Gaussian mixture background model with shadow information

Jung Ming Wang, Sei Wang Chen, Chiou Shann Fuh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we integrate shadow information into the background model of a scene in an attempt to detect both shadows and foreground objects at a time. Since shadows accompanying foreground objects are viewed as parts of the foreground objects, shadows will be extracted as well during foreground object detection. Shadows can distort object shapes and may connect multiple objects into one object. On the other hand, shadows tell the directions of light sources. In other words, shadows can be advantageous as well as disadvantageous. To begin, we use an adaptive Gaussian mixture model to describe the background of a scene. Based on this preliminary background model, we extract foreground objects and their accompanying shadows. Shadows are next separated from foreground objects through a series of intensity and color analyses. The characteristics of shadows are finally determined with the principal component analysis method and are embedded as an additional Gaussian in the background model. Experimental results demonstrated the feasibility of the proposed background model.

Original languageEnglish
Title of host publicationProc. of the IADIS Int. Conf, Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011
Pages217-222
Number of pages6
Publication statusPublished - 2011 Dec 1
EventIADIS International Conference Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conference on Computer Science and Information Systems 2011, MCCSIS 2011 - Rome, Italy
Duration: 2011 Jul 242011 Jul 26

Publication series

NameProc. of the IADIS Int. Conf. Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011

Other

OtherIADIS International Conference Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conference on Computer Science and Information Systems 2011, MCCSIS 2011
CountryItaly
CityRome
Period11/7/2411/7/26

Fingerprint

Principal component analysis
Light sources
Color
Object detection

Keywords

  • Adaptive Gaussian mixture model
  • Dynamic scene
  • Foreground detection
  • Shadow detection

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Information Systems

Cite this

Wang, J. M., Chen, S. W., & Fuh, C. S. (2011). Gaussian mixture background model with shadow information. In Proc. of the IADIS Int. Conf, Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011 (pp. 217-222). (Proc. of the IADIS Int. Conf. Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011).

Gaussian mixture background model with shadow information. / Wang, Jung Ming; Chen, Sei Wang; Fuh, Chiou Shann.

Proc. of the IADIS Int. Conf, Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011. 2011. p. 217-222 (Proc. of the IADIS Int. Conf. Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, JM, Chen, SW & Fuh, CS 2011, Gaussian mixture background model with shadow information. in Proc. of the IADIS Int. Conf, Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011. Proc. of the IADIS Int. Conf. Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011, pp. 217-222, IADIS International Conference Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conference on Computer Science and Information Systems 2011, MCCSIS 2011, Rome, Italy, 11/7/24.
Wang JM, Chen SW, Fuh CS. Gaussian mixture background model with shadow information. In Proc. of the IADIS Int. Conf, Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011. 2011. p. 217-222. (Proc. of the IADIS Int. Conf. Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011).
Wang, Jung Ming ; Chen, Sei Wang ; Fuh, Chiou Shann. / Gaussian mixture background model with shadow information. Proc. of the IADIS Int. Conf, Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011. 2011. pp. 217-222 (Proc. of the IADIS Int. Conf. Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011).
@inproceedings{a3b5791e5ea64acbb4f3ba3c8a6c4c42,
title = "Gaussian mixture background model with shadow information",
abstract = "In this paper, we integrate shadow information into the background model of a scene in an attempt to detect both shadows and foreground objects at a time. Since shadows accompanying foreground objects are viewed as parts of the foreground objects, shadows will be extracted as well during foreground object detection. Shadows can distort object shapes and may connect multiple objects into one object. On the other hand, shadows tell the directions of light sources. In other words, shadows can be advantageous as well as disadvantageous. To begin, we use an adaptive Gaussian mixture model to describe the background of a scene. Based on this preliminary background model, we extract foreground objects and their accompanying shadows. Shadows are next separated from foreground objects through a series of intensity and color analyses. The characteristics of shadows are finally determined with the principal component analysis method and are embedded as an additional Gaussian in the background model. Experimental results demonstrated the feasibility of the proposed background model.",
keywords = "Adaptive Gaussian mixture model, Dynamic scene, Foreground detection, Shadow detection",
author = "Wang, {Jung Ming} and Chen, {Sei Wang} and Fuh, {Chiou Shann}",
year = "2011",
month = "12",
day = "1",
language = "English",
isbn = "9789728939489",
series = "Proc. of the IADIS Int. Conf. Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011",
pages = "217--222",
booktitle = "Proc. of the IADIS Int. Conf, Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011",

}

TY - GEN

T1 - Gaussian mixture background model with shadow information

AU - Wang, Jung Ming

AU - Chen, Sei Wang

AU - Fuh, Chiou Shann

PY - 2011/12/1

Y1 - 2011/12/1

N2 - In this paper, we integrate shadow information into the background model of a scene in an attempt to detect both shadows and foreground objects at a time. Since shadows accompanying foreground objects are viewed as parts of the foreground objects, shadows will be extracted as well during foreground object detection. Shadows can distort object shapes and may connect multiple objects into one object. On the other hand, shadows tell the directions of light sources. In other words, shadows can be advantageous as well as disadvantageous. To begin, we use an adaptive Gaussian mixture model to describe the background of a scene. Based on this preliminary background model, we extract foreground objects and their accompanying shadows. Shadows are next separated from foreground objects through a series of intensity and color analyses. The characteristics of shadows are finally determined with the principal component analysis method and are embedded as an additional Gaussian in the background model. Experimental results demonstrated the feasibility of the proposed background model.

AB - In this paper, we integrate shadow information into the background model of a scene in an attempt to detect both shadows and foreground objects at a time. Since shadows accompanying foreground objects are viewed as parts of the foreground objects, shadows will be extracted as well during foreground object detection. Shadows can distort object shapes and may connect multiple objects into one object. On the other hand, shadows tell the directions of light sources. In other words, shadows can be advantageous as well as disadvantageous. To begin, we use an adaptive Gaussian mixture model to describe the background of a scene. Based on this preliminary background model, we extract foreground objects and their accompanying shadows. Shadows are next separated from foreground objects through a series of intensity and color analyses. The characteristics of shadows are finally determined with the principal component analysis method and are embedded as an additional Gaussian in the background model. Experimental results demonstrated the feasibility of the proposed background model.

KW - Adaptive Gaussian mixture model

KW - Dynamic scene

KW - Foreground detection

KW - Shadow detection

UR - http://www.scopus.com/inward/record.url?scp=84864994636&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864994636&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84864994636

SN - 9789728939489

T3 - Proc. of the IADIS Int. Conf. Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011

SP - 217

EP - 222

BT - Proc. of the IADIS Int. Conf, Computer Graphics, Visualization, Computer Vision and Image Processing 2011, Part of the IADIS Multi Conf. on Computer Science and Information Systems 2011, MCCSIS 2011

ER -