Fusion of Luma and Chroma GMMs for HMM-Based Object Detection

  • Wen-Hao Wang
  • Ruei-Cheng Wu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4319)


A spatial-temporal method is proposed for video object detection. The first stage is temporal segmentation which is comprised of GMM on luma and GMM on chroma. An efficient fusion method is proposed to combine the two GMM segmentation results such that the object mask can be improved to some extent. In the second stage, the mask produced in the first stage is statistically analyzed in spatial domain. HMM is employed to refine the segmentation result by estimating the foreground-background state such that the false detection in foreground and background area can be decreased and lead to robust and satisfactory detection results.


Gaussian Mixture Model Object Detection Segmentation Result Human Action Recognition Object Mask 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Stauffer, C., Grimson, W.E.L.: Adaptive Background Mixture Models for Real-Time Tracking. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2, 23–25 (1999)Google Scholar
  2. 2.
    Rittscher, J., Kato, J., Joga, S., Blake, A.: A Probabilistic Background Model for TrackingGoogle Scholar
  3. 3.
    Kato, J., Joga, S., Rittscher, J., Blake, A.: An HMM-Based Segmentation Method for Traffic Monitoring Movies. IEEE Trans. PAMI 24(9), 1291–1296 (2002)Google Scholar
  4. 4.
    Li, N., Bu, J., Chen, C.: Real-Time Video Object Segmentation Using HSV Space. In: ICIP, pp. II-85-II-88 (2002)Google Scholar
  5. 5.
    Junag, B.-H., Rabiner, L.R.: Mixture Autoregressive Hidden Markov Models for Speech Signals. IEEE Trans. Acoustics, Speech, and Signal Processing, 1404–1413 (1985)Google Scholar
  6. 6.
    Zivkovic, Z.: Improved Adaptive Gaussian Mixture Model for Background Subtraction. In: ICPR, vol. 2, pp. 28–31 (2004)Google Scholar
  7. 7.
    Dedeoglu, Y.: Human Action Recognition Using Gaussian Mixture Model Based Background Segmentation. In: Machine Learning Workshop, Bilkent University (2005)Google Scholar
  8. 8.
    Power, O.W.: Understanding Background Mixture Models for Foreground Segmentation. In: Proceedings of Image and Vision Computing New Zealand, pp. 267–271 (2002)Google Scholar
  9. 9.
    Horn, K.P.: Robot Vision, pp. 299–333. MIT Press, Cambridge (1986)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Wen-Hao Wang
    • 1
  • Ruei-Cheng Wu
    • 1
  1. 1.Industrial Technology Research InstituteTaiwan

Personalised recommendations