Show simple item record

dc.contributor.authorYaseen, Muhammad Usman
dc.contributor.authorAnjum, Ashiq
dc.contributor.authorFarid, Mohsen
dc.contributor.authorAntonopoulos, Nick
dc.date.accessioned2018-10-12T14:29:37Z
dc.date.available2018-10-12T14:29:37Z
dc.date.issued2018-09-13
dc.identifier.citationYaseen, M.U., Anjum A, Farid M, Antonopoulos N. (2018) 'Cloud‐based video analytics using convolutional neural networks', Software: Practice and Experience. DOI: 10.1002/spe.2636en
dc.identifier.issn0038-0644
dc.identifier.doi10.1002/spe.2636
dc.identifier.urihttp://hdl.handle.net/10545/623037
dc.description.abstractObject classification is a vital part of any video analytics system, which could aid in complex applications such as object monitoring and management. Traditional video analytics systems work on shallow networks and are unable to harness the power of distributed processing for training and inference. We propose a cloud‐based video analytics system based on an optimally tuned convolutional neural network to classify objects from video streams. The tuning of convolutional neural network is empowered by in‐memory distributed computing. The object classification is performed by comparing the target object with the prestored trained patterns, generating a set of matching scores. The matching scores greater than an empirically determined threshold reveal the classification of the target object. The proposed system proved to be robust to classification errors with an accuracy and precision of 97% and 96%, respectively, and can be used as a general‐purpose video analytics system.
dc.description.sponsorshipUniversity of Derbyen
dc.language.isoenen
dc.relation.urlhttp://doi.wiley.com/10.1002/spe.2636en
dc.rightsArchived with thanks to Software: Practice and Experienceen
dc.subjectDeep learningen
dc.subjectVideo analysisen
dc.subjectNeural networksen
dc.subjectCloud Computingen
dc.titleCloud-based video analytics using convolutional neural networks.en
dc.typeArticleen
dc.contributor.departmentUniversity of Derbyen
dc.identifier.journalSoftware: Practice and Experienceen
dc.contributor.institutionDepartment of Electronics, Computing and Mathematics; University of Derby; Derby UK
dc.contributor.institutionDepartment of Electronics, Computing and Mathematics; University of Derby; Derby UK
dc.contributor.institutionDepartment of Electronics, Computing and Mathematics; University of Derby; Derby UK
dc.contributor.institutionDepartment of Electronics, Computing and Mathematics; University of Derby; Derby UK
dc.internal.reviewer-note06/10/2018 Available online but no vol or issue info yet. https://onlinelibrary.wiley.com/journal/1097024xen
refterms.dateFOA2019-02-28T17:36:48Z
html.description.abstractObject classification is a vital part of any video analytics system, which could aid in complex applications such as object monitoring and management. Traditional video analytics systems work on shallow networks and are unable to harness the power of distributed processing for training and inference. We propose a cloud‐based video analytics system based on an optimally tuned convolutional neural network to classify objects from video streams. The tuning of convolutional neural network is empowered by in‐memory distributed computing. The object classification is performed by comparing the target object with the prestored trained patterns, generating a set of matching scores. The matching scores greater than an empirically determined threshold reveal the classification of the target object. The proposed system proved to be robust to classification errors with an accuracy and precision of 97% and 96%, respectively, and can be used as a general‐purpose video analytics system.


Files in this item

Thumbnail
Name:
cloud-based-video_Final.pdf
Size:
2.061Mb
Format:
PDF
Description:
pre print

This item appears in the following Collection(s)

Show simple item record