Noise-resistant unsupervised object segmentation in multi-view indoor point clouds

Dmytro Bobkov, Sili Chen, Martin Kiechle, Sebastian Hilsenbeck, Eckehard Steinbach

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

3D object segmentation in indoor multi-view point clouds (MVPC) is challenged by a high noise level, varying point density and registration artifacts. This severely deteriorates the segmentation performance of state-of-the-art algorithms in concave and highly-curved point set neighborhoods, because concave regions normally serve as evidence for object boundaries. To address this issue, we derive a novel robust criterion to detect and remove such regions prior to segmentation so that noise modelling is not required anymore. Thus, a significant number of inter-object connections can be removed and the graph partitioning problem becomes simpler. After initial segmentation, such regions are labelled using a novel recovery procedure. Our approach has been experimentally validated within a typical segmentation pipeline on multi-view and single-view point cloud data. To foster further research, we make the labelled MVPC dataset public (Bobkov et al., 2017).

Original languageEnglish
Title of host publicationVISAPP
EditorsFrancisco Imai, Alain Tremeau, Jose Braz
PublisherSciTePress
Pages149-156
Number of pages8
ISBN (Electronic)9789897582264
DOIs
StatePublished - 2017
Event12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2017 - Porto, Portugal
Duration: 27 Feb 20171 Mar 2017

Publication series

NameVISIGRAPP 2017 - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Volume5

Conference

Conference12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2017
Country/TerritoryPortugal
CityPorto
Period27/02/171/03/17

Keywords

  • Concavity criterion
  • Laser scanner
  • Object segmentation
  • Point cloud
  • Segmentation dataset

Fingerprint

Dive into the research topics of 'Noise-resistant unsupervised object segmentation in multi-view indoor point clouds'. Together they form a unique fingerprint.

Cite this