Cross3DReg
收藏资源简介:
Cross3DReg是一个大规模的真实世界跨源点云配准数据集,包含13,231对点云,分别由旋转机械激光雷达和混合半固态激光雷达捕获。数据集旨在解决跨源点云配准中缺乏大规模真实世界数据集的问题,并考虑了不同传感器捕获点云数据在密度、模式分布和噪声水平方面的显著差异。数据集由一个定制的无人地面车辆(UGV)平台收集,该平台配备了旋转机械激光雷达、混合固态激光雷达和RGB相机。数据集将有助于推动跨源点云配准领域的研究,并促进更准确和鲁棒的配准方法的发展。
Cross3DReg is a large-scale real-world cross-source point cloud registration dataset containing 13,231 pairs of point clouds captured by rotating mechanical LiDAR and hybrid semi-solid-state LiDAR respectively. This dataset aims to address the lack of large-scale real-world datasets in the field of cross-source point cloud registration, and takes into account the significant differences in point cloud data captured by different sensors in terms of density, pattern distribution and noise level. The dataset was collected using a custom unmanned ground vehicle (UGV) platform equipped with rotating mechanical LiDAR, hybrid solid-state LiDAR and RGB cameras. This dataset will help advance research in cross-source point cloud registration and promote the development of more accurate and robust registration methods.

- 1通过未知 · 2025年



