预览加载中，请您耐心等待几秒...

基于光流和特征点匹配相融合的低动态载体速度计算方法（英文）.docx

预览
1/3
2/3
3/3

在线预览结束，喜欢就下载吧，查找使用更方便

下载提示 文本预览

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

基于光流和特征点匹配相融合的低动态载体速度计算方法（英文） Title:CalculationMethodforLow-DynamicCarrierVelocityBasedonFusionofOpticalFlowandFeaturePointMatching Abstract Inordertoaccuratelycalculatethevelocityoflow-dynamiccarrier,acalculationmethodbasedonthefusionofopticalflowandfeaturepointmatchingisproposed.Firstly,opticalflowalgorithmisusedtoobtainthecoarsevelocityestimation,whichcanprovideaninitialvalueforfeaturepointmatching.Then,featurepointmatchingalgorithmisusedtoobtainaccurateandrobustvelocityestimationbyutilizingtheadvantagesofboththealgorithms.Finally,thevelocityestimationisfilteredtoobtainasmoothandaccuratevelocityestimation.Theproposedmethodhasbeentestedandcomparedwithothermethods,andtheexperimentalresultsshowthatithashighaccuracyandrobustness. Keywords:low-dynamiccarrier,velocityestimation,opticalflow,featurepointmatching,fusion Introduction Velocityestimationisanimportanttaskinmanyapplications,suchasvehiclenavigation,sportsanalysis,andsurveillancesystems.However,itischallengingtoestimatethevelocityaccuratelyforlow-dynamiccarriers,suchaswalkinghuman,crawlingrobotandflyinginsect,duetothesmallmotionandcomplexenvironment.Manymethodshavebeenproposedtosolvethisproblem,includingopticalflowandfeaturepointmatching.Opticalflowalgorithmisaclassicmethodforvelocityestimation,whichmeasuresthemotionbetweentwoconsecutiveframesbycalculatingthedisplacementofeachpixel.However,thismethodisnotrobusttoocclusions,texturelessregionsandbrightnesschange.Featurepointmatchingalgorithmisanotherpopularmethod,whichdetectsandtracksthedistinctivepointsinthesceneandestimatethemotionbymatchingthecorrespondencesbetweenthepointsinconsecutiveframes.Thismethodisrobusttoocclusionsandtexturelessregions,butsensitivetonoiseandoutlierpoints.Toovercomethelimitationsofbothmethods,afusionmethodthatintegratesopticalflowandfeaturepointmatchingisproposedinthispaper. Methodology Theproposedmethodconsistsofthreesteps:opticalflowestimation,featurepointmatchingandvelocityfiltering.Figure1showstheflowchartofthemethod. Step1:Opticalfl