基于多层反卷积网络的SAR图像分类

王云艳; 何楚; 赵守能; 陈东; 廖明生

doi:10.13203/j.whugis20140366

基于多层反卷积网络的SAR图像分类

王云艳^1,2,
何楚^1,3,,
赵守能³,
陈东⁴,
廖明生¹

1.
武汉大学测绘遥感信息工程国家重点实验室, 湖北武汉, 430079;
2.
湖北工业大学电气与电子工程学院, 湖北武汉, 430072;
3.
武汉大学电子信息学院, 湖北武汉, 430072;
4.
国防科技大学ATR重点实验室, 湖南长沙, 410073

基金项目: 国家重点基础研究发展计划(973计划)资助项目(2013CB733404);国家自然科学基金资助项目(41371342,61331016);湖北省自然科学基金资助项目。

详细信息

作者简介:
王云艳,博士,主要从事SAR图像解译研究。E-mail:helen9224@126.com

通讯作者:
何楚,博士,副教授。E-mail:chuhe@whu.edu.cn

中图分类号: P237.3
计量
- 文章访问数: 2103
- HTML全文浏览量: 70
- PDF下载量: 929
出版历程
- 收稿日期: 2014-05-06
- 发布日期: 2015-10-04

Classification of SAR Images Based on Deep Deconvolutional Network

1.
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
2.
School of Electrical and Electronic Engineering, Hubei University of Technology, Wuhan 430068, China;
3.
Electronic and Information School, Wuhan University, Wuhan 430072, China;
4.
ATR Key Laboratory, National University of Defense Technology, Changsha 410073, China

Funds: The National Key Basic Research and Development Program(973 Program) of China, No.2013CB733404;the National Natural Science Foundation of China, Nos.41371342, 61331016; the Natural Science Foundation of Hubei Province.

摘要

摘要: 针对传统特征提取方法不能提取目标高层结构特征的问题,提出了一种基于软概率的池化方法,结合多层反卷积网络,学习目标的高层结构特征,并将其用于合成孔径雷达(SAR)图像分类。首先对SAR图像进行子块划分,然后对每个子块进行基于多层反卷积网络的特征编码,学习出不同层次上的图像特征,最后将该特征用于支持向量机(SVM)分类器,实现SAR图像的分类。在国内首批SAR数据上的实验表明,该算法获得了较高的分类准确率。
- 合成孔径雷达 /
- 多层学习 /
- 反卷积网络 /
- 图像分类 /
- 软概率池化
Abstract: Aim at the problem that the traditional feature extraction methods cannot get the high level structure features, this paper put forward a new soft probability pooling method, which is used in multilayer Deconvolutional Network, then high level structure features can be learned and be used for classification of SAR image. Firstly, the SAR image was divided into patches; then, the feature coding of each patch was obtained by means of multilayer Deconvolutional Networks, which can learn features suitable for image classification in different scale ; finally, the SAR image was classified through the features used in SVM classifier. Experimental results on the first batch domestic PolSAR images show that the classification accuracy rate of the proposed algorithm is superior.
- synthetic aperture radar /
- multilayer learning /
- deconvolutional network /
- image classification /
- soft probability pooling

HTML全文

参考文献(12)

[1]	Maitre H. Synthetic Aperture Radar Image Processing[M]. Sun Hong. Beijing: Publishing House of Electronics Industry, 2005 (Maitre H. 合成孔径雷达图像处理[M]. 孙洪.北京: 电子工业出版社, 2005)
[2]	Wu Xiaohong, Xie Ming, Gan Ke,et al. Feature Extraction and Target Recognition of SAR Images[J]. Journal of Sichuan University(Natural Science Edition), 2007, 44(6): 1 275-1 280(吴晓红,谢明, 干可,等. SAR图像的特征提取与目标识别[J].四川大学学报(自然科学版), 2007, 44(6):1 275-1 280)
[3]	Wan Peng, Wang Jianguo, Huang Shunji. A Synthesis Method for SAR Image Target Detection[J]. Acta Electronica Sinica, 2001, 29(3):323-325(万朋, 王建国, 黄顺吉. SAR图像目标综合检测方法[J].电子学报, 2001, 29(3): 323-325)
[4]	Yin Hui. Research on Urban Scene Classification Method Using High Resolution Synthetic Aperture Radar Image Based on Local Feature Representation(殷慧. 基于局部特征表达的高分辨率SAR图像城区场景分类方法研究[D]. 武汉: 武汉大学,2010)
[5]	He Chu, Liu Ming, Xu Lianyu,et al. A Hierarchical Classification Method Based on Feature Selection and Adaptive Decision Tree for SAR Image[J].Geomatics and Information Science of Wuhan University, 2012, 37(1): 46-49 (何楚, 刘明, 许连玉,等. 利用特征选择自适应决策树的层次SAR图像分类[J]. 武汉大学学报·信息科学版, 2012,37(1):46-49)
[6]	Huan Ruohong, Zhang Ping, Pan Yun. SAR Target Recognition Using PCA, ICA and Gabor Wavelet Decision Fusion[J]. Journal of Remote Sensing, 2012, 16(2): 262-274(宦若虹, 张平, 潘赟. ICA、PCA和Gabor小波决策融合的SAR目标识别[J]. 遥感学报, 2012, 16(2): 262-274)
[7]	He Chu, Liu Ming,Feng Qian, et al. PolInSAR Image Classification Based on Compressed Sensing and Multi-scale Pyramid[J]. Acta Automatic Sinica, 2011, 37(7): 820-827(何楚, 刘明, 冯倩,等. 基于多尺度压缩感知金字塔的极化干涉SAR图像分类[J]. 自动化学报, 2011, 37(7): 820-827)
[8]	Hinton G E, Salakhutdinov R. Reducing the Dimensionality of Data with Neural Networks[J]. Science, 2006, 313(5 786):504-507
[9]	Zhang Xiaolei, Wu Ji. Deep Belief Networks Based Voice Activity Detection[J]. IEEE Transactions on Audio, Speech and Language Processing,2013,21(4):697-710
[10]	Vincent P, Larochelle H, Lajoie I, et al.Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion[J].Journal of Machine Learning Research, 2010,11:3 371-3 408
[11]	Yang J C, Yu K, Gong Y H,et al. Linear Spatial Pyramid Matching Using Sparse Coding for Image Classification[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009
[12]	Zeiler M D, Taylor G W, Fergus R. Adaptive Deconvolutional Networks for Mid and High Level Feature Learning[C].IEEE International Conference on Computer Vision (ICCV), Barcelona,Spain,2011

施引文献(12)

期刊类型引用(4)

1.	毕海霞，况祖正，李凡，高静怀，徐晨. 极化SAR图像分类深度学习算法综述. 科学通报. 2024(35): 5108-5128 . 百度学术
2.	谢雯，滑文强，焦李成，王若男. 采用深度学习的极化SAR地物分类方法综述. 西安电子科技大学学报. 2023(03): 151-170 . 百度学术
3.	杨鹤猛，孟秀军，陈艳芳，王彤，黄勇，孙振蓉. 极化SAR影像地物智能分类技术进展. 电子技术应用. 2022(08): 34-37+94 . 百度学术
4.	范剑超，王德毅，赵建华，宋德瑞，韩敏，姜大伟. 高分三号SAR影像在国家海域使用动态监测中的应用. 雷达学报. 2017(05): 456-472 . 百度学术