Plant species classification using deep

Plant species classification using deep

ID:40351866

大小:1.31 MB

頁(yè)數(shù):9頁(yè)

時(shí)間:2019-07-31

Plant species classification using deep_第1頁(yè)
Plant species classification using deep_第2頁(yè)
Plant species classification using deep_第3頁(yè)
Plant species classification using deep_第4頁(yè)
Plant species classification using deep_第5頁(yè)
資源描述:

《Plant species classification using deep》由會(huì)員上傳分享,免費(fèi)在線閱讀,更多相關(guān)內(nèi)容在學(xué)術(shù)論文-天天文庫(kù)

1、biosystemsengineering151(2016)72e80Availableonlineatwww.sciencedirect.comScienceDirectjournalhomepage:www.elsevier.com/locate/issn/15375110ResearchPaperPlantspeciesclassi?cationusingdeepconvolutionalneuralnetworka,*baMadsDyrmann,HenrikKarstoft,HenrikSkovMidtibyaTheMaerskMc-KinneyMolle

2、rInstitute,UniversityofSouthernDenmark,DenmarkbDepartmentofEngineering,AarhusUniversity,DenmarkarticleinfoInformationonwhichweedspeciesarepresentwithinagricultural?eldsisimportantforArticlehistory:sitespeci?cweedmanagement.Thispaperpresentsamethodthatiscapableofrecog-Received16March20

3、16nisingplantspeciesincolourimagesbyusingaconvolutionalneuralnetwork.TheReceivedinrevisedformnetworkisbuiltfromscratchtrainedandtestedonatotalof10,413imagescontaining2222August2016weedandcropspeciesatearlygrowthstages.TheseimagesoriginatefromsixdifferentAccepted26August2016datasets,wh

4、ichhavevariationswithrespecttolighting,resolution,andsoiltype.Thisincludesimagestakenundercontrolledconditionswithregardtocamerastabilisationandillumination,andimagesshotwithhand-heldmobilephonesin?eldswithchangingKeywords:lightingconditionsanddifferentsoiltypes.Forthese22species,then

5、etworkisabletoPlantclassi?cationachieveaclassi?cationaccuracyof86.2%.Deeplearning?2016IAgrE.PublishedbyElsevierLtd.Allrightsreserved.ConvolutionalNeuralNetworksWeedcontrolWeedcontrolmethods,whichrelyonmechanicalmeans,1.Introductionneedtoknowthepreciselocationofcropplants,whilemethodst

6、hatoptimisetheherbicideapplicationrequiresin-Inmodernfarming,thereisaneedforeffectiveweedcontrolformationonthespeciesoftheweedplants.Byusingdetailedasyieldlossescausedbynotcontrollingtheweedsaresig-informationaboutpresentweedplantspecies,theirgrowthni?cant(23%e71%dependingonthecrops,w

7、eedsandloca-stagesandplantdensitiesina?eld,theherbicideconsump-tion(Hodgson,1968;Oerke,2006;Slaughter,Giles,Fennimore,tioncanbereducedby40%onaverage(J?rgensenetal.,2007).&Smith,2008)).ThepreferredmethodusedforcontrollingTheDanishsystem,CropProtectionOnline,isatoolthathelpsweedsistoapp

8、lyher

當(dāng)前文檔最多預(yù)覽五頁(yè),下載文檔查看全文

此文檔下載收益歸作者所有

當(dāng)前文檔最多預(yù)覽五頁(yè),下載文檔查看全文
溫馨提示:
1. 部分包含數(shù)學(xué)公式或PPT動(dòng)畫(huà)的文件,查看預(yù)覽時(shí)可能會(huì)顯示錯(cuò)亂或異常,文件下載后無(wú)此問(wèn)題,請(qǐng)放心下載。
2. 本文檔由用戶上傳,版權(quán)歸屬用戶,天天文庫(kù)負(fù)責(zé)整理代發(fā)布。如果您對(duì)本文檔版權(quán)有爭(zhēng)議請(qǐng)及時(shí)聯(lián)系客服。
3. 下載前請(qǐng)仔細(xì)閱讀文檔內(nèi)容,確認(rèn)文檔內(nèi)容符合您的需求后進(jìn)行下載,若出現(xiàn)內(nèi)容與標(biāo)題不符可向本站投訴處理。
4. 下載文檔時(shí)可能由于網(wǎng)絡(luò)波動(dòng)等原因無(wú)法下載或下載錯(cuò)誤,付費(fèi)完成后未能成功下載的用戶請(qǐng)聯(lián)系客服處理。