CORC  > 清华大学
结合突变论和离散聚类思想的视点空间划分算法
苏淼 ; 马惠敏 ; 李凤亭 ; SU Miao ; MA Huimin ; LI Fengting
2010-05-12 ; 2010-05-12
关键词三维目标识别 形态图 视点空间划分 符号序列 3-D object recognition aspect graph viewpoint space partition sequenced symbol TP391.41
其他题名Catastrophe theory and clustering algorithm besed viewpoint space partition algorithm
中文摘要针对视点空间划分问题中算法复杂以及计算复杂度大的问题,提出了一种结合突变论和离散聚类思想的新方法。利用突变论获得视觉事件的空间切割曲面方程,然后在视点空间球面上选取有序采样并计算每个样点的符号序列,通过对符号序列的判断实现对离散点的聚类,使用点集替代传统的边界线方程来表达视点空间分划结果。该方法避免了突变理论中求解视点空间分划线方程数值解以及从分划线相互关系中寻找闭合区域的过程。实验结果表明该方法能够有效地提高三维目标识别的实时性。; An efficient algorithm was developed for viewpoint space partitioning which incorporates both catastrophe theory and clustering. Analytical equations are given for all possible visual events (EV and EEE). Then, the viewpoint space is sampled in order and the sequenced symbols related to the analytical equations are calculated for every sample. Finally, samples with the same sequenced symbols are clustered into a region. The algorithm simplifies the identification of a region by using a cluster of points rather than the partitioned area boundary. The algorithm avoids the complexity of solving the analytical equations to obtain the boundaries and partition the viewpoint space using the boundaries. Experimental results shown in this paper demonstrate the algorithm's effectiveness and speed.
语种中文 ; 中文
内容类型期刊论文
源URL[http://hdl.handle.net/123456789/28160]  
专题清华大学
推荐引用方式
GB/T 7714
苏淼,马惠敏,李凤亭,等. 结合突变论和离散聚类思想的视点空间划分算法[J],2010, 2010.
APA 苏淼,马惠敏,李凤亭,SU Miao,MA Huimin,&LI Fengting.(2010).结合突变论和离散聚类思想的视点空间划分算法..
MLA 苏淼,et al."结合突变论和离散聚类思想的视点空间划分算法".(2010).
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace