Video stream analysis in clouds: An object detection and classification framework for high performance video analytics

Hdl Handle:
http://hdl.handle.net/10545/617828
Title:
Video stream analysis in clouds: An object detection and classification framework for high performance video analytics
Authors:
Anjum, Ashiq; Abdullah, Tariq; Tariq, M. Fahim; Baltaci, Yusuf; Antonopoulos, Nikolaos
Abstract:
Email 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.
Affiliation:
University of Derby, UK
Citation:
Anjum, 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 Computing
Publisher:
IEEE
Journal:
IEEE Transactions on Cloud Computing
Issue Date:
13-Jan-2016
URI:
http://hdl.handle.net/10545/617828
DOI:
10.1109/TCC.2016.2517653
Additional Links:
http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7381631
Type:
Article
Language:
en
ISSN:
2168-7161
Appears in Collections:
Department of Electronics, Computing & Maths

Full metadata record

DC FieldValue Language
dc.contributor.authorAnjum, Ashiqen
dc.contributor.authorAbdullah, Tariqen
dc.contributor.authorTariq, M. Fahimen
dc.contributor.authorBaltaci, Yusufen
dc.contributor.authorAntonopoulos, Nikolaosen
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.en
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
All Items in UDORA are protected by copyright, with all rights reserved, unless otherwise indicated.