A Bayesian framework for foreground segmentation

Shih Shinh Huang; Li Chen Fu; Pei Yung Hsiao

doi:10.1109/ICSMC.2006.385021

A Bayesian framework for foreground segmentation

Shih Shinh Huang^*
, Li Chen Fu
, Pei Yung Hsiao

^*Corresponding author for this work

Department of Electronic Engineering

National Taiwan University

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

4 Scopus citations

Abstract

This paper presents a probabilistic approach for automatically segmenting foreground objects from a video sequence. A Bayesian network is presented to model the interactions among three variables, such as foreground segmentation mask, motion segmentation field, and motion vector field. Given two consecutive images, the conditional joint probability density of the three variables is maximized iteratively to simultaneously achieve foreground segmentation and motion segmentation in a mutually beneficial manner. The solution to the optimization problems are obtained by using iterative conditional mode (ICM) and graph cut algorithm. Incorporating motion information with background subtraction technique makes the segmentation perform in a more semantic level and obtain more accurate results. Experimental results for two video sequences are provided to demonstrate the effectiveness of the proposed approach.

Original language	English
Title of host publication	2006 IEEE International Conference on Systems, Man and Cybernetics
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1980-1985
Number of pages	6
ISBN (Print)	1424401003, 9781424401000
DOIs	https://doi.org/10.1109/ICSMC.2006.385021
State	Published - 2006
Event	2006 IEEE International Conference on Systems, Man and Cybernetics - Taipei, Taiwan Duration: 08 10 2006 → 11 10 2006

Publication series

Name	Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Volume	3
ISSN (Print)	1062-922X

Conference

Conference	2006 IEEE International Conference on Systems, Man and Cybernetics
Country/Territory	Taiwan
City	Taipei
Period	08/10/06 → 11/10/06

Access to Document

10.1109/ICSMC.2006.385021

Cite this

Huang, S. S., Fu, L. C., & Hsiao, P. Y. (2006). A Bayesian framework for foreground segmentation. In 2006 IEEE International Conference on Systems, Man and Cybernetics (pp. 1980-1985). Article 4274156 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics; Vol. 3). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSMC.2006.385021

@inproceedings{88eacf9d8bd1462ba061c6010bea6ea0,

title = "A Bayesian framework for foreground segmentation",

abstract = "This paper presents a probabilistic approach for automatically segmenting foreground objects from a video sequence. A Bayesian network is presented to model the interactions among three variables, such as foreground segmentation mask, motion segmentation field, and motion vector field. Given two consecutive images, the conditional joint probability density of the three variables is maximized iteratively to simultaneously achieve foreground segmentation and motion segmentation in a mutually beneficial manner. The solution to the optimization problems are obtained by using iterative conditional mode (ICM) and graph cut algorithm. Incorporating motion information with background subtraction technique makes the segmentation perform in a more semantic level and obtain more accurate results. Experimental results for two video sequences are provided to demonstrate the effectiveness of the proposed approach.",

author = "Huang, \{Shih Shinh\} and Fu, \{Li Chen\} and Hsiao, \{Pei Yung\}",

year = "2006",

doi = "10.1109/ICSMC.2006.385021",

language = "英语",

isbn = "1424401003",

series = "Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1980--1985",

booktitle = "2006 IEEE International Conference on Systems, Man and Cybernetics",

address = "美国",

note = "2006 IEEE International Conference on Systems, Man and Cybernetics ; Conference date: 08-10-2006 Through 11-10-2006",

}

Huang, SS, Fu, LC & Hsiao, PY 2006, A Bayesian framework for foreground segmentation. in 2006 IEEE International Conference on Systems, Man and Cybernetics., 4274156, Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, vol. 3, Institute of Electrical and Electronics Engineers Inc., pp. 1980-1985, 2006 IEEE International Conference on Systems, Man and Cybernetics, Taipei, Taiwan, 08/10/06. https://doi.org/10.1109/ICSMC.2006.385021

A Bayesian framework for foreground segmentation. / Huang, Shih Shinh; Fu, Li Chen; Hsiao, Pei Yung.
2006 IEEE International Conference on Systems, Man and Cybernetics. Institute of Electrical and Electronics Engineers Inc., 2006. p. 1980-1985 4274156 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics; Vol. 3).

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

TY - GEN

T1 - A Bayesian framework for foreground segmentation

AU - Huang, Shih Shinh

AU - Fu, Li Chen

AU - Hsiao, Pei Yung

PY - 2006

Y1 - 2006

N2 - This paper presents a probabilistic approach for automatically segmenting foreground objects from a video sequence. A Bayesian network is presented to model the interactions among three variables, such as foreground segmentation mask, motion segmentation field, and motion vector field. Given two consecutive images, the conditional joint probability density of the three variables is maximized iteratively to simultaneously achieve foreground segmentation and motion segmentation in a mutually beneficial manner. The solution to the optimization problems are obtained by using iterative conditional mode (ICM) and graph cut algorithm. Incorporating motion information with background subtraction technique makes the segmentation perform in a more semantic level and obtain more accurate results. Experimental results for two video sequences are provided to demonstrate the effectiveness of the proposed approach.

AB - This paper presents a probabilistic approach for automatically segmenting foreground objects from a video sequence. A Bayesian network is presented to model the interactions among three variables, such as foreground segmentation mask, motion segmentation field, and motion vector field. Given two consecutive images, the conditional joint probability density of the three variables is maximized iteratively to simultaneously achieve foreground segmentation and motion segmentation in a mutually beneficial manner. The solution to the optimization problems are obtained by using iterative conditional mode (ICM) and graph cut algorithm. Incorporating motion information with background subtraction technique makes the segmentation perform in a more semantic level and obtain more accurate results. Experimental results for two video sequences are provided to demonstrate the effectiveness of the proposed approach.

UR - https://www.scopus.com/pages/publications/34548136896

U2 - 10.1109/ICSMC.2006.385021

DO - 10.1109/ICSMC.2006.385021

M3 - 会议稿件

AN - SCOPUS:34548136896

SN - 1424401003

SN - 9781424401000

T3 - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

SP - 1980

EP - 1985

BT - 2006 IEEE International Conference on Systems, Man and Cybernetics

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2006 IEEE International Conference on Systems, Man and Cybernetics

Y2 - 8 October 2006 through 11 October 2006

ER -

A Bayesian framework for foreground segmentation

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this