简介:Blindrecognitionofconvolutionalcodesisnotonlyessentialforcognitiveradio,butalsofornon-cooperativecontext.Thispaperisdedicatedtotheblindidentificationofratek/nconvolutionalencodersinanoisycontextbasedonWalsh-Hadamardtransformationandblockmatrix(WHT-BM).Theproposedalgorithmconstructsasystemofnoisylinearequationsandutilizesallitscoefficientstorecoverparitycheckmatrix.Itisabletomakeuseoffault-tolerantfeatureofWHT,thusprovidingmoreaccurateresultsandachievingbettererrorperformanceinhighrawbiterrorrate(BER)regions.Moreover,itismorecomputationallyefficientwiththeuseoftheblockmatrix(BM)method.
简介:Thispaperconcernstheproblemofobjectsegmentationinreal-timeforpickingsystem.Aregionproposalmethodinspiredbyhumanglancebasedontheconvolutionalneuralnetworkisproposedtoselectpromisingregions,allowingmoreprocessingisreservedonlyfortheseregions.Thespeedofobjectsegmentationissignificantlyimprovedbytheregionproposalmethod.Bythecombinationoftheregionproposalmethodbasedontheconvolutionalneuralnetworkandsuperpixelmethod,thecategoryandlocationinformationcanbeusedtosegmentobjectsandimageredundancyissignificantlyreduced.Theprocessingtimeisreducedconsiderablybythistoachievetherealtime.Experimentsshowthattheproposedmethodcansegmenttheinterestedtargetobjectinrealtimeonanordinarylaptop.
简介:Synchronouschipsealisanadvancedroadconstructingtechnology,andthegravelcoveragerateisanimportantindicatoroftheconstructionquality.Inthispaper,anovelapproachforgravelcoverageratemeasurementisproposedbasedondeeplearning.Convolutionalneuralnetwork(CNN)isusedtosegmenttheimageofgroundcoveredwithgravels,andthegravelcoveragerateiscomputedbythepercentageofgravelpixelsinthesegmentedimage.Thegravelcoverageratedatasetformodeltrainingandtestingisbuilt.Theperformanceoffullyconvolutionalneuralnetwork(FCN)andU-Netmodelinthedatasetistested.AbettermodelnamedGravelNetisconstructedbasedonU-Net.Thescaledexponentiallinearunit(SELU)isemployedintheGravelNettoreplacethepopularcombinationofrectifiedlinearunit(ReLU)andbatchnormalization(BN).Dataaugmentationandalphadropoutareperformedtoreduceoverfitting.Theexperimentalresultsdemonstratetheeffectivenessandaccuracyofourproposedmethod.OurtrainedGravelNetachievesthemeangravelcoveragerateerrorof0.35%ontestdataset.