基于改进R-FCN的SAR图像识别

doi:10.12305/j.issn.1001-506X.2022.04.17

摘要/Abstract

摘要：

由于深度学习在目标识别方面取得了显著的成绩, 为提高合成孔径雷达(synthetic aperture radar, SAR)图像目标识别的精度与速度提供了新的思路。本文将区域全卷积网络(region-based fully convolutional networks, R-FCN)结构应用于SAR图像目标识别中, 取得了良好的效果。对于数据集较小和数据相似度较高的问题, 提出了基于迁移学习的R-FCN模型用于SAR图像目标识别。对更快的区域卷积神经网络(faster region convolutional neural networks, Faster R-CNN)和R-FCN进行模型训练及优化, 并与所提出的基于迁移学习的改进R-FCN模型实验结果进行对比。结果表明, 所提方法对SAR图像具有更好的识别效果和更快的识别速度。

关键词: 机器视觉, 目标识别, 合成孔径雷达, 全卷积网络, 迁移学习

Abstract:

With remarkable achievements in target recognition, deep learning provides new ideas for improving the accuracy and speed of target recognition in synthetic aperture radar (SAR) images. In this paper, region-based fully convolutional networks (R-FCN) are applied to SAR image target recognition, and good results have been achieved. In order to solve the problem of small data set and high data similarity, the R-FCN model based on transfer learning is proposed for target recognition in SAR images. The faster region convolutional neural networks (Faster R-CNN) and the R-FCN models are trained and optimized, and the experimental results are compared with the improved R-FCN model based on transfer learning proposed in this paper. The results show that the proposed method has better recognition effects and faster recognition speed for SAR images.

Key words: machine vision, target recognition, synthetic aperture radar(SAR), fully convolutional network (FCN), migration study

中图分类号:

TP751.1

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.

Xiaoling ZHOU, Zhaoxia ZHANG, Ya LU, Qian WANG, Kunkun WANG. SAR image recognition based on improved R-FCN[J]. Systems Engineering and Electronics, 2022, 44(4): 1202-1209.

