An Evaluation Pipeline For Indoor Laser Scanning Point Clouds

S. Karam, M. Peter, S. Hosseinyalamdary, G. Vosselman

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

3 Citations (Scopus)
16 Downloads (Pure)

Abstract

The necessity for the modelling of building interiors has encouraged researchers in recent years to focus on improving the capturing and modelling techniques for such environments. State-of-the-art indoor mobile mapping systems use a combination of laser scanners and/or cameras mounted on movable platforms and allow for capturing 3D data of buildings’ interiors. As GNSS positioning does not work inside buildings, the extensively investigated Simultaneous Localisation and Mapping (SLAM) algorithms seem to offer a suitable solution for the problem. Because of the dead-reckoning nature of SLAM approaches, their results usually suffer from registration errors. Therefore, indoor data acquisition has remained a challenge and the accuracy of the captured data has to be analysed and investigated. In this paper, we propose to use architectural constraints to partly evaluate the quality of the acquired point cloud in the absence of any ground truth model. The internal consistency of walls is utilized to check the accuracy and correctness of indoor models. In addition, we use a floor plan (if available) as an external information source to check the quality of the generated indoor model. The proposed evaluation method provides an overall impression of the reconstruction accuracy. Our results show that perpendicularity, parallelism, and thickness of walls are important cues in buildings and can be used for an internal consistency check.
Original languageEnglish
Title of host publicationISPRS TC I Mid-term Symposium Innovative Sensing – From Sensors to Methods and Applications (Volume IV-1) 10–12 October 2018, Karlsruhe, Germany
EditorsB. Jutzi, M. Weinmann, S. Hinz
Place of PublicationKarlsruhe
PublisherInternational Society for Photogrammetry and Remote Sensing (ISPRS)
Pages85-92
Number of pages8
DOIs
Publication statusPublished - 26 Sep 2018

Publication series

NameISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
PublisherCopernicus GmbH
VolumeIV-1
ISSN (Print)2194-9042

Fingerprint

Pipelines
Scanning
Lasers
Interiors (building)
Data acquisition
Cameras

Keywords

  • Evaluation, Analysis, Point Clouds, SLAM, IMMS, Comparison, Ground Truth
  • ITC-GOLD

Cite this

Karam, S., Peter, M., Hosseinyalamdary, S., & Vosselman, G. (2018). An Evaluation Pipeline For Indoor Laser Scanning Point Clouds. In B. Jutzi, M. Weinmann, & S. Hinz (Eds.), ISPRS TC I Mid-term Symposium Innovative Sensing – From Sensors to Methods and Applications (Volume IV-1) 10–12 October 2018, Karlsruhe, Germany (pp. 85-92). (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences; Vol. IV-1). Karlsruhe: International Society for Photogrammetry and Remote Sensing (ISPRS). https://doi.org/10.5194/isprs-annals-IV-1-85-2018
Karam, S. ; Peter, M. ; Hosseinyalamdary, S. ; Vosselman, G. / An Evaluation Pipeline For Indoor Laser Scanning Point Clouds. ISPRS TC I Mid-term Symposium Innovative Sensing – From Sensors to Methods and Applications (Volume IV-1) 10–12 October 2018, Karlsruhe, Germany. editor / B. Jutzi ; M. Weinmann ; S. Hinz. Karlsruhe : International Society for Photogrammetry and Remote Sensing (ISPRS), 2018. pp. 85-92 (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences).
@inbook{123ab99f5b054d77876d0ce071fef828,
title = "An Evaluation Pipeline For Indoor Laser Scanning Point Clouds",
abstract = "The necessity for the modelling of building interiors has encouraged researchers in recent years to focus on improving the capturing and modelling techniques for such environments. State-of-the-art indoor mobile mapping systems use a combination of laser scanners and/or cameras mounted on movable platforms and allow for capturing 3D data of buildings’ interiors. As GNSS positioning does not work inside buildings, the extensively investigated Simultaneous Localisation and Mapping (SLAM) algorithms seem to offer a suitable solution for the problem. Because of the dead-reckoning nature of SLAM approaches, their results usually suffer from registration errors. Therefore, indoor data acquisition has remained a challenge and the accuracy of the captured data has to be analysed and investigated. In this paper, we propose to use architectural constraints to partly evaluate the quality of the acquired point cloud in the absence of any ground truth model. The internal consistency of walls is utilized to check the accuracy and correctness of indoor models. In addition, we use a floor plan (if available) as an external information source to check the quality of the generated indoor model. The proposed evaluation method provides an overall impression of the reconstruction accuracy. Our results show that perpendicularity, parallelism, and thickness of walls are important cues in buildings and can be used for an internal consistency check.",
keywords = "Evaluation, Analysis, Point Clouds, SLAM, IMMS, Comparison, Ground Truth, ITC-GOLD",
author = "S. Karam and M. Peter and S. Hosseinyalamdary and G. Vosselman",
year = "2018",
month = "9",
day = "26",
doi = "10.5194/isprs-annals-IV-1-85-2018",
language = "English",
series = "ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences",
publisher = "International Society for Photogrammetry and Remote Sensing (ISPRS)",
pages = "85--92",
editor = "B. Jutzi and M. Weinmann and S. Hinz",
booktitle = "ISPRS TC I Mid-term Symposium Innovative Sensing – From Sensors to Methods and Applications (Volume IV-1) 10–12 October 2018, Karlsruhe, Germany",

