浏览全部资源
扫码关注微信
Received：29 March 2018，
Revised：2018-6-7，
Published：16 November 2018
移动端阅览
目的
2
海冰分类是海冰监测的主要任务之一。目前基于合成孔径雷达SAR影像的海冰分类方法分为两类：一类是基于海冰物理特性与SAR成像特征等进行分类，这需要一定的专业背景；另一类基于传统的图像特征分类，需要人为设计特征，受限于先验知识。近年来深度学习在图像分类和目标识别方面取得了巨大的成功，为了提高海冰分类精度及海冰分类速度，本文尝试将卷积神经网络（CNN）和深度置信网络（DBN）用于海冰的冰水分类，评估不同类型深度学习模型在SAR影像海冰分类方面的性能及其影响因素。
方法
2
首先根据加拿大海冰服务局（CIS）的冰蛋图构建海冰的冰水数据集；然后设计卷积神经网络和深度置信网络的网络架构；最后评估两种模型在不同训练样本尺寸、不同数据集大小和网络层数、不同冰水比例的测试影像以及不同中值滤波窗口的分类性能。
结果
2
两种模型的总体分类准确率达到93%以上，Kappa系数0.8以上，根据分类结果得到的海冰区域密集度与CIS的冰蛋图海冰密集度数据一致。海冰的训练样本尺寸对分类结果影响显著，而训练集大小以及网络层数的影响较小。在本文的实验条件下，CNN和DBN网络的最佳分类样本尺寸分别是16×16像素和32×32像素。
结论
2
利用CNN和DBN模型对SAR影像海冰冰水分类，并进行性能分析。发现深度学习模型用于SAR影像海冰分类具有潜力，与现有的海冰解译图的制作流程和信息量相比，基于深度学习模型的SAR影像海冰分类可以提供更加详细的海冰地理分布信息，并且减小时间和资源成本。
Objective
2
The classification of sea ice is an important task in sea ice monitoring. Synthetic aperture radar (SAR)
as an active microwave sensor
has all-weather
day-and-night
multi-view
and penetration imaging capabilities. SAR has been widely used for sea ice monitoring. Existing methods of automatic sea ice classification using SAR data are divided into two categories as follows:1) Classification based on the physical characteristics of sea ice and imaging characteristics of SAR imagery
such as the relationship between sea ice types and incidence angle
polarization mode
and backscatter coefficient of SAR image; SAR imagery requires professional background. 2) Traditional image classification methods with SAR imagery
such as support vector machine (SVM) and artificial neural network
must design features in advance and thus are limited by prior knowledge. In recent years
deep learning has achieved considerable success in image classification and object recognition. Image classification based on deep learning can automatically learn high-level features of sample data beyond low-level texture and color features
thus achieving a high accuracy of classification results without constraints of human prior knowledge. However
SAR images have different imaging mechanisms from optical imaging of ordinary camera
and sea ice shows lower identifiable characteristics on the SAR imagery than general ground objects with specific shape
texture
and other distinctive features. The effectiveness of deep learning models for sea ice classification remains unclear. We aim to use deep learning models
such as a convolutional neural network (CNN) and a deep belief network (DBN)
to classify sea ice and water in SAR imagery and evaluate the performance and influence factors of the two models to improve the accuracy and speed of sea ice classification.
Method
2
The entire process of sea ice-water classification experiment mainly includes four steps. First
the study area and the corresponding SAR images must be determined. Hudson Bay was selected
and 16 SAR images of the area were obtained from Sentinel-1 satellite. Second
an experimental data set must be constructed in accordance with the ice chart published by the Canadian Ice Service (CIS)
including image cutting
normalization
and labeling. A total of 2 000 training and 400 validation samples were prepared for each sample size
although the sample size varied from 16×16 pixels to 64×64 pixels. Eight regions were used for testing. Third
the structures of the CNN and DBN must be designed
and the influence of different network hyperparameters on classification performance must be discussed. Finally
the classification performance of models influenced by train patch size
data set size
layers of the models
sea ice proportion in the test image
and image filter size must be evaluated. The evaluation was based on the indices of precision ratio
recall ratio
F
1
score
and kappa coefficient.
