




版權(quán)說明:本文檔由用戶提供并上傳,收益歸屬內(nèi)容提供方,若內(nèi)容存在侵權(quán),請(qǐng)進(jìn)行舉報(bào)或認(rèn)領(lǐng)
文檔簡(jiǎn)介
RochesterInstituteofTechnology
RITDigitalInstitutionalRepository
Theses
12-2021
Camera-baseddeeplearningAIassistantsystemforbasketballtraining
GuangkunZeng
gz4641@
Followthisandadditionalworksat:
/theses
RecommendedCitation
Zeng,Guangkun,"Camera-baseddeeplearningAIassistantsystemforbasketballtraining"(2021).Thesis.RochesterInstituteofTechnology.Accessedfrom
ThisThesisisbroughttoyouforfreeandopenaccessbytheRITLibraries.Formoreinformation,pleasecontact
repository@
.
CAMERA-BASEDDEEPLEARNINGAIASSISTANTSYSTEMFORBASKETBALLTRAINING
RIT
Camera-baseddeeplearningAIassistantsystemforbasketballtraining
By
GuangkunZeng
AThesisSubmittedinPartialFulfillmentoftheRequirementsfortheDegreeofMasterofFineArtinVisualCommunicationDesign
School/DepartmentofDesignCollegeofArtandDesignRochesterInstituteofTechnology
Rochester,NYDecember,2021
ThesisApproval
Camera-baseddeeplearningAIassistantsystemforbasketballtraining
ThesisTitle
GuangkunZeng
ThesisAuthor
Submittedinpartialfulfillmentoftherequirementsforthe
degreeofMasterofFineArts
TheSchoolofDesign|VisualCommunicationDesign
RochesterInstituteofTechnology|Rochester,NewYork
MikeStrobert ChiefThesisAdvisor
Name Title
ElectronicSignature:UseAdobeAcrobat
AssociateThesisAdvisor
Name Title
ElectronicSignature:UseAdobeAcrobat
Name(Optionalforsomeprograms)
selectaTitle
Title(Optionalforsomeprograms)
ElectronicSignature:UseAdobeAcrobat(Optionalforsomeprograms)
selectaTitle
Name(Optionalforsomeprograms) Title(Optionalforsomeprograms)
ElectronicSignature:UseAdobeAcrobat(Optionalforsomeprograms)
CAMERA-BASEDDEEPLEARNINGAIASSISTANTSYSTEMFORBASKETBALLTRAINING
Abstract
TheYOLO,aComputerVisionAlgorithms,isbroughtouttoanalyzethebasketballplayer’sstatusasadataset.Itcanrecordtheplayers’behavioronthecourtincludingdribbling,shooting,andrunning.Inthisway,theappcouldcollectthefieldgoalyoumadeandmissed.First,youshouldusethisapptorecordavideoofyourshoottraining.Afterthat,theAIwouldanalyzeandbringsouta3dvirtualdiagraminterpretyourperformance.Thisdiagramwillshowthehotzoneandcoldzoneforyourfieldgoal.Also,thetrackofyourballwillbedisplayedonthevideosothatyoucanknowiftheangleofyourshootingistoolowortoohigh.Intheend,theAI-basedonmachinelearningwillgiveoutaplanaccordingtoyourperformanceonshooting.
Asatrainingmobileapplicationsupportedbycamera-basedactionrecognition,thetargetaudienceisthebasketballamateurplayerswhodon’thavetheresourcesasproplayersdo.Thisprojectwillbedesignedasanewtrainingexperienceandwillbedeliveredasapromovideothatshowshowtousetheapplicationandalsothescenariopeopleuse.
Keywords
MR,virtualenvironment,camera-based,trainingsystem,deep-learning,machinelearning,motioncapture,AI
CriticalAnalysisandSummary
Context
Manybasketballenthusiastswanttoupgradetheirskillstoafarbetterlevel,butunfortunately,noteveryonehasthefundstohireprofessionalcoachestotrainonthebestcourt.Andwhat’smore,manyamateurplayersdonotevenknowhowtopracticeinaproperwaybecausethevideotutorialisnotasintuitiveastherealcoachorastheprofessionalhumancoachis.What’smore,itisalmostimpossibleforthebasketballplayertoquantifyhowgoodhis/hershootingis.Butpeopledoneedverygoodshootingformandtechniquetoshootconsistently.Howmightweimproveplayers’trainingexperience?
