Towards Fully-Synthetic Training for Industrial Applications

Christopher Mayershofer (), Tao Ge () and Johannes Fottner ()
Additional contact information
Christopher Mayershofer: Technical University of Munich
Tao Ge: Technical University of Munich
Johannes Fottner: Technical University of Munich

A chapter in LISS 2020, 2021, pp 765-782 from Springer

Abstract: 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. material and size) of target objects. And third, we propose a Mixed-lighting Illumination (MLI), combining global and local light sources to automatically create a diverse illumination of the scene. In addition to the image generation approach we create an industry-centered dataset for evaluation purposes. Experiments show, that our approach enables fully synthetic training of object detectors for industrial use-cases. Moreover, an ablation study provides evidence on the performance boost in object detection when using our novel features.

Keywords: Object detection; Synthetic data; Domain randomization (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-981-33-4359-7_53

Ordering information: This item can be ordered from
http://www.springer.com/9789813343597

DOI: 10.1007/978-981-33-4359-7_53

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().