Publication:
A New Motion Segmentation Technique using Foreground-Background Bimodal

Simple item page
dc.contributor.authorAl-Smadi, M.en_US
dc.contributor.authorAbdul Rahim, K.en_US
dc.contributor.authorAbdul Salam, R.en_US
dc.date.accessioned2024-05-30T02:08:05Z
dc.date.available2024-05-30T02:08:05Z
dc.date.issued2018
dc.description.abstractVehicle detection is a fundamental step in urban traffic surveillance systems, since it provides necessary information for further processing. Conventional techniques utilize either background subtraction or foreground appearance-based detection, which involves either poor adaptation or high computation. The complexity of urban traffic scenarios lies in pose and orientation variations, slow or temporarily stopped vehicles and sudden illumination variations. In this work, a foreground-background bimodal is proposed to adapt for scene variation and complexity. Cumulative frame differencing and sigma-delta estimation are used to model foreground and background respectively. A correction feedback updates each model iteratively and recursively based on the detection mask of the other model. Variance update for sigma-delta estimation was limited to update background temporal activities, while cumulative frame differencing account for moving foreground by discarding limited background variations. Comparative experimental results for typical urban traffic sequences show that the proposed technique achieves robust and accurate detection, which improves adaptation, reduce false detection and satisfy real-time requirements.
dc.identifier.citationAl-Smadi, M., Abdul Rahim, K., & Abdul Salam, R. (2018). A New Motion Segmentation Technique using Foreground-Background Bimodal. Malaysian Journal of Science Health & Technology, 2(Special Issue). https://doi.org/10.33102/mjosht.v2i.44en_US
dc.identifier.doi10.33102/mjosht.v2i.44
dc.identifier.epage17
dc.identifier.issn2601-0003
dc.identifier.issue1
dc.identifier.spage12
dc.identifier.urihttps://mjosht.usim.edu.my/index.php/mjosht/article/view/44
dc.identifier.urihttps://oarep.usim.edu.my/handle/123456789/15503
dc.identifier.volume2
dc.languageEnglish
dc.language.isoen_USen_US
dc.publisherUniversiti Sains Islam Malaysiaen_US
dc.relation.ispartofMalaysian Journal of Science, Health & Technology
dc.subjectMotion segmentationen_US
dc.subjectCumulative frame differencingen_US
dc.subjectSigma-delta filteren_US
dc.subjectVehicle detectionen_US
dc.titleA New Motion Segmentation Technique using Foreground-Background Bimodalen_US
dc.typeArticleen_US
dspace.entity.typePublication

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
A New Motion Segmentation Technique Using ForegroundBackground Bimodal.pdf
Size:
875.36 KB
Format:
Adobe Portable Document Format
Download

Collections

Malaysian Journal of Science, Health & Technology (MJoSHT)