SAR Image Generation Method via PCGAN for Ship Detection

PAN Lei; GUO Yushi; LI Hengchao; WANG Weiye; LI Zechen; MA Tianyu

doi:10.3969/j.issn.0258-2724.20210630

Volume 59 Issue 3

Jun. 2024

Turn off MathJax

Article Contents

Abstract

References

Journal of Southwest Jiaotong University > 2024 > 59(3): 547-555.

PAN Lei, GUO Yushi, LI Hengchao, WANG Weiye, LI Zechen, MA Tianyu. SAR Image Generation Method via PCGAN for Ship Detection[J]. Journal of Southwest Jiaotong University, 2024, 59(3): 547-555. doi: 10.3969/j.issn.0258-2724.20210630

Citation:

PAN Lei, GUO Yushi, LI Hengchao, WANG Weiye, LI Zechen, MA Tianyu. SAR Image Generation Method via PCGAN for Ship Detection[J]. Journal of Southwest Jiaotong University, 2024, 59(3): 547-555. doi: 10.3969/j.issn.0258-2724.20210630

Citation:

PDF( 2274 KB)

SAR Image Generation Method via PCGAN for Ship Detection

doi: 10.3969/j.issn.0258-2724.20210630

PAN Lei^1
,,
GUO Yushi^{2
,
,},
LI Hengchao^{3, 4},
WANG Weiye³,
LI Zechen³,
MA Tianyu³

1.
The 10th Research Institute of China Electronics Technology Group Corporation, Chengdu 610036, China
2.
School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, China
3.
School of Information Science and Technology, Southwest Jiaotong University, Chengdu 611756, China
4.
National Engineering Laboratory of Integrated Transportation Big Data Application Technology, Southwest Jiaotong University, Chengdu 611756, China

Received Date: 03 Aug 2021
Rev Recd Date: 18 Jan 2022

Available Online: 03 Apr 2024

Publish Date: 06 Jul 2022

Abstract

Abstract

Most of existing synthetic aperture radar (SAR) image generation methods fail to generate SAR images and their detection labels simultaneously. A position-based conditional generative adversarial network (PCGAN) is constructed for SAR ship image generation and target detection. Firstly, ship position information is used as a constraint and a detection label to restrict its position in the generated image. Then, the Wasserstein distance is further introduced to stabilize the training process of PCGAN. Finally, the generated SAR images and their corresponding labels are applied for the end-to-end training of YOLOv3, so as to realize the cooperative learning of data enhancement and ship detection, and further obtain the diversified ship data more coupled with the practical application of ship detection. Experimental results conducted on HRSID dataset illustrate that PCGAN can generate clear and robust SAR ship data, and the accuracy of ship detection can be improved by up to 1.01%, thus verifying the proposed method.
- synthetic aperture radar,
- generative adversarial network (GAN),
- data enhancement,
- ship detection,
- position information

FullText(HTML)

References(23)

References

[1]	REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. (2018-04-08)[2020-10-13]. https://arxiv.org/abs/1804.02767.
[2]	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[EB/OL]. (2015-12-08)[2020-10-13]. https://arxiv.org/abs/1512.02325.
[3]	REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[4]	DING J, CHEN B, LIU H W, et al. Convolutional neural network with data augmentation for SAR target recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(3): 364-368.
[5]	朱柳. 高分辨SAR场景分布的重建方法研究[D]. 成都: 电子科技大学,2013.
[6]	刘鹏程. 基于特征调制的SAR欺骗干扰方法研究[D]. 成都: 电子科技大学,2013.
[7]	BALZ T, STILLA U. Hybrid GPU-based single- and double-bounce SAR simulation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(10): 3519-3529.
[8]	HAMMER H, SCHULZ K. Coherent simulation of SAR images[C]//Proceedings of SPIE—The International Society for Optical Engineering 7477. Berlin: [s.n.], 2009: 406-414.
[9]	VAN DEN OORD A, KALCHBRENNER N, KAVUKCUOGLU K. Pixel recurrent neural networks[C]//Proceedings of the 33rd International Conference on International Conference on Machine Learning. New York: [s.n.],2016: 1747-1756.
[10]	KINGMA D P, WELLING M. Auto-encoding variational bayes[EB/OL]. (2013-12-20)[2020-10-13]. https://arxiv.org/abs/1312.6114.
[11]	GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal:MIT Press, 2014: 2672-2680.
[12]	RADFORD A, METZ L, CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[EB/OL]. (2015-11-19)[2020-10-13]. https://arxiv.org/abs/1511.06434.
[13]	KARRAS T, AILA T, LAINE S, et al. Progressive growing of GANs for improved quality, stability, and variation[EB/OL]. (2017-10-27)[2020-10-13]. https://arxiv.org/abs/1710.10196.
[14]	MIRZA M, OSINDERO S. Conditional generative adversarial nets[EB/OL]. (2014-11-06)[2020-10-13]. https://arxiv.org/abs/1411.1784.
[15]	ARJOVSKY M, BOTTOU L. Towards principled methods for training generative adversarial networks[EB/OL]. (2017-01-17)[2020-10-13]. https://arxiv.org/abs/1701.04862.
[16]	ARJOVSKY M, CHINTALA S, BOTTOU L. Wasserstein GAN[EB/OL]. (2017-01-26)[2020-10-13]. https://arxiv.org/abs/1701.07875.
[17]	徐永士,贲可荣,王天雨,等. DCGAN模型改进与SAR图像生成研究[J]. 计算机科学,2020,47(12): 93-99. doi: 10.11896/jsjkx.200700109 XU Yongshi, BEN Kerong, WANG Tianyu, et al. Study on DCGAN model improvement and SAR images generation[J]. Computer Science, 2020, 47(12): 93-99. doi: 10.11896/jsjkx.200700109
[18]	HUANG H H, ZHANG F, ZHOU Y S, et al. High resolution SAR image synthesis with hierarchical generative adversarial networks[C]//IEEE International Geoscience and Remote Sensing Symposium. Yokohama: IEEE, 2019: 2782-2785.
[19]	GUO J Y, LEI B, DING C B, et al. Synthetic aperture radar image synthesis by using generative adversarial nets[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(7): 1111-1115.
[20]	LU Q L, JIANG H Y, LI G J, et al. Data augmentation method of SAR image dataset based on Wasserstein generative adversarial networks[C]//2019 International Conference on Electronic Engineering and Informatics (EEI). Nanjing: IEEE, 2019: 488-490.
[21]	GAO F, YANG Y, WANG J, et al. A deep convolutional generative adversarial networks (DCGANs)-based semi-supervised method for object recognition in synthetic aperture radar (SAR) images[J]. Remote Sensing, 2018, 10(6): 846.1-846.21.
[22]	WEI S J, ZENG X F, QU Q Z, et al. HRSID: a high-resolution SAR images dataset for ship detection and instance segmentation[J]. IEEE Access, 2020, 8: 120234-120254.
[23]	HEUSEL M, RAMSAUER H, UNTERTHINER T, et al. GANs trained by a two time-scale update rule converge to a local Nash equilibrium[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. California: ACM, 2017: 6629-6640.

Relative Articles

[1]	GAO Tianci, JIANG Lepeng, CONG Jianli, WANG Yuan, LIU Xiaozhou, ZHU Jiasong, LUO Qin, WANG Ping. Rapid Detection Method for Rail Corrugation in Metro Lines Based on Data Fusion of Train-Borne Vibration and Noise[J]. Journal of Southwest Jiaotong University. doi: 10.3969/j.issn.0258-2724.20240121
[2]	YANG bin, HU Jinming, ZHANG Qilin, WANG Congjun. Location Information Perception of Onsite Construction Crew Based on Person Re-identification[J]. Journal of Southwest Jiaotong University, 2025, 60(3): 761-769. doi: 10.3969/j.issn.0258-2724.20230125
[3]	CUI Yaping, YING Zhaopeng, HE Peng, ZHENG Yufeng, WU Dapeng, WANG Ruyan, CHEN Luo. Ultra-Reliable Low-Latency Communication Multi-Unmanned Aerial Vehicle Network Assisted by Intelligent Reflecting Surface in Air[J]. Journal of Southwest Jiaotong University, 2024, 59(4): 907-916. doi: 10.3969/j.issn.0258-2724.20230288
[4]	CHEN Yong, WANG Zhen, ZHANG Jiaojiao. Lightweight Detection of Railway Object Intrusion Based on Spectral Pooling and Shuffled-Convolutional Block Attention Module Enhancement[J]. Journal of Southwest Jiaotong University, 2024, 59(6): 1294-1304. doi: 10.3969/j.issn.0258-2724.20220074
[5]	CHEN Shuailin, YANG Wen, LI Hengchao, TAPETE Deodato, BALZ Timo. Edge-Aware Semi-Supervised Built-up Area Extraction Using Multi-Temporal Synthetic Aperture Radar Images[J]. Journal of Southwest Jiaotong University, 2024, 59(5): 1225-1234. doi: 10.3969/j.issn.0258-2724.20220807
[6]	HUA Zexi, SHI Huibin, LUO Yan, ZHANG Ziyuan, LI Weilong, TANG Yongchuan. Detection and Recognition of Digital Instruments Based on Lightweight YOLO-v4 Model at Substations[J]. Journal of Southwest Jiaotong University, 2024, 59(1): 70-80. doi: 10.3969/j.issn.0258-2724.20210544
[7]	YUE Chuan, WANG Lide, YAN Haipeng. Attack-Sample Generation Method for Train Communication Network Under Few-Shot Condition[J]. Journal of Southwest Jiaotong University, 2023, 58(6): 1277-1285. doi: 10.3969/j.issn.0258-2724.20210557
[8]	WANG Tao, ZENG Wenhao, YU Qi. Obstacle Detection and Tracking for Driverless Cars Based on Lidar[J]. Journal of Southwest Jiaotong University, 2021, 56(6): 1346-1354. doi: 10.3969/j.issn.0258-2724.20200240
[9]	YUAN Fei, ZHAO Xuyan, WANG Yige, ZHAO Zhisheng. Smoke Recognition Algorithm Based on Lightweight Convolutional Neural Network[J]. Journal of Southwest Jiaotong University, 2020, 55(5): 1111-1116, 1132. doi: 10.3969/j.issn.0258-2724.20190777
[10]	LI Sihui, CAI Baigen, XU Aiguo, SHANGGUAN Wei, WEN Yinghong, WANG Jian. Autonomous-Positioning Information Aided Train Integrity Detection Risk Analysis Method[J]. Journal of Southwest Jiaotong University, 2017, 30(5): 886-892. doi: 10.3969/j.issn.0258-2724.2017.05.007
[11]	LIAO Hongjian, ZHU Qingnü, ZAN Yuewen, XIE Yongyong, SUN Junyu. Detection of Ballastless Track Diseases in High-Speed Railway Based on Ground Penetrating Radar[J]. Journal of Southwest Jiaotong University, 2016, 29(1): 8-13. doi: 10.3969/j.issn.0258-2724.2016.01.002
[12]	HUANG Dingfa, ZHOU Letao, LU Jiankang, MEI Xi, FENG Wei, ZHANG Xi, YAN Li. Key Techniques of GNSS Ground-Based Augmentation System and Location Based Cloud Service[J]. Journal of Southwest Jiaotong University, 2016, 29(2): 388-395. doi: 10.3969/j.issn.0258-2724.2016.02.018
[13]	JU Chunhua, LI Yaolin. Outlier Detection Model for Data Streams Based on Attribute Associations and Match Difference Degree[J]. Journal of Southwest Jiaotong University, 2013, 26(1): 107-115. doi: 10.3969/j.issn.0258-2724.2013.01.017
[14]	ZHU Xiping, 2, FANG Xuming. Connectivity Enhancement Based on Network Coding for Wireless Multi-hop Ad Hoc Networks[J]. Journal of Southwest Jiaotong University, 2010, 23(6): 972-976. doi: 10.3969/j.issn.0258-2724.2010.06.025
[15]	WEI Guangxing. Flight Conflict Detection and Regulation between Aircraft Based on Radar[J]. Journal of Southwest Jiaotong University, 2006, 19(4): 507-511.
[16]	WANGXue-mei, LING Jian-hui, LIFu, NIWen-bo. Dynam ic Compensation for Railway Line InformationM onitoring System ofTilting Train[J]. Journal of Southwest Jiaotong University, 2005, 18(5): 628-632.
[17]	ZHANG Shan-shan, LIU Wen-xi. Organizing of Vector Data in 3D Geographic Information Systems[J]. Journal of Southwest Jiaotong University, 2000, 13(5): 505-508.

Supplements(0)

Cited By

Cited by

Periodical cited type(2)

1.	王雪松，游俊，强勇，汪小平. 基于深度学习网络的单目标SAR图像生成研究. 火控雷达技术. 2025(01): 16-24 .
2.	肖雨晴，罗亮，于博向，杨志渊，郝连东，艾君鹏. 面向海域环境感知的视觉处理方法研究综述. 计算机工程与应用. 2024(23): 62-78 .

Other cited types(0)

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Figures(8) / Tables(4)

Get Citation

PDF

XML

Article views(335) PDF downloads(44)