KOPS - The Institutional Repository of the University of Konstanz

Helmet Use Detection of Tracked Motorcycles Using CNN-Based Multi-Task Learning

Helmet Use Detection of Tracked Motorcycles Using CNN-Based Multi-Task Learning

Cite This

Files in this item

Checksum: MD5:dbca6d8b29f5eefc22b9295979e80d7f

LIN, Hanhe, Jeremiah D. DENG, Deike ALBERS, Felix Wilhelm SIEBERT, 2020. Helmet Use Detection of Tracked Motorcycles Using CNN-Based Multi-Task Learning. In: IEEE Access. Institute of Electrical and Electronics Engineers (IEEE). 8, pp. 162073-162084. eISSN 2169-3536. Available under: doi: 10.1109/ACCESS.2020.3021357

@article{Lin2020Helme-51046, title={Helmet Use Detection of Tracked Motorcycles Using CNN-Based Multi-Task Learning}, year={2020}, doi={10.1109/ACCESS.2020.3021357}, volume={8}, journal={IEEE Access}, pages={162073--162084}, author={Lin, Hanhe and Deng, Jeremiah D. and Albers, Deike and Siebert, Felix Wilhelm} }

<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/rdf/resource/123456789/51046"> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-09-28T08:00:11Z</dc:date> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/51046/1/Lin_2-16ksnw6g1ivnm8.pdf"/> <dcterms:issued>2020</dcterms:issued> <dc:contributor>Deng, Jeremiah D.</dc:contributor> <dc:creator>Lin, Hanhe</dc:creator> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/51046/1/Lin_2-16ksnw6g1ivnm8.pdf"/> <dc:creator>Albers, Deike</dc:creator> <dc:contributor>Siebert, Felix Wilhelm</dc:contributor> <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by/4.0/"/> <dc:contributor>Albers, Deike</dc:contributor> <dc:contributor>Lin, Hanhe</dc:contributor> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/51046"/> <dc:creator>Deng, Jeremiah D.</dc:creator> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dc:rights>Attribution 4.0 International</dc:rights> <dc:creator>Siebert, Felix Wilhelm</dc:creator> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dcterms:title>Helmet Use Detection of Tracked Motorcycles Using CNN-Based Multi-Task Learning</dcterms:title> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-09-28T08:00:11Z</dcterms:available> <dc:language>eng</dc:language> <dcterms:abstract xml:lang="eng">Automated detection of motorcycle helmet use through video surveillance can facilitate efficient education and enforcement campaigns that increase road safety. However, existing detection approaches have a number of shortcomings, such as the inabilities to track individual motorcycles through multiple frames, or to distinguish drivers from passengers in helmet use. Furthermore, datasets used to develop approaches are limited in terms of traffic environments and traffic density variations. In this paper, we propose a CNN-based multi-task learning (MTL) method for identifying and tracking individual motorcycles, and register rider specific helmet use. We further release the HELMET dataset, which includes 91,000 annotated frames of 10,006 individual motorcycles from 12 observation sites in Myanmar. Along with the dataset, we introduce an evaluation metric for helmet use and rider detection accuracy, which can be used as a benchmark for evaluating future detection approaches. We show that the use of MTL for concurrent visual similarity learning and helmet use classification improves the efficiency of our approach compared to earlier studies, allowing a processing speed of more than 8 FPS on consumer hardware, and a weighted average F-measure of 67.3% for detecting the number of riders and helmet use of tracked motorcycles. Our work demonstrates the capability of deep learning as a highly accurate and resource efficient approach to collect critical road safety related data.</dcterms:abstract> </rdf:Description> </rdf:RDF>

Downloads since Sep 28, 2020 (Information about access statistics)

Lin_2-16ksnw6g1ivnm8.pdf 106

This item appears in the following Collection(s)

Attribution 4.0 International Except where otherwise noted, this item's license is described as Attribution 4.0 International

Search KOPS


Browse

My Account