深度学习在大田种植中的应用及展望
|
摘要
深度学习是目前机器学习领域最前沿和最具前景的技术,本研究采用归纳总结法,介绍了深度学习的特征及与传统机器学习的区别,归纳和梳理了深度学习在大田种植中的应用现状。结果表明:1)深度学习在大田种植中的应用初现端倪,主要集中在作物的识别与分类、农业遥感影像应用、土壤环境监测、农业场景识别等;2)采用的主要模型有卷积神经网络(CNN)、自编码(AE)、深度置信网络(DBN)、堆栈自编码(SAE)、全卷积神经网络(FCN)、深度神经网络(DCNN)等,其对各领域的分类与识别精度均有提高;3)目前存在的主要问题是标注数据缺乏,尤其在遥感图像分类领域,普遍采用了迁移学习、数据增强、微调等技术来解决标注数据缺乏的问题。随着大田种植领域数据的增长以及信息技术的快速发展,基于深度学习和多源异构数据的作物识别与分类、作物长势监测、病虫害预测预警、农作物产量预测、果树花朵及果体识别、水果质量及产量的优化控制等将会获得较快发展。
Deep learning(DL)is currently the most advanced and promising technique.In order to analyze the current status of DL application and put forward potential key research point in field planting,literature is collected and combed based on inductive and summary method.Firstly,the characteristics of DL and difference between DL and traditional machine learning(ML)are introduced.Secondly,articles are surveyed and summarized in order to see the current progress of deep learning in agriculture.The results show that:1)The application of DL in field planting is in the early stage and interests are focused on crop detection and classification,agricultural remote sensing image classification,soil moisture monitoring and simulation,anomalies detection in agricultural field;2)Main models employed are Convolutional Neural Networks(CNN),Autoencoders(AE),Deep Belief Networks(DBN),Stacked Autoencoders(SAE),Fully Convolutional Networks(FCN),Deep Convolutional Neural Networks(DCNN),which improve classification and recognition accuracy;3)The main obstacle for the application of DL in agriculture is the lack of quantities of labelled data,especially in remote sensing.With the development of information technology and large volume of collected data,DL,driven by multi-source and heterogeneous data,fast development in many fields,such as crop identification and classification,monitoring of growth condition,diseases and insect pests forecasting and warning,crop yield forecasting,detection and identification of flower and fruit,optimization and control of fruit quality and quantity will be achieved.
Deep learning(DL)is currently the most advanced and promising technique.In order to analyze the current status of DL application and put forward potential key research point in field planting,literature is collected and combed based on inductive and summary method.Firstly,the characteristics of DL and difference between DL and traditional machine learning(ML)are introduced.Secondly,articles are surveyed and summarized in order to see the current progress of deep learning in agriculture.The results show that:1)The application of DL in field planting is in the early stage and interests are focused on crop detection and classification,agricultural remote sensing image classification,soil moisture monitoring and simulation,anomalies detection in agricultural field;2)Main models employed are Convolutional Neural Networks(CNN),Autoencoders(AE),Deep Belief Networks(DBN),Stacked Autoencoders(SAE),Fully Convolutional Networks(FCN),Deep Convolutional Neural Networks(DCNN),which improve classification and recognition accuracy;3)The main obstacle for the application of DL in agriculture is the lack of quantities of labelled data,especially in remote sensing.With the development of information technology and large volume of collected data,DL,driven by multi-source and heterogeneous data,fast development in many fields,such as crop identification and classification,monitoring of growth condition,diseases and insect pests forecasting and warning,crop yield forecasting,detection and identification of flower and fruit,optimization and control of fruit quality and quantity will be achieved.
引文
[1] Food and Agriculture Organization.How to feed the world in2050[EB/OL].2009-10-13http://www.fao.org/fileadmin/templates/wsfs/docs/expert_paper/How_to_Feed_the_World_in_2050.pdf
[2] Kitzes J,Wackernage M,Loh J,Peller A,Goldfinger S,Cheng D,Tea K.Shrink and share:Humanity’s present and future ecological footprint[J].Philosophical Transactions of the Royal Society B Biological Sciences,2008,363:467-475
[3] Ncube B,Mupangwa W,French A.Precision agriculture and food security in Africa[C].In:Systems Analysis Approach forComplexGlobalChallenges. Cham:Springer International Publishing AG,2018,159-178
[4] Sayer J,Cassman K G.Agricultural innovation to protect the environment[J].Proceedings of the National Academy of Sciences of the United States of America,2013,110(21):8345-8348
[5] Kamilaris A,Kartakoullis A,Prenafeta-BoldúF X.A review on the practice of big data analysis in agriculture[J].Computers and Electronics in Agriculture,2017,143:23-37
[6]李道亮.智慧农业:中国的机遇和挑战[J].高科技与产业化,2015,11(5):42-45Li D L.Smart agriculture:Opportunities and challenge for China[J].High-Technology&Industrialization,2015,11(5):42-45(in Chinese)
[7]孙志远,鲁成祥,史忠植,马刚.深度学习研究与进展[J].计算机科学,2016,43(2):1-8Sun Z Y,Lu C X,Shi Z Z,Ma G.Deep learning research and development[J].Computer Science,2016,43(2):1-8(in Chinese)
[8] Najafabadi M M,Villanustre F,Khoshgoftaar T M,Seliya N,Wald R, Muharemagic E.Deep learning applications and challenges in big data analytics[J].Journal of Big Data,2015,2(1):1-21
[9] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[C].In:Proceedings of the 2012 Advances in Neural Information Processing Systems.New York:Curran Associates Inc.,2012:1097-1105
[10]曾德伟,吴玉香,王聪.AUV深度的神经网络辨识和学习控制仿真研究[J].计算机工程与应用,2017,53(6):258-263Zeng D W,Wu Y X,Wang C.Research on simulation of neural network identification and learning for AUV depth control[J].Computer Engineering and Applications,2017,53(6):258-263(in Chinese)
[11]何西麟.基于深度学习的手写体字符识别研究与实现[D].广州:中山大学,2015He X L.The recognition and implementation of handwritten character based on deep learning[D]. Guangzhou:Zhongshan University,2015(in Chinese)
[12] Yang W X,Jin L W,Xie Z C,Feng Z Y.Improved deep convolutional neural network for online handwritten Chinese character recognition using domain-specific knowledge[C].In:Proceedings of the 13th International Conference on Document Analysis and Recognition.Piscataway:Institute of Electrical and Electronics Engineers Publisher,2015:551-555
[13] Yang W X,Jin L W,Liu M F.Character-level Chinese writer identification using path signature feature,dropstroke and deep CNN[C].In:Proceedings of 2015 13th International Conference on Document Analysis and Recognition.Piscataway:Institute of Electrical and Electronics Engineers Publisher,2015:546-550
[14] Yang W X,Jin L W,Tao D C,Xie Z C,Feng Z Y.DropSample:A new training method to enhance deep convolutional neural networks for large-scale unconstrained handwritten Chinese character recognition[J]. Pattern Recognition,2016,58(4):190-203
[15]梁军,柴玉梅,原慧斌,昝红英,刘铭.基于深度学习的微博情感分析[J].中文信息学报,2014,28(5):155-161Liang J,Chai Y M,Yuan H B,Zan H Y,Liu M.Deep learning for Chinese Micro-blog sentiment analysis[J].Journal of Chinese Information Processing,2014,28(5):155-161(in Chinese)
[16]吴蕾,张文生,王珏.基于深度学习框架的隐藏主题变量图模型[J].计算机研究与发展,2015,52(1):191-199Wu L,Zhang W S,Wang Y.Hidden topic variable graphical model based on deep learning framework[J].Journal of Computer Research and Development,2015,52(1):191-199(in Chinese)
[17]梁淑芬,刘银华,李立琛.基于LBP和深度学习的非限制条件下人脸识别算法[J].通信学报,2014,35(6):154-160Liang S F,Liu Y H,Li L C.Face recognition under unconstrained based on LBP and deep learning[J].Journal on Communications,2014,35(6):154-160(in Chinese)
[18]池燕玲.基于深度学习的人脸识别方法的研究[D].福州:福建师范大学,2015Chi Y L.The research of face recognition method based on deep learning[D].Fuzhou:Fujian Normal University,2015(in Chinese)
[19]林妙真.基于深度学习的人脸识别研究[D].大连:大连理工大学,2013Lin M Z.Research on face recognition base on deep learnin[D].Dalian:Dalian University of Technology,2013(in Chinese)
[20]由清圳.基于深度学习的视频人脸识别方法[D].哈尔滨:哈尔滨工业大学,2013You Q Z.The video face recognition method based on the deep learning[D].Harbin:Harbin Institute of Technology,2013(in Chinese)
[21]张安胜.深度学习在蛋白质二级结构预测中的应用研究[D].合肥:安徽大学,2015Zhang A S.The research on the application of deep learning in the prediction of the secondary structure of protein[D].Hefei:Anhui University,2015(in Chinese)
[22] Fan X N,Zhang S W.lncRNA-MFDL:Identification of human long non-coding RNAs by fusing multiple features and using deep learning[J].Molecular Biosystems,2015,11(3):892-897
[23] Liang M,Li Z,Chen T.Integrative data analysis of multiplatform cancer data with a multimodal deep learningapproach[J].IEEE/ACM Transactions on Computational Biology and Bioinformatics,2015,12(4):928-937
[24] Ibrahim R,Yousri N A,Ismail M A.Multi-level gene/Mi RNA feature selection using deep belief nets and active learning[C].In:Proceedings of Annual International Conference of the IEEE Engineering in Medicine and Biology,Piscataway:Institute of Electrical and Electronics Engineers Publisher,2014:3957-3960
[25] Ma J,Sheridan R P,Liaw A.Deep neural nets as a method for quantitative structure activity relationships[J].Journal of Chemical Information and Modeling,2015,55(2):263-274
[26]高君宇,杨小汕,张天柱,徐常胜.基于深度学习的鲁棒性视觉跟踪方法[J].计算机学报,2016,39(7):1419-1434Gao J Y,Yang X S,Zhang T Z,Xu C S.Robust visual tracking method via deep learning[J].Chinese Journal of Computers,2016,39(7):1419-1434(in Chinese)
[27]朱煜,赵江坤,王逸宁.基于深度学习的人体行为识别算法综述[J].自动化学报,2016,42(6):848-857Zhu Y,Zhao J K,Wang Y N.A review of human action recognition based on deep learning[J].Acta Automatica Sinica,2016,42(6):848-857(in Chinese)
[28] Zhou X Z,Xie L,Zhang P,Zhang Y N.An ensemble of deep neural networks for object tracking[C].In:Proceedings of the 2014 IEEE International Conference on Image Processing. Piscataway:InstituteofElectricaland Electronics Engineers Publisher,2014:843-847
[29] Kuen J,Lim K M,Lee C P.Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principle[J].Pattern Recognition,2015,48(10):2964-2982
[30] Ding J W,Huang Y Z,Liu W,Huang K Q.Severely blurred object tracking by learning deep imagerepresentations[J].IEEE Transactions on Circuits and Systems for Video Technology,2016,26(2):319-331
[31]丰晓霞.基于深度学习的图像识别算法研究[D].太原:太原理工大学,2015Feng X X.Research on image recognition based on deep learning algorithm[D].Taiyuan:Taiyuan University of Technology,2015(in Chinese)
[32]阮怀玉.基于稀疏表示和深度学习的SAR图像目标识别研究[D].合肥:中国科学技术大学,2016Ruan H Y.SAR image target recognition based on sparse representation and deep learning[D].Hefei:University of Science and Technology of China,2016(in Chinese)
[33]吕金涛.基于深度学习的相似图像搜索算法研究[D].北京:华北电力大学,2015Lv J T. Research on similar image retrieval based on deeplearning algorithm[D].Beijing:North China Electric Power University,2016(in Chinese)
[34]刘大伟,韩玲,韩晓勇.基于深度学习的高分辨率遥感影像分类研究[J].光学学报,2016,36(4):298-306Liu D W,Han L,Han X Y.High spatial resolution remote sensing image classification based on deep learning[J].Acta Optica Sinica,2016,36(4):298-306(in Chinese)
[35] Ma X R, Geng J,Wang H Y. Hyperspectral image classification via contextual deep learning[J].Journal on Image and Video Processing,2015,20(1):1-12
[36] Ma X,Wang H,Wang J.Semisupervised classification for hyperspectral image based on multi-decision labeling and deep feature learning[J].ISPRS Journal of Photogrammetry&Remote Sensing,2016,120:99-107
[37] Audebert N,Saux B L,Lefèvre S.Beyond RGB:Very high resolution urban remote sensing with multimodal deep networks[J].ISPRS Journal of Photogrammetry and Remote Sensing,2018,140:20-32
[38] Li Y S, Xie W Y, Li H Q. Hyperspectral image reconstruction by deep convolutional neural network for classification[J].Pattern Recognition,2017,63:371-383
[39] Ikasari I H,Ayumi V,Fanany M I.Multiple regularizations deep learning for paddy growth stages classification from LANDSAT-8[C]. In:Proceeding of International Conference on Advanced Computer Science and Information Systems.Piscataway:IEEE Publisher,2017:1-11
[40] Scott G J,EnglandM R,Starms W A.Training deep convolutional neural networks for Land-Cover classification of high-resolution imagery[J].IEEE Geoscience&Remote Sensing Letters,2017,14(4):549-553
[41] Collobert R, Weston J, Karlen M. Natural language processing(almost)from scratch[J].Journal of Machine Learning Research,2011,12(1):2493-2537
[42] Xiong W,Droppo J,Huang X,Seide F.,Seltzer M,Stolcke A, Yu D, Zweig G. Achieving human parity in conversational speech recognition[OL].arXiv:1610.05256v2[cs.CL],2017-2-17.https://arxiv.org/pdf/1610.05256v2
[43] Hinton G,Deng L,Yu D.Deep Neural networks for acoustic modeling in speech recognition:The shared views of four research groups[J].IEEE Signal Processing Magazine,2012,29(6):82-97
[44] Amodei D,Anubhai R,Battenberg E.Deep speech 2:endto-end speech recognition in English and Mandarin[OL].arXiv:1512.02595v1[cs.CL],2015-12-08.https://arxiv.org/pdf/1512.02595v1.pdf
[45] Sak H,Senior A,Rao K.Fast and accurate recurrent neural network acoustic models for speech recognition[C].In:the INTERSPEECH 2015 proceedings.Trier:DBLP Computer Science Bibliography,2015:1468-1472
[46] Graves A,Mohamed A R,Hinton G.Speech recognition with deep recurrent neural networks[C].In:Proceeding of IEEE International Conference on Acoustics,Speech and Signal Processing.Piscataway:Institute of Electrical and Electronics Engineers Publisher,2013:6645-6649
[47] Sutskever I,Vinyals O,Le Q V.Sequence to Sequence Learning with neural networks[OL].arXiv:1409.3215v3[cs.CL],2014-12-14.https://arxiv.org/pdf/1409.3215.pdf.
[48] Lecun Y,Bengio Y,Hinton G.Deep learning[J].Nature,2015,521(7553):436-444
[49] Kamilaris A, Prenafeta-BoldúF X. Deep learning in agriculture:A survey[J].Computers and Electronics in Agriculture,2018,147:70-90
[50] Goodfellow I,Bengio Y,Courville A.Deep Leaning[OL].2017-03-15.https://github.com/exacity/deeplearningbookenglish
[51]刘念.基于深度信念网络的植物叶片识别研究[D].北京:北京林业大学,2016Liu N.The study of plant leaf recognition based on the deep belief networks[D].Beijing:Beijing Forest University,2016(in Chinese)
[52]余滨,李绍滋,徐素霞,纪荣嵘.深度学习:开启大数据时代的钥匙[J].工程研究:跨学科视野中的工程,2014,6(3):233-243Yu B,Li S Z,Xu S X,Ji R R.Deep learning:A key of stepping into the era of big data[J].Journal of Engineering Studies,2014,6(3):233-24(in Chinese)
[53] Bengio Y. Learning deep architectures for AI[J].Foundations and Trends in Machine Learning,2009,2(1):1-12
[54] Braverman M.Poly-logarithmic independence fools boundeddepth boolean circuits[J].Communications of the ACM,2011,54(4):108-115
[55] Bengio Y,Delalleau O.On the expressive power of deep architectures[C].In:Proceeding of International Conference on Algorithmic Learning Theory,Berlin:Heidelberg,2011:18-36
[56] Socher R,Huval B,Bhat B.Convolutional-recursive deep Learning for 3Dobject classification[C].In:Proceeding of Advances in Neural Information Processing System 2012.Lake Tahoe:Neural Information Processing System,2012:665-673
[57]管皓,薛向阳,安志勇.深度学习在视频目标跟踪中的应用进展与展望[J].自动化学报,2016,42(6):834-847Guan H,Xue X Y,An Z Y.Advances on applicaton of deep learning for video object tracking[J].Acta Automatica Sinica,2016,42(6):834-847(in Chinese)
[58]段艳杰,吕宜生,张杰,赵学亮,王飞跃.深度学习在控制领域的研究现状与展望[J].自动化学报,2016,42(5):643-654Duang Y J,Lv Y S,Zhang J,Zhao X L,Wang F Y.Deep learning for control:the state of the art and prospects[J].Acta Automatica Sinica,2016,42(5):643-654(in Chinese)
[59] Dyrmann M, Karstoft H, Midtiby H S.Plant species classification using deep convolutional neural network[J].Biosystems Engineering,2016,151:72-80
[60] Grinblat G L,Uzal L C,Larese M G,Granitto P M.Granitto,Deep learning for plant identification using vein morphological patterns[J].Computers and Electronics in Agriculture,2016,127:418-424
[61] Ahlin K,Joffe B,Hu A P.Autonomous leaf picking using deep learning and visual-servoing[J].IFAC-Papers OnLine,2016,49(16):177-183
[62]王琨,刘大茂.基于深度学习的茶叶状态智能识别方法[J].重庆理工大学学报:自然科学版,2015,29(12):120-126Wang K,Liu D M.Intelligent identification for tea state based on deep learning[J].Journal of Chongqing University of Technology:Natural Science,2015,29(12):120-126(in Chinese)
[63]孙宏杰.基于叶片图像分析的葡萄品种识别方法研究[D],杨凌:西北农林科技大学,2016Sun H J.Indentification of grape varieties based on leaves image analysis[D].Yangling:Northwest Agricultural and Forest University,2016(in Chinese)
