arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.00744cs.CVcs.RO
收藏

DSLO:基于不一致时空传播的深度序列激光雷达里程计

DSLO: Deep Sequence LiDAR Odometry Based on Inconsistent Spatio-temporal Propagation

Shanghai Jiao Tong University(上海交通大学);UC Berkeley(加州大学伯克利分校);University of Cambridge(剑桥大学)

Huixin Zhang, Guangming Wang, Xinrui Wu, Chenfeng Xu, Mingyu Ding, Masayoshi Tomizuka, Wei Zhan, Hesheng Wang

AI总结:

DSLO 提出基于不一致时空传播的深度序列激光雷达里程计模型,通过空间特征复用、序列位姿初始化、门控分层位姿细化和时间特征传播,在 KITTI 和 Argoverse 数据集上显著提升了位姿估计精度并降低了运行时间。

摘要:

本文提出了一种基于不一致时空传播的三维点云序列学习模型,用于激光雷达里程计,称为 DSLO。该模型由具有空间信息复用策略的金字塔结构、序列位姿初始化模块、门控分层位姿细化模块和时间特征传播模块组成。首先,利用点特征金字塔编码空间特征,并在连续的位姿估计中复用特征以减少计算开销。其次,引入序列位姿初始化方法,利用激光雷达的高频采样特性来初始化激光雷达位姿。然后,提出门控分层位姿细化机制,通过基于门控估计选择性地保留或丢弃来自不同层的运动信息,从粗到细地细化位姿。最后,提出时间特征传播方法,以融合点云序列中的历史运动信息,并解决在帧间传递嵌入点云的运动信息时的空间不一致问题。在 KITTI 里程计数据集和 Argoverse 数据集上的实验结果表明,DSLO 优于最先进的方法,在 RTE 上至少实现了 15.67% 的提升,在 RRE 上至少实现了 12.64% 的提升,同时与基线方法相比运行时间减少了 34.69%。我们的实现将在 https://github.com/IRMVLab/DSLO 上公开。

英文摘要:

This paper introduces a 3D point cloud sequence learning model based on inconsistent spatio-temporal propagation for LiDAR odometry, termed DSLO. It consists of a pyramid structure with a spatial information reuse strategy, a sequential pose initialization module, a gated hierarchical pose refinement module, and a temporal feature propagation module. First, spatial features are encoded using a point feature pyramid, with features reused in successive pose estimations to reduce computational overhead. Second, a sequential pose initialization method is introduced, leveraging the high-frequency sampling characteristic of LiDAR to initialize the LiDAR pose. Then, a gated hierarchical pose refinement mechanism refines poses from coarse to fine by selectively retaining or discarding motion information from different layers based on gate estimations. Finally, temporal feature propagation is proposed to incorporate the historical motion information from point cloud sequences, and address the spatial inconsistency issue when transmitting motion information embedded in point clouds between frames. Experimental results on the KITTI odometry dataset and Argoverse dataset demonstrate that DSLO outperforms state-of-the-art methods, achieving at least a 15.67\% improvement on RTE and a 12.64\% improvement on RRE, while also achieving a 34.69\% reduction in runtime compared to baseline methods. Our implementation will be available at https://github.com/IRMVLab/DSLO.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