首页|基于语义图和语义扫描上下文的激光点云两步重定位方法

基于语义图和语义扫描上下文的激光点云两步重定位方法

扫码查看
为更好解决基于同步定位与地图构建(SLAM)地图无人车的长期定位问题,提出一种基于语义图相似匹配与候选帧的语义扫描上下文描述符,通过粗、细两步定位实现对点云场景的重定位.首先,提取点云语义和几何特征,剔除移动、可移动类对象,通过融合语义信息和拓扑关系构建语义图,以图相似度计算实现快速重定位粗匹配;其次,通过全局语义迭代最近点(ICP)方法计算点云之间的相对偏航角和水平位移,为点云配准提供良好的初始值;最后,通过语义扫描上下文生成全局语义描述符,通过对比描述符判别点云相似性,完成精准重定位.实验结果表明:所提方法相较基于语义图的地点识别方法在地点识别精度、遮挡场景和视角变化场景下精度分别提升20.10%、20.90%和20.47%.
Two-Step Relocalization Method for Laser Point Clouds Based on Semantic Graph and Semantic Scan Context
This study proposes a creative method of semantic graph matching and semantic scan context descriptors of candidate frames to address the long-term localization issues in unmanned vehicle based on simultaneous localization and mapping maps.The relocalization of point cloud scenes is achieved through a two-step process,involving coarse and fine localization.First,semantic and geometric features are extracted from the point cloud,eliminating mobile and movable objects.Thus,a semantic graph is constructed by fusing semantic information and topological relationships,and rapid relocalization coarse matching is realized through graph similarity calculation.Then,the relative yaw and horizontal movement between point clouds are computed through global semantic iterative closest point,providing a well-initialized alignment.Finally,the global semantic descriptor is generated through semantic scan context,and accurate relocalization is obtained by comparing descriptors to distinguish point cloud similarity.Experimental results demonstrate that the proposed method achieves a 20.10%,20.90%,and 20.47%improvement in accuracy in place recognition,occluded scenes,and perspective change scenes,respectively,compared to the semantic graph-based place recognition method.

simultaneous localization and mappingrelocalizationsemantic graphsemantic scan contextpoint cloud registration

黄孝鸿、彭育辉、黄炜

展开 >

福州大学机械工程及自动化学院,福建 福州 350116

同步定位与地图构建 重定位 语义图 语义扫描上下文 点云配准

福建省引导性科技计划项目福建省自然科学基金

2022H00072021J01559

2024

激光与光电子学进展
中国科学院上海光学精密机械研究所

激光与光电子学进展

CSTPCD北大核心
影响因子:1.153
ISSN:1006-4125
年,卷(期):2024.61(18)
  • 3