Registration accuracy is influenced by the presence of outliers and numerous robust solutions have been developed over the years to mitigate their effect. However, without a large scale comparison of solutions to filter outliers, it is becoming tedious to select an appropriate algorithm for a given application. This paper presents a comprehensive analyses of the effects of outlier filters on the ICP algorithm aimed at mobile robotic application. Fourteen of the most common outlier filters (such as M-estimators) have been tested in different types of environments, for a total of more than two million registrations. Furthermore, the influence of tuning parameters have been thoroughly explored. The experimental results show that most outlier filters have similar performance if they are correctly tuned. Nonetheless, filters such as Var. Trim., Cauchy, and Cauchy MAD are more stable against different environment types. Interestingly, the simple norm L1 produces comparable accuracy, while been parameterless.
Evaluation of Robust Point Set Registration Applied to Automotive Doppler Radar
Faculty of Computer Science(计算机科学学院);Faculty of Electrical Engineering and Information Technology(电气工程与信息技术学院);Chair of Automation Technology(自动化技术教研室)
IRON: Invariant-based Highly Robust Point Cloud Registration
East China University of Science and Technology(华东理工大学)
在本文中,我们提出了IRON(基于不变量的全局鲁棒估计和优化),一个非最小的和高度鲁棒的解决方案,点云配准与大量的离群点之间的对应关系。为了实现这一点,我们将配准问题解耦为尺度、旋转和平移的估计。我们的第一个贡献是提出了RANSIC(RANdom Samples with Invariant Compatibility),它利用不变相容性从随机样本中寻找内点,同时鲁棒地估计两组点云之间的尺度。一旦规模估计,我们的第二个贡献是放松到一个凸半定规划(SDP)的非凸全局注册问题,在可证明的方式使用平方和(SOS)松弛,并表明放松是紧的。对于鲁棒估计,我们进一步提出了RT-GNC(粗修剪和分级非凸性),一个全局离群拒绝启发式具有更好的鲁棒性和时间效率比传统的GNC,作为我们的第三个贡献。有了这些贡献,我们可以呈现我们的配准算法IRON。通过在真实数据集上的实验,我们证明了IRON是高效的,高度准确的,并且对多达99%的离群值具有鲁棒性,无论规模是已知的还是未知的,都优于现有的最先进的算法。
ICOS: Efficient and Highly Robust Rotation Search and Point Cloud Registration with Correspondences
East China University of Science and Technology(华东理工大学)
旋转搜索和点云配准是机器人学和计算机视觉中的两个基本问题,其目的分别是估计三维矢量集和点云之间的旋转和变换。由于在实际应用中,在假定的向量或点对应关系中可能存在大量的离群值,鲁棒估计非常重要。在本文中,我们提出了ICOS(Inlier searching using Compatible Structures),一种新颖的,高效的和高度鲁棒的求解器,用于基于对应的旋转搜索和点云配准问题。具体来说,我们(i)提出并构建了一系列兼容的结构,可以建立各种不变量的两个问题,和(ii)设计三个时间效率的框架,第一个旋转搜索,第二个已知规模的注册和第三个未知规模的注册,过滤出离群值和寻找内点的不变量约束随机抽样的基础上提出的兼容结构。通过这种方式,即使有极端的离群值比率,也可以筛选出并收集内点,以有效地解决最佳旋转和变换,从而产生我们强大的求解器ICOS。通过对标准数据集的大量实验,我们证明:(i)我们的求解器ICOS快速,准确,鲁棒性超过95%的离群值,旋转搜索以及已知尺度和未知尺度配准的内点召回率接近100%,优于其他最先进的方法,(ii)ICOS适用于多种现实世界的应用。
GMCR: Graph-based Maximum Consensus Estimation for Point Cloud Registration
BMW Group(宝马集团);Technical University of Munich(慕尼黑工业大学);University of Glasgow(格拉斯哥大学);Donders Institute for Brain and Cognition, Radboud University(拉德堡德大学唐德斯脑与认知研究所)
Multi-Mapcher: Loop Closure Detection-Free Heterogeneous LiDAR Multi-Session SLAM Leveraging Outlier-Robust Registration for Autonomous Vehicles
Laboratory for Information & Decision Systems, Massachusetts Institute of Technology(信息与决策系统实验室,麻省理工学院);School of Electrical Engineering, KAIST(电气工程学院,韩国科学技术院)
Robust and Accurate Multi-view 2D/3D Image Registration with Differentiable X-ray Rendering and Dual Cross-view Constraints
Department of Information Science and Engineering, Shandong University(信息科学与工程学院,山东大学);School of Control Science and Engineering, Shangdong University(控制科学与工程学院,山东大学);Shenzhen Key Laboratory of Robotics Perception and Intelligence(机器人感知与智能实验室);Dept. of Electronic and Electrical Engineering, Southern University of Science and Technology(电子与电气工程系,南方科技大学);Dept. of Electronic Engineering, The Chinese University of Hong Kong(电子工程系,香港中文大学)
PARTE: Plane-Assisted Robust Transformation Estimation for Point Cloud Registration
Colorado School of Mines(科罗拉多矿业大学);University of Texas at Dallas(德克萨斯大学达拉斯分校);U.S. Army Combat Capabilities Development Command, Army Research Laboratory(美国陆军作战能力发展司令部陆军研究实验室)
KISS-Matcher: Fast and Robust Point Cloud Registration Revisited
Laboratory for Information & Decision Systems (LIDS), Massachusetts Institute of Technology(信息与决策系统实验室,麻省理工学院);The School of Electrical Engineering, KAIST(电气工程学院,韩国科学技术院);Dexory, UK(英国Dexory);Computer Science Engineering and Interdisciplinary Program of AI, Seoul National University(人工智能工程与跨学科项目,首尔国立大学)