On the accuracy of the 3D normal distributions transform as a tool for spatial representation

Todor Stoyanov; Martin Magnusson; Håkan Almqvist; Achim J. Lilienthal

doi:10.1109/ICRA.2011.5979584

On the accuracy of the 3D normal distributions transform as a tool for spatial representation

Todor Stoyanov, Martin Magnusson, Håkan Almqvist, Achim J. Lilienthal

Örebro University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

28 Scopus citations

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.

Original language	English
Title of host publication	2011 IEEE International Conference on Robotics and Automation, ICRA 2011
Pages	4080-4085
Number of pages	6
DOIs	https://doi.org/10.1109/ICRA.2011.5979584
State	Published - 2011
Externally published	Yes
Event	2011 IEEE International Conference on Robotics and Automation, ICRA 2011 - Shanghai, China Duration: 9 May 2011 → 13 May 2011

Publication series

Name	Proceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)	1050-4729

Conference

Conference	2011 IEEE International Conference on Robotics and Automation, ICRA 2011
Country/Territory	China
City	Shanghai
Period	9/05/11 → 13/05/11

Access to Document

10.1109/ICRA.2011.5979584

Cite this

Stoyanov, T., Magnusson, M., Almqvist, H., & Lilienthal, A. J. (2011). On the accuracy of the 3D normal distributions transform as a tool for spatial representation. In 2011 IEEE International Conference on Robotics and Automation, ICRA 2011 (pp. 4080-4085). Article 5979584 (Proceedings - IEEE International Conference on Robotics and Automation). https://doi.org/10.1109/ICRA.2011.5979584

@inproceedings{5cecf61d012048738893bccd3b47df3e,

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.",

author = "Todor Stoyanov and Martin Magnusson and H{\aa}kan Almqvist and Lilienthal, {Achim J.}",

year = "2011",

doi = "10.1109/ICRA.2011.5979584",

language = "English",

isbn = "9781612843865",

series = "Proceedings - IEEE International Conference on Robotics and Automation",

pages = "4080--4085",

booktitle = "2011 IEEE International Conference on Robotics and Automation, ICRA 2011",

note = "2011 IEEE International Conference on Robotics and Automation, ICRA 2011 ; Conference date: 09-05-2011 Through 13-05-2011",

}

Stoyanov, T, Magnusson, M, Almqvist, H & Lilienthal, AJ 2011, On the accuracy of the 3D normal distributions transform as a tool for spatial representation. in 2011 IEEE International Conference on Robotics and Automation, ICRA 2011., 5979584, Proceedings - IEEE International Conference on Robotics and Automation, pp. 4080-4085, 2011 IEEE International Conference on Robotics and Automation, ICRA 2011, Shanghai, China, 9/05/11. https://doi.org/10.1109/ICRA.2011.5979584

On the accuracy of the 3D normal distributions transform as a tool for spatial representation. / Stoyanov, Todor; Magnusson, Martin; Almqvist, Håkan et al.
2011 IEEE International Conference on Robotics and Automation, ICRA 2011. 2011. p. 4080-4085 5979584 (Proceedings - IEEE International Conference on Robotics and Automation).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - On the accuracy of the 3D normal distributions transform as a tool for spatial representation

AU - Stoyanov, Todor

AU - Magnusson, Martin

AU - Almqvist, Håkan

AU - Lilienthal, Achim J.

PY - 2011

Y1 - 2011

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84871695120&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2011.5979584

DO - 10.1109/ICRA.2011.5979584

M3 - Conference contribution

AN - SCOPUS:84871695120

SN - 9781612843865

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 4080

EP - 4085

BT - 2011 IEEE International Conference on Robotics and Automation, ICRA 2011

T2 - 2011 IEEE International Conference on Robotics and Automation, ICRA 2011

Y2 - 9 May 2011 through 13 May 2011

ER -

On the accuracy of the 3D normal distributions transform as a tool for spatial representation

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this