卷积神经网络在SAR遥感海冰分类中的应用可行性分析-海洋预报

卷积神经网络在SAR遥感海冰分类中的应用可行性分析

单位：1. 上海海洋大学海洋科学学院, 上海 201306;
2. 国家卫星海洋应用中心, 北京 100081;
3. 国家海洋局空间海洋遥感与应用研究重点实验室, 北京 100081

分类号：P731.15

出版年·卷·期（页码）：2019·36·第五期（77-85）

摘要：

分别介绍了卫星遥感海冰监测、分类的传统方法，以及卷积神经网络在遥感影像分类识别中的应用成果。尝试将在图像识别、语言检测等方面取得成功的卷积神经网络算法应用在海冰图像分类中，利用其能够应对非线性、网络结构简单、可并行运算等能力去解决海冰数据分类问题。

This paper analyzes the traditional methods of sea ice monitoring and classification based on satellite remote sensing, and the application results of convolutional neural network in remote sensing image classification and recognition. Moreover, the convolutional neural networks algorithm, which has been successfully used in image recognition and language detection, is applied to the classification of sea ice images, and to solve the issues of sea ice data classification based on its simple network structure, capability in coping with nonlinearity and parallel computing.

参考文献：

[1] 张晰. 极化SAR渤海海冰厚度探测研究[D]. 青岛:中国海洋大学, 2011.
[2] 吴良斌. SAR图像处理与目标识别[M]. 北京:航空工业出版社, 2013.
[3] Maitre H. 合成孔径雷达图像处理[M]. 孙洪, 译. 北京:电子工业出版社, 2013.
[4] 胡雪丽. 基于支持向量机的SAR图像增强与分类[D]. 西安:西安科技大学, 2008.
[5] 周飞燕, 金林鹏, 董军. 卷积神经网络研究综述[J]. 计算机学报, 2017, 40(6):1229-1251.
[6] 刘惠颖, 郭华东, 张露. 基于HJ-1C SAR数据的辽东湾海冰分类[J]. 国土资源遥感, 2014, 26(3):125-129.
[7] Karvonen J. Baltic sea ice concentration estimation based on Cband dual-polarized SAR data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(9):5558-5566.
[8] Clausi D A, Yue B. Comparing cooccurrence probabilities and Markov random fields for texture analysis of SAR sea ice imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(1):215-228.
[9] Yu Q Y, Clausi D A. SAR sea-ice image analysis based on iterative region growing using semantics[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(12):3919-3931.
[10] Ochilov S, Clausi D A. Operational SAR sea-ice image classi-fication[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(11):4397-4408.
[11] Wang L, Wong A, Scott K A, et al. Sea ice concentration estimation from satellite SAR imagery using convolutional neural network and stochastic fully connected conditional random field[Z]. 2015.
[12] 刘建强, 吴奎桥, 黄润恒. Radarsat卫星渤海海冰监测研究[J]. 海洋预报, 1999, 16(3):62-70.
[13] 朱婷婷. 南北极典型场景SAR海冰解译研究[D]. 武汉:武汉大学, 2017.
[14] 金亚秋, 陈轶, 张巍, 等. 雷达卫星SAR与防卫气象卫星SSM/I对渤海海冰的观测研究[J]. 地球物理学报, 2001, 44(2):163-170.
[15] 纪永刚, 张杰, 孟俊敏. 辽东湾海冰类型SAR响应分析[J]. 遥感技术与应用, 2007, 22(2):195-199.
[16] 纪永刚, 张杰, 孟俊敏, 等. 基于PCNN的海冰SAR图像分类系统[J]. 高技术通讯, 2008, 18(2):190-195.
[17] 张晰, 张杰, 纪永刚. 基于纹理特征分析的辽东湾SAR影像海冰检测[J]. 海洋科学进展, 2008, 26(3):386-393.
[18] 于波. 辽东湾海冰多极化SAR影像解译分析与分类算法研究[D]. 青岛:中国海洋大学, 2009.
[19] 张盼. 基于ScanSAR海冰图像的冰水解译[D]. 合肥:合肥工业大学, 2016.
[20] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada:Curran Associates Inc., 2012:1097-1105.
[21] 焦计晗, 张帆, 张良. 基于改进AlexNet模型的油菜种植面积遥感估测[J]. 计算机测量与控制, 2018, 26(2):186-189.
[22] 吕鸿蒙, 赵地, 迟学斌. 基于增强AlexNet的深度学习的阿尔茨海默病的早期诊断[J]. 计算机科学, 2017, 44(S1):50-60.
[23] Yarotsky D. Error bounds for approximations with deep ReLU networks[J]. Neural Networks, 2017, 94:103-114.
[24] 袁文翠, 孔雪. 基于TensorFlow深度学习框架的卷积神经网络研究[J]. 微型电脑应用, 2018, 34(2):29-32.
[25] Jaderberg M, Simonyan K, Zisserman A, et al. Spatial transformer networks[J]. arXiv:1506.02025, 2015.
[26] Zeiler M D, Fergus R. Visualizing and understanding convolutional networks[C]//Proceedings of the 13th European Conference on Computer Vision. Zurich, Switzerland:Springer, 2014:818-833.
[27] Donahue J, Jia Y Q, Vinyals O, et al. DeCAF:a deep convolutional activation feature for generic visual recognition[C]//Proceedings of the 31st International Conference on International Conference on Machine Learning. Beijing, China:JMLR. org, 2014:I-647-I-655.
[28] Oquab M, Bottou L, Laptev I, et al. Learning and transferring midlevel image representations using convolutional neural networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Columbus,OH,USA:IEEE, 2014:1717-1724.
[29] Chatfield K, Simonyan K, Vedaldi A, et al. Return of the devil in the details:delving deep into convolutional nets[J]. arXiv:1405. 3531, 2014.
[30] Penatti O A B, Nogueira K, dos Santos J A. Do deep features generalize from everyday objects to remote sensing and aerial scenes domains?[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Boston, MA, USA:IEEE, 2015:44-51.
[31] Hu F, Xia G S, Hu J W, et al. Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery[J]. Remote Sensing, 2015, 7(11):14680-14707.
[32] Ng J Y H, Yang F, Davis L S. Exploiting local features from deep networks for image retrieval[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Boston, MA, USA:IEEE, 2015:53-61.
[33] Babenko A, Slesarev A, Chigorin A, et al. Neural codes for image retrieval[C]//Proceedings of the 13th European Conference on Computer Vision. Zurich, Switzerland:Springer, 2014:584-599.
[34] Dong Z, Pei M T, He Y, et al. Vehicle type classification using unsupervised convolutional neural network[C]//Proceedings of the 22nd International Conference on Pattern Recognition. Stockholm, Sweden:IEEE, 2014:172-177.
[35] Dong Z, Wu Y W, Pei M T, et al. Vehicle type classification using a semisupervised convolutional neural network[J]. IEEE Trans-actions on Intelligent Transportation Systems, 2015, 16(4):2247-2256.
[36] 黄冬梅, 李明慧, 宋巍, 等. 卷积神经网络和深度置信网络在SAR影像冰水分类的性能评估[J]. 中国图象图形学报, 2018, 23(11):1720-1732.
[37] 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.
[38] Wang L, Scott K A, Clausi D A. Sea ice concentration estimation during freeze-up from SAR imagery using a convolutional neural network[J]. Remote Sensing, 2017, 9(5):408.
[39] 李金鑫. 基于卷积神经网络的SAR图像分类[M]. 长春:吉林大学, 2018.

服务与反馈：

【文章下载】【发表评论】【查看评论】【加入收藏】