Automated video surveillance applications require accurate separation of foreground and background image content. Cost sensitive embedded platforms place realtime performance and efficiency demands on techniques to accomplish this task. In this paper we evaluate pixel-level foreground extraction techniques for a low cost integrated surveillance system. We introduce a new adaptive technique, multimodal mean (MM, which balances accuracy, performance, and efficiency to meet embedded system requirements. Our evaluation compares several pixel-level foreground extraction techniques in terms of their computation and storage requirements, and functional accuracy for three representative video sequences. The proposed MM algorithm delivers comparable accuracy of the best alternative (Mixture of Gaussians) with a 6X improvement in execution time and an 18% reduction in required storage.

APEWOKIN S, VALENTINE B, WILLS L, WILLS S, GENTILE A (2007). Multimodal Mean Adaptive Backgrounding for Embedded Real-Time Video Surveillance. ??????? it.cilea.surplus.oa.citation.tipologie.CitationProceedings.prensentedAt ??????? Computer Vision and Pattern Recognition, 2007. CVPR '07, USA [10.1109/CVPR.2007.383418].

Multimodal Mean Adaptive Backgrounding for Embedded Real-Time Video Surveillance

GENTILE, Antonio
2007-01-01

Abstract

Automated video surveillance applications require accurate separation of foreground and background image content. Cost sensitive embedded platforms place realtime performance and efficiency demands on techniques to accomplish this task. In this paper we evaluate pixel-level foreground extraction techniques for a low cost integrated surveillance system. We introduce a new adaptive technique, multimodal mean (MM, which balances accuracy, performance, and efficiency to meet embedded system requirements. Our evaluation compares several pixel-level foreground extraction techniques in terms of their computation and storage requirements, and functional accuracy for three representative video sequences. The proposed MM algorithm delivers comparable accuracy of the best alternative (Mixture of Gaussians) with a 6X improvement in execution time and an 18% reduction in required storage.
Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazioni
Computer Vision and Pattern Recognition, 2007. CVPR '07
USA
17-22 giugno 2007
2007
Multimodal Mean Adaptive Backgrounding for Embedded Real-Time Video Surveillance Apewokin, S.; Valentine, B.; Wills, L.; Wills, S.; Gentile, A.; Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on 17-22 June 2007 Page(s):1 - 6 Digital Object Identifier 10.1109/CVPR.2007.383418
APEWOKIN S, VALENTINE B, WILLS L, WILLS S, GENTILE A (2007). Multimodal Mean Adaptive Backgrounding for Embedded Real-Time Video Surveillance. ??????? it.cilea.surplus.oa.citation.tipologie.CitationProceedings.prensentedAt ??????? Computer Vision and Pattern Recognition, 2007. CVPR '07, USA [10.1109/CVPR.2007.383418].
Proceedings (atti dei congressi)
APEWOKIN S; VALENTINE B; WILLS L; WILLS S; GENTILE A
File in questo prodotto:
File Dimensione Formato  
04270416.pdf

Solo gestori archvio

Descrizione: pdf
Dimensione 355.49 kB
Formato Adobe PDF
355.49 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10447/16535
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 24
  • ???jsp.display-item.citation.isi??? 1
social impact