Nowadays,MR(mixedreality)haschangedourlife.ResearchbyVisualCapitalistprojectsthattheXRmarketwillbeworth$209billionby2022,markinganeight-foldincreasefrom20181.Furthermore,63%ofshareholdersinXRtechnologycompaniesbelievethetechnologywillbemainstreamby2024.Atthesametime,MixedRealityisquitewithinthemiddlebutalsothelongertermoftheentertainmentindustry.2Thistypeoftechnologycouldprovideacustomizedanduniquetrainingexperienceevencomparedtothebestcourtandtrainerscoulddo.3
TheMixedRealityisthetechnologythatcouldprovideanimmersiveexperienceanddirectdatavisualization.IproposetobringoutaMixedRealitymobileapplicationthatcangenerate3dvirtualdiagramofthebasketballcourttoassistplayerstounderstandtheirshootingperformance.Atthesametime,theappwillcollecttheplayer’sdataandmakethetrainingplanaccordingtotheAI-basedanalysissystem.
Methodology
Toimplementthissystem,multipletechnologieswillbeintegrated.TheYOLO,aComputerVisionAlgorithmswillrecognizetheballtraceandcollectdataofyourtraining.4Themotioncapturewith3Dvirtualenvironmenttechnologywillinterprettheshootinggestureandmovement.Thenthemachinelearningwillgenerateaspecifictrainingplan.
Thephaseofinterviewanduserresearchwillnotproceedbecausethisdesignputsmoreemphasisonconceptualdesign.Thisdesignfocuseson3problemsthatplayersoftenmeet.First,it’shardforamateurplayerstoquantifytheirskilllevel.Second,noteveryplayercanmakeapreciseplanasprofessional
1Emrich,T.(2020,February25).20for2020:AugmentedRealityTrendsandHowTheyMayPlayOutThisYear[Weblogpost].Retrievedfrom
/@tomemrich/20-augmented-reality-trends-to-keep-
an-eye-on-in-2020-d2b0258edbb
2Terry,Q.(2019,July23).ARiselevatingtheplayingfieldforsportsbycreatingsmartertrainingmethods.Retrievedfrom/futuresin/ar-is-elevating-the-playing-field-for-sports-by-creating-smarter-training-methods-77db01a84d64
3Lee,David."OurFirstShot(s)."Medium(blog).July17,2018./nex-team/our-first-shot-s-272c67d0349d.
4Terry,Q.(2019,July23).ARiselevatingtheplayingfieldforsportsbycreatingsmartertrainingmethods.Retrievedfrom/futuresin/ar-is-elevating-the-playing-field-for-sports-by-creating-smarter-training-methods-77db01a84d64
coachescando.Third,playersarenotsurethepracticeisexecutedperfectly.Peoplealsosometimesforgothowmanyshotsthey’vemade.
Threesolutionshavebeengivenout:First,A3ddiagramofyourplayscanhelpuserstoquantifytheirperformance.ThenAIDeeplearningcangiveyouadviceasgoodasacoachdoesorevenbetter.Finally,Asmartphonecamera-basedreal-timesystemcanrecordyourplayswithnomistakes.
Astheresultoftheproblemsolutions,HoopLabidentified3specificdesigngoalsthatareusedtoprototype:
Friendlytouse
Createanexperiencethatuserscanenjoy.Userscancustomizetheir3davatarandpickupfavoriteclothandhaircutsforit.Theavatarwillberiggedandmotioncapturedbyusersasawaytounderstandyourshootingmovement.
Easytounderstand
A360degrees3Ddiagramwillbegeneratedaccordingtotheplayrecording.Itisabletoturnyourstillcamerarecordinginto3dversionenvironment.TheAIwillcalculatethedistancebetweenobjects(player-player,shooter-hoop,defender-ball)
Convenienttorecord
Theuseronlyneedsasmartphonecameratodothebasicfunction.Usingasmartwatchtounlockadvancedfeatures.
Afterthreeroundsofprototyping,thecorrespondinginterfacelo-fiwireframesaredesigned.Basedonthoseinteractionwireframes,theoutputoftheUIvisualwireframeisfinallycompleted.ApromovideothatcombinedUIelementsandapplicationfunctionsisalsobemade.
Agamedesigntheoryisalsobroughtinforthissystem.Userscanearncoinsbyfinishingthetasks.Thentheycanusegamecoinstounlockavatarsandnewadvancedtasks.Thecirculareconomyisformedinthisprocess.
