Advertisement

Rejecting False Positives in Video Object Segmentation

  • Daniela Giordano
  • Isaak Kavasidis
  • Simone Palazzo
  • Concetto SpampinatoEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9256)

Abstract

False-positive removal is a necessary step for robust video object segmentation because of the presence of visual noise introduced by unavoidable factors such as background movements, light changes, artifacts, etc. In this paper we present a set of generic visual cues that enable the discrimination between true positives and false positives detected by a video object segmentation approach. The devised object features encode real-world object properties, such as shape regularity, marked boundaries, color and texture uniformity and motion continuity and can be used in a post-processing layer to reject false positives.

A thorough performance evaluation of the employed features and classifiers is carried out in order to identify which visual cues/classifier allow for a better separability between true and false positives. The experimental results, obtained on three challenging datasets, showed that a post-processing layer exploiting the devised visual features is able a) to reduce the false alarm rate by about 10% to 20%, while keeping the number of true positives almost unaltered, and b) to generalize over different object classes and application domains.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aha, D.W., Bankert, R.L.: A comparative evaluation of sequential feature selection algorithms, vol. 206, pp. 1–7. SpringerVerlag New York (1995)Google Scholar
  2. 2.
    Alexe, B., Deselaers, T., Ferrari, V.: Measuring the Objectness of Image Windows. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP(c), 1–14 (2012)Google Scholar
  3. 3.
    Bai, X., Wang, J., Sapiro, G.: Dynamic color flow: a motion-adaptive color model for object segmentation in video. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 617–630. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  4. 4.
    Barnich, O., Van Droogenbroeck, M.: ViBe: a universal background subtraction algorithm for video sequences. IEEE transactions on image processing : a publication of the IEEE Signal Processing Society 20(6), 1709–24 (2011)CrossRefGoogle Scholar
  5. 5.
    Bouguet, J.-Y.: Pyramidal Implementation of the Lucas-Kanade Feature Tracker Description of the algorithm (2000)Google Scholar
  6. 6.
    Brox, T., Malik, J.: Object segmentation by long term analysis of point trajectories. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 282–295. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  7. 7.
    Brutzer, S., Hoferlin, B., Heidemann, G.: Evaluation of background subtraction techniques for video surveillance. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1937–1944, June 2011Google Scholar
  8. 8.
    Cheng, C., Koschan, A., Chen, C.-H., Page, D.L., Abidi, M.: Outdoor scene image segmentation based on background recognition and perceptual organization. IEEE Transactions on Image Processing 21(3), 1007–1019 (2012)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Cortes, C., Vapnik, V.: Support-vector networks. Machine Learning 20(3), 273–297 (1995)zbMATHGoogle Scholar
  10. 10.
    Erdem, C.E., Sankur, B., Tekalp, A.M.: Performance measures for video object segmentation and tracking. IEEE Transactions on Image Processing 13(7), 937–951 (2004)CrossRefGoogle Scholar
  11. 11.
    Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. International Journal of Computer Vision 59(2), 167–181 (2004)CrossRefGoogle Scholar
  12. 12.
    Krzanowski, W.J.: Principles of Multivariate Analysis: A User’s Perspective. Oxford University Press, New York (1988)zbMATHGoogle Scholar
  13. 13.
    Lee, Y. J., Kim, J., Grauman, K.: Key-segments for video object segmentation. In: Proceedings of the 2011 International Conference on Computer Vision, ICCV 2011, pp. 1995–2002 (2011)Google Scholar
  14. 14.
    Li, L., Huang, W., Gu, I.Y.H., Tian, Q.: Foreground object detection from videos containing complex background. In: Proceedings of the Eleventh ACM International Conference on Multimedia MULTIMEDIA 2003, vol. 3, p. 2 (2003)Google Scholar
  15. 15.
    Lim, J., Han, B.: Generalized background subtraction using superpixels with label integrated motion estimation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol. 8693, pp. 173–187. Springer, Heidelberg (2014) Google Scholar
  16. 16.
    Liu, Z., Jacobs, D.W., Basri, R.: The role of convexity in perceptual completion: beyond good continuation. Vision Research 39(25), 4244–4257 (1999)CrossRefGoogle Scholar
  17. 17.
    Ochs, P., Malik, J., Brox, T.: Segmentation of moving objects by long term video analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 36(6), 1187–1200 (2014)CrossRefGoogle Scholar
  18. 18.
    Papazoglou, A., Ferrari, V.: Fast object segmentation in unconstrained video. In: 2013 IEEE International Conference on Computer Vision, pp. 1777–1784, December 2013Google Scholar
  19. 19.
    Ochs, P., Brox, T.: Object segmentation in video: a hierarchical variational approach for turning point trajectories into dense regions. In: IEEE International Conference on Computer Vision (ICCV) (2011)Google Scholar
  20. 20.
    Sheikh, Y., Shah, M.: Bayesian object detection in dynamic scenes. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition CVPR 2005, vol. 1, pp. 74–79 (2005)Google Scholar
  21. 21.
    Spampinato, C., Palazzo, S.: Enhancing object detection performance by integrating motion objectness and perceptual organization. In: 2012 21st International Conference on Pattern Recognition (ICPR), pp. 3640–3643, November 2012Google Scholar
  22. 22.
    Stauffer, C., Grimson, W.: Adaptive background mixture models for real-time tracking. In: Proceedings of 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), pp. 246–252 (1999)Google Scholar
  23. 23.
    Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 246–252 (1999)Google Scholar
  24. 24.
    Stauffer, C., Grimson, W.E.L.: Learning patterns of activity using real-time tracking (2000)Google Scholar
  25. 25.
    Zhang, D., Javed, O., Shah, M.: Video object segmentation through spatially accurate and temporally dense extraction of primary object regions. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 628–635 (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Daniela Giordano
    • 1
  • Isaak Kavasidis
    • 1
  • Simone Palazzo
    • 1
  • Concetto Spampinato
    • 1
    Email author
  1. 1.Department of Electrical, Electronics and Computer EngineeringUniversity of CataniaCataniaItaly

Personalised recommendations