图/表 8

图1

图2

图3

图4

图5

图6

图7

表1

参考文献 32

1	ZHOU Y S , WANG W , CHEN Z , et al. High-resolution and wide-swath SAR imaging mode using frequency diverse planar array[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 18 (2): 321- 325. doi: 10.1109/LGRS.2020.2974041
2	苏娟, 杨龙, 黄华, 等. 用于SAR图像小目标舰船检测的改进SSD算法[J]. 系统工程与电子技术, 2020, 42 (5): 1026- 1034.
	SU J , YANG L , HUANG H , et al. An improved SSD algorithm for small target ship detection in SAR images[J]. Systems Engineering and Electronics, 2020, 42 (5): 1026- 1034.
3	JANSEN R W , RAJ R G , LUKE R , et al. Practical multichannel SAR imaging in the maritime environment[J]. IEEE Trans. on Geoscience and Remote Sensing, 2018, 56 (7): 4025- 4036. doi: 10.1109/TGRS.2018.2820911
4	DING B Y , WEN G J , HUANG X H , et al. Target recognition in SAR images by exploiting the azimuth sensitivity[J]. Remote Sensing Letters, 2017, 8 (9): 821- 830. doi: 10.1080/2150704X.2017.1331052
5	ZHOU Z , WANG M , GAO Z J , et al. SAR image recognition with monogenic scale selection-based weighted multi-task joint sparse representation[J]. Remote Sensing, 2018, 10 (4): 504. doi: 10.3390/rs10040504
6	ZHOU L , WEI S Y , CUI Z M , et al. Lira-YOLO: a lightweight model for ship detection in radar images[J]. Journal of Systems Engineering and Electronics, 2020, 31 (5): 950- 956. doi: 10.23919/JSEE.2020.000063
7	GAO F , MA F , WANG J , et al. Semi-supervised generative adversarial nets with multiple generators for SAR image recognition[J]. Sensors, 2018, 18 (8): 2706- 2710. doi: 10.3390/s18082706
8	CHEN X Y , PENG X Y , DUAN R , et al. Deep kernel learning method for SAR image target recognition[J]. Review of Scienti-fic Instruments, 2017, 88 (10): 104706. doi: 10.1063/1.4993064
9	GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2014: 580-587.
10	CHEN C Y, LIU M Y, TUZEL O, et al. R-CNN for small object detection[C]//Proc. of the Asian Conference on Computer Vision, 2016: 214-230.
11	HU S C, WANG Y W, HUANG C L. Human object identification for human-robot interaction by using fast R-CNN[C]//Proc. of the IEEE International Conference on Robotic Computing, 2018: 201-204.
12	李健伟, 曲长文, 彭书娟, 等. 基于卷积神经网络的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2018, 40 (9): 1953- 1959.
	LI J W , QU C W , PENG S J , et al. Ship detection in SAR images based on convolutional neural network[J]. Systems Engineering and Electronics, 2018, 40 (9): 1953- 1959.
13	REN S Q , HE K M , GIRSHICK R , et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
14	CHEN Y H, LI W, SAKARIDIS C, et al. Domain adaptive faster R-CNN for object detection in the wild[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 3339-3348.
15	DAI W X , MAO Y Q , YUAN R A , et al. A novel detector based on convolution neural networks for multiscale SAR ship detection in complex background[J]. Sensors, 2020, 20 (9): 2547. doi: 10.3390/s20092547
16	DAI J F, LI Y, HE K M, et al. R-FCN: object detection via region-based fully convolutional networks[C]//Proc. of the 30th International Conference on Neural Information Processing Systems, 2016: 379-387.
17	SINGH B, LI H, SHARMA A, et al. R-FCN-3000 at 30fps: decoupling detection and classification[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 1081-1090.
18	田壮壮, 占荣辉, 胡杰民, 等. 基于卷积神经网络的SAR图像目标识别研究[J]. 雷达学报, 2016, 5 (3): 320- 325.
	TIAN Z Z , ZHAN R H , HU J M , et al. Research on target recognition of SAR image based on convolutional neural network[J]. Journal of Radar, 2016, 5 (3): 320- 325.
19	HUANG Z L , PAN Z X , LEI B . Transfer learning with deep convolutional neural network for SAR target classification with limited labeled data[J]. Remote Sensing, 2017, 9 (9): 907. doi: 10.3390/rs9090907
20	ALMEIDA F Q D , YOUNIS M , KRIEGER G , et al. Multichannel staggered sar azimuth processing[J]. IEEE Trans. on Geoscience and Remote Sensing, 2018, 56 (5): 2772- 2788. doi: 10.1109/TGRS.2017.2783444
21	WANG X L , CHEN C X . Ship detection for complex background SAR images based on a multiscale variance weighted image entropy method[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14 (2): 184- 187. doi: 10.1109/LGRS.2016.2633548
22	LEE S L, TSENG C C. Low-illuminated image enhancement using power law transformation and image fusion[C]//Proc. of the IEEE International Conference on Consumer Electronics, 2018: 120-126.
23	VERMA M , GHARPURE D C , WAGH V G . Pre-processing of data using logarithmic transformation to improve the spatial resolution of an EIT system for biomedical applications[J]. Journal of Physics: Conference Series, 2019, 1272 (1): 012021. doi: 10.1088/1742-6596/1272/1/012021
24	NUGROHO B , PUSPANINGRUM E Y , YUNIARTI A . Performance of face recognition with preprocessing techniques on robust regression method[J]. International Journal of Geomate, 2018, 15 (50): 101- 106.
25	DEMIR A, YILMAZ F, KOSE O. Early detection of skin cancer using deep learning architectures: resnet-101 and inception-v3[C]//Proc. of the Medical Technologies Congress, 2019.
26	HE K M, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proc. of the Computer Vision and Pattern Recognition, 2016: 770-778.
27	RAHMAN M A, WANG Y. Optimizing intersection-over-union in deep neural networks for image segmentation[C]//Proc. of the International Symposium on Visual Computing, 2016: 234-244.
28	韩子硕, 王春平. 基于改进FCM与MRF的SAR图像分割[J]. 系统工程与电子技术, 2019, 41 (8): 1726- 1734.
	HAN Z S , WANG C P . SAR image segmentation based on improved FCM and MRF[J]. Systems Engineering and Electro-nics, 2019, 41 (8): 1726- 1734.
29	YAO S J , CHEN Y W , TIAN X , et al. GeminiNet: combine fully convolution network with structure of receptive fields for object detection[J]. IEEE Access, 2020, 8, 60305- 60313. doi: 10.1109/ACCESS.2020.2982939
30	HOU Y , ZHANG H , ZHOU S L , et al. Efficient ConvNet feature extraction with multiple RoI pooling for landmark-based visual localization of autonomous vehicles[J]. Mobile Information Systems, 2017, 2017 (1): 1- 14.
31	BAI T , PANG Y , WANG J C , et al. An optimized faster R-CNN method based on DRNet and RoI align for building detection in remote sensing images[J]. Remote Sensing, 2020, 12 (5): 762. doi: 10.3390/rs12050762
32	DUBEY A K , JAIN V . Automatic facial recognition using VGG16 based transfer learning model[J]. Journal of Information and Optimization Sciences, 2020, 41 (7): 1589- 1596. doi: 10.1080/02522667.2020.1809126

