To Örebro University

oru.seÖrebro University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Comparative Analysis of Deep Neural Networks for the Detection and Decoding of Data Matrix Landmarks in Cluttered Indoor Environments
Örebro University, School of Science and Technology. IEETA, DEM, University of Aveiro, Aveiro, Portugal. (Center for Applied Autonomous Sensor Systems (AASS))ORCID iD: 0000-0001-9059-6175
IEETA, DEM, University of Aveiro, Aveiro, Portugal.
Örebro University, School of Science and Technology. (Center for Applied Autonomous Sensor Systems (AASS))ORCID iD: 0000-0002-3908-4921
IEETA, DEM, University of Aveiro, Aveiro, Portugal.
2021 (English)In: Journal of Intelligent and Robotic Systems, ISSN 0921-0296, E-ISSN 1573-0409, Vol. 103, no 1, article id 13Article in journal (Refereed) Published
Abstract [en]

Data Matrix patterns imprinted as passive visual landmarks have shown to be a valid solution for the self-localization of Automated Guided Vehicles (AGVs) in shop floors. However, existing Data Matrix decoding applications take a long time to detect and segment the markers in the input image. Therefore, this paper proposes a pipeline where the detector is based on a real-time Deep Learning network and the decoder is a conventional method, i.e. the implementation in libdmtx. To do so, several types of Deep Neural Networks (DNNs) for object detection were studied, trained, compared, and assessed. The architectures range from region proposals (Faster R-CNN) to single-shot methods (SSD and YOLO). This study focused on performance and processing time to select the best Deep Learning (DL) model to carry out the detection of the visual markers. Additionally, a specific data set was created to evaluate those networks. This test set includes demanding situations, such as high illumination gradients in the same scene and Data Matrix markers positioned in skewed planes. The proposed approach outperformed the best known and most used Data Matrix decoder available in libraries like libdmtx.

Place, publisher, year, edition, pages
Springer, 2021. Vol. 103, no 1, article id 13
Keywords [en]
Deep learning, Data matrix, Detection, Decoding, Localization
National Category
Computer graphics and computer vision Computer Sciences
Identifiers
URN: urn:nbn:se:oru:diva-93889DOI: 10.1007/s10846-021-01442-xISI: 000684216000002Scopus ID: 2-s2.0-85112339177OAI: oai:DiVA.org:oru-93889DiVA, id: diva2:1587552
Funder
Knut and Alice Wallenberg Foundation
Note

Funding Agencies:

Örebro University 

Spanish Ministerio de Ciencia, Innovacion y Universidades RTI2018-095599-A-C22

Project SeaAI-FA 02 2017 011

Wallenberg AI, Autonomous Systems and Software Program (WASP) Project PRODUTECH II SIF-POCI-01-0247-FEDER-024541

Available from: 2021-08-25 Created: 2021-08-25 Last updated: 2025-02-01Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Almeida, TiagoMartinez Mozos, Oscar

Search in DiVA

By author/editor
Almeida, TiagoMartinez Mozos, Oscar
By organisation
School of Science and Technology
In the same journal
Journal of Intelligent and Robotic Systems
Computer graphics and computer visionComputer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 208 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf