Point cloud registration is a fundamental task in many applications such as localization, mapping, tracking, and reconstruction. The successful registration relies on extracting robust and discriminative geometric features. Existing learning-based methods require high computing capacity for processing a large number of raw points at the same time. Although these approaches achieve convincing results, they are difficult to apply in real-world situations due to high computational costs. In this paper, we introduce a framework that efficiently and economically extracts dense features using graph attention network for point cloud matching and registration (DFGAT). The detector of the DFGAT is responsible for finding highly reliable key points in large raw data sets. The descriptor of the DFGAT takes these key points combined with their neighbors to extract invariant density features in preparation for the matching. The graph attention network uses the attention mechanism that enriches the relationships between point clouds. Finally, we consider this as an optimal transport problem and use the Sinkhorn algorithm to find positive and negative matches. We perform thorough tests on the KITTI dataset and evaluate the effectiveness of this approach. The results show that this method with the efficiently compact keypoint selection and description can achieve the best performance matching metrics and reach highest success ratio of 99.88% registration in comparison with other state-of-the-art approaches.
翻译:在本地化、绘图、跟踪和重建等许多应用中,云点登记是一项基本任务。成功注册取决于提取稳健和歧视性的几何特征。现有的学习方法要求同时处理大量原始点的高计算能力。虽然这些方法取得了令人信服的结果,但由于计算成本高,很难在现实世界中应用这些方法。在本文中,我们引入一个框架,利用点云匹配和登记(DFGAT)的笔记式关注网络,以高效和经济上提取密集的特征。DFGAT的探测器负责在大型原始数据集中找到高度可靠的关键点。DFGAT的描述器将这些关键点与其邻居结合,以提取不固定密度特征来准备匹配。图形关注网络使用关注机制来丰富点云之间的关系。最后,我们认为这是一个最佳的运输问题,使用Sinkhorn算法来找到正负匹配。我们对KITTI数据集进行彻底测试,并评估这一方法的有效性。结果显示,这一方法与99-GAT的紧凑关键点选择和描述方法能够实现最佳的进度对比。