Show simple item record

dc.contributor.authorSeker, Mert
dc.contributor.authorMännistö, Anssi
dc.contributor.authorIosifidis, Alexandros
dc.contributor.authorRaitoharju, Jenni
dc.date.accessioned2022-12-28T09:51:56Z
dc.date.available2022-12-28T09:51:56Z
dc.date.issued2022
dc.identifier.citationSeker, M., Männistö, A., Iosifidis, A., & Raitoharju, J. (2022). Automatic social distance estimation for photographic studies : Performance evaluation, test benchmark, and algorithm. <i>Machine Learning with Applications</i>, <i>10</i>, Article 100427. <a href="https://doi.org/10.1016/j.mlwa.2022.100427" target="_blank">https://doi.org/10.1016/j.mlwa.2022.100427</a>
dc.identifier.otherCONVID_160105277
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/84621
dc.description.abstractThe social distancing regulations introduced to slow down the spread of COVID-19 virus directly affect a basic form of non-verbal communication, and there may be longer term impacts on human behavior and culture that remain to be analyzed in proxemics studies. To obtain quantitative results for such studies, large media and/or personal photo collections must be analyzed. Several social distance monitoring methods have been proposed for safety purposes, but they are not directly applicable to general photo collections with large variations in the imaging setup. In such studies, the interest shifts from safety to analyzing subtle differences in social distances. Currently, there is no suitable benchmark for developing such algorithms. Collecting images with measured ground-truth pair-wise distances using different camera settings is cumbersome. Moreover, performance evaluation for these algorithms is not straightforward, and there is no widely accepted evaluation protocol. In this paper, we provide an image dataset with measured pair-wise social distances under different camera positions and settings. We suggest a performance evaluation protocol and provide a benchmark to easily evaluate such algorithms. We also propose an automatic social distance estimation method that can be applied on general photo collections. Our method is a hybrid method that combines deep learning-based object detection and human pose estimation with projective geometry. The method can be applied on uncalibrated single images with known focal length and sensor size. The results on our benchmark are encouraging with 91% human detection rate and only 38.24% average relative distance estimation error among the detected people.en
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.publisherElsevier
dc.relation.ispartofseriesMachine Learning with Applications
dc.rightsCC BY 4.0
dc.subject.othersocial distance estimation
dc.subject.otherperson detection
dc.subject.otherhuman pose estimation
dc.subject.otherperformance evaluation
dc.subject.othertest benchmark
dc.subject.otherproxemics
dc.titleAutomatic social distance estimation for photographic studies : Performance evaluation, test benchmark, and algorithm
dc.typearticle
dc.identifier.urnURN:NBN:fi:jyu-202212285855
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosFaculty of Information Technologyen
dc.type.urihttp://purl.org/eprint/type/JournalArticle
dc.type.coarhttp://purl.org/coar/resource_type/c_2df8fbb1
dc.description.reviewstatuspeerReviewed
dc.relation.issn2666-8270
dc.relation.volume10
dc.type.versionpublishedVersion
dc.rights.copyright© 2022 The Author(s)
dc.rights.accesslevelopenAccessfi
dc.subject.ysoCOVID-19
dc.subject.ysoarviointi
dc.subject.ysokonenäkö
dc.subject.ysoprojektiivinen geometria
dc.subject.ysokoneoppiminen
dc.subject.ysoalgoritmit
dc.subject.ysohahmontunnistus (tietotekniikka)
dc.subject.ysosyväoppiminen
dc.subject.ysovalokuvat
dc.subject.ysoetäisyys
dc.format.contentfulltext
jyx.subject.urihttp://www.yso.fi/onto/yso/p38829
jyx.subject.urihttp://www.yso.fi/onto/yso/p7413
jyx.subject.urihttp://www.yso.fi/onto/yso/p2618
jyx.subject.urihttp://www.yso.fi/onto/yso/p14431
jyx.subject.urihttp://www.yso.fi/onto/yso/p21846
jyx.subject.urihttp://www.yso.fi/onto/yso/p14524
jyx.subject.urihttp://www.yso.fi/onto/yso/p8266
jyx.subject.urihttp://www.yso.fi/onto/yso/p39324
jyx.subject.urihttp://www.yso.fi/onto/yso/p2699
jyx.subject.urihttp://www.yso.fi/onto/yso/p4168
dc.rights.urlhttps://creativecommons.org/licenses/by/4.0/
dc.relation.doi10.1016/j.mlwa.2022.100427
jyx.fundinginformationM. Seker, A. Männistö, and J. Raitoharju would like to acknowledge the financial support from Helsingin Sanomat foundation, project ‘‘Machine learning based analysis of the photographs of the corona crisis’’. A. Iosifidis acknowledges funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 957337 (MARVEL).
dc.type.okmA1


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

CC BY 4.0
Except where otherwise noted, this item's license is described as CC BY 4.0