You are here: Home → Proceedings
Document Actions

Citation and metadata

Back to the article.

Recommended citation

Azizpour M, Namazypour N, Kirchheim A (2022). Synthetic Data Generation for Robotic Order Picking. Logistics Journal : Proceedings, Vol. 2022. (urn:nbn:de:0009-14-55795)

Download Citation

Endnote

%0 Journal Article
%T Synthetic Data Generation for Robotic Order Picking
%A Azizpour, Moein
%A Namazypour, Nafiseh
%A Kirchheim, Alice
%J Logistics Journal : Proceedings
%D 2022
%V 2022
%N 18
%@ 2192-9084
%F azizpour2022
%X Advances in robotics, especially in computer vision, have led to the increasing use of robots in order picking. Deep Learning methods using CNN for computer vision purposes have shown good object detection and localization results. However, training neural networks requires a large amount of domain-specific labelled data. In this work, we generated synthetic data and converted it to the appropriate format to be fed to neural network. For this purpose, randomized camera angles, backgrounds, and object configuration are used for data augmentation. A generalized and balanced dataset is ensured by varying these parameters based on the properties of natural objects.
%L 620
%K Logistics
%K computer vision
%K order picking
%K pick and place
%K synthetic data generation
%R 10.2195/lj_proc_azizpour_en_202211_01
%U http://nbn-resolving.de/urn:nbn:de:0009-14-55795
%U http://dx.doi.org/10.2195/lj_proc_azizpour_en_202211_01
Download

Bibtex

@Article{azizpour2022,
  author = 	"Azizpour, Moein
		and Namazypour, Nafiseh
		and Kirchheim, Alice",
  title = 	"Synthetic Data Generation for Robotic Order Picking",
  journal = 	"Logistics Journal : Proceedings",
  year = 	"2022",
  volume = 	"2022",
  number = 	"18",
  keywords = 	"Logistics; computer vision; order picking; pick and place; synthetic data generation",
  abstract = 	"Advances in robotics, especially in computer vision, have led to the increasing use of robots in order picking. Deep Learning methods using CNN for computer vision purposes have shown good object detection and localization results. However, training neural networks requires a large amount of domain-specific labelled data. In this work, we generated synthetic data and converted it to the appropriate format to be fed to neural network. For this purpose, randomized camera angles, backgrounds, and object configuration are used for data augmentation. A generalized and balanced dataset is ensured by varying these parameters based on the properties of natural objects.",
  issn = 	"2192-9084",
  doi = 	"10.2195/lj_proc_azizpour_en_202211_01",
  url = 	"http://nbn-resolving.de/urn:nbn:de:0009-14-55795"
}
Download

RIS

TY  - JOUR
AU  - Azizpour, Moein
AU  - Namazypour, Nafiseh
AU  - Kirchheim, Alice
PY  - 2022
DA  - 2022//
TI  - Synthetic Data Generation for Robotic Order Picking
JO  - Logistics Journal : Proceedings
VL  - 2022
IS  - 18
KW  - Logistics
KW  - computer vision
KW  - order picking
KW  - pick and place
KW  - synthetic data generation
AB  - Advances in robotics, especially in computer vision, have led to the increasing use of robots in order picking. Deep Learning methods using CNN for computer vision purposes have shown good object detection and localization results. However, training neural networks requires a large amount of domain-specific labelled data. In this work, we generated synthetic data and converted it to the appropriate format to be fed to neural network. For this purpose, randomized camera angles, backgrounds, and object configuration are used for data augmentation. A generalized and balanced dataset is ensured by varying these parameters based on the properties of natural objects.
SN  - 2192-9084
UR  - http://nbn-resolving.de/urn:nbn:de:0009-14-55795
DO  - 10.2195/lj_proc_azizpour_en_202211_01
ID  - azizpour2022
ER  -
Download

Wordbib

<?xml version="1.0" encoding="UTF-8"?>
<b:Sources SelectedStyle="" xmlns:b="http://schemas.openxmlformats.org/officeDocument/2006/bibliography"  xmlns="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" >
<b:Source>
<b:Tag>azizpour2022</b:Tag>
<b:SourceType>ArticleInAPeriodical</b:SourceType>
<b:Year>2022</b:Year>
<b:PeriodicalTitle>Logistics Journal : Proceedings</b:PeriodicalTitle>
<b:Volume>2022</b:Volume>
<b:Issue>18</b:Issue>
<b:Url>http://nbn-resolving.de/urn:nbn:de:0009-14-55795</b:Url>
<b:Url>http://dx.doi.org/10.2195/lj_proc_azizpour_en_202211_01</b:Url>
<b:Author>
<b:Author><b:NameList>
<b:Person><b:Last>Azizpour</b:Last><b:First>Moein</b:First></b:Person>
<b:Person><b:Last>Namazypour</b:Last><b:First>Nafiseh</b:First></b:Person>
<b:Person><b:Last>Kirchheim</b:Last><b:First>Alice</b:First></b:Person>
</b:NameList></b:Author>
</b:Author>
<b:Title>Synthetic Data Generation for Robotic Order Picking</b:Title>
<b:Comments>Advances in robotics, especially in computer vision, have led to the increasing use of robots in order picking. Deep Learning methods using CNN for computer vision purposes have shown good object detection and localization results. However, training neural networks requires a large amount of domain-specific labelled data. In this work, we generated synthetic data and converted it to the appropriate format to be fed to neural network. For this purpose, randomized camera angles, backgrounds, and object configuration are used for data augmentation. A generalized and balanced dataset is ensured by varying these parameters based on the properties of natural objects.</b:Comments>
</b:Source>
</b:Sources>
Download

