崔萌,谢曹东,单杰

• 1:武汉大学遥感信息工程学院
• 2:普渡大学土木工程学院

摘要(Abstract)：

众源数据存在基数大、来源复杂、相关性低等特点,使得检索和筛选成为研究的热点,针对当前研究未能有效利用众源地理数据源的问题,该文提出了一种基于聚合平台的网络图片动态检索流程,以语义关键字和地理坐标为索引进行多图片库的聚合搜索。利用深度神经网络进行影像进行筛选的方法,解决了传统筛选方法筛选精度不高的缺点,具有高识别率和高效的特点。实验表明,本文提出的方案能够有效搜集高质量的众源影像,对于众源地理信息处理有潜在的价值。

关键词(KeyWords)： 众源影像;深度学习;影像检索;服务聚合;智能筛选

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(41271431)

作者(Author): 崔萌,谢曹东,单杰

DOI: 10.16251/j.cnki.1009-2307.2019.03.027

参考文献(References)：

• [1]GILES J.Wikipedia rival calls in the experts[J].Nature,2006,443(7111):493.
• [2]HOWE J.The rise of crowdsourcing[J].Wired Magazine,2006,14(6):1-4.
• [3]HEIPKE C.Crowdsourcing geospatial data[J].ISPRSJournal of Photogrammetry and Remote Sensing,2010,65(6):550-557.
• [4]单杰,秦昆,黄长青,等.众源地理数据处理与分析方法探讨[J].武汉大学学报(信息科学版),2014,39(4):390-396.(SHAN Jie,QIN Kun,HUANG Changqing,et al.Methods of crowd sourcing geographic dataprocessing and analysis[J].Geomatics and InformationScience of Wuhan University,2014,39(4):390-396.)
• [5]MILLER A D,EDWARDS W K.Give and take:astudy of consumer photo-sharing culture and practice[C]∥Proceedings of the SIGCHI conference onHuman factors in computing systems.San Jose:ACM,2007:347-356.
• [6]HEIPKE C.Crowdsourcing geospatial data[J].ISPRSJournal of Photogrammetry and Remote Sensing,2010,65(6):550-557.
• [7]NOV O,NAAMAN M,YE C.What drives contenttagging:the case of photos on Flickr[C]∥Proceedingsof the SIGCHI Conference on Human Factors inComputing Systems.New York,USA:ACM,2008:1097-1100.
• [8]KISILEVICH S,KRSTAJIC M,KEIM D,et al.Event-based analysis of people’s activities and behavior usingFlickr and Panoramio geotagged photo collections[C]∥Proceedings of the Information Visualisation Interna-tional Conference.London:IEEE,2010:289-296.
• [9]KISILEVICH S,KEIM D,ROKACH L.A novelapproach to mining travel sequences using collectionsof geotagged photos[J].Geospatial Thinking,2010:163-182.
• [10]BUCZAK A L,GUVEN E.A survey of data miningand machine learning methods for cyber securityintrusion detection[J].IEEE Communications Surveys&Tutorials,2016,18(2):1153-1176.
• [11]YANAI K,YAEGASHI K,QIU B.Detecting culturaldifferences using consumer-generated geotagged photos[C]∥Proceedings of International Workshop on Locationand the Web.Boston:ACM,2009:12-12.
• [12]ZHENG Y T,ZHAO M,SONG Y,et al.Tour theworld:building a web-scale landmark recognitionengine[C]∥Proceedings of IEEE Conference onComputer Vision and Pattern Recognition.Miami,USA:IEEE,2009:1085-1092.
• [13]刘志辉,许捍卫.基于Google Maps API和网络数据抓取技术的WebGIS开发[J].测绘通报,2009(3):68-70.(LIU Zhihui,XU Hanwei.Development method ofweb GIS based on the google maps API and web datacrawling[J].Bulletin of Surveying and Mapping,2009(3):68-70.)
• [14]王迪,陈庭毅,陈嘉彬.图像特征提取算法研究[J].电脑知识与技术,2017,13(15):149-150.(WANG Di,CHEN Tingyi,CHEN Jiabin.Research of imagefeature extraction algorithm[J].Computer Knowledgeand Technology,2017,13(15):149-150.)
• [15]STONE Z,ZICKLER T,DARRELL T.Autotaggingfacebook:Social network context improves photoannotation[C]∥Proceedings of IEEE Conference onComputer Vision and Pattern Recognition Workshops.Anchorage:IEEE,2008:1-8.
• [16]许可.卷积神经网络在图像识别上的应用的研究[D].杭州:浙江大学,2012:1-58.(XU Ke,Study of convolu-tional neural network applied on image recognition[D].Hangzhou:Zhejiang University,2012:1-58)
• [17]LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
• [18]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Image net classification with deep convolutional neuralnetworks[C]∥Proceedings of Advances in NeuralInformation Processing Systems.[S.l.:s.n.],2012:1097-1105.
• [19]SZEGEDY C,LIU W,JIA Y,et al.Going deeper withconvolutions[C]∥Proceedings of the IEEE conferenceon Computer Vision and Pattern Recognition.Boston:IEEE,2015:1-9.
• [20]NICAJONH.理解CNN卷积神经网络原理[EB/OL].[2017-08-30].http:∥blog.csdn.net/nicajonh/article/details/53142449.(NICAJONH.The understanding ofprinciples of convolution neural network[EB/OL].[2017-08-30].http:∥blog.csdn.net/nicajonh/article/details/53142449.)
• [21]SUN Y,LIANG D,WANG X,et al.Deepid3:Facerecognition with very deep neural networks[J].Computer Science,2015.
• [22]SIMONYAN K,ZISSERMAN A.Very deep convolu-tional networks for large-scale image recognition[EB/OL].(2014-04-09)[2017-08-30].https:∥arxiv.org/abs/1409.1556.
• [23]SHELHAMER E,LONG J,DARRELL T.Fully conv-olutional networks for semantic segmentation[J].IEEETransactions on Pattern Analysis and Machine Intelli-gence,2017,39(4):640-651.