[64]张帅,淮永建.基于分层卷积深度学习系统的植物叶片识别研究[J].北京林业大学学报,2016,38(9):108-115Zhang S,Huai Y J.Leaf image recognition based on layered convolutions neural network deep learning[J].Journal of Beijing Forestry University,2016,38(9):108-115(in Chinese)
[65] Mehdipour Ghazi M, Yanikoglu B, Aptoula E. Plant identification using deep neural networks via optimization of transfer learning parameters[J],Neurocomputing,2017,235:228-235
[66] Sakai Y,Oda T,Ikeda M,Barolli L.A vegetable category recognition system using deep neural network[C].In:Proceeding of 2016 10th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing(IMIS),Piscataway:Institute of Electrical and Electronics Engineers Publisher,2016:189-192
[67] Douarre C,Schielein R,Frindel C,Gerth S,Rousseau D.Transfer learning from synthetic data applied to soil-root segmentation in X-ray tomography images[J].Journal of Imaging,2018,4(5):1-14
[68]马珍玉.基于深度学习和SVM的植物叶片识别系统的研究与测试[D].呼和浩特:内蒙古农业大学,2016Ma Z Y.Research and test on plant leaves recognition system based on deep learning and support vector machine[D].Hohehot:Inner Mongolia Agricultural University,2016(in Chinese)
[69]邢晨.基于深度学习的高光谱遥感图像分类[D].北京:中国地质大学,2016Xing C. Hyperspectral image classification using deep learning method[D]. Beijing:China University of Geosciences,2016(in Chinese)
[70] Chen Y S,Lin Z H,Zhao X,Wang G,Gu Y F.Deep learning-based classification of hyperspectral data[J].IEEE Journal of Selected Topics in Applied Earth Observations And Remote Sensing,2014,7(6):2094-2107
[71] Kussul N,Lavreniuk M,Skakun S,Shelestov A.Deep learning classification of land cover and crop types using remote sensing data[J].IEEE Geoscience and Remote Sensing Letters,2017,14(5):778-782
[72] Xu G,Zhu X,Fu D,Dong J W,Xiao X M.Automatic land cover classification of geo-tagged field photos by deep learning[J].Environmental Modelling and Software,2017,91:127-1314
[73] Rebetez J,Satizábal H F, Mota M,Noll D,BüChi L,Wendling M,Cannelle B,Perez-Uribe A,Burgos S E.Augmenting a convolutional neural network with local histograms-A case study in crop classification from highresolution UAVimagery[C]. In:ESANN 2016proceedings,European Symposium on Artificial Neural Networks, Computational IntelligenceandMachine Learning.Bruges:i6doc.com publisher,2016:515-520
[74]孙钰,韩京冶,陈志泊,史明昌,付红萍,杨猛.基于深度学习的大棚及地膜农田无人机航拍监测方法[J].农业机械学报,2018,49(2):133-140Sun Y,Han J Y,Chen Z B,Shi M C,Fu H P,Yang M.Monitoring method for UAV image of greenhouse and plasticmulched landcover based on deep learning[J].Transactions of the Chinese Society of Agricultural Machinery,2018,49(2):133-140(in Chinese)
[75] Chen S W,Shivakumar S S,Dcunha S,Das J,Okon E,Qu C,Taylor C J,Kumar V.Counting Apples and oranges with deep learning:A data-driven approach[J].IEEE robotics and Automation Letters,2017,2(2):782-789
[76] Philipe A D,Amy T,Henry M.Apple flower detection using deep convolutional networks[J]. Computers in Industry,2018,99:17-28
[77]谭文学,赵春江,吴华瑞,高荣华.基于弹性动量深度学习神经网络的果体病理图像识别[J].农业机械学报,2015,46(1):20-25Tan W X,Zhao C J,Wu H R,Gao R H.A deep learning network for recognizing fruit pathologic images based on flexible momentum[J].Transaction of the Chinese Society for Agricultural Machinery,2015,46(1):20-25(in Chinese)
[78] Osterloff J,Nilssen I,Jrnegren J,Buhl-Mortensen P,Nattkemper T W.Polyp activity estimation and monitoring for cold water corals with a deep learning approach[C].In:Proceedings of 2nd workshop on Computer Vision for Analysis of Underwater Imagery,Piscataway:Institute of Electrical and Electronics Engineers Publisher,2016:1-6
[79]熊俊涛,刘振,汤林越,林睿,榕彬,彭红星.自然环境下绿色柑橘的视觉检测技术研究[J].农业机械学报,2018,49(4):1-9Xiong J T,Liu Z,Tang L Y,Lin R,Rong B,Peng H X.Visual detection of green citrus under natural environment[J].Transaction of the Chinese Society for Agricultural Machinery,2018,49(4):1-9(in Chinese)
[80] Sa I,Ge Z Y,Dayoub F,Upcroft B,Perez T,McCool C.DeepFruits:A fruit detection system using deep neural networks[J].Sensors,2016,16(8):1-23
[81] Bargoti S,Underwood J.Deep fruit detection in orchards[C]. In:Proceedings of 2017 IEEE International Conference on Robotics and Automation. Piscataway:Institute of Electrical and Electronics Engineers Publisher,2017:3626-3633
[82]王前程.基于深度学习的水果图像识别算法研究[D],保定:河北大学,2016Wang Q C.The algorithm research of fruit image recognition based on deep learning[D].Baoding:Hebei University,2016(in Chinese)
[83]张善文,张传雷,丁军.基于改进深度置信网络的大棚冬枣病虫害预测模型[J].农业工程学报,2017,33(19):202-208Zhang S W,Zhang C L,Ding J.Disease and insect pest forecasting model of greenhouse winter jujube based on modified deep belief network[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(19):202-208(in Chinese)
[84] Mohanty S P,Hughes D,SalathéM.Inference of plant diseases from leaf images through deep learning[OL].arXiv:1604.03169v1[cs.CV],2016-04-15.https://arxiv.org/pdf/1604.03169v1
[85] Tan W X,Zhao C J,Wu H R.Intelligent alerting for fruitmelon lesion image based on momentum deep learning[J].Multimedia Tools and Applications,2016,75(24):16741-16761
[86] Ding W G,Taylor G.Automatic moth detection from trap images for pest management[J].Computers and Electronics in Agriculture,2016,123:17-28