ISI

PT Journal
AU Azizpour, M
   Namazypour, N
   Kirchheim, A
TI Synthetic Data Generation for Robotic Order Picking
SO Logistics Journal : Proceedings
PY 2022
VL 2022
IS 18
DI 10.2195/lj_proc_azizpour_en_202211_01
DE Logistics; computer vision; order picking; pick and place; synthetic data generation
AB Advances in robotics, especially in computer vision, have led to the increasing use of robots in order picking. Deep Learning methods using CNN for computer vision purposes have shown good object detection and localization results. However, training neural networks requires a large amount of domain-specific labelled data. In this work, we generated synthetic data and converted it to the appropriate format to be fed to neural network. For this purpose, randomized camera angles, backgrounds, and object configuration are used for data augmentation. A generalized and balanced dataset is ensured by varying these parameters based on the properties of natural objects.
ER
Download

Mods

<mods>
  <titleInfo>
    <title>Synthetic Data Generation for Robotic Order Picking</title>
  </titleInfo>
  <name type="personal">
    <namePart type="family">Azizpour</namePart>
    <namePart type="given">Moein</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Namazypour</namePart>
    <namePart type="given">Nafiseh</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Kirchheim</namePart>
    <namePart type="given">Alice</namePart>
  </name>
  <abstract>Advances in robotics, especially in computer vision, have led to the increasing use of robots in order picking. Deep Learning methods using CNN for computer vision purposes have shown good object detection and localization results. However, training neural networks requires a large amount of domain-specific labelled data. In this work, we generated synthetic data and converted it to the appropriate format to be fed to neural network. For this purpose, randomized camera angles, backgrounds, and object configuration are used for data augmentation. A generalized and balanced dataset is ensured by varying these parameters based on the properties of natural objects.</abstract>
  <subject>
    <topic>Logistics</topic>
    <topic>computer vision</topic>
    <topic>order picking</topic>
    <topic>pick and place</topic>
    <topic>synthetic data generation</topic>
  </subject>
  <classification authority="ddc">620</classification>
  <relatedItem type="host">
    <genre authority="marcgt">periodical</genre>
    <genre>academic journal</genre>
    <titleInfo>
      <title>Logistics Journal : Proceedings</title>
    </titleInfo>
    <part>
      <detail type="volume">
        <number>2022</number>
      </detail>
      <detail type="issue">
        <number>18</number>
      </detail>
      <date>2022</date>
    </part>
  </relatedItem>
  <identifier type="issn">2192-9084</identifier>
  <identifier type="urn">urn:nbn:de:0009-14-55795</identifier>
  <identifier type="doi">10.2195/lj_proc_azizpour_en_202211_01</identifier>
  <identifier type="uri">http://nbn-resolving.de/urn:nbn:de:0009-14-55795</identifier>
  <identifier type="citekey">azizpour2022</identifier>
</mods>
Download

Full Metadata

Bibliographic Citation Logistics Journal : referierte Veröffentlichungen, Vol. 2022, Iss. 18
Title

Synthetic Data Generation for Robotic Order Picking (eng)
Author Moein Azizpour, Nafiseh Namazypour, Alice Kirchheim
Language eng
Abstract Advances in robotics, especially in computer vision, have led to the increasing use of robots in order picking. Deep Learning methods using CNN for computer vision purposes have shown good object detection and localization results. However, training neural networks requires a large amount of domain-specific labelled data. In this work, we generated synthetic data and converted it to the appropriate format to be fed to neural network. For this purpose, randomized camera angles, backgrounds, and object configuration are used for data augmentation. A generalized and balanced dataset is ensured by varying these parameters based on the properties of natural objects. Fortschritte in der Robotik, insbesondere in der Computer Vision, haben zu einem zunehmenden Einsatz von Robotern in der Kommissionierung geführt. Deep-Learning-Methoden, die CNN für Computer-Vision-Zwecke verwenden, haben gute Ergebnisse bei der Objekterkennung und -lokalisierung gezeigt. Das Trainieren neuronaler Netze erfordert jedoch eine große Menge an objektspezifisch markierten Daten. In diesem Beitrag haben wir synthetische Daten generiert und in ein geeignetes Format konvertiert, um damit neuronale netzte zu trainieren. Zu diesem Zweck werden randomisierte Kamerawinkel, Hintergründe und Objektkonfigurationen zur Datenerweiterung verwendet. Durch die Variation dieser Parameter auf der Grundlage der Eigenschaften natürlicher Objekte wird ein allgemeiner und ausgewogener Datensatz gewährleistet.
Subject Logistics, computer vision, order picking, pick and place, synthetic data generation
DDC 620
Rights fDPPL
URN: urn:nbn:de:0009-14-55795
DOI https://doi.org/10.2195/lj_proc_azizpour_en_202211_01