Show simple item record

dc.contributor.authorAlvarez Piña, Gerardo
dc.contributor.authorMoya Sánchez, Eduardo Ulises
dc.contributor.authorSánchez-Pérez, Abraham
dc.contributor.authorCortés García, Claudio Ulises
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Ciències de la Computació
dc.contributor.otherBarcelona Supercomputing Center
dc.date.accessioned2022-11-04T12:02:31Z
dc.date.available2022-11-04T12:02:31Z
dc.date.issued2022
dc.identifier.citationAlvarez, G. [et al.]. Automatic vehicle counting area creation based on vehicle deep learning detection and DBSCAN. A: IEEE International Conference on Cluster Computing. "2022 IEEE International Conference on Cluster Computing, Cluster 2022: Heidelberg, Germany, 6-9 September 2022: proceedings". Institute of Electrical and Electronics Engineers (IEEE), 2022, p. 535-538. ISBN 978-1-6654-9856-2. DOI 10.1109/CLUSTER51413.2022.00069.
dc.identifier.isbn978-1-6654-9856-2
dc.identifier.urihttp://hdl.handle.net/2117/375674
dc.description.abstractDeep learning and high-performance computing have augmented and speed-up the scope of video-based vehicles' massive counting. The automatic vehicle counts result from the detection and tracking of the vehicles in certain areas or Regions of Interest (ROI). In this paper, we propose a technique to create a counting area with different traffic-flow directions based on YOLO and DBSCAN You Only Look Once version five (YOLOv5) and Density-Based Spatial Clustering of Applications with Noise (DBSCAN). We compare the performance of the method against the manually counted ground truth. The proposed method showed that it is possible to generate the ROIs (counting areas) according to the traffic flow using deep learning techniques with relatively good accuracy (less than 5 % error). These results are promising but we need to explore the limits of this method with more street-view configurations, time and other detection and tracking algorithms, and in an HPC environment.
dc.format.extent4 p.
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
dc.subjectÀrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Aplicacions informàtiques a la física i l‘enginyeria
dc.subject.lcshDeep learning
dc.subject.lcshHigh performance computing
dc.subject.lcshVehicle detectors
dc.subject.otherVehicle counting
dc.subject.otherDBSCAN
dc.titleAutomatic vehicle counting area creation based on vehicle deep learning detection and DBSCAN
dc.typeConference report
dc.subject.lemacAprenentatge profund
dc.subject.lemacCàlcul intensiu (Informàtica)
dc.identifier.doi10.1109/CLUSTER51413.2022.00069
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://ieeexplore.ieee.org/document/9912668
dc.rights.accessOpen Access
local.identifier.drac34844645
dc.description.versionPostprint (author's final draft)
local.citation.authorAlvarez, G.; Moya, E.; Sánchez-Pérez, A.; Cortes, U.
local.citation.contributorIEEE International Conference on Cluster Computing
local.citation.publicationName2022 IEEE International Conference on Cluster Computing, Cluster 2022: Heidelberg, Germany, 6-9 September 2022: proceedings
local.citation.startingPage535
local.citation.endingPage538


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record