简介:Thispapershowsthemethodofestimatingspatiotemporaldistributionofpedestriansbyusingwatchcameras.Weestimatethedistributionwithouttrackingtechnology,withpedestrian’sprivacyprotectedandinUmedaundergroundmall.Latelyspatiotemporaldistributionofpedestrianshasbeingincreasinglyimportantinthefieldofurbanplanning,disasterpreventionplanning,marketingandsoon.Althoughmanyresearchershavetriedtocapturetheinformationoflocationasdealingwithsomesensors,someproblemsstillremain,suchastheinvestmentofsensors,therestrictionofthenumberofpeoplewhohasthedevicetheyareabletocapture.Fromsuchbackground,wedevelopanoriginallabellingalgorithmandestimatethespatiotemporaldistributionofpedestriansandtheinformationofthepassingtimeandthedirectionofpedestriansfromsequentialimagesofawatchcamera.
简介:Basedonthenichegeneticalgorithm,theintelligentandoptimizingmodelfortherollingforcedistributioninhotstripmillswasputforward.Theresearchshowedthatthemodelhadmanyadvantagessuchasfastsearchingspeed,highcalculatingprecisionandsuitingforon-linecalculation.Agoodstripshapecouldbeachievedbyusingthemodelanditisappropriateandpracticableforrollingproducing.