Data from: Object recognition and localisation from 3D point clouds by maximum likelihood estimation

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 (ICP) 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 degree of freedom (DOF) example is given, followed by a full 6 DOF 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.我们提出了一种基于最大似然分析（maximum likelihood analysis）的算法，可从3D点云（3D point cloud）中自动识别物体并估计其位姿（pose）。该算法将从深度图像（depth image）中分割得到的表面作为特征，与通常会丢弃此类数据的基于兴趣点（interest point）的算法截然不同。相较于6D霍夫变换（6D Hough transform），本算法的内存占用可忽略不计；相较于迭代最近点（iterative closest point, ICP）算法，其计算效率更为高效。通过合理选择概率密度函数（probability density function）的离散程度，同一方法可同时适用于初始识别与位姿估计任务，以及后续的位姿精修环节。因此这种统一的单一方案，无需为这两项任务分别采用不同的算法。除理论阐述之外，本文还给出了一个简易的2自由度（degree of freedom, DOF）示例，随后针对由投影条纹式扫描仪（projected fringe-based scanner）采集的杂乱场景3D点云数据开展了完整的6自由度分析，实验结果显示该方法的均方根对齐误差（root mean square alignment error）最低可达0.3毫米。