Publikation:

Positional Encoding : Improving Class-Imbalanced Motorcycle Helmet use Classification

Lade...
Vorschaubild

Dateien

Zu diesem Dokument gibt es keine Dateien.

Datum

2021

Autor:innen

Siebert, Felix Wilhelm

Herausgeber:innen

Kontakt

ISSN der Zeitschrift

Electronic ISSN

ISBN

Bibliografische Daten

Verlag

Schriftenreihe

Auflagebezeichnung

URI (zitierfähiger Link)
ArXiv-ID

Internationale Patentnummer

Angaben zur Forschungsförderung

Projekt

Open Access-Veröffentlichung
Core Facility der Universität Konstanz

Gesperrt bis

Titel in einer weiteren Sprache

Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published

Erschienen in

2021 IEEE International Conference on Image Processing (ICIP). IEEE, 2021, pp. 1194-1198. ISSN 2381-8549. ISBN 978-1-66544-115-5. Available under: doi: 10.1109/ICIP42928.2021.9506178

Zusammenfassung

Recent advances in the automated detection of motorcycle riders’ helmet use have enabled road safety actors to process large scale video data efficiently and with high accuracy. To distinguish drivers from passengers in helmet use, the most straightforward way is to train a multi-class classifier, where each class corresponds to a specific combination of rider position and individual riders’ helmet use. However, such strategy results in long-tailed data distribution, with critically low class samples for a number of uncommon classes. In this paper, we propose a novel approach to address this limitation. Let n be the maximum number of riders a motorcycle can hold, we encode the helmet use on a motorcycle as a vector with 2n bits, where the first n bits denote if the encoded positions have riders, and the latter n bits denote if the rider in the corresponding position wears a helmet. With the novel helmet use positional encoding, we propose a deep learning model that stands on existing image classification architecture. The model simultaneously trains 2n binary classifiers, which allows more balanced samples for training. This method is simple to implement and requires no hyperparameter tuning. Experimental results demonstrate our approach outperforms the state-of-the-art approaches by 1.9% accuracy

Zusammenfassung in einer weiteren Sprache

Fachgebiet (DDC)
004 Informatik

Schlagwörter

Konferenz

2021 IEEE International Conference on Image Processing (ICIP), 19. Sept. 2021 - 22. Sept. 2021, Anchorage, AK, USA
Rezension
undefined / . - undefined, undefined

Forschungsvorhaben

Organisationseinheiten

Zeitschriftenheft

Zugehörige Datensätze in KOPS

Zitieren

ISO 690LIN, Hanhe, Guangan CHEN, Felix Wilhelm SIEBERT, 2021. Positional Encoding : Improving Class-Imbalanced Motorcycle Helmet use Classification. 2021 IEEE International Conference on Image Processing (ICIP). Anchorage, AK, USA, 19. Sept. 2021 - 22. Sept. 2021. In: 2021 IEEE International Conference on Image Processing (ICIP). IEEE, 2021, pp. 1194-1198. ISSN 2381-8549. ISBN 978-1-66544-115-5. Available under: doi: 10.1109/ICIP42928.2021.9506178
BibTex
@inproceedings{Lin2021Posit-56019,
  year={2021},
  doi={10.1109/ICIP42928.2021.9506178},
  title={Positional Encoding : Improving Class-Imbalanced Motorcycle Helmet use Classification},
  isbn={978-1-66544-115-5},
  issn={2381-8549},
  publisher={IEEE},
  booktitle={2021 IEEE International Conference on Image Processing (ICIP)},
  pages={1194--1198},
  author={Lin, Hanhe and Chen, Guangan and Siebert, Felix Wilhelm}
}
RDF
<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/56019">
    <dc:contributor>Siebert, Felix Wilhelm</dc:contributor>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dcterms:title>Positional Encoding : Improving Class-Imbalanced Motorcycle Helmet use Classification</dcterms:title>
    <dcterms:issued>2021</dcterms:issued>
    <dc:contributor>Chen, Guangan</dc:contributor>
    <dc:creator>Siebert, Felix Wilhelm</dc:creator>
    <dc:language>eng</dc:language>
    <dc:contributor>Lin, Hanhe</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-12-23T09:08:39Z</dcterms:available>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Lin, Hanhe</dc:creator>
    <dc:creator>Chen, Guangan</dc:creator>
    <dcterms:abstract xml:lang="eng">Recent advances in the automated detection of motorcycle riders’ helmet use have enabled road safety actors to process large scale video data efficiently and with high accuracy. To distinguish drivers from passengers in helmet use, the most straightforward way is to train a multi-class classifier, where each class corresponds to a specific combination of rider position and individual riders’ helmet use. However, such strategy results in long-tailed data distribution, with critically low class samples for a number of uncommon classes. In this paper, we propose a novel approach to address this limitation. Let n be the maximum number of riders a motorcycle can hold, we encode the helmet use on a motorcycle as a vector with 2n bits, where the first n bits denote if the encoded positions have riders, and the latter n bits denote if the rider in the corresponding position wears a helmet. With the novel helmet use positional encoding, we propose a deep learning model that stands on existing image classification architecture. The model simultaneously trains 2n binary classifiers, which allows more balanced samples for training. This method is simple to implement and requires no hyperparameter tuning. Experimental results demonstrate our approach outperforms the state-of-the-art approaches by 1.9% accuracy</dcterms:abstract>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/56019"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-12-23T09:08:39Z</dc:date>
    <dc:rights>terms-of-use</dc:rights>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
  </rdf:Description>
</rdf:RDF>

Interner Vermerk

xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter

Kontakt
URL der Originalveröffentl.

Prüfdatum der URL

Prüfungsdatum der Dissertation

Finanzierungsart

Kommentar zur Publikation

Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Diese Publikation teilen