6 papers
G3Reg: Pyramid Graph-based Global Registration using Gaussian Ellipsoid Model
Zhijian Qiao, Zehuan Yu, Binqian Jiang +2
This study introduces a novel framework, G3Reg, for fast and robust global registration of LiDAR point clouds. In contrast to conventional complex keypoints and descriptors, we ext…
Pyramid Semantic Graph-based Global Point Cloud Registration with Low Overlap
Zhijian Qiao, Zehuan Yu, Huan Yin +1
Global point cloud registration is essential in many robotics tasks like loop closing and relocalization. Unfortunately, the registration often suffers from the low overlap between…
Online Monocular Lane Mapping Using Catmull-Rom Spline
Zhijian Qiao, Zehuan Yu, Huan Yin +1
In this study, we introduce an online monocular lane mapping approach that solely relies on a single camera and odometry for generating spline-based maps. Our proposed technique mo…
Multi-Session, Localization-oriented and Lightweight LiDAR Mapping Using Semantic Lines and Planes
Zehuan Yu, Zhijian Qiao, Liuyang Qiu +2
In this paper, we present a centralized framework for multi-session LiDAR mapping in urban environments, by utilizing lightweight line and plane map representations instead of wide…
A Registration-aided Domain Adaptation Network for 3D Point Cloud Based Place Recognition
Zhijian Qiao, Hanjiang Hu, Weiang Shi +3
In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness…
End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences
Zhijian Qiao, Huanshu Wei, Zhe Liu +2
3D Point cloud registration is still a very challenging topic due to the difficulty in finding the rigid transformation between two point clouds with partial correspondences, and i…