Point sets non-rigid registration using student's-t mixture model with spatial constraints
文献类型：期刊论文
| 作者 | Zhang T.
|
| 刊名 | Zidonghua Xuebao/Acta Automatica Sinica
 |
| 出版日期 | 2014 |
| 卷号 | 40期号:4页码:683-696 |
| ISSN号 | ISBN/02544156 |
| 英文摘要 | A robust non-rigid registration framework using the student's-t mixture model with spatial constraints is proposed in this paper. The Gaussian mixture model which is vulnerable to outliers and data longer than normal tails is a special case of the student's-t mixture model in theory. The Dirichlet distribution is used as a prior distribution to reduce the impact of outliers. The Dirichlet parameter set with spatial constrains is structured to incorporate the spatial information into the decision process. The closed form solution of the parameter set of the student's-t mixture model is solved by re-parameterizing the student's-t mixture model in the expectation maximization (EM) algorithm. The degree of freedom of each moving point is calculated to change the probability density to reduce the registration error. It can also avoid estimating the outlier level of data sets that may bring additional error. The experiments showed that this non-rigid registration algorithm has features of high-accuracy and good robustness compared to other point set registration approaches. 2014 Acta Automatica Sinica. All rights reserved. |
| 收录类别 | EI |
| 语种 | 中文 |
| 公开日期 | 2015-05-27 |
| 源URL | [http://ir.ciomp.ac.cn/handle/181722/44275]  |
| 专题 | 长春光学精密机械与物理研究所_中科院长春光机所知识产出 |
| 推荐引用方式 GB/T 7714 | Zhang T.. Point sets non-rigid registration using student's-t mixture model with spatial constraints[J]. Zidonghua Xuebao/Acta Automatica Sinica,2014,40(4):683-696. |
| APA | Zhang T..(2014).Point sets non-rigid registration using student's-t mixture model with spatial constraints.Zidonghua Xuebao/Acta Automatica Sinica,40(4),683-696. |
| MLA | Zhang T.."Point sets non-rigid registration using student's-t mixture model with spatial constraints".Zidonghua Xuebao/Acta Automatica Sinica 40.4(2014):683-696. |
入库方式： OAI收割
浏览0
下载0
收藏0
其他版本
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。