[87]程曦,张友华,陈祎琼,吴云志,乐毅.深度学习在储粮害虫的特征提取与分类上的应用[J].皖西学院学报,2017,33(5):67-72Cheng X,Zhang Y H,Chen Y Q, Wu Y Z,Yue Y.Application of deep learning in feature extraction and classification stored-grain pest[J].Journal of West Anhui University,2017,33(5):67-72(in Chinese)
[88] Sladojevic S, Arsenovic M, Anderla A, Culibrk D,Stefanovic D.Deep neural networks based recognition of plant diseases by leaf image classification[J].Computational Intelligence and Neuroscience,2016,2016(6):1-11
[89] Zhou D M,Song X,Zhao F J,Gu B H.Soil environment and pollution remediation[J].Pedosphere,2017,27(3):387-388
[90]邓芳明,吴翔,李兵,汪涛,刘珺.基于无源RFID传感标签的农田土壤环境监测技术研究[J].农业机械学报,2018,49(8):187-193,202Deng F M,Wu X,Li B,Wang T,Liu J.Research on monitoring technology of farmland soil environment based on passive RFID sensor tag[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(8):187-193,202(in Chinese)
[91] Song X D,Zhang G L,Liu F,Li D C,Zhao Y G,Yang J L.Modeling spatio-temporal distribution of soil moisture by deep learning-based cellular automata model[J].Journal of Arid Land,2016,8(5):734-748
[92] Christiansen P,Nielsen L N,Steen K A,Jrgensen R N,Karstoft H.DeepAnomaly:Combining background subtraction and deep learning for detecting obstacles and anomalies in an agricultural field[J].Sensors,2016,16(11):1-21
[2] Kitzes J,Wackernage M,Loh J,Peller A,Goldfinger S,Cheng D,Tea K.Shrink and share:Humanity’s present and future ecological footprint[J].Philosophical Transactions of the Royal Society B Biological Sciences,2008,363:467-475
[3] Ncube B,Mupangwa W,French A.Precision agriculture and food security in Africa[C].In:Systems Analysis Approach forComplexGlobalChallenges. Cham:Springer International Publishing AG,2018,159-178
[4] Sayer J,Cassman K G.Agricultural innovation to protect the environment[J].Proceedings of the National Academy of Sciences of the United States of America,2013,110(21):8345-8348
[5] Kamilaris A,Kartakoullis A,Prenafeta-BoldúF X.A review on the practice of big data analysis in agriculture[J].Computers and Electronics in Agriculture,2017,143:23-37
[6]李道亮.智慧农业:中国的机遇和挑战[J].高科技与产业化,2015,11(5):42-45Li D L.Smart agriculture:Opportunities and challenge for China[J].High-Technology&Industrialization,2015,11(5):42-45(in Chinese)
[7]孙志远,鲁成祥,史忠植,马刚.深度学习研究与进展[J].计算机科学,2016,43(2):1-8Sun Z Y,Lu C X,Shi Z Z,Ma G.Deep learning research and development[J].Computer Science,2016,43(2):1-8(in Chinese)
[8] Najafabadi M M,Villanustre F,Khoshgoftaar T M,Seliya N,Wald R, Muharemagic E.Deep learning applications and challenges in big data analytics[J].Journal of Big Data,2015,2(1):1-21
[9] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[C].In:Proceedings of the 2012 Advances in Neural Information Processing Systems.New York:Curran Associates Inc.,2012:1097-1105
[10]曾德伟,吴玉香,王聪.AUV深度的神经网络辨识和学习控制仿真研究[J].计算机工程与应用,2017,53(6):258-263Zeng D W,Wu Y X,Wang C.Research on simulation of neural network identification and learning for AUV depth control[J].Computer Engineering and Applications,2017,53(6):258-263(in Chinese)
[11]何西麟.基于深度学习的手写体字符识别研究与实现[D].广州:中山大学,2015He X L.The recognition and implementation of handwritten character based on deep learning[D]. Guangzhou:Zhongshan University,2015(in Chinese)
[12] Yang W X,Jin L W,Xie Z C,Feng Z Y.Improved deep convolutional neural network for online handwritten Chinese character recognition using domain-specific knowledge[C].In:Proceedings of the 13th International Conference on Document Analysis and Recognition.Piscataway:Institute of Electrical and Electronics Engineers Publisher,2015:551-555
[13] Yang W X,Jin L W,Liu M F.Character-level Chinese writer identification using path signature feature,dropstroke and deep CNN[C].In:Proceedings of 2015 13th International Conference on Document Analysis and Recognition.Piscataway:Institute of Electrical and Electronics Engineers Publisher,2015:546-550
[14] Yang W X,Jin L W,Tao D C,Xie Z C,Feng Z Y.DropSample:A new training method to enhance deep convolutional neural networks for large-scale unconstrained handwritten Chinese character recognition[J]. Pattern Recognition,2016,58(4):190-203
[15]梁军,柴玉梅,原慧斌,昝红英,刘铭.基于深度学习的微博情感分析[J].中文信息学报,2014,28(5):155-161Liang J,Chai Y M,Yuan H B,Zan H Y,Liu M.Deep learning for Chinese Micro-blog sentiment analysis[J].Journal of Chinese Information Processing,2014,28(5):155-161(in Chinese)
[16]吴蕾,张文生,王珏.基于深度学习框架的隐藏主题变量图模型[J].计算机研究与发展,2015,52(1):191-199Wu L,Zhang W S,Wang Y.Hidden topic variable graphical model based on deep learning framework[J].Journal of Computer Research and Development,2015,52(1):191-199(in Chinese)
[17]梁淑芬,刘银华,李立琛.基于LBP和深度学习的非限制条件下人脸识别算法[J].通信学报,2014,35(6):154-160Liang S F,Liu Y H,Li L C.Face recognition under unconstrained based on LBP and deep learning[J].Journal on Communications,2014,35(6):154-160(in Chinese)
[18]池燕玲.基于深度学习的人脸识别方法的研究[D].福州:福建师范大学,2015Chi Y L.The research of face recognition method based on deep learning[D].Fuzhou:Fujian Normal University,2015(in Chinese)
[19]林妙真.基于深度学习的人脸识别研究[D].大连:大连理工大学,2013Lin M Z.Research on face recognition base on deep learnin[D].Dalian:Dalian University of Technology,2013(in Chinese)
[20]由清圳.基于深度学习的视频人脸识别方法[D].哈尔滨:哈尔滨工业大学,2013You Q Z.The video face recognition method based on the deep learning[D].Harbin:Harbin Institute of Technology,2013(in Chinese)
