首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于多视图SIFT特征的三维模型检索
引用本文:江秋鑫,华顺刚,时树胜.基于多视图SIFT特征的三维模型检索[J].光电技术应用,2011,26(4):56-60,80.
作者姓名:江秋鑫  华顺刚  时树胜
作者单位:1. 大连理工大学机械工程学院,辽宁大连,116024
2. 大连理工大学教务处,辽宁大连,116024
基金项目:国家部委预研项目(40401010105)
摘    要:研究了一种基于多视图SIFT特征的三维模型检索算法。首先对三维模型进行多视图投影,得到其余方位的三维投影深度图,并在各投影深度图上提取SIFT特征。分别利用按模型特征数比例分次建立码本及建立模型库整体码本这两种方式建立了模型库的码本,继而将模型的SIFT特征聚类量化,并用一个多维向量将其表示出来。通过计算三维模型特征向...

关 键 词:三维模型检索  SIFT特征  k-means  多视图投影

Multi-View 3D Retrieval Using SIFT Feature
JIANG Qiu-xin,HUA Shun-gang,SHI Shu-sheng.Multi-View 3D Retrieval Using SIFT Feature[J].Electro-Optic Technology Application,2011,26(4):56-60,80.
Authors:JIANG Qiu-xin  HUA Shun-gang  SHI Shu-sheng
Institution:JIANG Qiu-xin1,HUA Shun-gang1,SHI Shu-sheng2(1.School of Mechanical Engineering,Dalian University of Technology,Dalian 116024,China,2.Teaching Affairs Division,China)
Abstract:A 3D model retrieval algorithm based on multi-view scale invariant feature transform(SIFT) feature is researched.By carrying on the multi-view projection of a 3D model,the omnidirectional 2D projection depth maps are obtained,from which SIFT features are extracted.Individual-k-means and Whole-k-means are used to establish the codebook for shape benchmark respectively.Using the feature quantization codebook,all the features are clustered and generated the histogram as the 3D model feature vector.The similari...
Keywords:3D retrieval  scale invariant feature transform(SIFT)feature  k-means  multi-view projection  
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号