}

Karam, S, Peter, M, Hosseinyalamdary, S & Vosselman, G 2018, An Evaluation Pipeline For Indoor Laser Scanning Point Clouds. in B Jutzi, M Weinmann & S Hinz (eds), ISPRS TC I Mid-term Symposium Innovative Sensing – From Sensors to Methods and Applications (Volume IV-1) 10–12 October 2018, Karlsruhe, Germany. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. IV-1, International Society for Photogrammetry and Remote Sensing (ISPRS), Karlsruhe, pp. 85-92. https://doi.org/10.5194/isprs-annals-IV-1-85-2018

An Evaluation Pipeline For Indoor Laser Scanning Point Clouds. / Karam, S.; Peter, M.; Hosseinyalamdary, S.; Vosselman, G.

ISPRS TC I Mid-term Symposium Innovative Sensing – From Sensors to Methods and Applications (Volume IV-1) 10–12 October 2018, Karlsruhe, Germany. ed. / B. Jutzi; M. Weinmann; S. Hinz. Karlsruhe : International Society for Photogrammetry and Remote Sensing (ISPRS), 2018. p. 85-92 (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences; Vol. IV-1).

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

TY - CHAP

T1 - An Evaluation Pipeline For Indoor Laser Scanning Point Clouds

AU - Karam, S.

AU - Peter, M.

AU - Hosseinyalamdary, S.

AU - Vosselman, G.

PY - 2018/9/26

Y1 - 2018/9/26

N2 - The necessity for the modelling of building interiors has encouraged researchers in recent years to focus on improving the capturing and modelling techniques for such environments. State-of-the-art indoor mobile mapping systems use a combination of laser scanners and/or cameras mounted on movable platforms and allow for capturing 3D data of buildings’ interiors. As GNSS positioning does not work inside buildings, the extensively investigated Simultaneous Localisation and Mapping (SLAM) algorithms seem to offer a suitable solution for the problem. Because of the dead-reckoning nature of SLAM approaches, their results usually suffer from registration errors. Therefore, indoor data acquisition has remained a challenge and the accuracy of the captured data has to be analysed and investigated. In this paper, we propose to use architectural constraints to partly evaluate the quality of the acquired point cloud in the absence of any ground truth model. The internal consistency of walls is utilized to check the accuracy and correctness of indoor models. In addition, we use a floor plan (if available) as an external information source to check the quality of the generated indoor model. The proposed evaluation method provides an overall impression of the reconstruction accuracy. Our results show that perpendicularity, parallelism, and thickness of walls are important cues in buildings and can be used for an internal consistency check.

AB - The necessity for the modelling of building interiors has encouraged researchers in recent years to focus on improving the capturing and modelling techniques for such environments. State-of-the-art indoor mobile mapping systems use a combination of laser scanners and/or cameras mounted on movable platforms and allow for capturing 3D data of buildings’ interiors. As GNSS positioning does not work inside buildings, the extensively investigated Simultaneous Localisation and Mapping (SLAM) algorithms seem to offer a suitable solution for the problem. Because of the dead-reckoning nature of SLAM approaches, their results usually suffer from registration errors. Therefore, indoor data acquisition has remained a challenge and the accuracy of the captured data has to be analysed and investigated. In this paper, we propose to use architectural constraints to partly evaluate the quality of the acquired point cloud in the absence of any ground truth model. The internal consistency of walls is utilized to check the accuracy and correctness of indoor models. In addition, we use a floor plan (if available) as an external information source to check the quality of the generated indoor model. The proposed evaluation method provides an overall impression of the reconstruction accuracy. Our results show that perpendicularity, parallelism, and thickness of walls are important cues in buildings and can be used for an internal consistency check.

KW - Evaluation, Analysis, Point Clouds, SLAM, IMMS, Comparison, Ground Truth

KW - ITC-GOLD

UR - https://ezproxy2.utwente.nl/login?url=https://webapps.itc.utwente.nl/library/2018/chap/karam_eva.pdf

U2 - 10.5194/isprs-annals-IV-1-85-2018

DO - 10.5194/isprs-annals-IV-1-85-2018

M3 - Chapter

T3 - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

SP - 85

EP - 92

BT - ISPRS TC I Mid-term Symposium Innovative Sensing – From Sensors to Methods and Applications (Volume IV-1) 10–12 October 2018, Karlsruhe, Germany

A2 - Jutzi, B.

A2 - Weinmann, M.

A2 - Hinz, S.

PB - International Society for Photogrammetry and Remote Sensing (ISPRS)

CY - Karlsruhe

ER -

Karam S, Peter M, Hosseinyalamdary S, Vosselman G. An Evaluation Pipeline For Indoor Laser Scanning Point Clouds. In Jutzi B, Weinmann M, Hinz S, editors, ISPRS TC I Mid-term Symposium Innovative Sensing – From Sensors to Methods and Applications (Volume IV-1) 10–12 October 2018, Karlsruhe, Germany. Karlsruhe: International Society for Photogrammetry and Remote Sensing (ISPRS). 2018. p. 85-92. (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences). https://doi.org/10.5194/isprs-annals-IV-1-85-2018