LiDAR-based localization approach is a fundamental module for large-scale navigation tasks, such as last-mile delivery and autonomous driving, and localization robustness highly relies on viewpoints and 3D feature extraction. Our previous work provides a viewpoint-invariant descriptor to deal with viewpoint differences; however, the global descriptor suffers from a low signal-noise ratio in unsupervised clustering, reducing the distinguishable feature extraction ability. We develop SphereVLAD++, an attention-enhanced viewpoint invariant place recognition method in this work. SphereVLAD++ projects the point cloud on the spherical perspective for each unique area and captures the contextual connections between local features and their dependencies with global 3D geometry distribution. In return, clustered elements within the global descriptor are conditioned on local and global geometries and support the original viewpoint-invariant property of SphereVLAD. In the experiments, we evaluated the localization performance of SphereVLAD++ on both public KITTI360 datasets and self-generated datasets from the city of Pittsburgh. The experiment results show that SphereVLAD++ outperforms all relative state-of-the-art 3D place recognition methods under small or even totally reversed viewpoint differences and shows 0.69% and 15.81% successful retrieval rates with better than the second best. Low computation requirements and high time efficiency also help its application for low-cost robots.
翻译:以 LiDAR 为基础的本地化方法是大型导航任务的基本模块, 如最后一英里的交付和自主驱动, 以及本地化强度高度依赖于视图和 3D 特征提取。 我们先前的工作为处理观点差异提供了一个视图内变量描述符; 然而, 全球描述符在不受监督的组合中受到低信号- 噪音比率的影响, 降低了可辨别的特征提取能力。 我们开发了 SphereVLAD+++, 这是一种在这项工作中, 关注增强的观点, 不同位置识别方法。 SpphereVLAD++ 将每个独特区域的球形视角的点云投射点云, 捕捉到本地特征及其与全球 3D 几度分布的依存关系。 反过来, 全球描述符内组合元素以本地和全球的组合为条件, 支持 SphereVLADAD 原始的观点- 变量。 在实验中, 我们评估了SphereVAD++在公共数据集和自生成数据集中, 包括来自 15VLAD 10 的低时间- AS ASl ASl ASl AS AS AS ASl ASl ASl ASl ASl ASl ASl ASl AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS ASl ASl AL ASl ASl AS SA AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA