This paper proposes \textit{Contour Context}, a simple, effective, and efficient topological loop closure detection pipeline with accurate 3-DoF metric pose estimation, targeting the urban utonomous driving scenario. We interpret the Cartesian birds' eye view (BEV) image projected from 3D LiDAR points as layered distribution of structures. To recover elevation information from BEVs, we slice them at different heights, and connected pixels at each level will form contours. Each contour is parameterized by abstract information, e.g., pixel count, center position, covariance, and mean height. The similarity of two BEVs is calculated in sequential discrete and continuous steps. The first step considers the geometric consensus of graph-like constellations formed by contours in particular localities. The second step models the majority of contours as a 2.5D Gaussian mixture model, which is used to calculate correlation and optimize relative transform in continuous space. A retrieval key is designed to accelerate the search of a database indexed by layered KD-trees. We validate the efficacy of our method by comparing it with recent works on public datasets.
翻译:本文建议 \ textit{ contour concern}, 是一个简单、有效和高效的表层环环闭检测管道, 准确的 3- DoF 度构成估计, 以城市自主驱动情景为对象。 我们从 3D LiDAR 点中将Cartesian 鸟类眼睛视图(BEV) 映射为结构的分层分布 。 要从 BEV 中恢复高地信息, 我们从不同高度切除它们, 在每个级别上连接像素, 将形成等离子。 每个等深线都通过抽象信息进行参数的参数化, 例如像像像像素计数、 中心位置、 变量和 平均高度等。 两个 BEV 的相似性是按相近的离心和连续步骤计算 。 第一步是考虑由特定地点的等离子组成的图形形星座星座的几何一致性 。 第二步模型是高斯 大部分 2.5D 混合模型, 用来计算相关性, 优化连续空间的相对变化 。 。 一个检索键是用来加速搜索数据库中以分层 KD 。 我们用最近的数据比较方法的有效性 。