KIT | KIT-Bibliothek | Impressum | Datenschutz

CAD2Real: Deep learning with domain randomization of CAD data for 3D pose estimation of electronic control unit housings

Bäuerle, Simon; Barth, Jonas; Tavares, Elton de Menezes; Steimer, Andreas; Mikut, Ralf ORCID iD icon

Abstract (englisch):

Electronic control units (ECUs) are essential for many automobile components,
e.g. engine, anti-lock braking system (ABS), steering and airbags. For some
products, the 3D pose of each single ECU needs to be determined during
series production. Deep learning approaches can not easily be applied to this
problem, because labeled training data is not available in sufficient numbers.
Thus, we train state-of-the-art artificial neural networks (ANNs) on purely
synthetic training data, which is automatically created from a single CAD file.
By randomizing parameters during rendering of training images, we enable
inference on RGB images of a real sample part. In contrast to classic image
processing approaches, this data-driven approach poses only few requirements
regarding the measurement setup and transfers to related use cases with little
development effort.

Verlagsausgabe §
DOI: 10.5445/IR/1000127954
Veröffentlicht am 22.12.2020
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Automation und angewandte Informatik (IAI)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2020
Sprache Englisch
Identifikator ISBN: 978-3-7315-1051-2
KITopen-ID: 1000127954
Erschienen in Proceedings - 30. Workshop Computational Intelligence : Berlin, 26. - 27. November 2020
Veranstaltung 30. Workshop Computational Intelligence (2020), Berlin, Deutschland, 26.11.2020 – 27.11.2020
Verlag KIT Scientific Publishing
Seiten 33-52
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page