Ithinktherewillbesustainableiterationstoevaluatemyproposal.Atphaseone,whichistheinitialstateofaproduct,alargenumberofA/Btestswillbegiventotheusers.AccordingtotheA/Btestresultsthatwecollect,itcanbedecidedwhichfeatureisbetterforusers.Inphasetwo,theproductstartstooperatesmoothly,thenplentyofdatacanbeanalyzedbymachinelearning.DuetoAI,wecandecidewhatnewfeaturesthatmaysatisfyusersshouldbebuiltfurther.
Conclusion
It’sdifficulttoquantifytheexperienceofthesystem.Ifthesystemcouldpresentacustomizedtrainingplanfortheuserandcreateavirtual3denvironmentofarealcourtthattheplayerdoesn’tfeelstrangeaboutit,thisdesignwillbeasatisfiedsolution.
However,withthelimitofreal-timerendertechnologyandhardwarehashingpower,itisstillimpossibletoimplementanapplicationlikethisinamobilephone.ThisprojectisanapproachthatrepresentsonepossibilityofwhatAIalgorithmscandoforsportsgames.
AppendixA:ExpandedThesisDefensePresentation
Initialdesign
Designintension
溫馨提示
- 1. 本站所有資源如無特殊說明,都需要本地電腦安裝OFFICE2007和PDF閱讀器。圖紙軟件為CAD,CAXA,PROE,UG,SolidWorks等.壓縮文件請(qǐng)下載最新的WinRAR軟件解壓。
- 2. 本站的文檔不包含任何第三方提供的附件圖紙等,如果需要附件,請(qǐng)聯(lián)系上傳者。文件的所有權(quán)益歸上傳用戶所有。
- 3. 本站RAR壓縮包中若帶圖紙,網(wǎng)頁內(nèi)容里面會(huì)有圖紙預(yù)覽,若沒有圖紙預(yù)覽就沒有圖紙。
- 4. 未經(jīng)權(quán)益所有人同意不得將文件中的內(nèi)容挪作商業(yè)或盈利用途。
- 5. 人人文庫網(wǎng)僅提供信息存儲(chǔ)空間,僅對(duì)用戶上傳內(nèi)容的表現(xiàn)方式做保護(hù)處理,對(duì)用戶上傳分享的文檔內(nèi)容本身不做任何修改或編輯,并不能對(duì)任何下載內(nèi)容負(fù)責(zé)。
- 6. 下載文件中如有侵權(quán)或不適當(dāng)內(nèi)容,請(qǐng)與我們聯(lián)系,我們立即糾正。
- 7. 本站不保證下載資源的準(zhǔn)確性、安全性和完整性, 同時(shí)也不承擔(dān)用戶因使用這些下載資源對(duì)自己和他人造成任何形式的傷害或損失。
最新文檔
- 學(xué)校教學(xué)群管理制度
- 學(xué)校電設(shè)備管理制度
- 學(xué)校鋼琴室管理制度
- 學(xué)生助教團(tuán)管理制度
- 學(xué)科實(shí)驗(yàn)室管理制度
- 安全與責(zé)任管理制度
- 安全設(shè)施室管理制度
- 實(shí)訓(xùn)室部門管理制度
- 審計(jì)局財(cái)務(wù)管理制度
- 客餐廳配電管理制度
- 建行反洗錢應(yīng)急預(yù)案
- 路燈養(yǎng)護(hù)投標(biāo)方案(技術(shù)方案)
- 國(guó)家開放大學(xué)電大本科《管理英語4》期末試題題庫及答案(試卷號(hào):1389)
- 詢價(jià)投標(biāo)文件(范本)
- 去小學(xué)化家長(zhǎng)培訓(xùn)講座課件
- 單光纖光鑷數(shù)值仿真和光阱力計(jì)算的中期報(bào)告
- 一份完整的鹵菜店創(chuàng)業(yè)計(jì)劃書 工作計(jì)劃
- 手術(shù)物品清點(diǎn)手術(shù)室護(hù)理實(shí)踐指南課件
- 中國(guó)鋁業(yè)股份有限公司偃師市東溝鋁土礦礦山地質(zhì)環(huán)境保護(hù)與土地復(fù)墾方案
- 2023-2024學(xué)年河南省濮陽市小學(xué)語文五年級(jí)期末通關(guān)考試題附參考答案和詳細(xì)解析
- 國(guó)語經(jīng)典歌曲歌詞接龍考試題庫(180題)
評(píng)論
0/150
提交評(píng)論