Paper Info
Title
On the accuracy of the 3D Normal Distributions Transform as a tool for spatial representation
Abstract
The Three-Dimensional Normal Distributions Transform (3D-NDT) is a spatial modeling technique with applications in point set registration, scan similarity comparison, change detection and path planning. This work concentrates on evaluating three common variations of the 3D-NDT in terms of accuracy of representing sampled semi-structured environments. In a novel approach to spatial representation quality measurement, the 3D geometrical modeling task is formulated as a classification problem and its accuracy is evaluated with standard machine learning performance metrics. In this manner the accuracy of the 3D-NDT variations is shown to be comparable to, and in some cases to outperform that of the standard occupancy grid mapping model.
Year
DOI
Venue
2011
10.1109/ICRA.2011.5979584
Robotics and Automation
Keywords
Field
DocType
computational geometry,normal distribution,pattern classification,3D geometrical modeling,3D normal distributions transform,change detection,classification problem,machine learning performance metrics,path planning,point set registration,scan similarity comparison,semistructured environment,spatial modeling technique,spatial representation quality measurement,standard occupancy grid mapping model
Normal distribution,Change detection,Control theory,Computer science,Interpolation,Computational geometry,Artificial intelligence,Spatial representation,Motion planning,Computer vision,Point set registration,Pattern recognition,Occupancy grid mapping
Conference
Volume
Issue
ISSN
2011
1
1050-4729
ISBN
Citations 
PageRank 
978-1-61284-386-5
12
0.81
References 
Authors
12
4
Name
Order
Citations
PageRank
Todor Stoyanov126026.07
Martin Magnusson228712.86
Almqvist, Hakan3120.81
Achim J. Lilienthal41468113.18