[21]张安胜.深度学习在蛋白质二级结构预测中的应用研究[D].合肥:安徽大学,2015Zhang A S.The research on the application of deep learning in the prediction of the secondary structure of protein[D].Hefei:Anhui University,2015(in Chinese)
[22] Fan X N,Zhang S W.lncRNA-MFDL:Identification of human long non-coding RNAs by fusing multiple features and using deep learning[J].Molecular Biosystems,2015,11(3):892-897
[23] Liang M,Li Z,Chen T.Integrative data analysis of multiplatform cancer data with a multimodal deep learningapproach[J].IEEE/ACM Transactions on Computational Biology and Bioinformatics,2015,12(4):928-937
[24] Ibrahim R,Yousri N A,Ismail M A.Multi-level gene/Mi RNA feature selection using deep belief nets and active learning[C].In:Proceedings of Annual International Conference of the IEEE Engineering in Medicine and Biology,Piscataway:Institute of Electrical and Electronics Engineers Publisher,2014:3957-3960
[25] Ma J,Sheridan R P,Liaw A.Deep neural nets as a method for quantitative structure activity relationships[J].Journal of Chemical Information and Modeling,2015,55(2):263-274
[26]高君宇,杨小汕,张天柱,徐常胜.基于深度学习的鲁棒性视觉跟踪方法[J].计算机学报,2016,39(7):1419-1434Gao J Y,Yang X S,Zhang T Z,Xu C S.Robust visual tracking method via deep learning[J].Chinese Journal of Computers,2016,39(7):1419-1434(in Chinese)
[27]朱煜,赵江坤,王逸宁.基于深度学习的人体行为识别算法综述[J].自动化学报,2016,42(6):848-857Zhu Y,Zhao J K,Wang Y N.A review of human action recognition based on deep learning[J].Acta Automatica Sinica,2016,42(6):848-857(in Chinese)
[28] Zhou X Z,Xie L,Zhang P,Zhang Y N.An ensemble of deep neural networks for object tracking[C].In:Proceedings of the 2014 IEEE International Conference on Image Processing. Piscataway:InstituteofElectricaland Electronics Engineers Publisher,2014:843-847
[29] Kuen J,Lim K M,Lee C P.Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principle[J].Pattern Recognition,2015,48(10):2964-2982
[30] Ding J W,Huang Y Z,Liu W,Huang K Q.Severely blurred object tracking by learning deep imagerepresentations[J].IEEE Transactions on Circuits and Systems for Video Technology,2016,26(2):319-331
[31]丰晓霞.基于深度学习的图像识别算法研究[D].太原:太原理工大学,2015Feng X X.Research on image recognition based on deep learning algorithm[D].Taiyuan:Taiyuan University of Technology,2015(in Chinese)
[32]阮怀玉.基于稀疏表示和深度学习的SAR图像目标识别研究[D].合肥:中国科学技术大学,2016Ruan H Y.SAR image target recognition based on sparse representation and deep learning[D].Hefei:University of Science and Technology of China,2016(in Chinese)
[33]吕金涛.基于深度学习的相似图像搜索算法研究[D].北京:华北电力大学,2015Lv J T. Research on similar image retrieval based on deeplearning algorithm[D].Beijing:North China Electric Power University,2016(in Chinese)
[34]刘大伟,韩玲,韩晓勇.基于深度学习的高分辨率遥感影像分类研究[J].光学学报,2016,36(4):298-306Liu D W,Han L,Han X Y.High spatial resolution remote sensing image classification based on deep learning[J].Acta Optica Sinica,2016,36(4):298-306(in Chinese)
[35] Ma X R, Geng J,Wang H Y. Hyperspectral image classification via contextual deep learning[J].Journal on Image and Video Processing,2015,20(1):1-12
[36] Ma X,Wang H,Wang J.Semisupervised classification for hyperspectral image based on multi-decision labeling and deep feature learning[J].ISPRS Journal of Photogrammetry&Remote Sensing,2016,120:99-107
[37] Audebert N,Saux B L,Lefèvre S.Beyond RGB:Very high resolution urban remote sensing with multimodal deep networks[J].ISPRS Journal of Photogrammetry and Remote Sensing,2018,140:20-32
[38] Li Y S, Xie W Y, Li H Q. Hyperspectral image reconstruction by deep convolutional neural network for classification[J].Pattern Recognition,2017,63:371-383
[39] Ikasari I H,Ayumi V,Fanany M I.Multiple regularizations deep learning for paddy growth stages classification from LANDSAT-8[C]. In:Proceeding of International Conference on Advanced Computer Science and Information Systems.Piscataway:IEEE Publisher,2017:1-11
[40] Scott G J,EnglandM R,Starms W A.Training deep convolutional neural networks for Land-Cover classification of high-resolution imagery[J].IEEE Geoscience&Remote Sensing Letters,2017,14(4):549-553
[41] Collobert R, Weston J, Karlen M. Natural language processing(almost)from scratch[J].Journal of Machine Learning Research,2011,12(1):2493-2537
[42] Xiong W,Droppo J,Huang X,Seide F.,Seltzer M,Stolcke A, Yu D, Zweig G. Achieving human parity in conversational speech recognition[OL].arXiv:1610.05256v2[cs.CL],2017-2-17.https://arxiv.org/pdf/1610.05256v2
[43] Hinton G,Deng L,Yu D.Deep Neural networks for acoustic modeling in speech recognition:The shared views of four research groups[J].IEEE Signal Processing Magazine,2012,29(6):82-97
[44] Amodei D,Anubhai R,Battenberg E.Deep speech 2:endto-end speech recognition in English and Mandarin[OL].arXiv:1512.02595v1[cs.CL],2015-12-08.https://arxiv.org/pdf/1512.02595v1.pdf
[45] Sak H,Senior A,Rao K.Fast and accurate recurrent neural network acoustic models for speech recognition[C].In:the INTERSPEECH 2015 proceedings.Trier:DBLP Computer Science Bibliography,2015:1468-1472
[46] Graves A,Mohamed A R,Hinton G.Speech recognition with deep recurrent neural networks[C].In:Proceeding of IEEE International Conference on Acoustics,Speech and Signal Processing.Piscataway:Institute of Electrical and Electronics Engineers Publisher,2013:6645-6649
[47] Sutskever I,Vinyals O,Le Q V.Sequence to Sequence Learning with neural networks[OL].arXiv:1409.3215v3[cs.CL],2014-12-14.https://arxiv.org/pdf/1409.3215.pdf.
