基于背景預(yù)測(cè)的紅外小目標(biāo)檢測(cè).pdf_第1頁
已閱讀1頁，還剩59頁未讀， 繼續(xù)免費(fèi)閱讀

下載本文檔

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

1、南京航空航天大學(xué)碩士學(xué)位論文基于背景預(yù)測(cè)的紅外小目標(biāo)檢測(cè)姓名：尹丹艷申請(qǐng)學(xué)位級(jí)別：碩士專業(yè)：信號(hào)與信息處理指導(dǎo)教師：吳一全201012基于背景預(yù)測(cè)的紅外小目標(biāo)檢測(cè)IIABSTRACTThedetectionofsmallinfraredtargetisthekeyprobleminareassuchasearlywarningsearchtrackinginfraredautomatichomingguidance.Howtoimpro

2、vethereliabilityaccuracyofsmalltargetdetectionhasmuchresearchsignificanceininfrareddetectionimaging.Onthebasisofintroducingdomesticfeigndevelopmentofsmalltargetdetectionthispaperstudiesthemethodsofsmallinfraredtargetdete

3、ctionbasedonbackgroundprediction.Themaintasksareasfollows:Firstlytwodetectionmethodsofsmallinfraredtargetarestudied.Oneisbasedondualtreecomplexwavelettransfm(DTCWT)supptvectregression(SVR).theotherisbasedonfuzzyleastsqua

4、ressupptvectmachines(FLSSVM).ThefmermethodsuppressesthenoiseininfraredimagebyDTCWTpredictsthebackgroundbySVR.thelatteroneadoptsFLSSVMtopredictthebackgroundofinfraredimage.Theexperimentalresultsshowthatbothmethodscandetec

5、tthesmallinfraredtargetaccuratelyhavehighdetectionprobability.Theirdetectionresultsarebetterthantheexistingmethodsofsmallinfraredtargetdetection.Secondlyadetectionmethodofsmalltargetininfraredimageusingnonsubsampledconto

6、urlettransfm(NSCT)kernelfuzzyCmeans(KFCM)clusteringmultimodelLSSVMisproposed.FirsttheinfraredimageisdenoisedbyNSCT.ThenthemultimodelLSSVMbasedonKFCMclusteringisadoptedtopredictthebackgroundofthedenoisedinfraredimage.Fina

7、llytherealsmalltagetisdetectedbysegmentingtheresidualimageusingthemotionacteristicsofsmalltarget.Theresultsshowthatthismethodhashigherdetectionprobabilitygainofsignaltonoiseratio(GSNR).Thirdlyadetectionmethodofsmallinfra

8、redtargetisproposedwhichisbasedonchaoticparticleswarmoptimization(CPSO)spartialtempalbackgroundpredictionbyleastabsolutedeviation.Firstamodelofspatialtempalbackgroundpredictionisbuilt.Accdingtopropertiesofleastabsolutede

9、viationtheextremevalueinleastabsolutedeviationisedbyCPSO.Thebackgroundininfraredimageispredictedbythismodelthesmalltargetisdetectedbysegmentingtheresidualimage.Theresultsshowthismethodissuperitothemethodofsmallinfraredta

10、rgetdetectionbasedonbackgroundpredicationbyleastsquares.Fourthlyadetectionmethodofsmallinfraredtargetbasedongraypredictionisrealized.TheGM(1.1)modelofgraysystemtheeyisadoptedtopredicttheinfraredimagebackgroundintimedomai

11、n.Thesmalltargetcanbedetectedbysegmentingtheresidualimage.Theexperimentalresultsshowthatthismethodcanachievelongrangesmalltargetdetection.Fifthlysomethresholdsegmentationalgithmsfthesmallinfraredtargetofresidualimageares

12、tudiedsuchasthethresholdionmethodbasedonfuzzyTsallisHavrdavat’sentropythethresholdionmethodbasedonrecursivemaximumbetweenclusterabsolutedifferenceatwodimensionalhistogramobliquesegmentationmethodbasedonCPSOfuzzymaximumen

13、tropy.Theresultsshowthatthethresholdedbythesemethodscanaccuratelysegmentthesmalltargetfrominfraredresidualimage.KeyWds:smallinfraredtargetdetectionsupptvectmachineskernelfuzzyCmeansclusteringgraypredictionleastabsolutede

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. 眾賞文庫僅提供信息存儲(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。

評(píng)論

0/150

提交評(píng)論