| 基于3D活动轮廓模型的缺陷点云分割方法 |
| |
| 引用本文： | 莫堃,尹周平.基于3D活动轮廓模型的缺陷点云分割方法[J].华中科技大学学报(自然科学版),2011(1):82-85. |
| |
| 作者姓名： | 莫堃 尹周平 |
| |
| 作者单位： | 华中科技大学数字制造装备与技术国家重点实验室; |
| |
| 基金项目： | 国家自然科学基金资助项目(50835004,50625516) |
| |
| 摘 要： | 提出一种基于3D活动轮廓模型的缺陷点云自动分割方法,通过扩展数学形态学方法构造符号距离函数估算点云的平均曲率,并应用中值滤波方法去除点云噪声对曲率估算精度的影响,避免了点云的一致性法矢估算和三角网格重构,在保证点云分割精度的同时有效提高了计算效率.应用结果表明本文方法能够有效处理点云缺陷并实现大规模散乱点云的快速分割.
|
| 关 键 词： | 点云分割 活动轮廓模型 数学形态学 中值滤波 三角网格 |
Segmentation of defective point clouds using 3D active contour model |
| |
| Mo Kun Yin Zhouping.Segmentation of defective point clouds using 3D active contour model[J].JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY.NATURE SCIENCE,2011(1):82-85. |
| |
| Authors: | Mo Kun Yin Zhouping |
| |
| Institution: | Mo Kun Yin Zhouping(State Key Laboratory of Digital Manufacturing Equipment and Technology,Huazhong University of Science and Technology,Wuhan 430074,China) |
| |
| Abstract: | An efficient segmentation method of defective point clouds based on 3D active contour model was proposed,which extends the morphology operation to quickly construct signed distance function and employed median filter to reduce noise influence for curvature estimation.This approach can be performed without consistent normal or triangular mesh.It not only guarantees the segment accuracy but also increase the efficiency of segmentation.The industrial example demonstrates this method can reduce the defective in... |
| |
| Keywords: | point clouds segmentation active contour model mathematical morphology median filter triangular mesh |
| 本文献已被 CNKI 等数据库收录！ |