[48] Lecun Y,Bengio Y,Hinton G.Deep learning[J].Nature,2015,521(7553):436-444
[49] Kamilaris A, Prenafeta-BoldúF X. Deep learning in agriculture:A survey[J].Computers and Electronics in Agriculture,2018,147:70-90
[50] Goodfellow I,Bengio Y,Courville A.Deep Leaning[OL].2017-03-15.https://github.com/exacity/deeplearningbookenglish
[51]刘念.基于深度信念网络的植物叶片识别研究[D].北京:北京林业大学,2016Liu N.The study of plant leaf recognition based on the deep belief networks[D].Beijing:Beijing Forest University,2016(in Chinese)
[52]余滨,李绍滋,徐素霞,纪荣嵘.深度学习:开启大数据时代的钥匙[J].工程研究:跨学科视野中的工程,2014,6(3):233-243Yu B,Li S Z,Xu S X,Ji R R.Deep learning:A key of stepping into the era of big data[J].Journal of Engineering Studies,2014,6(3):233-24(in Chinese)
[53] Bengio Y. Learning deep architectures for AI[J].Foundations and Trends in Machine Learning,2009,2(1):1-12
[54] Braverman M.Poly-logarithmic independence fools boundeddepth boolean circuits[J].Communications of the ACM,2011,54(4):108-115
[55] Bengio Y,Delalleau O.On the expressive power of deep architectures[C].In:Proceeding of International Conference on Algorithmic Learning Theory,Berlin:Heidelberg,2011:18-36
[56] Socher R,Huval B,Bhat B.Convolutional-recursive deep Learning for 3Dobject classification[C].In:Proceeding of Advances in Neural Information Processing System 2012.Lake Tahoe:Neural Information Processing System,2012:665-673
[57]管皓,薛向阳,安志勇.深度学习在视频目标跟踪中的应用进展与展望[J].自动化学报,2016,42(6):834-847Guan H,Xue X Y,An Z Y.Advances on applicaton of deep learning for video object tracking[J].Acta Automatica Sinica,2016,42(6):834-847(in Chinese)
[58]段艳杰,吕宜生,张杰,赵学亮,王飞跃.深度学习在控制领域的研究现状与展望[J].自动化学报,2016,42(5):643-654Duang Y J,Lv Y S,Zhang J,Zhao X L,Wang F Y.Deep learning for control:the state of the art and prospects[J].Acta Automatica Sinica,2016,42(5):643-654(in Chinese)
[59] Dyrmann M, Karstoft H, Midtiby H S.Plant species classification using deep convolutional neural network[J].Biosystems Engineering,2016,151:72-80
[60] Grinblat G L,Uzal L C,Larese M G,Granitto P M.Granitto,Deep learning for plant identification using vein morphological patterns[J].Computers and Electronics in Agriculture,2016,127:418-424
[61] Ahlin K,Joffe B,Hu A P.Autonomous leaf picking using deep learning and visual-servoing[J].IFAC-Papers OnLine,2016,49(16):177-183
[62]王琨,刘大茂.基于深度学习的茶叶状态智能识别方法[J].重庆理工大学学报:自然科学版,2015,29(12):120-126Wang K,Liu D M.Intelligent identification for tea state based on deep learning[J].Journal of Chongqing University of Technology:Natural Science,2015,29(12):120-126(in Chinese)
[63]孙宏杰.基于叶片图像分析的葡萄品种识别方法研究[D],杨凌:西北农林科技大学,2016Sun H J.Indentification of grape varieties based on leaves image analysis[D].Yangling:Northwest Agricultural and Forest University,2016(in Chinese)
[64]张帅,淮永建.基于分层卷积深度学习系统的植物叶片识别研究[J].北京林业大学学报,2016,38(9):108-115Zhang S,Huai Y J.Leaf image recognition based on layered convolutions neural network deep learning[J].Journal of Beijing Forestry University,2016,38(9):108-115(in Chinese)
[65] Mehdipour Ghazi M, Yanikoglu B, Aptoula E. Plant identification using deep neural networks via optimization of transfer learning parameters[J],Neurocomputing,2017,235:228-235
[66] Sakai Y,Oda T,Ikeda M,Barolli L.A vegetable category recognition system using deep neural network[C].In:Proceeding of 2016 10th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing(IMIS),Piscataway:Institute of Electrical and Electronics Engineers Publisher,2016:189-192
[67] Douarre C,Schielein R,Frindel C,Gerth S,Rousseau D.Transfer learning from synthetic data applied to soil-root segmentation in X-ray tomography images[J].Journal of Imaging,2018,4(5):1-14
[68]马珍玉.基于深度学习和SVM的植物叶片识别系统的研究与测试[D].呼和浩特:内蒙古农业大学,2016Ma Z Y.Research and test on plant leaves recognition system based on deep learning and support vector machine[D].Hohehot:Inner Mongolia Agricultural University,2016(in Chinese)
[69]邢晨.基于深度学习的高光谱遥感图像分类[D].北京:中国地质大学,2016Xing C. Hyperspectral image classification using deep learning method[D]. Beijing:China University of Geosciences,2016(in Chinese)
[70] Chen Y S,Lin Z H,Zhao X,Wang G,Gu Y F.Deep learning-based classification of hyperspectral data[J].IEEE Journal of Selected Topics in Applied Earth Observations And Remote Sensing,2014,7(6):2094-2107
[71] Kussul N,Lavreniuk M,Skakun S,Shelestov A.Deep learning classification of land cover and crop types using remote sensing data[J].IEEE Geoscience and Remote Sensing Letters,2017,14(5):778-782
[72] Xu G,Zhu X,Fu D,Dong J W,Xiao X M.Automatic land cover classification of geo-tagged field photos by deep learning[J].Environmental Modelling and Software,2017,91:127-1314