类型	Faster R-CNN			R-FCN			改进的R-FCN
类型	识别率	漏检率	误检率	识别率	漏检率	误检率	识别率	漏检率	误检率
2s1	86.6	7.0	7.7	97.8	0.7	1.4	98.7	0	1.3
D7	95.6	1.3	3.0	97.6	0.3	2.0	98.3	0	1.6
T62	82.3	4.7	12.7	97.6	0	2.3	99.3	0	0.7
ZIL131	90.3	3.7	5.7	95.6	1.0	3.3	99.7	0	0.3
ZSU	92.3	2.3	5.3	97.8	0.7	1.4	99.7	0	0.3
平均数	89.2	3.8	6.9	97.4	0.5	2.1	99.1	0	0.9

[1]	苗添, 曾虹程, 王贺, 陈杰. 基于迭代阈值分割的星载SAR洪水区域快速提取[J]. 系统工程与电子技术, 2022, 44(9): 2760-2768.
[2]	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.
[3]	王彩云, 吴钇达, 王佳宁, 马璐, 赵焕玥. 基于改进的CNN和数据增强的SAR目标识别[J]. 系统工程与电子技术, 2022, 44(8): 2483-2487.
[4]	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.
[5]	傅东宁, 廖桂生, 黄岩, 张邦杰, 王幸. 基于图拉普拉斯嵌入的合成孔径雷达时变窄带干扰抑制算法[J]. 系统工程与电子技术, 2022, 44(6): 1846-1853.
[6]	盖明慧, 张苏, 孙卫天, 倪育德, 杨磊. 复数兼容全变分SAR目标结构特征增强[J]. 系统工程与电子技术, 2022, 44(6): 1862-1872.
[7]	徐安林, 张毓, 周峰. 基于Beta过程的高分辨ISAR成像[J]. 系统工程与电子技术, 2022, 44(6): 1873-1879.
[8]	纪朋徽, 代大海, 邢世其, 冯德军. 密集虚假运动目标生成方法[J]. 系统工程与电子技术, 2022, 44(5): 1502-1511.
[9]	刘丰恺, 黄大荣, 郭新荣, 冯存前. 基于吕氏分布的机动目标参数化平动补偿方法[J]. 系统工程与电子技术, 2022, 44(4): 1166-1173.
[10]	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.
[11]	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.
[12]	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.
[13]	杨磊, 张苏, 盖明慧, 方澄. 高分辨SAR目标成像方向性结构特征增强[J]. 系统工程与电子技术, 2022, 44(3): 808-818.
[14]	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.
[15]	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.