基于时频图自主学习的海面小目标检测

doi:10.3969/j.issn.1001-506X.2021.01.05

摘要/Abstract

摘要：

多维特征检测方法已成功运用于海面小目标探测中。针对人工特征提取的局限性,将检测问题转变为两分类问题,提出了一种基于时频图深度学习的目标检测方法。首先,将一维观测回波变换到二维时频域,并通过归一化时频图进行白化预处理。其次,建立半仿真含目标回波数据库,解决两类训练样本非均衡问题。然后,搭建迁移学习模型自主学习时频图特性,具有深度网络结构和减小训练代价的优势。最后,将两分类的概率值作为统计量,获得虚警可控的判决区域。基于IPIX实测数据实验结果表明:所提的检测器能深入挖掘目标和杂波的差异性,低信杂比下仍能有效提升海面小目标的探测能力。

关键词: 海杂波, 目标检测, 时频图, 迁移学习

Abstract:

Multi-dimensional feature detection method has been successfully applied to sea-surface small target detection. Due to the limitation of artificial feature extraction, detection problem is converted into two classification problems and the target detection method based on deep learning of time-frequency (TF) graph is proposed. Fristly, one-dimensional observation echo is transformed into two-dimensional TF domain, and the whitening pre-treating is carried out by normalized TF graph. Second, a semi-simulated database with target echo is established to solve the problem of unbalanced two training samples. Then, transfer learning model is built to independently study the properties of TF graph, which has the advantages of deep network structure and reducing training cost. Finally, the probabilities of two class serve as statistics to obtain the decision region with controllable false alarm rate. Experimental results by IPIX datasets show that the proposed detector can deeply mine the differences between target and clutter, which can effectively improve the detection capability of sea-surface small targets at low signal-to-clutter ratio case.

Key words: sea clutter, target detection, time-frequency (TF) graph, transfer learning

中图分类号:

TN911.23

施赛楠, 董泽远, 杨静, 杨春娇. 基于时频图自主学习的海面小目标检测[J]. 系统工程与电子技术, 2021, 43(1): 33-41.

Sainan SHI, Zeyuan DONG, Jing YANG, Chunjiao YANG. Sea-surface small target detection based on autonomic learning of time-frequency graph[J]. Systems Engineering and Electronics, 2021, 43(1): 33-41.

