Advanced search
1 file | 505.38 KB

Mixture models based background subtraction for video surveillance applications

Chris Poppe (UGent) , Gaëtan Martens (UGent) , Peter Lambert (UGent) and Rik Van de Walle (UGent)
Author
Organization
Abstract
Background subtraction is a method commonly used to segment objects of interest in image sequences. By comparing new frames to a background model, regions of interest can be found. To cope with highly dynamic and complex environments, a mixture of several models has been proposed in the literature. This paper proposes a novel background subtraction technique based on the popular Mixture of Gaussian Models technique. Moreover edge-based image segmentation is used to improve the results of the proposed technique. Experimental analysis shows that our system outperforms the standard system both in processing speed and detection accuracy.
Keywords
object detection, video surveillance

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 505.38 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Poppe, Chris, Gaëtan Martens, Peter Lambert, and Rik Van de Walle. 2007. “Mixture Models Based Background Subtraction for Video Surveillance Applications.” In Lecture Notes in Computer Science, ed. WG Kropatsch, M Kampel, and A Hanbury, 4673:28–35. Berlin, Germany: Springer.
APA
Poppe, Chris, Martens, G., Lambert, P., & Van de Walle, R. (2007). Mixture models based background subtraction for video surveillance applications. In W. Kropatsch, M. Kampel, & A. Hanbury (Eds.), LECTURE NOTES IN COMPUTER SCIENCE (Vol. 4673, pp. 28–35). Presented at the 12th International conference on Computer Analysis of Images and Patterns, Berlin, Germany: Springer.
Vancouver
1.
Poppe C, Martens G, Lambert P, Van de Walle R. Mixture models based background subtraction for video surveillance applications. In: Kropatsch W, Kampel M, Hanbury A, editors. LECTURE NOTES IN COMPUTER SCIENCE. Berlin, Germany: Springer; 2007. p. 28–35.
MLA
Poppe, Chris, Gaëtan Martens, Peter Lambert, et al. “Mixture Models Based Background Subtraction for Video Surveillance Applications.” Lecture Notes in Computer Science. Ed. WG Kropatsch, M Kampel, & A Hanbury. Vol. 4673. Berlin, Germany: Springer, 2007. 28–35. Print.
@inproceedings{417101,
  abstract     = {Background subtraction is a method commonly used to segment objects of interest in image sequences. By comparing new frames to a background model, regions of interest can be found. To cope with highly dynamic and complex environments, a mixture of several models has been proposed in the literature. This paper proposes a novel background subtraction technique based on the popular Mixture of Gaussian Models technique. Moreover edge-based image segmentation is used to improve the results of the proposed technique. Experimental analysis shows that our system outperforms the standard system both in processing speed and detection accuracy.},
  author       = {Poppe, Chris and Martens, Ga{\"e}tan and Lambert, Peter and Van de Walle, Rik},
  booktitle    = {LECTURE NOTES IN COMPUTER SCIENCE},
  editor       = {Kropatsch, WG and Kampel, M and Hanbury, A},
  isbn         = {9783540742715},
  issn         = {0302-9743},
  language     = {eng},
  location     = {Vienna, Austria},
  pages        = {28--35},
  publisher    = {Springer},
  title        = {Mixture models based background subtraction for video surveillance applications},
  url          = {http://dx.doi.org/10.1007/978-3-540-74272-2\_4},
  volume       = {4673},
  year         = {2007},
}

Altmetric
View in Altmetric
Web of Science
Times cited: