论文标题
HITPR：层次变压器用于点云中的位置识别
HiTPR: Hierarchical Transformer for Place Recognition in Point Cloud
论文作者
论文摘要
位置识别或循环闭合检测是完整大满贯系统中的核心组件之一。在本文中，旨在加强本地相邻点的相关性和同时的全局点之间的上下文依赖性，我们研究了基于变压器的网络用于特征提取的利用，并提出了一个层次变压器以识别位置识别（HITPR）。 HITPR由四个主要部分组成：点细胞产生，短距离变压器（SRT），远程变压器（LRT）和全局描述符聚合。具体而言，最初通过下采样和最近的邻居搜索将点云分为小单元。在SRT中，我们提取每个点单元的局部特征。在LRT中，我们在整个点云中的所有点单元中构建了全局依赖性。几个标准基准的实验证明了HITPR在平均召回率方面的优越性，例如，在牛津Robotcar数据集中，在最高1％达到93.71％，在最高1％的最高率和86.63％。
Place recognition or loop closure detection is one of the core components in a full SLAM system. In this paper, aiming at strengthening the relevancy of local neighboring points and the contextual dependency among global points simultaneously, we investigate the exploitation of transformer-based network for feature extraction, and propose a Hierarchical Transformer for Place Recognition (HiTPR). The HiTPR consists of four major parts: point cell generation, short-range transformer (SRT), long-range transformer (LRT) and global descriptor aggregation. Specifically, the point cloud is initially divided into a sequence of small cells by downsampling and nearest neighbors searching. In the SRT, we extract the local feature for each point cell. While in the LRT, we build the global dependency among all of the point cells in the whole point cloud. Experiments on several standard benchmarks demonstrate the superiority of the HiTPR in terms of average recall rate, achieving 93.71% at top 1% and 86.63% at top 1 on the Oxford RobotCar dataset for example.
