曹林林,李海涛,韩颜顺,余凡,顾海燕

• 1:辽宁工程技术大学测绘学院
• 2:中国测绘科学研究院

摘要(Abstract)：

针对目前应用于高分辨率遥感影像分类的常用算法,其精度已无法满足大数据环境下的分类要求的问题,该文提出了卷积神经网络分类算法。卷积神经网络模型降低了因图像平移、比例缩放、倾斜或者共他形式的变形而引起的误差。在大数据环境下,采用卷积神经网络算法对高分辨率遥感影像进行分类,避免了特征提取和分类过程中数据重建的复杂度,提高了分类精度。通过实验比对分析,证明了卷积神经网络在高分辨率遥感影像分类中的可行性及精度优势,对遥感图像处理领域等相关工作提供了参考价值。

关键词(KeyWords)： 卷积神经网络;深度学习;大数据;遥感影像分类

Abstract:

Keywords:

基金项目(Foundation): 信息化测绘生产基地构建技术研究与应用示范(201412008)

作者(Author): 曹林林,李海涛,韩颜顺,余凡,顾海燕

DOI: 10.16251/j.cnki.1009-2307.2016.09.033

参考文献(References)：

• [1]王圆圆,李京.遥感影像土地利用/覆盖分类方法研究综述[J].遥感信息,2004(1):53-59.
• [2]刘敏,李海涛,顾海燕,等.WorldView-2高分辨率卫星影像面向对象分类[C]//第十八届中国遥感大会,2012:123-129.
• [3]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems.Red Hook,NY:Curran Associates,2012:1097-1105.
• [4]DAHL G E,YU D,DENG L,et al.Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition[J].Audio,Speech,and Language Processing,IEEE Transactions on,2012,20(1):30-42.
• [5]ERHAN D,COURVILLE A,BENGIC Y.Understanding representations learned in deep architectures,TR1355[R/OL].(2010-10-19)[2016-06-11].http://www.dumitru.ca/files/publications/invarianes_techreport.pdf.
• [6]HINTON G E,SALAKHUTDINOV R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
• [7]SOOMRO K,ZAMIR A R,SHAN M.Ucf101:a dataset of 101human actions classes from videos in the wild[J].CoRR,2012:abs/1212.0402.
• [8]DANL G E,SAINATH T N,HINTON G E.Improving deep neural networks for LVCSR using rectified linear units and dropout[C]//Acoustics,Speech and Signal Processing(ICASSP),2013IEEE International Conference on.Piscataway,NJ:IEEE,2013:8609-8613.
• [9]LE Q V,RAMZATO M,MONGA R,et al.Building high-level features using large scale unsupervised learning,1112.6209[R].New York,USA:Cornell University,2012.
• [10]HINTON G E,OSINDERO S,TEH Y W.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18(7):1527-1554.
• [11]GLOROT X,BORDES A,BENGTO Y.Deep sparse rectifier networks[C].JMLR Workshoop and Conference Proceedings:AISTATS 2011.Brookline,MA:Microtome Publishing,2011:315-323.
• [12]YU D,DENG L.Deep learning and its applications to signal and information processing[J].Signal Processing Magazine,IEEE,2011,28(1):145-154.
• [13]LU C,TANG X.Surpassing human-level face verification performance on LFW with GaussianFace[J].CoRR,2014:abs/1404.3840.
• [14]ACL 2014Ninth Workshop on Statistical Machine Translation[DB/OL].(2014-09-23).[2016-06-11].http://www.statmt.org/wmt14/translation-task.html.
• [15]顾佳玲,彭宏京.增长式卷积神经网络及其在人脸检测中的应用[J].系统仿真学报,2009:2441-2445.
• [16]KOREKADO K,MORIE T,NOMURA O,et al.A convolutional neural network VLSI for image recognition using merged/mixed analog-digital architecture[M].7th International Conference,KES 2003,Oxford,UK,September 2003Proceedings,Part II,2003:169-176.
• [17]STRIGL D.Performance and Scalability of GPU-based convolutional neural networks[C]//in Euromicro International Conference onParallel,Distributed and Network-Based Processing,2010.
• [18]GLOROT X,BORDES A,BENGIO Y.Deep sparse rectifier networks[C]//JMLR Workshop and Conference Proceedings Volume 15:AISTATS 2011.Brookline,MA:Microtome Publishing,2011:315-323.
• [19]JI S,XU W,YANG M,et al.3Dconvolutional neural networks for human action recognition[C].IEEE Transaction on Pattern Analysis and Machine Intelligence,2012.
• [20]SEIDE F,LI G,YU D.Conversational speech transcription using context-dependent deep neural networks[C]//International Speech Communication Association.Annual Conference.12th 2011.Red Hook,NY:Curran Associates,2011:437-440.
• [21]CHO K,VAN MERRIENBOER B,GULCEHRE C,et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[J].CoRR,2014.
• [22]LEE T,MUMFORD D.Hierarchical Bayesian Inference In The Visual Cortex[J].Journal of the Optical Society of America A,2003,20:1434-1448.
• [23]LEE T,MUMFORD D,ROMERO R,et al.The role of the primary visual cortex in higher level vision[J].Vision Research,1998,38:2429-2454,
• [24]JARRETT K,KAVUKCUOGLU K,RANZATO M,et al.What is the best multi-stage architecture for object recognition[C]//Computer Vision,2009IEEE 12th International Conference on.Piscataway,NJ:IEEE,2009:2146-2153.
• [25]HUBEL D H,WIESEL T N.Receptive fields,binocular interaction,and functional architecture in the cat's visual cortex[J].Journal of Physiology,1962,160:106-154.
• [26]NUMENTA,Inc.Available:http://www.numenta.com.
• [27]FUKUSHIMA K.Neocognition:A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in postion[J].Biological Cybernetics,1980,36:193-202.
• [28]HUBELD H,WIESEL T N.Receptive fields,binocular interaction,and functional architecture in the cat's visual cortex[J].Journal of Physiology,1962,160:106-154.