Advanced search
1 file | 1.50 MB

Foreground background segmentation in front of changing footage on a video screen

Gianni Allebosch (UGent) , Maarten Slembrouck (UGent) , Sanne Roegiers (UGent) , Hiep Luong (UGent) , Peter Veelaert (UGent) and Wilfried Philips (UGent)
Author
Organization
Abstract
In this paper, a robust approach for detecting foreground objects moving in front of a video screen is presented. The proposed method constructs a background model for every image shown on the screen, assuming these images are known up to an appearance transformation. This transformation is guided by a color mapping function, constructed in the beginning of the sequence. The foreground object is then segmented at runtime by comparing the input from the camera with a color mapped representation of the background image, by analysing both direct color and edge feature differences. The method is tested on challenging sequences, where the background screen displays photo-realistic videos. It is shown that the proposed method is able to produce accurate foreground masks, with obtained F1-scores ranging from 85.61% to 90.74% on our dataset.
Keywords
Foreground background segmentation, Video screen, Changing background, Color mapping

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.50 MB

Citation

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

Chicago
Allebosch, Gianni, Maarten Slembrouck, Sanne Roegiers, Hiep Luong, Peter Veelaert, and Wilfried Philips. 2018. “Foreground Background Segmentation in Front of Changing Footage on a Video Screen.” In Advanced Concepts for Intelligent Vision Systems, 11182:175–187. Cham: Springer International Publishing.
APA
Allebosch, G., Slembrouck, M., Roegiers, S., Luong, H., Veelaert, P., & Philips, W. (2018). Foreground background segmentation in front of changing footage on a video screen. Advanced Concepts for Intelligent Vision Systems (Vol. 11182, pp. 175–187). Presented at the Advanced Concepts for Intelligent Vision Systems, Cham: Springer International Publishing.
Vancouver
1.
Allebosch G, Slembrouck M, Roegiers S, Luong H, Veelaert P, Philips W. Foreground background segmentation in front of changing footage on a video screen. Advanced Concepts for Intelligent Vision Systems. Cham: Springer International Publishing; 2018. p. 175–87.
MLA
Allebosch, Gianni, Maarten Slembrouck, Sanne Roegiers, et al. “Foreground Background Segmentation in Front of Changing Footage on a Video Screen.” Advanced Concepts for Intelligent Vision Systems. Vol. 11182. Cham: Springer International Publishing, 2018. 175–187. Print.
@inproceedings{8575716,
  abstract     = {In this paper, a robust approach for detecting foreground objects moving in front of a video screen is presented. The proposed method constructs a background model for every image shown on the screen, assuming these images are known up to an appearance transformation. This transformation is guided by a color mapping function, constructed in the beginning of the sequence. The foreground object is then segmented at runtime by comparing the input from the camera with a color mapped representation of the background image, by analysing both direct color and edge feature differences. The method is tested on challenging sequences, where the background screen displays photo-realistic videos. It is shown that the proposed method is able to produce accurate foreground masks, with obtained F1-scores ranging from 85.61\% to 90.74\% on our dataset.},
  author       = {Allebosch, Gianni and Slembrouck, Maarten and Roegiers, Sanne and Luong, Hiep and Veelaert, Peter and Philips, Wilfried},
  booktitle    = {Advanced Concepts for Intelligent Vision Systems},
  isbn         = {9783030014483},
  issn         = {0302-9743},
  language     = {eng},
  location     = {Poitiers},
  pages        = {175--187},
  publisher    = {Springer International Publishing},
  title        = {Foreground background segmentation in front of changing footage on a video screen},
  url          = {http://dx.doi.org/10.1007/978-3-030-01449-0\_15},
  volume       = {11182},
  year         = {2018},
}

Altmetric
View in Altmetric