Multi-Spectral Segmentation with Synthesized Data for Refuse Sorting

Harald Ganster; Alfred Rinnhofer; Georg Waltner; Christian Payer; Heimo Gursch; Christian Oberwinkler; Reinhard Meisenbichler; Horst Bischof

doi:10.3217/978-3-85125-869-1-16

Multi-Spectral Segmentation with Synthesized Data for Refuse Sorting

Harald Ganster, Alfred Rinnhofer, Georg Waltner, Christian Payer, Heimo Gursch, Christian Oberwinkler, Reinhard Meisenbichler, Horst Bischof

Publikation: Beitrag in Buch/Bericht/Konferenzband › Beitrag in einem Konferenzband › Begutachtung

Abstract

Refuse sorting is a key technology to increase the recycling rate and reduce the growths of landfills worldwide. However, monitoring and parameterization of sorting facilities is still done in a mostly static fashion. This work combines multi-spectral imaging with deep learning based image recognition to monitor and dynamically optimize processes in sorting facilities.
Our solution is capable of monitoring the sorting process remotely avoiding potentially harmful working conditions due to dust, bacteria, and fungal spores. Furthermore, the introduction of objective sorting performance measures enables informed decisions to improve the sorting parameters and react quicker to changes in the refuse composition.

Originalsprache	englisch
Titel	Proceedings of the OAGM Workshop 2021
Redakteure/-innen	Markus Seidl, Matthias Zeppelzauer, Peter M. Roth
Herausgeber (Verlag)	Verlag der Technischen Universität Graz
Seitenumfang	3
DOIs	https://doi.org/10.3217/978-3-85125-869-1-16
Publikationsstatus	Veröffentlicht - 2021
Veranstaltung	44th OAGM Workshop 2021: Computer Vision and Pattern Analysis Across Domains: ÖAGM 2021 - University of Applied Sciences St. Pölten, abgesagt, Österreich Dauer: 24 Nov. 2021 → 25 Nov. 2021

Konferenz

Konferenz	44th OAGM Workshop 2021: Computer Vision and Pattern Analysis Across Domains
Land/Gebiet	Österreich
Ort	abgesagt
Zeitraum	24/11/21 → 25/11/21

Zugriff auf Dokument

10.3217/978-3-85125-869-1-16Lizenz: CC BY 4.0

Dieses zitieren

Multi-Spectral Segmentation with Synthesized Data for Refuse Sorting. / Ganster, Harald; Rinnhofer, Alfred; Waltner, Georg et al.
Proceedings of the OAGM Workshop 2021. Hrsg. / Markus Seidl; Matthias Zeppelzauer; Peter M. Roth. Verlag der Technischen Universität Graz, 2021.

Publikation: Beitrag in Buch/Bericht/Konferenzband › Beitrag in einem Konferenzband › Begutachtung

Ganster, H, Rinnhofer, A, Waltner, G, Payer, C, Gursch, H, Oberwinkler, C, Meisenbichler, R & Bischof, H 2021, Multi-Spectral Segmentation with Synthesized Data for Refuse Sorting. in M Seidl, M Zeppelzauer & PM Roth (Hrsg.), Proceedings of the OAGM Workshop 2021. Verlag der Technischen Universität Graz, 44th OAGM Workshop 2021: Computer Vision and Pattern Analysis Across Domains, abgesagt, Österreich, 24/11/21. https://doi.org/10.3217/978-3-85125-869-1-16

@inproceedings{3618bd4c32b04815b88cd4fd3dc1beec,

title = "Multi-Spectral Segmentation with Synthesized Data for Refuse Sorting",

abstract = "Refuse sorting is a key technology to increase the recycling rate and reduce the growths of landfills worldwide. However, monitoring and parameterization of sorting facilities is still done in a mostly static fashion. This work combines multi-spectral imaging with deep learning based image recognition to monitor and dynamically optimize processes in sorting facilities.Our solution is capable of monitoring the sorting process remotely avoiding potentially harmful working conditions due to dust, bacteria, and fungal spores. Furthermore, the introduction of objective sorting performance measures enables informed decisions to improve the sorting parameters and react quicker to changes in the refuse composition.",

author = "Harald Ganster and Alfred Rinnhofer and Georg Waltner and Christian Payer and Heimo Gursch and Christian Oberwinkler and Reinhard Meisenbichler and Horst Bischof",

year = "2021",

doi = "10.3217/978-3-85125-869-1-16",

language = "English",

editor = "Markus Seidl and Matthias Zeppelzauer and Roth, {Peter M.}",

booktitle = "Proceedings of the OAGM Workshop 2021",

publisher = "Verlag der Technischen Universit{\"a}t Graz",

note = "44th OAGM Workshop 2021: Computer Vision and Pattern Analysis Across Domains : {\"O}AGM 2021 ; Conference date: 24-11-2021 Through 25-11-2021",

}

TY - GEN

T1 - Multi-Spectral Segmentation with Synthesized Data for Refuse Sorting

AU - Ganster, Harald

AU - Rinnhofer, Alfred

AU - Waltner, Georg

AU - Payer, Christian

AU - Gursch, Heimo

AU - Oberwinkler, Christian

AU - Meisenbichler, Reinhard

AU - Bischof, Horst

PY - 2021

Y1 - 2021

N2 - Refuse sorting is a key technology to increase the recycling rate and reduce the growths of landfills worldwide. However, monitoring and parameterization of sorting facilities is still done in a mostly static fashion. This work combines multi-spectral imaging with deep learning based image recognition to monitor and dynamically optimize processes in sorting facilities.Our solution is capable of monitoring the sorting process remotely avoiding potentially harmful working conditions due to dust, bacteria, and fungal spores. Furthermore, the introduction of objective sorting performance measures enables informed decisions to improve the sorting parameters and react quicker to changes in the refuse composition.

AB - Refuse sorting is a key technology to increase the recycling rate and reduce the growths of landfills worldwide. However, monitoring and parameterization of sorting facilities is still done in a mostly static fashion. This work combines multi-spectral imaging with deep learning based image recognition to monitor and dynamically optimize processes in sorting facilities.Our solution is capable of monitoring the sorting process remotely avoiding potentially harmful working conditions due to dust, bacteria, and fungal spores. Furthermore, the introduction of objective sorting performance measures enables informed decisions to improve the sorting parameters and react quicker to changes in the refuse composition.

U2 - 10.3217/978-3-85125-869-1-16

DO - 10.3217/978-3-85125-869-1-16

M3 - Conference paper

BT - Proceedings of the OAGM Workshop 2021

A2 - Seidl, Markus

A2 - Zeppelzauer, Matthias

A2 - Roth, Peter M.

PB - Verlag der Technischen Universität Graz

T2 - 44th OAGM Workshop 2021: Computer Vision and Pattern Analysis Across Domains

Y2 - 24 November 2021 through 25 November 2021

ER -

Multi-Spectral Segmentation with Synthesized Data for Refuse Sorting

Abstract

Konferenz

Zugriff auf Dokument

Fingerprint

Dieses zitieren