Application of Ontologies for Semantic Scene Segmentation and Object Recognition

Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review

Authors

  • P. Venet
  • K. Safronov
  • A. Ehambram
  • S. Wagner
  • J. Bock
  • U. E. Zimmermann

Research Organisations

External Research Organisations

  • Magazino GmbH
  • KUKA
View graph of relations

Details

Original languageEnglish
Title of host publicationISR 2020; 52th International Symposium on Robotics
PublisherVDE Verlag GmbH
Pages1-7
Number of pages7
ISBN (electronic)978-3-8007-5428-1
Publication statusPublished - 2020
Event52th International Symposium on Robotics - online
Duration: 9 Dec 2020 → 10 Dec 2020

Abstract

Semantic scene segmentation is a key block of many human-robot collaboration applications. Existing methods yield good results in lab environment both on a class and instance level. Additionally, some work was done in the development of tools to simplify the task of teaching the semantics. However, this resides a tedious task that doesn’t adapt well, and lacks reusability. We propose a novel pipeline design that allows to build shareable, sensor agnostic models for objects that can later be used to identify scene segments. The result is an ontology IRI that can be shared and to which much more information can be linked. The method is based on traditional 3D vision techniques and deep learning classifiers, combined together using a RDF topology of OWL concepts.

Cite this

Application of Ontologies for Semantic Scene Segmentation and Object Recognition. / Venet, P.; Safronov, K.; Ehambram, A. et al.
ISR 2020; 52th International Symposium on Robotics. VDE Verlag GmbH, 2020. p. 1-7.

Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review

Venet, P, Safronov, K, Ehambram, A, Wagner, S, Bock, J & Zimmermann, UE 2020, Application of Ontologies for Semantic Scene Segmentation and Object Recognition. in ISR 2020; 52th International Symposium on Robotics. VDE Verlag GmbH, pp. 1-7, 52th International Symposium on Robotics, online, 9 Dec 2020. <https://ieeexplore.ieee.org/document/9307480>
Venet, P., Safronov, K., Ehambram, A., Wagner, S., Bock, J., & Zimmermann, U. E. (2020). Application of Ontologies for Semantic Scene Segmentation and Object Recognition. In ISR 2020; 52th International Symposium on Robotics (pp. 1-7). VDE Verlag GmbH. https://ieeexplore.ieee.org/document/9307480
Venet P, Safronov K, Ehambram A, Wagner S, Bock J, Zimmermann UE. Application of Ontologies for Semantic Scene Segmentation and Object Recognition. In ISR 2020; 52th International Symposium on Robotics. VDE Verlag GmbH. 2020. p. 1-7
Venet, P. ; Safronov, K. ; Ehambram, A. et al. / Application of Ontologies for Semantic Scene Segmentation and Object Recognition. ISR 2020; 52th International Symposium on Robotics. VDE Verlag GmbH, 2020. pp. 1-7
Download
@inproceedings{e629c6d1653f4eddb0b0ba41079cdc53,
title = "Application of Ontologies for Semantic Scene Segmentation and Object Recognition",
abstract = "Semantic scene segmentation is a key block of many human-robot collaboration applications. Existing methods yield good results in lab environment both on a class and instance level. Additionally, some work was done in the development of tools to simplify the task of teaching the semantics. However, this resides a tedious task that doesn{\textquoteright}t adapt well, and lacks reusability. We propose a novel pipeline design that allows to build shareable, sensor agnostic models for objects that can later be used to identify scene segments. The result is an ontology IRI that can be shared and to which much more information can be linked. The method is based on traditional 3D vision techniques and deep learning classifiers, combined together using a RDF topology of OWL concepts.",
author = "P. Venet and K. Safronov and A. Ehambram and S. Wagner and J. Bock and Zimmermann, {U. E.}",
year = "2020",
language = "English",
pages = "1--7",
booktitle = "ISR 2020; 52th International Symposium on Robotics",
publisher = "VDE Verlag GmbH",
address = "Germany",
note = "52th International Symposium on Robotics, ISR 2020 ; Conference date: 09-12-2020 Through 10-12-2020",

}

Download

TY - GEN

T1 - Application of Ontologies for Semantic Scene Segmentation and Object Recognition

AU - Venet, P.

AU - Safronov, K.

AU - Ehambram, A.

AU - Wagner, S.

AU - Bock, J.

AU - Zimmermann, U. E.

PY - 2020

Y1 - 2020

N2 - Semantic scene segmentation is a key block of many human-robot collaboration applications. Existing methods yield good results in lab environment both on a class and instance level. Additionally, some work was done in the development of tools to simplify the task of teaching the semantics. However, this resides a tedious task that doesn’t adapt well, and lacks reusability. We propose a novel pipeline design that allows to build shareable, sensor agnostic models for objects that can later be used to identify scene segments. The result is an ontology IRI that can be shared and to which much more information can be linked. The method is based on traditional 3D vision techniques and deep learning classifiers, combined together using a RDF topology of OWL concepts.

AB - Semantic scene segmentation is a key block of many human-robot collaboration applications. Existing methods yield good results in lab environment both on a class and instance level. Additionally, some work was done in the development of tools to simplify the task of teaching the semantics. However, this resides a tedious task that doesn’t adapt well, and lacks reusability. We propose a novel pipeline design that allows to build shareable, sensor agnostic models for objects that can later be used to identify scene segments. The result is an ontology IRI that can be shared and to which much more information can be linked. The method is based on traditional 3D vision techniques and deep learning classifiers, combined together using a RDF topology of OWL concepts.

M3 - Conference contribution

SP - 1

EP - 7

BT - ISR 2020; 52th International Symposium on Robotics

PB - VDE Verlag GmbH

T2 - 52th International Symposium on Robotics

Y2 - 9 December 2020 through 10 December 2020

ER -