| 基于网格Laplace的三维几何模型分割 |
| |
| 引用本文： | 杨 军,田振华,李龙杰,王小鹏.基于网格Laplace的三维几何模型分割[J].计算机科学,2015,42(5):295-299. |
| |
| 作者姓名： | 杨 军 田振华 李龙杰 王小鹏 |
| |
| 作者单位： | 1. 兰州交通大学电子与信息工程学院 兰州730070
2. 兰州交通大学自动化与电气工程学院 兰州730070 |
| |
| 基金项目： | 本文受国家自然科学基金(61462059),中国博士后科学基金资助 |
| |
| 摘 要： | 模型分割是模型分析的重要方法和手段.针对已有网格分割算法对姿态敏感和计算速度慢的问题,提出了一种基于网格Laplace和k-means聚类的三维几何模型分割算法.通过网格Laplace将三维模型从空域嵌入到谱空间中进行分析,得到了模型的归一化形式,克服了姿态变化对分割结果的影响,并极大地减少了计算时间,获得了视觉上有意义的分割结果.实验结果表明,本算法能快速有效地实现网格模型的正确分割,并对模型姿态的变化有较好的鲁棒性.
|
| 关 键 词： | 网格分割 网格Laplace k-means聚类 谱嵌入 鲁棒性 |
Segmentation of 3D Geometric Models Based on Mesh Laplace |
| |
| YANG Jun,TIAN Zhen-hu,LI Long-jie and WANG Xiao-peng.Segmentation of 3D Geometric Models Based on Mesh Laplace[J].Computer Science,2015,42(5):295-299. |
| |
| Authors: | YANG Jun TIAN Zhen-hu LI Long-jie and WANG Xiao-peng |
| |
| Affiliation: | School of Electronic and Information Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China,School of Automation and Electrical Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China,School of Electronic and Information Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China and School of Electronic and Information Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China |
| |
| Abstract: | Segmentation is one of important methods and means to analyze shapes.A novel algorithm for segmentation of 3D geometric models was proposed based on mesh Laplace and k-means cluster aiming at the problem that the exis-ting mesh segmentation algorithms are sensitive to shape pose and time-consuming.Models are converted from spatial domain to spectral domain by using mesh Laplace in order to obtain the normalized forms,which are analyzed in spectral domain to avoid influence of variation of shape pose to segmentation results and greatly reduce the computing time.Experimental results show that the proposed algorithm is not only more efficient for generating correct and meaningful segmentations,but also more robust to variation of shape pose than existing algorithms. |
| |
| Keywords: | Mesh segmentation Mesh Laplace k-means cluster Spectral embeding Robustness |
| 本文献已被 万方数据 等数据库收录！ |
|
点击此处可从《计算机科学》下载全文 |
|
