Show simple item record

dc.contributor.authorAnjum, Ashiq
dc.contributor.authorAbdullah, Tariq
dc.contributor.authorTariq, M. Fahim
dc.contributor.authorBaltaci, Yusuf
dc.contributor.authorAntonopoulos, Nikolaos
dc.date.accessioned2016-08-02T13:48:39Z
dc.date.available2016-08-02T13:48:39Z
dc.date.issued2016-01-13
dc.identifier.citationAnjum, A. et al., 'Video Stream Analysis in Clouds: An Object Detection and Classification Framework for High Performance Video Analytics', 2016:1, IEEE Transactions on Cloud Computingen
dc.identifier.issn2168-7161
dc.identifier.doi10.1109/TCC.2016.2517653
dc.identifier.urihttp://hdl.handle.net/10545/617828
dc.description.abstractEmail Print Request Permissions Object detection and classification are the basic tasks in video analytics and become the starting point for other complex applications. Traditional video analytics approaches are manual and time consuming. These are subjective due to the very involvement of human factor. We present a cloud based video analytics framework for scalable and robust analysis of video streams. The framework empowers an operator by automating the object detection and classification process from recorded video streams. An operator only specifies an analysis criteria and duration of video streams to analyse. The streams are then fetched from a cloud storage, decoded and analysed on the cloud. The framework executes compute intensive parts of the analysis to GPU powered servers in the cloud. Vehicle and face detection are presented as two case studies for evaluating the framework, with one month of data and a 15 node cloud. The framework reliably performed object detection and classification on the data, comprising of 21,600 video streams and 175 GB in size, in 6.52 hours. The GPU enabled deployment of the framework took 3 hours to perform analysis on the same number of video streams, thus making it at least twice as fast than the cloud deployment without GPUs.
dc.language.isoenen
dc.publisherIEEEen
dc.relation.urlhttp://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7381631en
dc.rightsArchived with thanks to IEEE Transactions on Cloud Computingen
dc.subjectVideo stream analysisen
dc.subjectObject detectionen
dc.subjectObject classificationen
dc.subjectCloud computingen
dc.titleVideo stream analysis in clouds: An object detection and classification framework for high performance video analyticsen
dc.typeArticleen
dc.contributor.departmentUniversity of Derby, UKen
dc.identifier.journalIEEE Transactions on Cloud Computingen
dc.internal.reviewer-noteLA (17/6/16) Early publisher proof attached. Email sent to Julia Stockdale (IEEE) for clarification on policy. LA 2/8/16 Julia Stockdale confirmed the publisher PDF or early proof attached cannot be uploaded to UDORA. Authors are sent a copy of their accepted manuscript that can be uploaded to repositories.en
html.description.abstractEmail Print Request Permissions Object detection and classification are the basic tasks in video analytics and become the starting point for other complex applications. Traditional video analytics approaches are manual and time consuming. These are subjective due to the very involvement of human factor. We present a cloud based video analytics framework for scalable and robust analysis of video streams. The framework empowers an operator by automating the object detection and classification process from recorded video streams. An operator only specifies an analysis criteria and duration of video streams to analyse. The streams are then fetched from a cloud storage, decoded and analysed on the cloud. The framework executes compute intensive parts of the analysis to GPU powered servers in the cloud. Vehicle and face detection are presented as two case studies for evaluating the framework, with one month of data and a 15 node cloud. The framework reliably performed object detection and classification on the data, comprising of 21,600 video streams and 175 GB in size, in 6.52 hours. The GPU enabled deployment of the framework took 3 hours to perform analysis on the same number of video streams, thus making it at least twice as fast than the cloud deployment without GPUs.


This item appears in the following Collection(s)

Show simple item record