Advanced search
1 file | 1.78 MB Add to list

C-EFIC: Color and edge based foreground background segmentation with interior classification

Gianni Allebosch (UGent) , David Van Hamme (UGent) , Francis Deboeverie (UGent) , Peter Veelaert (UGent) and Wilfried Philips (UGent)
Author
Organization
Abstract
The detection of foreground regions in video streams is an essential part of many computer vision algorithms. Considerable contributions were made to this field over the past years. However, varying illumination circumstances and changing camera viewpoints provide major challenges for all available algorithms. In this paper, a robust foreground background segmentation algorithm is proposed. Both Local Ternary Pattern based edge descriptors and RGB color information are used to classify individual pixels. Furthermore, camera viewpoints are detected and compensated for. We will show that this algorithm is able to handle challenging conditions and achieves state-of-the-art results on the comprehensive ChangeDetection.NET 2014 dataset.
Keywords
Foreground background segmentation, Camera motion compensation, Moving edges, Illumination invariance

Downloads

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

Citation

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

MLA
Allebosch, Gianni et al. “C-EFIC: Color and Edge Based Foreground Background Segmentation with Interior Classification.” Communications in Computer and Information Science. Ed. José Braz et al. Vol. 598. Cham, Switzerland: Springer, 2016. 433–454. Print.
APA
Allebosch, G., Van Hamme, D., Deboeverie, F., Veelaert, P., & Philips, W. (2016). C-EFIC: Color and edge based foreground background segmentation with interior classification. In J. Braz, J. Pettré, P. Richard, L. Linsen, S. Battiato, & F. Imai (Eds.), Communications in Computer and Information Science (Vol. 598, pp. 433–454). Presented at the 10th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP), Cham, Switzerland: Springer.
Chicago author-date
Allebosch, Gianni, David Van Hamme, Francis Deboeverie, Peter Veelaert, and Wilfried Philips. 2016. “C-EFIC: Color and Edge Based Foreground Background Segmentation with Interior Classification.” In Communications in Computer and Information Science, ed. José Braz, Julien Pettré, Paul Richard, Lars Linsen, Sebastiano Battiato, and Francisco Imai, 598:433–454. Cham, Switzerland: Springer.
Chicago author-date (all authors)
Allebosch, Gianni, David Van Hamme, Francis Deboeverie, Peter Veelaert, and Wilfried Philips. 2016. “C-EFIC: Color and Edge Based Foreground Background Segmentation with Interior Classification.” In Communications in Computer and Information Science, ed. José Braz, Julien Pettré, Paul Richard, Lars Linsen, Sebastiano Battiato, and Francisco Imai, 598:433–454. Cham, Switzerland: Springer.
Vancouver
1.
Allebosch G, Van Hamme D, Deboeverie F, Veelaert P, Philips W. C-EFIC: Color and edge based foreground background segmentation with interior classification. In: Braz J, Pettré J, Richard P, Linsen L, Battiato S, Imai F, editors. Communications in Computer and Information Science. Cham, Switzerland: Springer; 2016. p. 433–54.
IEEE
[1]
G. Allebosch, D. Van Hamme, F. Deboeverie, P. Veelaert, and W. Philips, “C-EFIC: Color and edge based foreground background segmentation with interior classification,” in Communications in Computer and Information Science, Berlin, Germany, 2016, vol. 598, pp. 433–454.
@inproceedings{7155467,
  abstract     = {The detection of foreground regions in video streams is an
essential part of many computer vision algorithms. Considerable contributions were made to this field over the past years. However, varying illumination circumstances and changing camera viewpoints provide major challenges for all available algorithms. In this paper, a robust foreground background segmentation algorithm is proposed. Both Local Ternary Pattern based edge descriptors and RGB color information are used to classify individual pixels. Furthermore, camera viewpoints are detected and compensated for. We will show that this algorithm is able to handle challenging conditions and achieves state-of-the-art results on the comprehensive ChangeDetection.NET 2014 dataset.},
  author       = {Allebosch, Gianni and Van Hamme, David and Deboeverie, Francis and Veelaert, Peter and Philips, Wilfried},
  booktitle    = {Communications in Computer and Information Science},
  editor       = {Braz, José and Pettré, Julien and Richard, Paul and Linsen, Lars and Battiato, Sebastiano and Imai, Francisco},
  isbn         = {978-3-319-29971-6},
  issn         = {1865-0929},
  keywords     = {Foreground background segmentation,Camera motion compensation,Moving edges,Illumination invariance},
  language     = {eng},
  location     = {Berlin, Germany},
  pages        = {433--454},
  publisher    = {Springer},
  title        = {C-EFIC: Color and edge based foreground background segmentation with interior classification},
  url          = {http://dx.doi.org/10.1007/978-3-319-29971-6_23},
  volume       = {598},
  year         = {2016},
}

Altmetric
View in Altmetric
Web of Science
Times cited: