RadLoc：基于快速、鲁棒且轻量空间描述子的雷达 3-DoF 全局定位，跨多样环境场景
RadLoc: Radar-based 3-DoF Global Localization via Fast, Robust, and Lightweight Spatial Descriptor Across Diverse Environmental Scenarios
Hogyun Kim · Jiwon Choi · Jungwoo Lee · Younggun Cho
中文摘要
旋转雷达全局定位因对恶劣天气和挑战性环境的鲁棒性而受到关注，但许多研究只聚焦于地点识别或位姿估计等单个组件。该工作从整体视角审视基于雷达传感器的全局定位，提出 RadLoc——一条从地点识别到 3-DoF 位姿估计的快速、鲁棒、轻量端到端流水线。RadLoc 使用 1D CA-CFAR 滤波加速预处理，并利用旋转雷达图像中的近距主导特性设计紧凑描述子和高效的分层由粗到细检索策略。结合基于相位相关的 3-DoF 位姿估计，它构成可适用于 SLAM 和多会话 SLAM 系统的通用全局定位模块。在 5 个数据集、15 个序列上的大量实验表明，RadLoc 在保持鲁棒性能的同时，相比现有最先进方法具有最小的描述子尺寸和最快的检索时间。补充材料见 https://sparolab.github.io/research/radloc/。
关键要点
- 01现有雷达全局定位研究多聚焦地点识别或位姿估计等单个组件，缺少端到端整体方案。
- 02用 1D CA-CFAR 滤波加速预处理，并利用近距主导特性设计紧凑描述子与分层由粗到细检索。
- 03结合相位相关实现 3-DoF 位姿估计，可接入 SLAM 与多会话 SLAM 系统。
- 04在 5 个数据集 15 个序列上验证，描述子尺寸最小、检索时间最快且性能鲁棒。
解读
尚无解读。
原始英文摘要
arXiv:2607.08115v2 Announce Type: replace Abstract: While global localization using spinning radar has gained attention for its robustness to adverse weather and challenging environments, many studies have focused on individual components such as place recognition or pose estimation. In this paper, we take a holistic view of radar sensor-based global localization and present RadLoc, a fast, robust, and lightweight end-to-end pipeline from place recognition to 3-DoF pose estimation. RadLoc accelerates pre-processing using 1D CA-CFAR filtering and leverages the near-range dominance in spinning radar images to design a compact descriptor and an efficient hierarchical coarse-to-fine retrieval strategy. Moreover, coupled with phase correlation-based 3-DoF pose estimation, it forms a versatile global localization module applicable to SLAM and multi-session SLAM systems. Extensive experiments on 15 sequences across 5 datasets demonstrate that RadLoc achieves robust performance while maintaining the smallest descriptor size and fastest retrieval time among state-of-the-art approaches. The supplementary materials are available at https://sparolab.github.io/research/radloc/.