图/表 12

图1

图2

图3

图4

表1

图5

图6

图7

图8

图9

图10

表2

参考文献 29

1	YAN K , BAI Y , WU H C , et al. Robust target detection within sea clutter based on graphs[J]. IEEE Trans.on Geoscience and Remote Sensing, 2019, 57 (9): 7093- 7103. doi: 10.1109/TGRS.2019.2911451
2	SHI S N , LIANG X , SHUI P L , et al. Low-velocity small target detection with Doppler-guided retrospective filter in high-resolution radar at fast scan mode[J]. IEEE Trans.on Geoscience and Remote Sensing, 2019, 57 (11): 8937- 8953. doi: 10.1109/TGRS.2019.2923790
3	赵文静, 金明录, 刘文龙. 海杂波环境下改进的中值矩阵检测方法[J]. 系统工程与电子技术, 2018, 40 (10): 2173- 2179. doi: 10.3969/j.issn.1001-506X.2018.10.03
	ZHAO W J , JIN M L , LIU W L . Modified median matrix detection method for sea clutter environment[J]. Systems Engineering and Electronics, 2018, 40 (10): 2173- 2179. doi: 10.3969/j.issn.1001-506X.2018.10.03
4	LI D C , SHUI P L . Floating small target detection in sea clutter via normalized Doppler power spectrum[J]. IET Radar, Sonar & Navigation, 2016, 10 (4): 699- 706.
5	时艳玲, 林毓峰, 梁丹丹. 非平稳海杂波背景下子带分段ANMF检测器[J]. 系统工程与电子技术, 2018, 40 (4): 782- 789.
	SHI Y L , LIN Y F , LIANG D D . Subband segmented ANMF detector in non-stationary sea clutter[J]. Systems Engineering and Electronics, 2018, 40 (4): 782- 789.
6	HU J , TUNG W W , GAO J B . Detection of low observable targets with sea clutter by structure function based multifractal analysis[J]. IEEE Trans.on Antennas Propagation, 2006, 54 (1): 136- 143. doi: 10.1109/TAP.2005.861541
7	LI Y , YANG Y H , ZHU X Y . Target detection in sea clutter based on multifractal characteristics after empirical mode decomposition[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14 (9): 1547- 1551. doi: 10.1109/LGRS.2017.2721463
8	刘宁波, 黄勇, 关键, 等. 实测海杂波频域分形特性分析[J]. 电子与信息学报, 2012, 34 (4): 929- 935.
	LIU N B , HUANG Y , GUAN J , et al. Fractal analysis of real sea clutter in frequency domain[J]. Journal of Electronics & Information Technology, 2012, 34 (4): 929- 935.
9	SHUI P L , LI D C , XU S W . Tri-feature-based detection of floating targets in sea clutter[J]. IEEE Trans.on Aerospace and Electronic Systems,, 2014, 50 (2): 1416- 1430. doi: 10.1109/TAES.2014.120657
10	SHUI P L , GUO Z X , SHI S N . Feature-compression-based detection of sea-surface small targets[J]. IEEE Access, 2020, 8, 8371- 8385. doi: 10.1109/ACCESS.2019.2962793
11	XU S W , ZHENG J B , PU J , et al. Sea-surface floating small target detection based on polarization features[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15 (10): 1505- 1509.
12	GU T C . Detection of small floating targets on the sea surface based on multi-features and principal component analysis[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17 (5): 809- 813. doi: 10.1109/LGRS.2019.2935262
13	SHI S N , SHUI P L . Sea-surface floating small target detection by one-class classifier in time-frequency feature space[J]. IEEE Trans.on Geoscience and Remote Sensing, 2018, 56 (11): 6395- 6411. doi: 10.1109/TGRS.2018.2838260
14	周龙, 韦素媛, 崔忠马, 等. 基于深度学习的复杂背景雷达图像多目标检测[J]. 系统工程与电子技术, 2019, 41 (6): 1258- 1264.
	ZHOU L , WEI S Y , CUI Z M , et al. Multi-objective detection of complex background radar image based on deep learning[J]. Systems Engineering and Electronics, 2019, 41 (6): 1258- 1264.
15	徐雅楠, 刘宁波, 丁昊, 等. 利用CNN的海上目标探测背景分类方法[J]. 电子学报, 2019, 47 (12): 2505- 2513.
	XU Y N , LIU N B , DING H , et al. Background classification method for marine target detection based on CNN[J]. Acta Electronic Sinica, 2019, 47 (12): 2505- 2513.
16	DARZIKOLAEI M A, EBRAHIMZADE A, GHOLAMI E. Classification of radar clutters with artificial neural network[C]//Proc.of the 2nd International Conference on Knowledge-Based Engineering and Innovation, 2015: 577-581.
17	LI G Q, SONG Z Y, FU Q. Small boat detection via time-frequency analysis and densenet[C]//Proc.of the IEEE 4th International Conference on Signal and Image Processing, 2019: 410-414.
18	MACHADO F J R , BACALLAO V J . Improved shape parameter estimation in K clutter with neural networks and deep learning[J]. International Journal of Interactive Multimedia and Artificial Intelligence, 2016, 3 (7): 96- 103. doi: 10.9781/ijimai.2016.3714
19	LI Y Z , XIE P C , TANG Z S , et al. SVM-based sea-surface small target detection: a false-alarm-rate-controllable approach[J]. IEEE Geoscience Remote Sensing Letters, 2019, 16 (8): 1225- 1229. doi: 10.1109/LGRS.2019.2894385
20	苏宁远, 陈小龙, 关键, 等. 基于卷积神经网络的海上微动目标检测与分类方法[J]. 雷达学报, 2018, 7 (5): 565- 574.
	SU N Y , CHEN X L , GUAN J , et al. Detection and classification of maritime target with micro-motion based on CNNs[J]. Journal of Radars, 2018, 7 (5): 565- 574.
21	SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//Proc.of the IEEE Conference on Computer Vision and Pattern Recognition, 2015.
22	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: 770-778.
23	SZEGEDY C, IOFFE S, VANHOUCKE V. Inception-v4, inception-resnet and the impact of residual connections on learning[C]//Proc.of the AAAI 31st Conference on Artificial Intelligence, 2016.
24	CHOLLET F. Xception: deep learning with depthwise separable convolutions[C]//Proc.of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 1800-1807.
25	WANG N, YEUNG D Y. Learning a deep compact image representation for visual tracking[C]//Proc.of the 26th International Conference on Neural Information Processing Systems, 2013: 809-817.
26	SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision[C]//Proc.of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 2818-2826.
27	PAN S J , YANG Q . A survey on transfer learning[J]. IEEE Trans.on Knowledge and Data Engineering, 2010, 22, 1345- 1359. doi: 10.1109/TKDE.2009.191
28	WANG J D, CHEN Y Q, YU H, et al. Easy transfer learning by exploiting intra-domain structures[C]//Proc.of the IEEE International Conference on Multimedia and Expo, 2019: 1210-1215.
29	Cognitive Systems Laboratory, McMaster University, Canada. The IPIX radar database[EB/OL].[2020-06-11].http://soma.mcmaster.ca//ipix.php.

数据名称	#26	#30	#310	#311
编号	1	2	3	4
目标单元	7	7	7	7
影响单元	6~8	6~8	6~9	6~9
风速/(km/h)	9	19	33	33
有效浪高/m	1.1	0.9	0.9	0.9
ASCR/dB	4.3	-0.3	2.3	11.9
多普勒距离	0.66	0.68	0.88	0.95

检测器名称	比较因子
检测器名称	#26	#30	#310	#311	训练时间/s	测试时间/s
AlexNet^[20]	0.165	0.094	0.506	0.877	-	-
AlexNet+NTFD	0.168	0.118	0.764	0.892	1 084	0.67
ALTG检测器	0.426	0.140	0.885	0.942	1 681	0.09

[1]	宋爽, 张悦, 张琳娜, 岑翼刚, 李浥东. 基于深度学习的轻量化目标检测算法[J]. 系统工程与电子技术, 2022, 44(9): 2716-2725.
[2]	肖宇, 邓正宏, 张展. 基于双阶段互信息准则的多目标检测波形设计[J]. 系统工程与电子技术, 2022, 44(9): 2736-2742.
[3]	杨立儒, 刘永祥, 杨威. 基于迁移学习的雷达杂波幅度统计模型选择[J]. 系统工程与电子技术, 2022, 44(8): 2457-2467.
[4]	刘祥, 黄天耀, 刘一民. 频率捷变雷达的扩展目标检测[J]. 系统工程与电子技术, 2022, 44(6): 1833-1838.
[5]	孙晶明, 虞盛康, 孙俊. 基于元学习的雷达小样本目标识别方法及改进[J]. 系统工程与电子技术, 2022, 44(6): 1839-1845.
[6]	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.
[7]	魏文晓, 刘洁瑜, 沈强, 李成. 基于人眼视点图的特征融合小目标检测算法[J]. 系统工程与电子技术, 2022, 44(4): 1120-1127.
[8]	周晓玲, 张朝霞, 鲁雅, 王倩, 王琨琨. 基于改进R-FCN的SAR图像识别[J]. 系统工程与电子技术, 2022, 44(4): 1202-1209.
[9]	李洪瑶, 李小强, 韩心中, 谢学立, 席建祥. 基于决策融合的多无人机协同目标检测识别算法[J]. 系统工程与电子技术, 2022, 44(3): 746-754.
[10]	何立, 沈亮, 李辉, 王壮, 唐文泉. 强化学习中的策略重用: 研究进展[J]. 系统工程与电子技术, 2022, 44(3): 884-899.
[11]	吴涛, 王伦文, 朱敬成. 基于迁移学习和注意力机制的伪装图像分割[J]. 系统工程与电子技术, 2022, 44(2): 376-384.
[12]	时艳玲, 王磊, 李君豪. 基于投影空间下奇异值分解的海面小目标CFAR检测[J]. 系统工程与电子技术, 2022, 44(2): 512-519.
[13]	潘超凡, 李润生, 许岩, 胡庆, 牛朝阳, 刘伟. 基于感知向量的光学遥感图像舰船检测[J]. 系统工程与电子技术, 2022, 44(12): 3631-3640.
[14]	贾晓雅, 汪洪桥, 杨亚聃, 崔忠马, 熊斌. 基于YOLO框架的无锚框SAR图像舰船目标检测[J]. 系统工程与电子技术, 2022, 44(12): 3703-3709.
[15]	薛春岭, 曹菲, 孙庆, 秦建强, 冯晓伟. 基于多特征信息融合的海面微弱目标检测[J]. 系统工程与电子技术, 2022, 44(11): 3338-3345.