Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration
Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration
复制标题
Go-ICP：3D ICP 点集配准的全局最优解决方案
DOI：
10.1109/tpami.2015.2513405
复制
发表时间：
2016-11-01
影响因子：
23.6
通讯作者：
Jia, Yunde
中科院分区：
文献类型：
--
作者：
Yang, Jiaolong;Li, Hongdong;Jia, Yunde
迭代最近点 (ICP) 算法是最广泛使用的点集配准方法之一。然而，由于 ICP 基于局部迭代优化，因此容易受到局部最小值的影响。其性能严重依赖于初始化的质量，并且仅保证局部最优。本文提出了第一个全局最优算法，名为 Go-ICP，用于在 <inline-formula><tex-math notation="LaTeX">$L_2$</tex-math><alternatives> <inline-graphic xlink:type="simple" 下对两个 3D 点集进行欧几里德（刚性）配准 xlink:href="yang-ieq1-2513405.gif"/></alternatives></inline-formula> ICP 中定义的错误度量。 Go-ICP 方法基于分支定界方案，该方案搜索整个 3D 运动空间 <inline-formula> <tex-math notation="LaTeX">$SE(3)$</tex-math><alternatives> <inline-graphic xlink:type="simple" xlink:href="yang-ieq2-2513405.gif"/></alternatives></inline-formula>。通过利用 <inline-formula><tex-math notation="LaTeX">$SE(3)$</tex-math><alternatives> <inline-graphic xlink:type="simple" xlink:href="yang-ieq3-2513405.gif"/></alternatives></inline-formula> 几何形状的特殊结构，我们推导了配准误差的新颖上限和下限 功能。本地ICP集成到BnB方案中，在保证全局最优性的同时加快了新方法的速度。我们还讨论了扩展，解决了异常值的稳健性问题。评估表明，无论初始化如何，所提出的方法都能够产生可靠的配准结果。 Go-ICP 可应用于需要最佳解决方案或无法始终获得良好初始化的场景。
The Iterative Closest Point (ICP) algorithm is one of the most widely used methods for point-set registration. However, being based on local iterative optimization, ICP is known to be susceptible to local minima. Its performance critically relies on the quality of the initialization and only local optimality is guaranteed. This paper presents the first globally optimal algorithm, named Go-ICP, for Euclidean (rigid) registration of two 3D point-sets under the <inline-formula><tex-math notation="LaTeX">$L_2$</tex-math><alternatives> <inline-graphic xlink:type="simple" xlink:href="yang-ieq1-2513405.gif"/></alternatives></inline-formula> error metric defined in ICP. The Go-ICP method is based on a branch-and-bound scheme that searches the entire 3D motion space <inline-formula> <tex-math notation="LaTeX">$SE(3)$</tex-math><alternatives> <inline-graphic xlink:type="simple" xlink:href="yang-ieq2-2513405.gif"/></alternatives></inline-formula>. By exploiting the special structure of <inline-formula><tex-math notation="LaTeX">$SE(3)$</tex-math><alternatives> <inline-graphic xlink:type="simple" xlink:href="yang-ieq3-2513405.gif"/></alternatives></inline-formula> geometry, we derive novel upper and lower bounds for the registration error function. Local ICP is integrated into the BnB scheme, which speeds up the new method while guaranteeing global optimality. We also discuss extensions, addressing the issue of outlier robustness. The evaluation demonstrates that the proposed method is able to produce reliable registration results regardless of the initialization. Go-ICP can be applied in scenarios where an optimal solution is desirable or where a good initialization is not always available.