Multiple Segmentation of Moving Objects by Quasi-simultaneous Parametric Motion Estimation

  • Raúl Montoliu
  • Filiberto Pla
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2652)


This paper presents a new framework for the motion segmentation and estimation task on sequences of two grey images without a priori information of the number of moving regions present in the sequence. The proposed algorithm combines temporal information, by using an accurate Generalized Least-Squares Motion Estimation process and spatial information by using an inlier/outlier classification process which classifies regions of pixels, in a first step, and the pixels directly, in a second step, into the different motion models present in the sequence. The performance of the algorithm has been tested on synthetic and real images with multiple objects undergoing different types of motion.


Motion Estimation Motion Model Generalize Little Square Motion Segmentation Synthetic Sequence 
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.
    Bad-Hadiashar, A., Suter, D.: Robust motion segmentation using rank ordering estimators. In: Third Asian Coference on Computer Vision ACCV 1998, Honk Kong (1998)Google Scholar
  2. 2.
    Bober, M., Kittler, J.V.: Estimation of complex multimodal motion: An approach based on robust statistics and hough transform. IVC 12(10), 661–668 (1994)CrossRefGoogle Scholar
  3. 3.
    Danuser, G., Stricker, M.: Parametric model-fitting: From inlier characterization to outlier detection. PAMI 20(3), 263–280 (1998)CrossRefGoogle Scholar
  4. 4.
    Irani, M., Rousso, B., Peleg, S.: Computing occluding and transparent motion. IJVC 12(1), 5–16 (1994)Google Scholar
  5. 5.
    Kim, J.B., Kim, H.J.: Effient region-based motion segmentation for a video monitoring system. Pattern Recognition Letters 24, 113–128 (2003)CrossRefGoogle Scholar
  6. 6.
    Lee, K.-M., Meer, P., Park, R.-H.: Robust adaptive segmentation of range images. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(2), 200–205 (1998)CrossRefGoogle Scholar
  7. 7.
    Miller, J.V., Stewart, C.V.: Muse: Robust surface fitting using unbiased scale estimates. In: Computer Vision and Pattern Recognition 1996, pp. 300–306 (1996)Google Scholar
  8. 8.
    Montoliu, R., Pla, F.: Multiple parametric motion model estimation and segmentation. In: ICIP 2001, 2001 International Conference on Image Processing, October 2001, vol. II, pp. 933–936 (2001)Google Scholar
  9. 9.
    Montoliu, R., Traver, V.J., Pla, F.: Log-polar mapping in generalized leastsquares motion estimation. In: Proccedings of 2002 IASTED International Conference on Visualization, Imaging, and Image Processing (VIIP 2002), September 2002, pp. 656–661 (2002)Google Scholar
  10. 10.
    Odone, F., Fusiello, A., Trucco, E.: Robust motion segmentation for contentbased video coding. In: RIAO 2000 6th Conference on Content-Based Multimedia Information Access, pp. 594–601 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Raúl Montoliu
    • 1
  • Filiberto Pla
    • 1
  1. 1.Dept. Lenguajes y Sistemas InformáticosJaume I UniverisityCastellónSpain

Personalised recommendations