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



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.
Original languageEnglish
Title of host publicationProceedings of the 2019 ACM International Conference on Interactive Surfaces and Spaces, ISS 2019
Number of pages13
PublisherAssociation for Computing Machinery
Publication year2019
Publication statusPublished - 2019
Event2019 Acm International Conference on Interactive Surfaces and Spaces - Daejeon, Korea, Republic of
Duration: 10 Nov 201913 Nov 2019


Conference2019 Acm International Conference on Interactive Surfaces and Spaces
LandKorea, Republic of

See relations at Aarhus University Citationformats

Download statistics

No data available

ID: 168584868