Please use this identifier to cite or link to this item:
Publisher DOI: 10.1007/978-3-030-74032-0_27
Title: Towards synthetic AI training data for image classification in intralogistic settings
Language: English
Authors: Schoepflin, Daniel  
Iyer, Karthik 
Gomse, Martin 
Schüppstuhl, Thorsten  
Editor: Schüppstuhl, Thorsten  
Tracht, Kirsten 
Raatz, Annika 
Keywords: Synthetic data;Training data generation;Image classification;Production supplying logistic
Issue Date: 1-Jan-2022
Publisher: Springer
Source: Annals of Scientific Society for Assembly, Handling and Industrial Robotics 2021. - Cham, 2022. - Seite 325-336
Abstract (english): 
Obtaining annotated data for proper training of AI image classifiers remains a challenge for successful deployment in industrial settings. As a promising alternative to handcrafted annotations, synthetic training data generation has grown in popularity. However, in most cases the pipelines used to generate this data are not of universal nature and have to be redesigned for different domain applications. This requires a detailed formulation of the domain through a semantic scene grammar. We aim to present such a grammar that is based on domain knowledge for the production-supplying transport of components in intralogistic settings. We present a use-case analysis for the domain of production supplying logistics and derive a scene grammar, which can be used to formulate similar problem statements in the domain for the purpose of data generation. We demonstrate the use of this grammar to feed a scene generation pipeline and obtain training data for an AI based image classifier.
DOI: 10.15480/882.4071
ISBN: 978-3-030-74031-3
Institute: Flugzeug-Produktionstechnik M-23 
Document Type: Chapter/Article (Proceedings)
Project: Entwicklung und prototypische Erprobung von intelligenten und modularen Ladungsträgern zur schnelleren und effizienteren Materialversorgung bei der Flugzeugproduktion 
Funded by: Bundesministerium für Wirtschaft und Energie - BMWi 
More Funding information: Research was funded by the German Federal Ministry for Economics and Energy under the Program LuFo V-3 DEPOT.
Peer Reviewed: Yes
License: CC BY 4.0 (Attribution) CC BY 4.0 (Attribution)
Appears in Collections:Publications with fulltext

Files in This Item:
File Description SizeFormat
Schoepflin2022_Chapter_TowardsSyntheticAITrainingData.pdf471,69 kBAdobe PDFView/Open
Show full item record

Page view(s)

checked on Jan 21, 2022


checked on Jan 21, 2022

Google ScholarTM


Note about this record

Cite this record


This item is licensed under a Creative Commons License Creative Commons