Video-object segmentation using multi-sprite background subtraction

D.S. Farin; P.H.N. With, de; W.W.J. Effelsberg

doi:10.1109/ICME.2004.1394199

Video-object segmentation using multi-sprite background subtraction

D.S. Farin, P.H.N. With, de, W.W.J. Effelsberg

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

34 Citations (Scopus)

Abstract

The background subtraction algorithm is a frequently-used object segmentation technique because of its algorithmic simplicity. However, we show that for general rotational camera-motion, it is impractical or even impossible to use a single background image. As a solution, we propose to use multi-sprite backgrounds which enables processing of arbitrary rotational camera-motion. This paper describes a complete video-object segmentation system employing multi-sprites. The system generates object masks and background sprites that are compatible with the MPEG-4 object-oriented video-coding tools. Good segmentation results are also obtained for sequences, which cannot be processed with ordinary background images.

Original language	English
Title of host publication	2004 IEEE International Conference on Multimedia and Expo (ICME)
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	343-346
Volume	1
ISBN (Print)	0-7803-8604-3
DOIs	https://doi.org/10.1109/ICME.2004.1394199
Publication status	Published - 2004
Event	2004 IEEE International Conference on Multimedia and Expo (ICME 2004) - Taipei, Taiwan Duration: 27 Jun 2004 → 30 Jun 2004

Conference

Conference	2004 IEEE International Conference on Multimedia and Expo (ICME 2004)
Abbreviated title	ICME 2004
Country/Territory	Taiwan
City	Taipei
Period	27/06/04 → 30/06/04

Access to Document

10.1109/ICME.2004.1394199

Cite this

@inproceedings{e6a7cab03442425b81c78a5879fc65dc,

title = "Video-object segmentation using multi-sprite background subtraction",

abstract = "The background subtraction algorithm is a frequently-used object segmentation technique because of its algorithmic simplicity. However, we show that for general rotational camera-motion, it is impractical or even impossible to use a single background image. As a solution, we propose to use multi-sprite backgrounds which enables processing of arbitrary rotational camera-motion. This paper describes a complete video-object segmentation system employing multi-sprites. The system generates object masks and background sprites that are compatible with the MPEG-4 object-oriented video-coding tools. Good segmentation results are also obtained for sequences, which cannot be processed with ordinary background images.",

author = "D.S. Farin and {With, de}, P.H.N. and W.W.J. Effelsberg",

year = "2004",

doi = "10.1109/ICME.2004.1394199",

language = "English",

isbn = "0-7803-8604-3",

volume = "1",

pages = "343--346",

booktitle = "2004 IEEE International Conference on Multimedia and Expo (ICME)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "2004 IEEE International Conference on Multimedia and Expo (ICME 2004), ICME 2004 ; Conference date: 27-06-2004 Through 30-06-2004",

}

Farin, DS, With, de, PHN & Effelsberg, WWJ 2004, Video-object segmentation using multi-sprite background subtraction. in 2004 IEEE International Conference on Multimedia and Expo (ICME). vol. 1, Institute of Electrical and Electronics Engineers, Piscataway, pp. 343-346, 2004 IEEE International Conference on Multimedia and Expo (ICME 2004), Taipei, Taiwan, 27/06/04. https://doi.org/10.1109/ICME.2004.1394199

Video-object segmentation using multi-sprite background subtraction. / Farin, D.S.; With, de, P.H.N.; Effelsberg, W.W.J.

2004 IEEE International Conference on Multimedia and Expo (ICME). Vol. 1 Piscataway : Institute of Electrical and Electronics Engineers, 2004. p. 343-346.

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

TY - GEN

T1 - Video-object segmentation using multi-sprite background subtraction

AU - Farin, D.S.

AU - With, de, P.H.N.

AU - Effelsberg, W.W.J.

PY - 2004

Y1 - 2004

N2 - The background subtraction algorithm is a frequently-used object segmentation technique because of its algorithmic simplicity. However, we show that for general rotational camera-motion, it is impractical or even impossible to use a single background image. As a solution, we propose to use multi-sprite backgrounds which enables processing of arbitrary rotational camera-motion. This paper describes a complete video-object segmentation system employing multi-sprites. The system generates object masks and background sprites that are compatible with the MPEG-4 object-oriented video-coding tools. Good segmentation results are also obtained for sequences, which cannot be processed with ordinary background images.

AB - The background subtraction algorithm is a frequently-used object segmentation technique because of its algorithmic simplicity. However, we show that for general rotational camera-motion, it is impractical or even impossible to use a single background image. As a solution, we propose to use multi-sprite backgrounds which enables processing of arbitrary rotational camera-motion. This paper describes a complete video-object segmentation system employing multi-sprites. The system generates object masks and background sprites that are compatible with the MPEG-4 object-oriented video-coding tools. Good segmentation results are also obtained for sequences, which cannot be processed with ordinary background images.

U2 - 10.1109/ICME.2004.1394199

DO - 10.1109/ICME.2004.1394199

M3 - Conference contribution

SN - 0-7803-8604-3

VL - 1

SP - 343

EP - 346

BT - 2004 IEEE International Conference on Multimedia and Expo (ICME)

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 2004 IEEE International Conference on Multimedia and Expo (ICME 2004)

Y2 - 27 June 2004 through 30 June 2004

ER -

Video-object segmentation using multi-sprite background subtraction

Abstract

Conference

Access to Document

Fingerprint

Cite this