A coarse-to-fine algorithm for registration in 3D street-view cross-source point clouds

TL;DR

This paper introduces a novel coarse-to-fine registration algorithm for aligning large-scale cross-source 3D point clouds from LiDAR and SFM, overcoming limitations of traditional ICP-based methods in handling variable data sources.

Contribution

The paper presents a new coarse-to-fine registration approach specifically designed for large-scale, cross-source 3D point clouds, improving registration accuracy and robustness.

Findings

Successfully registers LiDAR and SFM point clouds from street views

Outperforms traditional ICP-based methods in large-scale scenarios

Applicable to robotics and smart city applications

Abstract

With the development of numerous 3D sensing technologies, object registration on cross-source point cloud has aroused researchers' interests. When the point clouds are captured from different kinds of sensors, there are large and different kinds of variations. In this study, we address an even more challenging case in which the differently-source point clouds are acquired from a real street view. One is produced directly by the LiDAR system and the other is generated by using VSFM software on image sequence captured from RGB cameras. When it confronts to large scale point clouds, previous methods mostly focus on point-to-point level registration, and the methods have many limitations.The reason is that the least mean error strategy shows poor ability in registering large variable cross-source point clouds. In this paper, different from previous ICP-based methods, and from a statistic view, we propose a effective coarse-to-fine algorithm to detect and register a small scale SFM point cloud in a large scale Lidar point cloud. Seen from the experimental results, the model can successfully run on LiDAR and SFM point clouds, hence it can make a contribution to many applications, such as robotics and smart city development.