User: Guest  Login
Title:

Towards Fully-Synthetic Training for Industrial Applications

Document type:
Konferenzbeitrag
Author(s):
Mayershofer, C.; Ge, T.; Fottner, J.
Non-TUM Co-author(s):
nein
Cooperation:
-
Abstract:
This paper proposes a scalable approach for synthetic image generation of industrial objects leveraging Blender for image rendering. In addition to common components in synthetic image generation research, three novel features are presented: First, we model relations between target objects and randomly apply those during scene generation (Object Relation Modelling (ORM)). Second, we extend the idea of distractors and create Object-alike Distractors (OAD), resembling the textural appearance (i.e....     »
Keywords:
Object detection, Synthetic data, Domain randomization
Intellectual Contribution:
Contribution to Practice
Book / Congress title:
10th International Conference on Logistics, Informatics and Service Sciences (LISS)
Congress (additional information):
Budapest, Hungary
Year:
2020
Fulltext / DOI:
doi:no DOI available
Key publication:
Ja
Peer reviewed:
Ja
International:
Ja
Commissioned:
not commissioned
Technology:
Ja
Interdisciplinarity:
Ja
Mission statement:
;
Ethics and Sustainability:
Nein
 BibTeX
versions