CADTrack: Instructions and Support for Orientation Disambiguation of Near-Symmetrical Objects

Joao Marcelo Evangelista Belo*, Jon Wissing, Tiare Feuchtner, Kaj Grønbæk

*Corresponding author for this work

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

Abstract

Determining the correct orientation of objects can be critical to succeed in tasks like assembly and quality assurance. In particular, near-symmetrical objects may require careful inspection of small visual features to disambiguate their orientation. We propose CADTrack, a digital assistant for providing instructions and support for tasks where the orientation of near-symmetrical objects matters. Additionally, we present a deep learning pipeline for tracking the orientation of near-symmetrical objects. In contrast to existing approaches which require labeled datasets involving laborious data acquisition and annotation processes, CADTrack uses a digital model of the object to generate synthetic data and train a convolutional neural network. Furthermore, we extend the architecture of Mask R-CNN with a confidence prediction branch to avoid errors caused by misleading orientation guidance. We evaluate CADTrack through a user study, comparing our tracking-based instructions to other methods, confirming the benefits of our approach in terms of preference and lower
Original languageEnglish
Title of host publicationProceedings of the ACM on Human-Computer Interaction
EditorsVille Mäkelä, Andrés Lucero, Florian Alt, Mark Hancock
Number of pages20
Place of publicationNew York
PublisherAssociation for Computing Machinery
Publication dateNov 2023
Article number426
DOIs
Publication statusPublished - Nov 2023
EventACM Interactive Surfaces and Spaces - Carnegie Mellon Hamerschlag Hall, Pittsburg, United States
Duration: 5 Nov 20238 Nov 2023
https://iss2023.acm.org/

Conference

ConferenceACM Interactive Surfaces and Spaces
LocationCarnegie Mellon Hamerschlag Hall
Country/TerritoryUnited States
CityPittsburg
Period05/11/202308/11/2023
Internet address
SeriesProceedings of the ACM on Human-Computer Interaction
NumberISS
Volume7
ISSN2573-0142

Keywords

  • dataset generation
  • deep learning
  • guidance
  • industry 4.0
  • near-symmetrical objects
  • tracking
  • user study

Fingerprint

Dive into the research topics of 'CADTrack: Instructions and Support for Orientation Disambiguation of Near-Symmetrical Objects'. Together they form a unique fingerprint.

Cite this