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

Gustavo Silva, Paul Rodriguez

Sección de Electricidad y Electrónica

Pontifical Catholic Univ. of Peru

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

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.

Original language	English
Title of host publication	Conference Record of the 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015
Editors	Michael B. Matthews
Publisher	IEEE Computer Society
Pages	1403-1407
Number of pages	5
ISBN (Electronic)	9781467385763
DOIs	https://doi.org/10.1109/ACSSC.2015.7421373
State	Published - 26 Feb 2016
Event	49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015 - Pacific Grove, United States Duration: 8 Nov 2015 → 11 Nov 2015

Publication series

Name	Conference Record - Asilomar Conference on Signals, Systems and Computers
Volume	2016-February
ISSN (Print)	1058-6393

Conference

Conference	49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015
Country/Territory	United States
City	Pacific Grove
Period	8/11/15 → 11/11/15

Keywords

Principal Component Pursuit
Rigid transformations
Video Background Modeling

Access to Document

10.1109/ACSSC.2015.7421373

Cite this

Silva, G., & Rodriguez, P. (2016). Jitter invariant incremental principal component pursuit for video background modeling on the TK1. In M. B. Matthews (Ed.), Conference Record of the 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015 (pp. 1403-1407). Article 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. in 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, United States, 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).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

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. In 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

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this