原创力文档- 1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
- 2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击 这里二次下载。
- 3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
结合多特征与深度学习模型的云和云阴影检测方法研究
Abstract
Withthecontinuousinnovationofsatelliteremotesensingtechnology,theEarth
observationsystemhastheabilitytoobtainmulti-scaledata.Themassiveopticalsatellite
datasetplaysahugeroleinlanduseandchangedetection,promotingthedevelopmentofa
comprehensiveremotesensingservicesystem.However,duetothephysicallimitationsofthe
imagingsystem,therearealwaysissuessuchascloudcoverinopticalsatelliteimages.
Cloudsandtheirshadowshindersatellitesensorsfromobtainingsurfaceinformationunder
lightingconditions,resultingininformationbiasormissingwhenusingremotesensing
methodstoextracttargetfeatures,greatlyreducingtheutilizationrateofimages.Therefore,
cloudandshadowdetectionhasbecomeanimportantprerequisiteforeffectivelyobtaining
quantitativeparametersofthesurface.However,atthisstage,manydetectionmethodsare
difficulttoachievesatisfactoryaccuracyincomplexscenes,andthegeneralizationand
stabilityofdetectionmethodsbasedonasinglemodelarestillinsufficient.Inresponsetothe
variousproblemsincloudandcloudshadowdetectionmentionedabove,thisarticlewill
focusontheapplicationofdeeplearningandtheconstructionofdetectionprocesses.Based
onthewidefieldofview(WFV)imagingdataofthedomesticGaofen-1(GF-1)satellite,the
cloudandcloudshadowdetectionmethodcombiningmulti-scalemodelswillbestudied.The
maincontentofthisarticleisasfollows:
(1)ThisstudysummarizesthecharacteristicsofGF-1WFVimagesinresponsetoissues
suchastheinabilityofthepubliclyavailableGF1_WHUdatasettobedirectlyappliedto
machinelearningmodeltraining.Basedontheparameterrequirementsoftheclassicdeep
learningmodel,theGF1_WHUdatasetwasprocessedandimproved.Throughnumerical
transformation,cropping,filtering,andenhance
文档评论（0）