预览加载中,请您耐心等待几秒...
1/10
2/10
3/10
4/10
5/10
6/10
7/10
8/10
9/10
10/10

在线预览结束,喜欢就下载吧,查找使用更方便

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

计算机研究与发展ISSN10001239CN111777TPJournalofComputerResearchandDevelopment45(7):12491258,2008一种姿态无关的人体模型骨骼提取方法1,2,31,21,21,2,3于勇王兆其夏时洪毛天露1(中国科学院计算技术研究所虚拟现实技术实验室北京100190)2(中国科学院计算技术研究所智能信息处理重点实验室北京100190)3(中国科学院研究生院北京100049)(yyu@ict.ac.cn)PoseIndependentJointExtractionfromScannedHumanBodyYuYong1,2,3,WangZhaoqi1,2,XiaShihong1,2,andMaoTianlu1,2,31(VirtualRealityLaboratory,InstituteofComputingTechnology,ChineseAcademyofSciences,Beijing100190)2(KeyLaboratoryofIntelligentInformationProcessing,InstituteofComputingTechnology,ChineseAcademyofSciences,Beijing100190)3(GraduateUniversityofChineseAcademyofSciences,Beijing100049)AbstractWiththedevelopmentof3Dscanningtechnique,jointextractionfromscannedhumanbodymodelisoneofthemostactiveresearchareasinvirtualhumanmodeling.Manydifferentapproacheshavebeenproposedwiththeaimofextractingjointsfromscannedhumanbody.Butmostofthesemethodscannotguaranteeposeindependence,whileothermethodswhichcanensureposeindependencerequiremanualintervention.Tosolvethisproblem,anewframeworkispresentedforautomaticposeindependentjointextractionfromscannedhumanbody.Firstly,anewMorsefunctionisdefinedonthescannedhumanbodyshapeasgeodesicdistancefrompointstoasourcepointwhichcanbeextractedbyaheuristicmethod.Secondly,theMorsefunctioniscalculated,andthenfeaturepointsandtopologicalstructureofthemodelshapecanbeextractedautomaticallyaccordingtoMorsetheory.Finally,shapeisdividedintosegmentsbasedonMorsefunctionisolines,andjointscanbeextractedfromthecorrespondingsegmentsofthehumanbodyshapebyanalyzingthecircularityofMorsefunctionisolinesofthemodel.Experimentshavebeendoneon20scannedhumanbodieswithabout5000facesand2300pointsineachbodyshape.Theexperimentresultsdemonstratethatthismethodisaposeindependentandautomaticmethod,andismoreaccuratethanpreviousmethods.Keywordsvirtualhuman;skeletonextraction;Morsetheory;poseindependence;scannedmodel摘要随着三维扫描技术的逐渐成熟,三维人体扫描模型的骨骼提取逐渐成为虚拟人建模研究领域的热点之一.现有的三维人体模型骨骼提取方法,存在手工标注任务繁重、对模型姿态过于敏感、计算结果不准确等问题.提出了一种新的三维人体模型的骨骼提取算法:首先,根据M