Fast Global Point Cloud Registration using Semantic NDT

Robust and accurate point cloud registration is an essential part of many robotic tasks such as SLAM or object pose retrieval. In this paper, we address the problem of global 3D point cloud registration, i. e. , the task of estimating the 3D rigid body transform between a source and a target point cloud without any initial guess. Typically, the problem is solved by extracting and matching features to find a data association and then computing a transform that minimizes the squared distance between points. Our approach combines the normal distributions transform and oriented point pair framework and introduces the NDT distance histogram to quickly generate and test candidate transforms. Our method further exploits semantic information if available for greater speed. We implement our algorithm in C++ and compare it to other state-of-the-art approaches on a diverse set of environments. Our evaluation shows that our method outperforms the other approaches, especially concerning run-time and compute efficiency.

Authors

• Robert Schirmer
• Narunas Vaskevicius
• Peter Biber
• Cyrill Stachniss

Keywords

• Point cloud compression
• Location awareness
• Histograms
• Three-dimensional displays
• Simultaneous localization and mapping
• Semantic segmentation
• Semantics
• Transforms
• Feature extraction
• Intelligent robots
• Point Cloud
• Point Cloud Registration
• Global Registration
• Global Cloud
• Normal Distribution Transform
• Global Point Cloud
• Global Point Cloud Registration
• Semantic Information
• Pair Of Points
• Histogram Of Distances
• Robust Registration
• Outcome Information
• Line Segment
• Open Set
• Hash Function
• Rigid Transformation
• Global Set
• True Mean
• Sensor Noise
• Noisy Labels
• Semantic Labels
• Registration Approach
• Registration Problem
• Registration Results
• Key Claims
• Indoor Settings
• Convincing Results
• Loop Closure