Jitter invariant incremental principal component pursuit for video background modeling on the TK1

Gustavo Silva; Paul Rodriguez

doi:10.1109/ACSSC.2015.7421373

Jitter invariant incremental principal component pursuit for video background modeling on the TK1

Sección de Electricidad y Electrónica

Pontifical Catholic Univ. of Peru

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

4 Citas (Scopus)

Resumen

While Principal Component Pursuit (PCP) is currently considered to be the state of the art method for video background modeling, it suffers from a number of limitations, including high computational cost, batch operating mode, and sensitivity to camera jitter. In this work we present a real-time, CUDA-aware C / CUDA C implementation of a novel and fully incremental PCP algorithm for video background modeling that can also deal with rigid transformation jitter. Our implementation has a computational complexity that allows (TK1 platform) a processing frame rate throughput (jittered video) of 2.6 and 0.4 f.p.s. for color videos of 640 × 480 and 1920 × 1088 respectively.

Idioma original	Inglés
Título de la publicación alojada	Conference Record of the 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015
Editores	Michael B. Matthews
Editorial	IEEE Computer Society
Páginas	1403-1407
Número de páginas	5
ISBN (versión digital)	9781467385763
DOI	https://doi.org/10.1109/ACSSC.2015.7421373
Estado	Publicada - 26 feb. 2016
Evento	49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015 - Pacific Grove, Estados Unidos Duración: 8 nov. 2015 → 11 nov. 2015

Serie de la publicación

Nombre	Conference Record - Asilomar Conference on Signals, Systems and Computers
Volumen	2016-February
ISSN (versión impresa)	1058-6393

Conferencia

Conferencia	49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015
País/Territorio	Estados Unidos
Ciudad	Pacific Grove
Período	8/11/15 → 11/11/15

Acceder al documento

10.1109/ACSSC.2015.7421373

Otros archivos y enlaces

Enlace a la publicación en Scopus

Citar esto

Silva, G., & Rodriguez, P. (2016). Jitter invariant incremental principal component pursuit for video background modeling on the TK1. En M. B. Matthews (Ed.), Conference Record of the 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015 (pp. 1403-1407). Artículo 7421373 (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2016-February). IEEE Computer Society. https://doi.org/10.1109/ACSSC.2015.7421373

Silva, Gustavo ; Rodriguez, Paul. / Jitter invariant incremental principal component pursuit for video background modeling on the TK1. Conference Record of the 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015. editor / Michael B. Matthews. IEEE Computer Society, 2016. pp. 1403-1407 (Conference Record - Asilomar Conference on Signals, Systems and Computers).

@inproceedings{a09e77b88067411b82e50e44a73a2b15,

title = "Jitter invariant incremental principal component pursuit for video background modeling on the TK1",

abstract = "While Principal Component Pursuit (PCP) is currently considered to be the state of the art method for video background modeling, it suffers from a number of limitations, including high computational cost, batch operating mode, and sensitivity to camera jitter. In this work we present a real-time, CUDA-aware C / CUDA C implementation of a novel and fully incremental PCP algorithm for video background modeling that can also deal with rigid transformation jitter. Our implementation has a computational complexity that allows (TK1 platform) a processing frame rate throughput (jittered video) of 2.6 and 0.4 f.p.s. for color videos of 640 × 480 and 1920 × 1088 respectively.",

keywords = "Principal Component Pursuit, Rigid transformations, Video Background Modeling",

author = "Gustavo Silva and Paul Rodriguez",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015 ; Conference date: 08-11-2015 Through 11-11-2015",

year = "2016",

month = feb,

day = "26",

doi = "10.1109/ACSSC.2015.7421373",

language = "English",

series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

publisher = "IEEE Computer Society",

pages = "1403--1407",

editor = "Matthews, {Michael B.}",

booktitle = "Conference Record of the 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015",

}

Silva, G & Rodriguez, P 2016, Jitter invariant incremental principal component pursuit for video background modeling on the TK1. En MB Matthews (ed.), Conference Record of the 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015., 7421373, Conference Record - Asilomar Conference on Signals, Systems and Computers, vol. 2016-February, IEEE Computer Society, pp. 1403-1407, 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015, Pacific Grove, Estados Unidos, 8/11/15. https://doi.org/10.1109/ACSSC.2015.7421373

Jitter invariant incremental principal component pursuit for video background modeling on the TK1. / Silva, Gustavo; Rodriguez, Paul.
Conference Record of the 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015. ed. / Michael B. Matthews. IEEE Computer Society, 2016. p. 1403-1407 7421373 (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2016-February).

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

TY - GEN

T1 - Jitter invariant incremental principal component pursuit for video background modeling on the TK1

AU - Silva, Gustavo

AU - Rodriguez, Paul

PY - 2016/2/26

Y1 - 2016/2/26

N2 - While Principal Component Pursuit (PCP) is currently considered to be the state of the art method for video background modeling, it suffers from a number of limitations, including high computational cost, batch operating mode, and sensitivity to camera jitter. In this work we present a real-time, CUDA-aware C / CUDA C implementation of a novel and fully incremental PCP algorithm for video background modeling that can also deal with rigid transformation jitter. Our implementation has a computational complexity that allows (TK1 platform) a processing frame rate throughput (jittered video) of 2.6 and 0.4 f.p.s. for color videos of 640 × 480 and 1920 × 1088 respectively.

AB - While Principal Component Pursuit (PCP) is currently considered to be the state of the art method for video background modeling, it suffers from a number of limitations, including high computational cost, batch operating mode, and sensitivity to camera jitter. In this work we present a real-time, CUDA-aware C / CUDA C implementation of a novel and fully incremental PCP algorithm for video background modeling that can also deal with rigid transformation jitter. Our implementation has a computational complexity that allows (TK1 platform) a processing frame rate throughput (jittered video) of 2.6 and 0.4 f.p.s. for color videos of 640 × 480 and 1920 × 1088 respectively.

KW - Principal Component Pursuit

KW - Rigid transformations

KW - Video Background Modeling

UR - http://www.scopus.com/inward/record.url?scp=84969835611&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2015.7421373

DO - 10.1109/ACSSC.2015.7421373

M3 - Conference contribution

AN - SCOPUS:84969835611

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 1403

EP - 1407

BT - Conference Record of the 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015

A2 - Matthews, Michael B.

PB - IEEE Computer Society

T2 - 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015

Y2 - 8 November 2015 through 11 November 2015

ER -

Silva G, Rodriguez P. Jitter invariant incremental principal component pursuit for video background modeling on the TK1. En Matthews MB, editor, Conference Record of the 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015. IEEE Computer Society. 2016. p. 1403-1407. 7421373. (Conference Record - Asilomar Conference on Signals, Systems and Computers). doi: 10.1109/ACSSC.2015.7421373

Jitter invariant incremental principal component pursuit for video background modeling on the TK1

Resumen

Serie de la publicación

Conferencia

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto