End-to-End Full Complex-Valued Domain SAR Target Classification Neural Network

FANG Cheng; GUAN Fang-heng; LI Tian-chi; ZOU Zheng-feng; YANG Lei

doi:10.12263/DZXB.20230536

您当前的位置：

首页 >

文章列表页 >

End-to-End Full Complex-Valued Domain SAR Target Classification Neural Network

PAPERS | 更新时间：2025-12-24

- End-to-End Full Complex-Valued Domain SAR Target Classification Neural Network
- ACTA ELECTRONICA SINICA Vol. 52, Issue 7, Pages: 2449-2460(2024)
- 作者机构：
  
  中国民航大学电子信息与自动化学院，天津 300300
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62271487);Safety Capacity Building Fund Project of the Civil Aviation Administration of China(KLZ49420200019;KLZ49420200023)
- DOI：10.12263/DZXB.20230536
  CLC： TN957.52;
- Received：13 June 2023，
  
  Revised：2024-04-24，
  
  Published：25 July 2024
- 稿件说明：
移动端阅览
方澄, 管方恒, 李天驰, 等. 端到端全复数域SAR目标分类神经网络[J]. 电子学报, 2024, 52(07): 2449-2460.

FANG Cheng, GUAN Fang-heng, LI Tian-chi, et al. End-to-End Full Complex-Valued Domain SAR Target Classification Neural Network[J]. Acta Electronica Sinica, 2024, 52(07): 2449-2460.
方澄, 管方恒, 李天驰, 等. 端到端全复数域SAR目标分类神经网络[J]. 电子学报, 2024, 52(07): 2449-2460. DOI：10.12263/DZXB.20230536

FANG Cheng, GUAN Fang-heng, LI Tian-chi, et al. End-to-End Full Complex-Valued Domain SAR Target Classification Neural Network[J]. Acta Electronica Sinica, 2024, 52(07): 2449-2460. DOI：10.12263/DZXB.20230536

摘要

合成孔径雷达（Synthetic Aperture Radar，SAR）图像探测经常遇到误差敏感和计算量大的问题，给SAR图像目标识别带来困难，为此研究人员针对SAR数据提出很多新颖高效的深度学习方法，但面向SAR目标识别的深度学习网络大多使用与光学实值处理相同的方法，直接将实值深度神经网络应用于SAR图像.实值的神经网络都不同程度丢失了相位信息，不能充分利用SAR数据复数特性.相位信息是SAR图像独有的数据特征，在SAR干涉测量、信息检索、目标识别等应用中起到至关重要作用.本文为了使网络更适合SAR复数数据特征提取，打破传统神经网络架构，将整体网络端到端复数化，提出一种新型的端到端全复数域多层级神经网络（Complex-valued mUltI-Stage convolutIonal Neural nEtworks，CUISINE）架构，从SAR复数图像数据的输入到卷积计算，再到分类标签，实现全网络复数域下的计算.通过在MSTAR（Moving and Stationary Target Acquisition and Recognition）公开数据集上实验对比表明，本文的方法在SAR数据目标分类上有很好表现，在相位误差为0 rad的测试集上正确率达到99.42%，在相位误差为50 rad的测试集上正确率达到88.05%.

Abstract

Synthetic aperture radar (SAR) image detection often encounters problems such as error sensitivity and high computational complexity

which pose challenges to SAR target recognition. Researchers have proposed many novel and efficient deep learning methods for SAR data. However

most of these deep learning networks for SAR target recognition use the same methods as optical real-valued processing

directly applying real-valued deep neural networks to SAR images. Real-valued neural networks to some extent lose the phase information

which cannot fully utilize the complex characteristics of SAR data. As phase information is a unique data feature in SAR images

it plays a crucial role in applications such as SAR interferometry

information retrieval

and target recognition. In order to make the network more suitable for extracting complex data features from SAR

breaking the architecture of traditional neural networks

this paper proposes a novel end-to-end fully complex-valued multi-stage convolutional neural network (Complex-valued mUltI-Stage convolutIonal Neural nEtworks

CUISINE) architecture. It realizes the computation in the full complex-valued domain from the input of SAR complex image data to convolutional calculations

and finally to classification labels. Experimental comparisons on the publicly available MSTAR dataset show that our method performs well in SAR target classification. The accuracy reaches 99.42% on the test set with a phase error of 0 rad

and 88.05% on the test set with a phase error of 50 rad.

关键词

Keywords

references

KRIZHEVSKY A , SUTSKEVER I , HINTON G E . ImageNet classification with deep convolutional neural networks [J ] . Communications of the ACM , 2017 , 60 ( 6 ): 84 - 90 .

SZEGEDY C , LIU W , JIA Y Q , et al . Going deeper with convolutions [C ] // 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2015 : 1 - 9 .

MEI X , NIE W , LIU J Y , et al . Polsar image crop classification based on deep residual learning network [C ] // 2018 7th International Conference on Agro-geoinformatics . Piscataway : IEEE , 2018 : 1 - 6 .

GENG J , WANG H Y , FAN J C , et al . SAR image classification via deep recurrent encoding neural networks [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2018 , 56 ( 4 ): 2255 - 2269 .

ZENG Z Q , SUN J P , HAN Z , et al . SAR automatic target recognition method based on multi-stream complex-valued networks [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2022 , 60 : 5228618 .

WANG R N , WANG Z C , XIA K W , et al . Target recognition in single-channel SAR images based on the complex-valued convolutional neural network with data augmentation [J ] . IEEE Transactions on Aerospace and Electronic Systems , 2023 , 59 ( 2 ): 796 - 804 .

ZHANG Z M , WANG H P , XU F , et al . Complex-valued convolutional neural network and its application in polarimetric SAR image classification [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2017 , 55 ( 12 ): 7177 - 7188 .

