapping, 2014, 43 (7): 690- 697.
26	XIE S, GIRSHICK R, DOLLAR P, et al. Aggregated residual transformations for deep neural networks[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017.
27	HUANG G, LIU Z, MAATEN L V, et al. Densely connected convolutional networks[C]//Proc. of IEEE Conference on Computer Vision and Pattern Recognition, 2017.
28	ZHANG K Q , LIAO Q . FPGA implementation of eight-direction Sobel edge detection algorithm based on adaptive threshold[J]. Journal of Physics: Conference Series, 2020, 1678 (1): 012105.
29	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2015.
30	TAN S Y , CHEN L F , PAN Z H , et al. Geospatial contextual attention mechanism for automatic and fast airport detection in SAR imagery[J]. IEEE Access, 2020, 8, 173627- 173640. doi: 10.1109/ACCESS.2020.3024546
31	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016.
32	SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision[C]//Proc. of the International Conference on Computer Vision and Pattern Recogintion, 2015.

实验	方法	PA	IOU	测试时间/s
1	FCN	0.91	0.87	2.7
	RefineNet	0.92	0.88	4.1
	本文方法	0.95	0.94	2.9
2	FCN	0.92	0.89	2.3
	RefineNet	0.92	0.90	3.5
	本文方法	0.94	0.93	2.6

[1]	韩啸, 陈世文, 陈蒙, 杨锦程. 基于互易点学习的LPI信号开集识别[J]. 系统工程与电子技术, 2022, 44(9): 2752-2759.
[2]	张立民, 谭凯文, 闫文君, 张聿远. 基于多级跳线残差网络的雷达辐射源识别[J]. 系统工程与电子技术, 2022, 44(7): 2148-2156.
[3]	金国栋, 薛远亮, 谭力宁, 许剑锟. 基于孪生神经网络的目标跟踪算法进展研究[J]. 系统工程与电子技术, 2022, 44(6): 1805-1822.
[4]	赵晓枫, 徐叶斌, 吴飞, 牛家辉, 蔡伟, 张志利. 基于全局感知机制的地面红外目标检测方法[J]. 系统工程与电子技术, 2022, 44(5): 1461-1467.
[5]	邹虹, 白陈阳, 何鹏, 崔亚平, 王汝言, 吴大鹏. 基于分布式深度学习的边缘服务放置策略[J]. 系统工程与电子技术, 2022, 44(5): 1728-1737.
[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]	孙晶明, 虞盛康, 孙俊. 基于深度学习的HRRP识别姿态敏感性分析[J]. 系统工程与电子技术, 2022, 44(3): 802-807.
[8]	姚云翔, 陈莹. 注意力机制下双模态交互融合的目标跟踪网络[J]. 系统工程与电子技术, 2022, 44(2): 410-419.
[9]	高涌荇, 王旭东, 汪玲, 朱岱寅, 郭军, 孟凡旺. 基于RCNN的双极化气象雷达天气信号检测[J]. 系统工程与电子技术, 2022, 44(11): 3380-3387.
[10]	周毅恒, 杨军, 夏赛强, 吕明久. 闪烁现象下旋翼目标微动参数估计方法[J]. 系统工程与电子技术, 2022, 44(1): 54-63.
[11]	付蓉, 黄天耀, 刘一民. 基于深度学习的捷变相参雷达1-Bit块稀疏重构[J]. 系统工程与电子技术, 2022, 44(1): 70-75.
[12]	张聿远, 张立民, 闫文君. 基于互相关特征图和扩张稠密卷积网络的SFBC-OFDM识别方法[J]. 系统工程与电子技术, 2021, 43(9): 2657-2664.
[13]	王彩云, 李阳雨, 李晓飞, 王佳宁, 魏文怡. 基于稀疏性深度学习的航拍图像超分辨重构[J]. 系统工程与电子技术, 2021, 43(8): 2045-2050.
[14]	黄月平, 李小锋, 杨小冈, 齐乃新, 卢瑞涛, 张胜修. 基于相关滤波的视觉目标跟踪算法新进展[J]. 系统工程与电子技术, 2021, 43(8): 2051-2065.
[15]	谢春思, 刘志赢, 桑雨. 基于特征匹配的舰载对陆导弹目标识别模型[J]. 系统工程与电子技术, 2021, 43(8): 2244-2253.