A Maximum Feasible Subsystem for Globally Optimal 3D Point Cloud Registration.

A Maximum Feasible Subsystem for Globally Optimal 3D Point Cloud Registration.
复制标题

DOI:
10.3390/s18020544
复制
发表时间:
2018-02-10
期刊:
Sensors (Basel, Switzerland)
影响因子:
--
通讯作者:
Ju DY
Ju DY
中科院分区:
其他
文献类型:
--
作者:
Yu C;Ju DY

文献摘要

参考文献

被引文献

相似文献

本文提出了一种基于最大可行子系统框架的全局最优点云数据稳健配准算法。配准问题是一个混合整数线性规划的分支定界问题。在两组范围数据之间的三维(3D)特征的假定匹配中,该算法在存在不正确匹配的情况下找到几何正确对应的最大数量,并且以全局最优的方式估计变换参数。优化不需要初始化变换参数。实验结果表明,该算法比现有的配准方法更准确和可靠,并对严重的离群值/失配表现出鲁棒性。这种全局优化技术非常有效,即使数据集之间的几何重叠非常小。
In this paper, a globally optimal algorithm based on a maximum feasible subsystem framework is proposed for robust pairwise registration of point cloud data. Registration is formulated as a branch-and-bound problem with mixed-integer linear programming. Among the putative matches of three-dimensional (3D) features between two sets of range data, the proposed algorithm finds the maximum number of geometrically correct correspondences in the presence of incorrect matches, and it estimates the transformation parameters in a globally optimal manner. The optimization requires no initialization of transformation parameters. Experimental results demonstrated that the presented algorithm was more accurate and reliable than state-of-the-art registration methods and showed robustness against severe outliers/mismatches. This global optimization technique was highly effective, even when the geometric overlap between the datasets was very small.
DOI: 10.3390/s140405785
发表时间: 2014-03-25
期刊: Sensors (Basel, Switzerland)
影响因子: --
作者:
Alsadik B;Gerke M;Vosselman G;Daham A;Jasim L
通讯作者: Jasim L
使用多尺度局部特征识别 3D 点云中的对象
DOI: 10.3390/s141224156
发表时间: 2014-12-15
期刊: Sensors (Basel, Switzerland)
影响因子: --
作者:
Lu M;Guo Y;Zhang J;Ma Y;Lei Y
通讯作者: Lei Y
DOI: 10.1109/34.121791
发表时间: 1992-02-01
影响因子: 23.6
作者:
BESL, PJ;MCKAY, ND
通讯作者: MCKAY, ND
DOI: 10.1109/tpami.2006.213
发表时间: 2006-10-01
影响因子: 23.6
作者:
Mian, Ajmal S.;Bennamoun, Mohammed;Owens, Robyn
通讯作者: Owens, Robyn
DOI: 10.1007/bf01580665
发表时间: 1976-01-01
影响因子: 2.7
作者:
MCCORMICK, GP
通讯作者: MCCORMICK, GP