XIAO D L , LIU C , WANG Q , et al . PolSAR image classification based on dilated convolution and pixel-refining parallel mapping network in the complex domain [EB/OL ] . ( 2020-11-20 )[ 2023-06-11 ] . http://arxiv.org/abs/1909.10783 http://arxiv.org/abs/1909.10783 .

SUN Z B , XU X H , PAN Z . SAR ATR using complex-valued CNN [C ] // 2020 Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC) . Piscataway : IEEE , 2020 : 125 - 128 .

TRABELSI C , BILANIUK O , ZHANG Y , et al . Deep complex networks [EB/OL ] . ( 2018-12-25 )[ 2023-06-11 ] . http://arxiv.org/abs/1705.09792 http://arxiv.org/abs/1705.09792 .

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 .

张智 , 易华挥 , 郑锦 . 聚焦小目标的航拍图像目标检测算法 [J ] . 电子学报 , 2023 , 51 ( 4 ): 944 - 955 .

ZHANG Z , YI H H , ZHENG J . Focusing on small objects detector in aerial images [J ] . Acta Electronica Sinica , 2023 , 51 ( 4 ): 944 - 955 . (in Chinese)

HE K M , GKIOXARI G , DOLLÁR P , et al . Mask R-CNN [C ] // 2017 IEEE International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2017 : 2980 - 2988 .

郭晓轩 , 冯其波 , 冀振燕 , 等 . 多线激光光条图像缺陷分割模型研究 [J ] . 电子学报 , 2023 , 51 ( 1 ): 172 - 179 .

GUO X X , FENG Q B , JI Z Y , et al . Research on segmentation model of multi-line laser strip image’s defects [J ] . Acta Electronica Sinica , 2023 , 51 ( 1 ): 172 - 179 . (in Chinese)

SUN Q G , LI X F , LI L L , et al . Semi-supervised complex-valued GAN for polarimetric SAR image classification [C ] // IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium . Piscataway : IEEE , 2019 : 3245 - 3248 .

AHMAD DEDMARI M , CONJETI S , ESTRADA S , et al . Complex fully convolutional neural networks for MR image reconstruction [C ] // International Workshop on Machine Learning for Medical Image Reconstruction . Cham : Springer , 2018 : 30 - 38 .

COLE E K , CHENG J Y , PAULY J M , et al . Analysis of deep complex-valued convolutional neural networks for MRI reconstruction [EB/OL ] . ( 2020-05-12 )[ 2023-06-11 ] . http://arxiv.org/abs/2004.01738 http://arxiv.org/abs/2004.01738 .

QUAN Y H , CHEN Y X , SHAO Y Z , et al . Image denoising using complex-valued deep CNN [J ] . Pattern Recognition , 2021 , 111 : 107639 .

MULLISSA A G , PERSELLO C , REICHE J . Despeckling polarimetric SAR data using a multistream complex-valued fully convolutional network [J ] . IEEE Geoscience and Remote Sensing Letters , 2022 , 19 : 4011805 .

LI Y Y , CHEN Y Q , LIU G Y , et al . A novel deep fully convolutional network for PolSAR image classification‍ [J ] . Remote Sensing , 2018 , 10 ( 12 ): 1984 .

HE K M , ZHANG X Y , REN S Q , et al . Deep residual learning for image recognition [C ] // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2016 : 770 - 778 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [EB/OL ] . ( 2023-08-02 )[ 2023-06-11 ] . http://arxiv.org/abs/1706.03762 http://arxiv.org/abs/1706.03762 .

CHOLLET F . Xception: Deep learning with depthwise separable convolutions [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2017 : 1800 - 1807 .

ROSS T D , WORRELL S W , VELTEN V J , et al . Standard SAR ATR evaluation experiments using the MSTAR public release data set [C ] // Algorithms for Synthetic Aperture Radar Imagery V . Orlando : SPIE , 1998 , 3370 : 566 - 573 .

KOLLIAS D , ZAFEIRIOU S . Exploiting multi-CNN features in CNN-RNN based dimensional emotion recognition on the OMG in-the-wild dataset [J ] . IEEE Transactions on Affective Computing , 2021 , 12 ( 3 ): 595 - 606 .

CHEN S Z , WANG H P , XU F , et al . Target classification using the deep convolutional networks for SAR images [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2016 , 54 ( 8 ): 4806 - 4817 .

ZENG Z Q , SUN J P , XU C A , et al . Unknown SAR target identification method based on feature extraction network and KLD-RPA joint discrimination [J ] . Remote Sensing , 2021 , 13 ( 15 ): 2901 .

SHI B , MA X , ZHANG W , et al . Complex-valued convolutional neural networks design and its application on UAV DOA estimation in urban environments [J ] . Journal of Communications and Information Networks , 2020 , 5 ( 2 ): 130 - 137 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Cross-Modal SAR Target Detection via Progressive Knowledge Transfer

Real-Time Gesture Recognition Algorithm Based on LoRa Signals

Continual Learning Methods and Applications in Computer Vision

End-to-End Speech Keyword Spotting Training Method Based on Sample's Class Uncertainty

Related Author

FANG Cheng

GUAN Fang-heng

LI Tian-chi

ZOU Zheng-feng

YANG Lei

ZHAO Guo-wei

JIANG Jia-qing

DONG Gang-gang

Related Institution

National Key Laboratory of Radar Signal Processing, Xidian University

College of Computer, Nanjing University of Posts and Telecommunications

Jiangsu Key Laboratory of Intelligent Sensing and Computing for Internet of Things

School of Computer Science and Technology, Beijing Jiaotong University

School of Control Science and Engineering, Shandong University

⁰