Two Video Analysis Applications Using Foreground/Background Segmentation

Z. Zivkovic; M. Petkovic; R. van Mierlo; Maurice van Keulen; Ferdinand van der Heijden; Willem Jonker; E. Rijnierse

Two Video Analysis Applications Using Foreground/Background Segmentation

Z. Zivkovic, M. Petkovic, R. van Mierlo, Maurice van Keulen, Ferdinand van der Heijden, Willem Jonker, E. Rijnierse

Databases (Former)

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

189 Downloads (Pure)

Abstract

Probably the most frequently solved problem when videos are analyzed is segmenting a foreground object from its background in an image. After some regions in an image are detected as the foreground objects, some features are extracted that describe the segmented regions. These features together with the domain knowledge are often enough to extract the needed high-level semantics from the video material. In this paper we present two automatic systems for video analysis and indexing. In both systems the segmentation of the foreground objects is the basic processing step. The extracted features are then used to solve the problem. One system analyses traffic videos, the other tennis games.

Original language	Undefined
Title of host publication	Proceedings of the VIE2003 Conference on Visual Information Engineering
Place of Publication	Los Alamitos
Publisher	IEEE
Pages	310-313
Number of pages	4
ISBN (Print)	0-85296-757-8
Publication status	Published - Jul 2003
Event	VIE2003 International Conference on Visual Information Engineering - Guildford, UK Duration: 7 Jul 2003 → 9 Jul 2003

Publication series

Name	IEEE Conference Proceedings
Publisher	IEEE Computer Society
Volume	495
ISSN (Print)	0537-9989

Conference

Conference	VIE2003 International Conference on Visual Information Engineering
Period	7/07/03 → 9/07/03
Other	7-9 July 2003

Keywords

IR-46153
EWI-7384
DB-MMR: MULTIMEDIA RETRIEVAL
METIS-214156

Access to Document

http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1341355

Cite this

Zivkovic, Z., Petkovic, M., van Mierlo, R., van Keulen, M., van der Heijden, F., Jonker, W., & Rijnierse, E. (2003). Two Video Analysis Applications Using Foreground/Background Segmentation. In Proceedings of the VIE2003 Conference on Visual Information Engineering (pp. 310-313). (IEEE Conference Proceedings; Vol. 495). IEEE. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1341355

@inproceedings{073d1f6954ed4795a3b78f3a2dbb3c39,

title = "Two Video Analysis Applications Using Foreground/Background Segmentation",

abstract = "Probably the most frequently solved problem when videos are analyzed is segmenting a foreground object from its background in an image. After some regions in an image are detected as the foreground objects, some features are extracted that describe the segmented regions. These features together with the domain knowledge are often enough to extract the needed high-level semantics from the video material. In this paper we present two automatic systems for video analysis and indexing. In both systems the segmentation of the foreground objects is the basic processing step. The extracted features are then used to solve the problem. One system analyses traffic videos, the other tennis games.",

keywords = "IR-46153, EWI-7384, DB-MMR: MULTIMEDIA RETRIEVAL, METIS-214156",

author = "Z. Zivkovic and M. Petkovic and {van Mierlo}, R. and {van Keulen}, Maurice and {van der Heijden}, Ferdinand and Willem Jonker and E. Rijnierse",

note = "Imported from EWI/DB PMS [db-utwente:inpr:0000003271]; VIE2003 International Conference on Visual Information Engineering ; Conference date: 07-07-2003 Through 09-07-2003",

year = "2003",

month = jul,

language = "Undefined",

isbn = "0-85296-757-8",

series = "IEEE Conference Proceedings",

publisher = "IEEE",

pages = "310--313",

booktitle = "Proceedings of the VIE2003 Conference on Visual Information Engineering",

address = "United States",

}

Zivkovic, Z, Petkovic, M, van Mierlo, R, van Keulen, M , van der Heijden, F , Jonker, W & Rijnierse, E 2003, Two Video Analysis Applications Using Foreground/Background Segmentation. in Proceedings of the VIE2003 Conference on Visual Information Engineering. IEEE Conference Proceedings, vol. 495, IEEE, Los Alamitos, pp. 310-313, VIE2003 International Conference on Visual Information Engineering, 7/07/03. <http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1341355>

Two Video Analysis Applications Using Foreground/Background Segmentation. / Zivkovic, Z.; Petkovic, M.; van Mierlo, R. et al.
Proceedings of the VIE2003 Conference on Visual Information Engineering. Los Alamitos: IEEE, 2003. p. 310-313 (IEEE Conference Proceedings; Vol. 495).

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

TY - GEN

T1 - Two Video Analysis Applications Using Foreground/Background Segmentation

AU - Zivkovic, Z.

AU - Petkovic, M.

AU - van Mierlo, R.

AU - van Keulen, Maurice

AU - van der Heijden, Ferdinand

AU - Jonker, Willem

AU - Rijnierse, E.

N1 - Imported from EWI/DB PMS [db-utwente:inpr:0000003271]

PY - 2003/7

Y1 - 2003/7

N2 - Probably the most frequently solved problem when videos are analyzed is segmenting a foreground object from its background in an image. After some regions in an image are detected as the foreground objects, some features are extracted that describe the segmented regions. These features together with the domain knowledge are often enough to extract the needed high-level semantics from the video material. In this paper we present two automatic systems for video analysis and indexing. In both systems the segmentation of the foreground objects is the basic processing step. The extracted features are then used to solve the problem. One system analyses traffic videos, the other tennis games.

AB - Probably the most frequently solved problem when videos are analyzed is segmenting a foreground object from its background in an image. After some regions in an image are detected as the foreground objects, some features are extracted that describe the segmented regions. These features together with the domain knowledge are often enough to extract the needed high-level semantics from the video material. In this paper we present two automatic systems for video analysis and indexing. In both systems the segmentation of the foreground objects is the basic processing step. The extracted features are then used to solve the problem. One system analyses traffic videos, the other tennis games.

KW - IR-46153

KW - EWI-7384

KW - DB-MMR: MULTIMEDIA RETRIEVAL

KW - METIS-214156

M3 - Conference contribution

SN - 0-85296-757-8

T3 - IEEE Conference Proceedings

SP - 310

EP - 313

BT - Proceedings of the VIE2003 Conference on Visual Information Engineering

PB - IEEE

CY - Los Alamitos

T2 - VIE2003 International Conference on Visual Information Engineering

Y2 - 7 July 2003 through 9 July 2003

ER -