BMTDL for Scene Modeling on the SBI Dataset

  • Nicoletta NocetiEmail author
  • Alessandra Staglianò
  • Alessandro Verri
  • Francesca Odone
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9281)


In this paper we evaluate our method for Background Modeling Through Dictionary Learning (BMTDL) and sparse coding on the recently proposed Scene Background Initialization (SBI) dataset. The BMTDL, originally proposed in [1] for the specific purpose of detecting the foreground of a scene, leverages on the availability of long time observations, where we can treat foreground objects as noise. The SBI dataset refers to more general scene modeling problems – as for video segmentation, compression or editing – where video sequences may be generally short, and often include foreground objects occupying a large portion on the image for the majority of the sequence. The experimental analysis we report is very promising and show how the BMTDL may be also appropriate for these different and challenging conditions.


Video Sequence Background Model Image Patch Sparse Code Foreground Object 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Stagliano, A., Noceti, N., Verri, A., Odone, F.: Online Space-Variant Background Modeling With Sparse Coding. IEEE Trans. on Image Processing 24(8), 2415–2428 (2015)CrossRefMathSciNetGoogle Scholar
  2. 2.
    Stauffer, C., Grimson, W.: Adaptive background mixture models for real-time tracking. In: CVPR, vol. 2 (1999)Google Scholar
  3. 3.
    Kim, K., Chalidabhongse, T., Harwood, D., Davis, L.: Real-time foreground-background segmentation using codebook model. Real-time imaging 11(3), 172–185 (2005)CrossRefGoogle Scholar
  4. 4.
    Dikmen, M., Tsai, F., Huang, T.: Base selection in estimating sparse foreground in video. In: ICIP, pp. 3217–3220 (2009)Google Scholar
  5. 5.
    Dikmen, M., Huang, T.: Robust estimation of foreground in surveillance videos by sparse error estimation. In: ICPR, pp. 1–4 (2008)Google Scholar
  6. 6.
    Sivalingam, R., D’Souza, A., Bazakos, M., Miezianko, R., Morellas, V., Papanikolopoulos, N.: Dictionary learning for robust background modeling. In: ICRA, pp. 4234–4239 (2011)Google Scholar
  7. 7.
    Zhao, C., Wang, X., Kuen Cham, W.: Background Subtraction via Robust Dictionary Learning. Journ. on Image and Video Proc. (2011)Google Scholar
  8. 8.
    Aharon, M., Elad, M., Bruckstein, A.: K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. on Signal Processing 54(11), 4311–4322 (2006)CrossRefGoogle Scholar
  9. 9.
    Staglianò, A., Chiusano, G., Basso, C., Santoro, M.: Learning adaptive and sparse representations of medical images. In: Menze, B., Langs, G., Tu, Z., Criminisi, A. (eds.) MICCAI 2010. LNCS, vol. 6533, pp. 130–140. Springer, Heidelberg (2011) Google Scholar
  10. 10.
    Ranzato, M., Huang, F., Boureau, Y., LeCun, Y.: Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: CVPR (2007)Google Scholar
  11. 11.
    Basso, C., Santoro, M., Verri, A., Villa, S.: PADDLE: proximal algorithm for dual dictionaries learning. In: Honkela, T. (ed.) ICANN 2011, Part I. LNCS, vol. 6791, pp. 379–386. Springer, Heidelberg (2011) CrossRefGoogle Scholar
  12. 12.
    Lee, H., Battle, A., Raina, R., Ng, A.: Effcient sparse coding algorithms. In: NIPS, pp. 801–808 (2006)Google Scholar
  13. 13.
    Lu, C., Shi, J., Jia, J.: Online robust dictionary learning. In: CVPR, pp. 415–422 (2013)Google Scholar
  14. 14.
    Tibshirani, R.: Regression shrinkage and selection via the lasso. J. of the Royal Statistical Society, Series B, 267–288 (1996)Google Scholar
  15. 15.
    Toyama, K., Krumm, J., Brumitt, B., Meyers, B.: Wallflower: Principles and practice of background maintenance. In: ICCV, vol. 1 (1999)Google Scholar
  16. 16.
    Barnich, O., Droogenbroeck, M.V.: Vibe: A universal background subtraction algorithm for video sequences. Trans. on IP 20(6) (2011)Google Scholar
  17. 17.
    Bouwmans, T.: Recent advanced statistical background modeling for foreground detection: A systematic survey. Recent Patents on Computer Science 4(3), 147–176 (2011)Google Scholar
  18. 18.
    Brutzer, S., Hoferlin, B., Heidemann, G.: Evaluation of background subtraction techniques for video surveillance. In: CVPR, pp. 1937–1944 (2011)Google Scholar
  19. 19.
    Alman, Y., Erturk, I.: A new color image quality measure based on YUV transformation and PSNR for human vision system. Turkish Jour. of Electrical Engineering & Computer Sciences 21(2), 603 (2013)Google Scholar
  20. 20.
    David, C., Gui, V.: Sparse coding and gaussian modeling of coefficients average for background subtraction. In: ISPA, pp. 230–235 (2013)Google Scholar
  21. 21.
    Maddalena, L., Petrosino, A.: Towards Benchmarking Scene Background Initialization. arXiv:1506.04051 (2015)

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Nicoletta Noceti
    • 1
    Email author
  • Alessandra Staglianò
    • 1
  • Alessandro Verri
    • 1
  • Francesca Odone
    • 1
  1. 1.DIBRISUniversità Degli Studi di GenovaGenovaItaly

Personalised recommendations