Aarhus University Seal / Aarhus Universitets segl

Kaj Grønbæk

Digital Assistance for Quality Assurance: Augmented Workspaces Using Deep Learning for Tracking Near-Symmetrical Objects

Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearchpeer-review

Standard

Digital Assistance for Quality Assurance: Augmented Workspaces Using Deep Learning for Tracking Near-Symmetrical Objects. / Evangelista Belo, Joao Marcelo; Fender, Andreas; Feuchtner, Tiare; Grønbæk, Kaj.

Proceedings of the 2019 ACM International Conference on Interactive Surfaces and Spaces, ISS 2019. Association for Computing Machinery, 2019.

Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearchpeer-review

Harvard

Evangelista Belo, JM, Fender, A, Feuchtner, T & Grønbæk, K 2019, Digital Assistance for Quality Assurance: Augmented Workspaces Using Deep Learning for Tracking Near-Symmetrical Objects. in Proceedings of the 2019 ACM International Conference on Interactive Surfaces and Spaces, ISS 2019. Association for Computing Machinery, 2019 Acm International Conference on Interactive Surfaces and Spaces, Daejeon, Korea, Republic of, 10/11/2019. https://doi.org/10.1145/3343055.3359699

APA

Evangelista Belo, J. M., Fender, A., Feuchtner, T., & Grønbæk, K. (2019). Digital Assistance for Quality Assurance: Augmented Workspaces Using Deep Learning for Tracking Near-Symmetrical Objects. In Proceedings of the 2019 ACM International Conference on Interactive Surfaces and Spaces, ISS 2019 Association for Computing Machinery. https://doi.org/10.1145/3343055.3359699

CBE

Evangelista Belo JM, Fender A, Feuchtner T, Grønbæk K. 2019. Digital Assistance for Quality Assurance: Augmented Workspaces Using Deep Learning for Tracking Near-Symmetrical Objects. In Proceedings of the 2019 ACM International Conference on Interactive Surfaces and Spaces, ISS 2019. Association for Computing Machinery. https://doi.org/10.1145/3343055.3359699

MLA

Evangelista Belo, Joao Marcelo et al. "Digital Assistance for Quality Assurance: Augmented Workspaces Using Deep Learning for Tracking Near-Symmetrical Objects". Proceedings of the 2019 ACM International Conference on Interactive Surfaces and Spaces, ISS 2019. Association for Computing Machinery. 2019. https://doi.org/10.1145/3343055.3359699

Vancouver

Evangelista Belo JM, Fender A, Feuchtner T, Grønbæk K. Digital Assistance for Quality Assurance: Augmented Workspaces Using Deep Learning for Tracking Near-Symmetrical Objects. In Proceedings of the 2019 ACM International Conference on Interactive Surfaces and Spaces, ISS 2019. Association for Computing Machinery. 2019 https://doi.org/10.1145/3343055.3359699

Author

Evangelista Belo, Joao Marcelo ; Fender, Andreas ; Feuchtner, Tiare ; Grønbæk, Kaj. / Digital Assistance for Quality Assurance: Augmented Workspaces Using Deep Learning for Tracking Near-Symmetrical Objects. Proceedings of the 2019 ACM International Conference on Interactive Surfaces and Spaces, ISS 2019. Association for Computing Machinery, 2019.

Bibtex

@inproceedings{44777628e97e4eee8e927d1b3e3b1f8a,
title = "Digital Assistance for Quality Assurance: Augmented Workspaces Using Deep Learning for Tracking Near-Symmetrical Objects",
abstract = "We present a digital assistance approach for applied metrology on near-symmetrical objects. In manufacturing, systematically measuring products for quality assurance is often a manual task, where a main challenge for the workers lies in accurately identifying positions to measure and correctly documenting these measurements. This paper focuses on a use-case, which involves metrology of small near-symmetrical objects, such as LEGO bricks. We aim to support this task through situated visual measurement guides. Aligning these guides poses a major challenge, since fine grained details, such as embossed logos, serve as the only feature by which to retrieve an object's unique orientation. We present a two-step approach, which consists of (1) locating and orienting the object based on its shape, and then (2) disambiguating the object's rotational symmetry based on small visual features. We apply and compare different deep learning approaches and discuss our guidance system in the context of our use case.",
author = "{Evangelista Belo}, {Joao Marcelo} and Andreas Fender and Tiare Feuchtner and Kaj Gr{\o}nb{\ae}k",
year = "2019",
doi = "10.1145/3343055.3359699",
language = "English",
booktitle = "Proceedings of the 2019 ACM International Conference on Interactive Surfaces and Spaces, ISS 2019",
publisher = "Association for Computing Machinery",
note = "2019 Acm International Conference on Interactive Surfaces and Spaces ; Conference date: 10-11-2019 Through 13-11-2019",

}

RIS

TY - GEN

T1 - Digital Assistance for Quality Assurance: Augmented Workspaces Using Deep Learning for Tracking Near-Symmetrical Objects

AU - Evangelista Belo, Joao Marcelo

AU - Fender, Andreas

AU - Feuchtner, Tiare

AU - Grønbæk, Kaj

PY - 2019

Y1 - 2019

N2 - We present a digital assistance approach for applied metrology on near-symmetrical objects. In manufacturing, systematically measuring products for quality assurance is often a manual task, where a main challenge for the workers lies in accurately identifying positions to measure and correctly documenting these measurements. This paper focuses on a use-case, which involves metrology of small near-symmetrical objects, such as LEGO bricks. We aim to support this task through situated visual measurement guides. Aligning these guides poses a major challenge, since fine grained details, such as embossed logos, serve as the only feature by which to retrieve an object's unique orientation. We present a two-step approach, which consists of (1) locating and orienting the object based on its shape, and then (2) disambiguating the object's rotational symmetry based on small visual features. We apply and compare different deep learning approaches and discuss our guidance system in the context of our use case.

AB - We present a digital assistance approach for applied metrology on near-symmetrical objects. In manufacturing, systematically measuring products for quality assurance is often a manual task, where a main challenge for the workers lies in accurately identifying positions to measure and correctly documenting these measurements. This paper focuses on a use-case, which involves metrology of small near-symmetrical objects, such as LEGO bricks. We aim to support this task through situated visual measurement guides. Aligning these guides poses a major challenge, since fine grained details, such as embossed logos, serve as the only feature by which to retrieve an object's unique orientation. We present a two-step approach, which consists of (1) locating and orienting the object based on its shape, and then (2) disambiguating the object's rotational symmetry based on small visual features. We apply and compare different deep learning approaches and discuss our guidance system in the context of our use case.

U2 - 10.1145/3343055.3359699

DO - 10.1145/3343055.3359699

M3 - Article in proceedings

BT - Proceedings of the 2019 ACM International Conference on Interactive Surfaces and Spaces, ISS 2019

PB - Association for Computing Machinery

T2 - 2019 Acm International Conference on Interactive Surfaces and Spaces

Y2 - 10 November 2019 through 13 November 2019

ER -