Cargando…

Depth-Image Segmentation Based on Evolving Principles for 3D Sensing of Structured Indoor Environments

This paper presents an approach of depth image segmentation based on the Evolving Principal Component Clustering (EPCC) method, which exploits data locality in an ordered data stream. The parameters of linear prototypes, which are used to describe different clusters, are estimated in a recursive man...

Descripción completa

Detalles Bibliográficos
Autores principales: Antić, Miloš, Zdešar, Andrej, Škrjanc, Igor
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8271552/
https://www.ncbi.nlm.nih.gov/pubmed/34198980
http://dx.doi.org/10.3390/s21134395
_version_ 1783721029146771456
author Antić, Miloš
Zdešar, Andrej
Škrjanc, Igor
author_facet Antić, Miloš
Zdešar, Andrej
Škrjanc, Igor
author_sort Antić, Miloš
collection PubMed
description This paper presents an approach of depth image segmentation based on the Evolving Principal Component Clustering (EPCC) method, which exploits data locality in an ordered data stream. The parameters of linear prototypes, which are used to describe different clusters, are estimated in a recursive manner. The main contribution of this work is the extension and application of the EPCC to 3D space for recursive and real-time detection of flat connected surfaces based on linear segments, which are all detected in an evolving way. To obtain optimal results when processing homogeneous surfaces, we introduced two-step filtering for outlier detection within a clustering framework and considered the noise model, which allowed for the compensation of characteristic uncertainties that are introduced into the measurements of depth sensors. The developed algorithm was compared with well-known methods for point cloud segmentation. The proposed approach achieves better segmentation results over longer distances for which the signal-to-noise ratio is low, without prior filtering of the data. On the given database, an average rate higher than 90% was obtained for successfully detected flat surfaces, which indicates high performance when processing huge point clouds in a non-iterative manner.
format Online
Article
Text
id pubmed-8271552
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-82715522021-07-11 Depth-Image Segmentation Based on Evolving Principles for 3D Sensing of Structured Indoor Environments Antić, Miloš Zdešar, Andrej Škrjanc, Igor Sensors (Basel) Article This paper presents an approach of depth image segmentation based on the Evolving Principal Component Clustering (EPCC) method, which exploits data locality in an ordered data stream. The parameters of linear prototypes, which are used to describe different clusters, are estimated in a recursive manner. The main contribution of this work is the extension and application of the EPCC to 3D space for recursive and real-time detection of flat connected surfaces based on linear segments, which are all detected in an evolving way. To obtain optimal results when processing homogeneous surfaces, we introduced two-step filtering for outlier detection within a clustering framework and considered the noise model, which allowed for the compensation of characteristic uncertainties that are introduced into the measurements of depth sensors. The developed algorithm was compared with well-known methods for point cloud segmentation. The proposed approach achieves better segmentation results over longer distances for which the signal-to-noise ratio is low, without prior filtering of the data. On the given database, an average rate higher than 90% was obtained for successfully detected flat surfaces, which indicates high performance when processing huge point clouds in a non-iterative manner. MDPI 2021-06-27 /pmc/articles/PMC8271552/ /pubmed/34198980 http://dx.doi.org/10.3390/s21134395 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Antić, Miloš
Zdešar, Andrej
Škrjanc, Igor
Depth-Image Segmentation Based on Evolving Principles for 3D Sensing of Structured Indoor Environments
title Depth-Image Segmentation Based on Evolving Principles for 3D Sensing of Structured Indoor Environments
title_full Depth-Image Segmentation Based on Evolving Principles for 3D Sensing of Structured Indoor Environments
title_fullStr Depth-Image Segmentation Based on Evolving Principles for 3D Sensing of Structured Indoor Environments
title_full_unstemmed Depth-Image Segmentation Based on Evolving Principles for 3D Sensing of Structured Indoor Environments
title_short Depth-Image Segmentation Based on Evolving Principles for 3D Sensing of Structured Indoor Environments
title_sort depth-image segmentation based on evolving principles for 3d sensing of structured indoor environments
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8271552/
https://www.ncbi.nlm.nih.gov/pubmed/34198980
http://dx.doi.org/10.3390/s21134395
work_keys_str_mv AT anticmilos depthimagesegmentationbasedonevolvingprinciplesfor3dsensingofstructuredindoorenvironments
AT zdesarandrej depthimagesegmentationbasedonevolvingprinciplesfor3dsensingofstructuredindoorenvironments
AT skrjancigor depthimagesegmentationbasedonevolvingprinciplesfor3dsensingofstructuredindoorenvironments