期刊文献+

基于连接点的3D多角弧匹配 被引量:3

Matching 3D Polygonal Arcs Based on Junctions
下载PDF
导出
摘要 为了满足实际应用的要求 ,快速地进行多角弧匹配是必要的 ,因此 ,提出了一种快速的 3D多角弧表示和匹配的方法。该方法是在分析多角弧几何形状基础上 ,引入连接点的概念 ,同时 ,通过在连接点处建立局部直角坐标系来得到每一连接点处的球面坐标。并用连接点的球面坐标集表示多角弧 ,因这一表示在旋转和平移变换下是不变的 ,所以可取该球面坐标集作为多角弧匹配的特征集 ,用该特征集可保持多角弧的几何属性和拓扑结构。这样3D多角弧匹配就降为 1D数值串匹配 ,从而使使匹配变得简单快速。其测量函数为对应连接点间的均方差。实验结果表明 ,该匹配算法效果良好 ,并且对于数值污染具有健壮性。 For realistic application, near real time matching 3D polygonal arcs is required. The method for representing and matching 3D polygonal arcs is presented., in this paper. The polygonal arcs junction is defined. 3D polygonal arcs are represented by Spherical coordinates sets that are obtained by defined local Cartesian coordinates system of each junction. This representation is invariant to translation and rotation transformation. The set is views as feature sets. The benefits of using this feature sets include attribute of geometry and structure of topology of polygon. The 3D polygonal arcs matching task is reduce into a 1D numerical string-matching problem so that the matching is easy and the processing time is greatly saved. The objection function is defined as the mean square errors between the feature sets. Experiments with different classes polygonal arcs and real images show that the matching algorithm produces sufficiently reliable and is robust to digitization errors and noise effects.
出处 《中国图象图形学报(A辑)》 CSCD 北大核心 2004年第5期584-588,共5页 Journal of Image and Graphics
基金 国家自然科学基金项目 ( 60 3 72 0 72 ) 陕西省教育厅专项基金项目 ( 0 3 JK15 5 )
关键词 连接点 3D多角弧匹配 1D数值串匹配 数值污染 计算机视觉 特征集 computer vision, polygonal arcs, junction, feature sets, representation, matching
  • 相关文献

参考文献10

  • 1Douglas R Heisterkamp, Prabir Bhattacharya. Matching 2D polygonal arcs by using a subgroup of the unit quaternion[J].Computer Vision and Image Understanding, 1998,69 (2):246-249.
  • 2黄良明,彭立中,程民德.利用几何代数进行线段模型匹配和运动估计[J].中国图象图形学报(A辑),2001,6(3):270-274. 被引量:11
  • 3Parsi B,Margalit A,Rosenfeld A.Matching general polygonal arcs[J].Computer Vision,Graphics and Image Process~ng,Image Understanding,1991,53(2):227~234.
  • 4Theodosios Pavlidis.The use of a syntactic shape analyzer for contour matching [J].IEEE Transactions on.Pattern Analysis and Machine Intelligence,1979,1(3):307~310.
  • 5Ross Beveridge J, Riseman Edward M. How easy is matching 2D line models using local search? [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(6): 564-579.
  • 6Zhan Zheng-you. Estimating motion and Structure from Correspondences of line Segments between two perspective Image [J],IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995,17(12):1129-1139.
  • 7Shen Xin-quan, Palme Philr. Uncertainty propagation and the matching of junction as feature groupings [J]. IEEE Transactions on. Pattern Analysis and Machine Intelligence, 2000, 22 (12):1381-1395.
  • 8Eyal Kishon,Trevor Hastie, Haim Wolfson. 3-Dcurve matching using splines[J]. Journal of Robotic Systems, 1991,8(6): 723-743.
  • 9Mather A, Farhad Kamangar. Planar curve representation and matching [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995,6 (2) : 167-174.
  • 10Wang Guo-jin, Wang Guo-zhao. Computer aided geometric design EMT- Beijing: China Higher Education press, Verlag Berlin Heidelberg : Springer press, 2001.

二级参考文献1

  • 1封举富.计算机视觉中若干问题的研究(博士研究生学位论文)[M].北京:北京大学,1997..

共引文献10

同被引文献28

  • 1茹少峰,周明全,耿国华.基于遗传算法的多边形逼近3D数字曲线[J].计算机辅助设计与图形学学报,2004,16(4):503-507. 被引量:9
  • 2茹少峰,贾建,周明全.基于连接点的二维多角弧匹配[J].中国图象图形学报(A辑),2003,8(4):464-467. 被引量:3
  • 3张志刚,周明全.一种轮廓曲线的多边形近似算法[J].计算机应用,2006,26(3):577-578. 被引量:10
  • 4李春龙,周明全,成欣,程日彬.轴对称破碎文物的虚拟复原方法[J].计算机辅助设计与图形学学报,2006,18(5):620-624. 被引量:13
  • 5周术诚,耿国华,周明全.三维破碎物体多尺度拼接技术[J].计算机辅助设计与图形学学报,2006,18(10):1525-1530. 被引量:10
  • 6KISHON E, HASITE T, WOFSON H. 3-D Curve Matching Using Splines [ J ]. Journal of Robotic Systems, 1991,8(6) :723-743.
  • 7COHEN F S, HUANG Zhao-hui, YANG Zheng-wei. Invariant matching and identification of curves Using B-splines curve representation [ J ], IEEE transactions on Image Processing, 1995,4( 1 ) :1-10.
  • 8BOLLES R C,CAIN R.A. Recognizing and locating partially visible objects : The local-feature-focus method [ J ].The International Journal of Robotics Research, 1982,1 :57 -82.
  • 9BESL P J, JAIN R C. Three-dimensional object recognition [ J ]. ACM Computing Surveys, 1986,18:67-108.
  • 10TSCHWARTZ J, SHARI M. Identification of partially obscured objets in two or three dimensions by matching of noisy characteristic curves [ J ]. The International Journal of Robotics Research, 1987,6:29-44.

引证文献3

二级引证文献16

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部