Object recognition and localization from 3D point clouds by maximum-likelihood estimation.
Object recognition and localization from 3D point clouds by maximum-likelihood estimation.
复制标题
DOI：
10.1098/rsos.160693
复制
发表时间：
2017-08
影响因子：
3.5
通讯作者：
Huntley JM
中科院分区：
文献类型：
--
作者：
Dantanarayana HG;Huntley JM
我们提出了一种基于最大似然分析的算法，用于从3D点云自动识别物体并估计其姿态。从深度图像分割的表面被用作特征，不像基于“兴趣点”的算法通常会丢弃这些数据。与6D Hough变换相比，它具有可忽略的存储器需求，并且与迭代最近点算法相比计算效率高。相同的方法适用于初始识别/姿态估计问题以及通过适当选择概率密度函数的分散的后续姿态细化。因此，这种统一的方法避免了这两个任务通常需要不同的算法。除了理论描述之外，还使用简单的2个自由度（d.f.）给出了一个例子，然后是一个完整的6 d.f.分析了由基于投影条纹的扫描仪采集的杂乱场景中的3D点云数据，结果表明RMS对准误差低至0.3 mm。
We present an algorithm based on maximum-likelihood analysis for the automated recognition of objects, and estimation of their pose, from 3D point clouds. Surfaces segmented from depth images are used as the features, unlike ‘interest point’-based algorithms which normally discard such data. Compared to the 6D Hough transform, it has negligible memory requirements, and is computationally efficient compared to iterative closest point algorithms. The same method is applicable to both the initial recognition/pose estimation problem as well as subsequent pose refinement through appropriate choice of the dispersion of the probability density functions. This single unified approach therefore avoids the usual requirement for different algorithms for these two tasks. In addition to the theoretical description, a simple 2 degrees of freedom (d.f.) example is given, followed by a full 6 d.f. analysis of 3D point cloud data from a cluttered scene acquired by a projected fringe-based scanner, which demonstrated an RMS alignment error as low as 0.3 mm.
登录
查看更多内容
DOI：
10.1364/josaa.14.003188
发表时间：
1997-12-01
影响因子：
1.9
作者：
Huntley, JM;Saldner, HO
通讯作者：
Saldner, HO
DOI：
10.1109/tpami.2005.188
发表时间：
2005-10-01
影响因子：
23.6
作者：
Mikolajczyk, K;Schmid, C
通讯作者：
Schmid, C
影响因子：
19.5
作者：
Yu, Tsz-Ho;Woodford, Oliver J.;Cipolla, Roberto
通讯作者：
Cipolla, Roberto
影响因子：
4.5
作者：
Greenspan, H;Goldberger, J;Ridel, L
通讯作者：
Ridel, L
DOI：
10.1109/tpami.2002.1008392
发表时间：
2002-06-01
影响因子：
23.6
作者：
Olson, CF
通讯作者：
Olson, CF