Aligning point cloud views using persistent feature histograms

In this paper we investigate the usage of persistent point feature histograms for the problem of aligning point cloud data views into a consistent global model. Given a collection of noisy point clouds, our algorithm estimates a set of robust 16D features which describe the geometry of each point locally. By analyzing the persistence of the features at different scales, we extract an optimal set which best characterizes a given point cloud. The resulted persistent features are used in an initial alignment algorithm to estimate a rigid transformation that approximately registers the input datasets. The algorithm provides good starting points for iterative registration algorithms such as ICP (Iterative Closest Point), by transforming the datasets to its convergence basin. We show that our approach is invariant to pose and sampling density, and can cope well with noisy data coming from both indoor and outdoor laser scans.

Authors

• Radu Bogdan Rusu
• Nico Blodow
• Zoltán-Csaba Márton
• Michael Beetz

Keywords

• Meteorology
• Distance measurement
• Histograms
• Three dimensional displays
• Indexes
• Rough surfaces
• Noise measurement
• Point Cloud
• Persistent Features
• Histogram Features
• Noisy Data
• Feature Points
• Rigid Transformation
• Point Cloud Data
• Registration Algorithm
• Iterative Closest Point
• Initial Algorithm
• Point Geometry
• Geometric Properties
• Point Source
• Error Function
• Iteration Step
• Corresponding Points
• Distance Metrics
• Geometric Constraints
• Surface Curvature
• Neighboring Points
• Dense Point Cloud
• Set Of Data Points
• Surface Normals
• Geometric Primitives
• Registration Problem
• 3D Point Cloud Data
• Registration Method
• Error Metrics
• Good Alignment
• Subset Of Points