Fast and Robust Registration of Partially Overlapping Point Clouds
Fast and Robust Registration of Partially Overlapping Point Clouds
复制标题
DOI：
10.1109/lra.2021.3137888
复制
发表时间：
2021-12
影响因子：
5.2
通讯作者：
Eduardo Arnold;Sajjad Mozaffari;M. Dianati
中科院分区：
文献类型：
--
作者：
Eduardo Arnold;Sajjad Mozaffari;M. Dianati
部分重叠点云的实时配准在自主车辆和多智能体SLAM的协作感知中有着新兴的应用。这些应用中的点云之间的相对平移高于传统的SLAM和里程计应用，这对对应关系的识别和成功配准提出了挑战。在本文中，我们提出了一种新的注册方法，部分重叠的点云，其中的对应关系是学习使用一个有效的逐点特征编码器，并使用基于图形的注意力网络细化。该注意力网络利用关键点之间的几何关系来改善具有低重叠的点云中的匹配。在推理时，通过样本一致性鲁棒地拟合对应关系来获得相对姿态变换。KITTI数据集和一个新的合成数据集，包括低重叠的点云位移高达30米进行评估。该方法在KITTI数据集上实现了与最先进方法相同的性能，并且在低重叠点云上优于现有方法。此外，所提出的方法实现了显著更快的推理时间，低至410 ms，比竞争方法快5到35倍。我们的代码和数据集可以在https://github.com/eduardohenriquearnold/fastreg上找到。
Real-time registration of partially overlapping point clouds has emerging applications in cooperative perception for autonomous vehicles and multi-agent SLAM. The relative translation between point clouds in these applications is higher than in traditional SLAM and odometry applications, which challenges the identification of correspondences and a successful registration. In this paper, we propose a novel registration method for partially overlapping point clouds where correspondences are learned using an efficient point-wise feature encoder, and refined using a graph-based attention network. This attention network exploits geometrical relationships between key points to improve the matching in point clouds with low overlap. At inference time, the relative pose transformation is obtained by robustly fitting the correspondences through sample consensus. The evaluation is performed on the KITTI dataset and a novel synthetic dataset including low-overlapping point clouds with displacements of up to 30 m. The proposed method achieves on-par performance with state-of-the-art methods on the KITTI dataset, and outperforms existing methods for low overlapping point clouds. Additionally, the proposed method achieves significantly faster inference times, as low as 410 ms, between 5 and 35 times faster than competing methods. Our code and dataset are available at https://github.com/eduardohenriquearnold/fastreg.