Result
2
The CNN and DBN models reached more than 93% overall accuracy and 0.8 kappa coefficient given the pixel-level ground truth generated by SVM and manual correction. Regional concentration values computed by the classification results were close to the concentration data provided in the CIS ice chart with a mean squared error of 0.001 for CNN and 0.016 for DBN. The train patch size of sea ice significantly influenced the classification performance of the models
whereas the data set size and layers of the models only slightly influenced the classification performance of the models. Additional ice and water would be misclassified when the size of the training samples was large. Therefore
the sample size of the CNN and DBN should not be very large. Under our experimental conditions
the optimal train patch size of CNN and DBN was 16×16 pixels and 32×32 pixels
correspondingly. In addition
the sea ice-water ratio of the test samples affected the precision and recall ratios. The ice and water in terms of
F
1
score and the kappa coefficient stabilized when the sea ice-water ratio was at 0.5. The precision and recall of the DBN were relatively sensitive to the sea ice-water ratio of the test samples.
Conclusion
2
We evaluated the performance of the sea ice-water classification in SAR imagery with CNN and DBN. Notably
deep learning demonstrates considerable potential in the sea ice classification. The sea ice classification of SAR images based on deep learning without designing features in advance can be robustly applied to different SAR data products over several traditional classification methods
such as SVM. The classification method based on deep learning models can provide more convenient and more detailed sea ice interpretations than the complex production process of the CIS ice chart and the rough range of sea ice-type tagging information. Owing to the different resolutions of SAR images
the patch size of the optimal classification sample will be different. In this study
errors in the ground truth are inevitable considering the limitations of current sea ice observation methods; these limitations have been discussed. The main contributions of this study are as follows:1) In the sea ice-water classification using SAR images
two typical deep learning networks with different mechanisms have been used. The convolution operation of the CNN is suitable for exploring the local spatial correlation of images and has a robust application in the image recognition field. The restricted Boltzmann machine
as an important component of the DBN
is better at exploring probabilistic relationships among different elements and is more suitable for incremental learning than the CNN. The CNN showed better performance than the DBN in the classification of sea ice-water with SAR imagery. 2) A complete experimental procedure for sea ice classification of SAR images through deep learning methods
which can help guide related research
is summarized. 3) A new idea of using the deep learning method for sea ice classification is proposed. This method can shorten the existing process of creating a sea ice interpretation map and provide accurate geographic distribution information of a sea ice type. In our future work
we will compare the classification performance of different SAR data sources.
Manore M J, Flett D G, De Abreu R A, et al. Multi-polarization SAR data for operational ice monitoring[C]//Scanning the Present and Resolving the Future. 2001 International Geoscience and Remote Sensing Symposium. Sydney, NSW, Australia, Australia: IEEE, 2001: 1246-1248.[ DOI: 10.1109/IGARSS.2001.976807 http://dx.doi.org/10.1109/IGARSS.2001.976807 ]
Moen M A N, Doulgeris A P, Anfinsen S N, et al. Comparison of feature based segmentation of full polarimetric SAR satellite sea ice images with manually drawn ice charts[J]. The Cryosphere, 2013, 7(6):1693-1705.[DOI:10.5194/tc-7-1693-2013]
Ressel R, Singha S, Lehner S, et al. Investigation into different polarimetric features for sea ice classification using X-Band synthetic aperture radar[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(7):3131-3143.[DOI:10.1109/JSTARS.2016.2539501]
Zakhvatkina N, Korosov A, Muckenhuber S, et al. Operational algorithm for ice-water classification on dual-polarized RADARSAT-2 images[J]. The Cryosphere, 2017, 11(1):33-46.[DOI:10.5194/tc-11-33-2017]
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.[DOI:10.1109/TGRS.2003.817218]
Ressel R, Frost A, Lehner S. A neural network-based classification for sea ice types on X-Band SAR images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(7):3672-3680.[DOI:10.1109/JSTARS.2015.2436993]
Sun Z J, Xue L, Xu Y M, et al. Overview of deep learning[J]. Application Research of Computer, 2012, 29(8):2806-2810.
