Cargando…

Underwater Object Recognition Using Point-Features, Bayesian Estimation and Semantic Information

This paper proposes a 3D object recognition method for non-coloured point clouds using point features. The method is intended for application scenarios such as Inspection, Maintenance and Repair (IMR) of industrial sub-sea structures composed of pipes and connecting objects (such as valves, elbows a...

Descripción completa

Detalles Bibliográficos
Autores principales: Himri, Khadidja, Ridao, Pere, Gracias, Nuno
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7961582/
https://www.ncbi.nlm.nih.gov/pubmed/33807708
http://dx.doi.org/10.3390/s21051807
_version_ 1783665292714442752
author Himri, Khadidja
Ridao, Pere
Gracias, Nuno
author_facet Himri, Khadidja
Ridao, Pere
Gracias, Nuno
author_sort Himri, Khadidja
collection PubMed
description This paper proposes a 3D object recognition method for non-coloured point clouds using point features. The method is intended for application scenarios such as Inspection, Maintenance and Repair (IMR) of industrial sub-sea structures composed of pipes and connecting objects (such as valves, elbows and R-Tee connectors). The recognition algorithm uses a database of partial views of the objects, stored as point clouds, which is available a priori. The recognition pipeline has 5 stages: (1) Plane segmentation, (2) Pipe detection, (3) Semantic Object-segmentation and detection, (4) Feature based Object Recognition and (5) Bayesian estimation. To apply the Bayesian estimation, an object tracking method based on a new Interdistance Joint Compatibility Branch and Bound (IJCBB) algorithm is proposed. The paper studies the recognition performance depending on: (1) the point feature descriptor used, (2) the use (or not) of Bayesian estimation and (3) the inclusion of semantic information about the objects connections. The methods are tested using an experimental dataset containing laser scans and Autonomous Underwater Vehicle (AUV) navigation data. The best results are obtained using the Clustered Viewpoint Feature Histogram (CVFH) descriptor, achieving recognition rates of [Formula: see text] , [Formula: see text] and [Formula: see text] , respectively, clearly showing the advantages of using the Bayesian estimation ([Formula: see text] increase) and the inclusion of semantic information ([Formula: see text] further increase).
format Online
Article
Text
id pubmed-7961582
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-79615822021-03-17 Underwater Object Recognition Using Point-Features, Bayesian Estimation and Semantic Information Himri, Khadidja Ridao, Pere Gracias, Nuno Sensors (Basel) Article This paper proposes a 3D object recognition method for non-coloured point clouds using point features. The method is intended for application scenarios such as Inspection, Maintenance and Repair (IMR) of industrial sub-sea structures composed of pipes and connecting objects (such as valves, elbows and R-Tee connectors). The recognition algorithm uses a database of partial views of the objects, stored as point clouds, which is available a priori. The recognition pipeline has 5 stages: (1) Plane segmentation, (2) Pipe detection, (3) Semantic Object-segmentation and detection, (4) Feature based Object Recognition and (5) Bayesian estimation. To apply the Bayesian estimation, an object tracking method based on a new Interdistance Joint Compatibility Branch and Bound (IJCBB) algorithm is proposed. The paper studies the recognition performance depending on: (1) the point feature descriptor used, (2) the use (or not) of Bayesian estimation and (3) the inclusion of semantic information about the objects connections. The methods are tested using an experimental dataset containing laser scans and Autonomous Underwater Vehicle (AUV) navigation data. The best results are obtained using the Clustered Viewpoint Feature Histogram (CVFH) descriptor, achieving recognition rates of [Formula: see text] , [Formula: see text] and [Formula: see text] , respectively, clearly showing the advantages of using the Bayesian estimation ([Formula: see text] increase) and the inclusion of semantic information ([Formula: see text] further increase). MDPI 2021-03-05 /pmc/articles/PMC7961582/ /pubmed/33807708 http://dx.doi.org/10.3390/s21051807 Text en © 2021 by the authors. 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 (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Himri, Khadidja
Ridao, Pere
Gracias, Nuno
Underwater Object Recognition Using Point-Features, Bayesian Estimation and Semantic Information
title Underwater Object Recognition Using Point-Features, Bayesian Estimation and Semantic Information
title_full Underwater Object Recognition Using Point-Features, Bayesian Estimation and Semantic Information
title_fullStr Underwater Object Recognition Using Point-Features, Bayesian Estimation and Semantic Information
title_full_unstemmed Underwater Object Recognition Using Point-Features, Bayesian Estimation and Semantic Information
title_short Underwater Object Recognition Using Point-Features, Bayesian Estimation and Semantic Information
title_sort underwater object recognition using point-features, bayesian estimation and semantic information
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7961582/
https://www.ncbi.nlm.nih.gov/pubmed/33807708
http://dx.doi.org/10.3390/s21051807
work_keys_str_mv AT himrikhadidja underwaterobjectrecognitionusingpointfeaturesbayesianestimationandsemanticinformation
AT ridaopere underwaterobjectrecognitionusingpointfeaturesbayesianestimationandsemanticinformation
AT graciasnuno underwaterobjectrecognitionusingpointfeaturesbayesianestimationandsemanticinformation