A Coarse-to-Fine Algorithm for Registration in 3D Street-View Cross-Source Point Clouds

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.

A comprehensive survey on point cloud registration

“…The registration is solved by using ICP. Following the coarseto-fine strategy, CSGMM [42] applies GMM-based algorithm to estimate the transformation. GM-CSPC [43] assumes the cross-source point clouds are coming from the same Gaussian mixture models and the two input point clouds are two samples from the Gaussian mixture.…”

“…According to [77], [41], cross-source point cloud registration is much more challenging because of the combination of considerable noise and outliers, density difference, partial overlap and scale difference. Several algorithms [42], [41], [43], [39] use sophisticated optimization strategies to solve the crosssource point cloud registration problem by overcoming the cross-source challenges. For example, CSGM [41] transforms the registration problem into a graph matching problem and leverage the graph matching theory to overcome these challenges.…”

“…Lidar has a long view range while generating sparse point clouds. Data fusion of these different kinds of 3D sensors combines their advantages and is a cross-source point cloud registration problem [43], [41], [42]. The crosssource point cloud registration has wide applications such as building construction, augmented reality, and driverless vehicles.…”

Fast Registration for Cross-Source Point Clouds by using Weak Regional Affinity and Pixel-Wise Refinement

“…They have not designed for scale variation. To compare fairly, we conduct an automatically scale normalization for all the other methods by following [14], which is assuming the size of the point cloud's 3D containing voxel is the same. Because JR-MPC becomes not practical when the point number increases significantly, we uniformly down-sample the point cloud to approximately 2000 points for JR-MPC.…”

Briefing: UK-RAS white paper in robotics and autonomous systems for resilient infrastructure

“…Ampatzidis et al, 2017;Ermacora et al, 2016;Foina et al, 2016;Huang et al, 2016;Salmerón-García et al, 2017), Building Information Modelling (e.g. Chuang et al, 2011;Edenhofer et al, 2016;Feng et al, 2015;Lundeen et al, 2017;Rausch et al, 2017;Schlette and Roßmann, 2017;Vähä et al, 2013), Big Data or the Internet of Things (e.g.…”