Rotational Outlier Identification in Pose Graphs using Dual Decomposition
Rotational Outlier Identification in Pose Graphs using Dual Decomposition
复制标题
DOI：
10.1007/978-3-030-58577-8_24
复制
发表时间：
2020-08
期刊：
影响因子：
--
通讯作者：
Arman Karimian;Ziqi Yang;Roberto Tron
中科院分区：
文献类型：
--
作者：
Arman Karimian;Ziqi Yang;Roberto Tron
在过去的几年中，从位姿平均（计算机视觉中也称为全局 SfM）或位姿图优化（PGO，机器人学）的角度考虑运动结构（SfM，计算机视觉）和同步定位与建图（SLAM，机器人学）问题的趋势越来越明显，其中相机的运动通过仅考虑相对刚体变换来重建，而不是还包括 3-D 点（如在完整 Bundle 中所做的那样）调整）。从较高的层面来看，这种方法的优点是现代求解器可以有效地避免大多数局部极小值问题，并且更容易推断离群姿势（由图像中的特征不匹配和重复结构引起）。在本文中，我们提出了一种在位姿图优化之前通过检查旋转测量的几何一致性来检测不正确的方向测量的方法，为后者的最新技术做出了贡献。我们方法的新颖之处在于使用期望最大化来微调内点测量中噪声的协方差，以及一种具有独立兴趣的新近似图推理程序，该程序专门设计用于利用比标准方法（置信传播）性能更好的循环证据。该论文包括模拟和实验结果，用于评估我们的异常值检测和基于循环的推理算法对合成和真实数据的性能。
In the last few years, there has been an increasing trend to consider Structure from Motion (SfM, in computer vision) and Simultaneous Localization and Mapping (SLAM, in robotics) problems from the point of view ofpose averaging(also known asglobal SfM, in computer vision) orPose Graph Optimization(PGO, in robotics), where the motion of the camera is reconstructed by considering only relative rigid body transformations instead of including also 3-D points (as done in a full Bundle Adjustment). At a high level, the advantage of this approach is that modern solvers can effectively avoid most of the problems of local minima, and that it is easier to reason about outlier poses (caused by feature mismatches and repetitive structures in the images). In this paper, we contribute to the state of the art of the latter, by proposing a method to detect incorrect orientation measurements prior to pose graph optimization by checking the geometric consistency of rotation measurements. The novel aspects of our method are the use of Expectation-Maximization to fine-tune the covariance of the noise in inlier measurements, and a new approximate graph inference procedure, of independent interest, that is specifically designed to take advantage of evidence on cycles with better performance than standard approaches (Belief Propagation). The paper includes simulation and experimental results that evaluate the performance of our outlier detection and cycle-based inference algorithms on synthetic and real-world data.