孙志军, 薛磊, 许阳明, 等.深度学习研究综述[J].计算机应用研究, 2012, 29(8):2806-2810. [DOI:10.3969/j.issn.1001-3695.2012.08.002]
Lv Q, Dou Y, Niu X, et al. Classification of land cover based on deep belief networks using polarimetric RADARSAT-2 data[C]//Proceedings of 2014 IEEE Geoscience and Remote Sensing Symposium. Quebec City, QC, Canada: IEEE, 2014: 4679-4682.[ DOI: 10.1109/IGARSS.2014.6947537 http://dx.doi.org/10.1109/IGARSS.2014.6947537 ]
Deng L, Fu S S, Zhang R X. Application of deep belief network in polarimetric SAR image classification[J]. Journal of Image and Graphics, 2016, 21(7):933-941.
邓磊, 付姗姗, 张儒侠.深度置信网络在极化SAR图像分类中的应用[J].中国图象图形学报, 2016, 21(7):933-941. [DOI:10.11834/jig.20160711]
Li J X, Wang C, Wang S G, et al. Classification of very high resolution SAR image based on convolutional neural network[C]//Proceedings of 2017 International Workshop on Remote Sensing with Intelligent Processing. Shanghai, China: IEEE, 2017: 1-4.[ DOI: 10.1109/RSIP.2017.7958811 http://dx.doi.org/10.1109/RSIP.2017.7958811 ]
Chen SZ, 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.[DOI:10.1109/TGRS.2016.2551720]
Zhang W, Zheng K, Tang P, et al. Land cover classification with features extracted by deep convolutional neural network[J]. Journal of Image and Graphics, 2017, 22(8):1144-1153.
张伟, 郑柯, 唐娉, 等.深度卷积神经网络特征提取用于地表覆盖分类初探[J].中国图象图形学报, 2017, 22(8):1144-1153. [DOI:10.11834/jig.170139]
Zhou M, Shi Z W, Ding H P. Aircraft classification in remote-sensing images using convolutional neural networks[J]. Journal of Image and Graphics, 2017, 22(5):702-708.
周敏, 史振威, 丁火平.遥感图像飞机目标分类的卷积神经网络方法[J].中国图象图形学报, 2017, 22(5):702-708. [DOI:10.11834/jig.160595]
Wang L, Scott K A, Xu L L, et al. Sea ice concentration estimation during melt from dual-pol SAR scenes using deep convolutional neural networks:a case study[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(8):4524-4533.[DOI:10.1109/TGRS.2016.2543660]
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.[DOI:10.3390/rs9050408]
Petrou Z I, Tian Y L. Prediction of sea ice motion with recurrent neural networks[C]//Proceedings of 2017 IEEE International Geoscience and Remote Sensing Symposium. Fort Worth, TX, USA: IEEE, 2017.[ DOI: 10.1109/IGARSS.2017.8128230 http://dx.doi.org/10.1109/IGARSS.2017.8128230 ]
LeCun Y, Boser B, Denker J S, et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989, 1(4):541-551.[DOI:10.1162/neco.1989.1.4.541]
Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7):1527-1554.[DOI:10.1162/neco.2006.18.7.1527]
Chi J, Kim H C. Prediction of arctic sea ice concentration using a fully data driven deep neural network[J]. Remote Sensing, 2017, 9(12):1305.[DOI:10.3390/rs9121305]
Carrieres T, Greenan B, Prinsenberg S, et al. Comparison of Canadian daily ice charts with surface observations off newfoundland, winter 1992[J]. Atmosphere-Ocean, 1996, 34(1):207-226.[DOI:10.1080/07055900.1996.9649563]
相关文章
相关作者
相关机构
京公网安备11010802024621
