Multi-level height maps-based registration method for sparse LiDAR point clouds in an urban scene.

Abstract

The LiDAR sensor has been widely used for reconstruction in urban scenes. However, the current registration method makes it difficult to find stable 3D point correspondences from sparse and low overlapping LiDAR point clouds. In the urban situation, most of the LiDAR point clouds have a common flat ground. Therefore, we propose a novel, to the best of our knowledge, multi-level height (MH) maps-based coarse registration method. It requires that source and target point clouds have a common flat ground, which is easily satisfied for LiDAR point clouds in urban scenes. With MH maps, 3D registration is simplified as 2D registration, increasing the speed of registration. Robust correspondences are extracted in MH maps with different height intervals and statistic height information, improving the registration accuracy. The solid-state LiDAR Livox Mid-100 and mechanical LiDAR Velodyne HDL-64E are used in real-data and dataset experiments, respectively. Verification results demonstrate that our method is stable and outperforms state-of-the-art coarse registration methods for the sparse case. Runtime analysis shows that our method is faster than these methods, for it is non-iterative. Furthermore, our method can be extended for the unordered multi-view point clouds.