预览加载中，请您耐心等待几秒...

基于稀疏表示的高分辨距离像自动目标识别(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

基于稀疏表示的高分辨距离像自动目标识别(英文) SparseRepresentation-BasedHigh-ResolutionDistanceImageAutomaticTargetRecognition Abstract: Automatictargetrecognition(ATR)playsanimportantroleinvariousapplicationssuchasautonomousdriving,surveillance,andguidancesystems.Inthispaper,weproposeanovelapproachforATRusinghigh-resolutiondistanceimagesandsparserepresentation-basedclassification.Ourmethodfirstextractsfeaturesfromhigh-resolutiondistanceimagesandthenusessparserepresentation-basedclassificationtorecognizethetargets.Theproposedmethodachieveshighaccuracyinrecognizingtargetsindifferentscenarios,includingocclusionandclutter. Introduction: Automatictargetrecognition(ATR)isanimportanttaskinmanyapplicationssuchasautonomousdriving,surveillance,andguidancesystems.Itisachallengingtaskduetothecomplexityofthetargetsandthevariousenvironmentalconditions.TraditionalATRalgorithmsusehand-craftedfeaturesandmachinelearningalgorithmstorecognizetargets.However,duetothecomplexityofthetargetsandthevariabilityoftheenvironment,thesemethodshavelimitationsinaccuracyandgeneralizationability. Recentadvancesinsensortechnologyhaveledtothedevelopmentofhigh-resolutiondistanceimagingsystems,whichprovideaccuraterangeinformationofthetargets.Comparedwithtraditionalimagingsystems,high-resolutiondistanceimagingsystemscanovercomethelimitationsofocclusionandcluttercausedbytheinterferenceofdifferentobjectsinthescene.Therefore,high-resolutiondistanceimageshavebeenusedinvariousapplicationssuchasobjectdetectionandrecognition. Sparserepresentation-basedclassification(SRC)isapromisingmethodforATRduetoitsabilitytorepresentsignalsusingasetoflinearlyindependentbasisfunctions.SRChasbeenshowntoachievehighaccuracyinvariousapplicationssuchasfacerecognitionandobjectrecognition.Inthispaper,weproposeanovelapproachforATRusinghigh-resolutiondistanceimagesandSRC. Methodology: Ourproposedmethodconsistsoftwomainsteps,featureextraction,andclassification.Inthefeatureextractionstep,wefirstobtainhigh-resolutiondistanceimagesusingatime-of-flightcameraora