[73] Rebetez J,Satizábal H F, Mota M,Noll D,BüChi L,Wendling M,Cannelle B,Perez-Uribe A,Burgos S E.Augmenting a convolutional neural network with local histograms-A case study in crop classification from highresolution UAVimagery[C]. In:ESANN 2016proceedings,European Symposium on Artificial Neural Networks, Computational IntelligenceandMachine Learning.Bruges:i6doc.com publisher,2016:515-520
[74]孙钰,韩京冶,陈志泊,史明昌,付红萍,杨猛.基于深度学习的大棚及地膜农田无人机航拍监测方法[J].农业机械学报,2018,49(2):133-140Sun Y,Han J Y,Chen Z B,Shi M C,Fu H P,Yang M.Monitoring method for UAV image of greenhouse and plasticmulched landcover based on deep learning[J].Transactions of the Chinese Society of Agricultural Machinery,2018,49(2):133-140(in Chinese)
[75] Chen S W,Shivakumar S S,Dcunha S,Das J,Okon E,Qu C,Taylor C J,Kumar V.Counting Apples and oranges with deep learning:A data-driven approach[J].IEEE robotics and Automation Letters,2017,2(2):782-789
[76] Philipe A D,Amy T,Henry M.Apple flower detection using deep convolutional networks[J]. Computers in Industry,2018,99:17-28
[77]谭文学,赵春江,吴华瑞,高荣华.基于弹性动量深度学习神经网络的果体病理图像识别[J].农业机械学报,2015,46(1):20-25Tan W X,Zhao C J,Wu H R,Gao R H.A deep learning network for recognizing fruit pathologic images based on flexible momentum[J].Transaction of the Chinese Society for Agricultural Machinery,2015,46(1):20-25(in Chinese)
[78] Osterloff J,Nilssen I,Jrnegren J,Buhl-Mortensen P,Nattkemper T W.Polyp activity estimation and monitoring for cold water corals with a deep learning approach[C].In:Proceedings of 2nd workshop on Computer Vision for Analysis of Underwater Imagery,Piscataway:Institute of Electrical and Electronics Engineers Publisher,2016:1-6
[79]熊俊涛,刘振,汤林越,林睿,榕彬,彭红星.自然环境下绿色柑橘的视觉检测技术研究[J].农业机械学报,2018,49(4):1-9Xiong J T,Liu Z,Tang L Y,Lin R,Rong B,Peng H X.Visual detection of green citrus under natural environment[J].Transaction of the Chinese Society for Agricultural Machinery,2018,49(4):1-9(in Chinese)
[80] Sa I,Ge Z Y,Dayoub F,Upcroft B,Perez T,McCool C.DeepFruits:A fruit detection system using deep neural networks[J].Sensors,2016,16(8):1-23
[81] Bargoti S,Underwood J.Deep fruit detection in orchards[C]. In:Proceedings of 2017 IEEE International Conference on Robotics and Automation. Piscataway:Institute of Electrical and Electronics Engineers Publisher,2017:3626-3633
[82]王前程.基于深度学习的水果图像识别算法研究[D],保定:河北大学,2016Wang Q C.The algorithm research of fruit image recognition based on deep learning[D].Baoding:Hebei University,2016(in Chinese)
[83]张善文,张传雷,丁军.基于改进深度置信网络的大棚冬枣病虫害预测模型[J].农业工程学报,2017,33(19):202-208Zhang S W,Zhang C L,Ding J.Disease and insect pest forecasting model of greenhouse winter jujube based on modified deep belief network[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(19):202-208(in Chinese)
[84] Mohanty S P,Hughes D,SalathéM.Inference of plant diseases from leaf images through deep learning[OL].arXiv:1604.03169v1[cs.CV],2016-04-15.https://arxiv.org/pdf/1604.03169v1
[85] Tan W X,Zhao C J,Wu H R.Intelligent alerting for fruitmelon lesion image based on momentum deep learning[J].Multimedia Tools and Applications,2016,75(24):16741-16761
[86] Ding W G,Taylor G.Automatic moth detection from trap images for pest management[J].Computers and Electronics in Agriculture,2016,123:17-28
[87]程曦,张友华,陈祎琼,吴云志,乐毅.深度学习在储粮害虫的特征提取与分类上的应用[J].皖西学院学报,2017,33(5):67-72Cheng X,Zhang Y H,Chen Y Q, Wu Y Z,Yue Y.Application of deep learning in feature extraction and classification stored-grain pest[J].Journal of West Anhui University,2017,33(5):67-72(in Chinese)
[88] Sladojevic S, Arsenovic M, Anderla A, Culibrk D,Stefanovic D.Deep neural networks based recognition of plant diseases by leaf image classification[J].Computational Intelligence and Neuroscience,2016,2016(6):1-11
[89] Zhou D M,Song X,Zhao F J,Gu B H.Soil environment and pollution remediation[J].Pedosphere,2017,27(3):387-388
[90]邓芳明,吴翔,李兵,汪涛,刘珺.基于无源RFID传感标签的农田土壤环境监测技术研究[J].农业机械学报,2018,49(8):187-193,202Deng F M,Wu X,Li B,Wang T,Liu J.Research on monitoring technology of farmland soil environment based on passive RFID sensor tag[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(8):187-193,202(in Chinese)
[91] Song X D,Zhang G L,Liu F,Li D C,Zhao Y G,Yang J L.Modeling spatio-temporal distribution of soil moisture by deep learning-based cellular automata model[J].Journal of Arid Land,2016,8(5):734-748
[92] Christiansen P,Nielsen L N,Steen K A,Jrgensen R N,Karstoft H.DeepAnomaly:Combining background subtraction and deep learning for detecting obstacles and anomalies in an agricultural field[J].Sensors,2016,16(11):1-21