Skip to main content
SpringerLink
Log in

2D Motion Description and Contextual Motion Analysis: Issues and New Models

  • Conference paper
Spatial Coherence for Visual Motion Analysis (SCVMA 2004)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 3667))

Included in the following conference series:

  • 373 Accesses

Abstract

In this paper, several important issues related to visual motion analysis are addressed with a focus on the type of motion information to be estimated and the way contextual information is expressed and exploited. Assumptions (i.e., data models) must be formulated to relate the observed image intensities with motion, and other constraints (i.e., motion models) must be added to solve problems like motion segmentation, optical flow computation, or motion recognition. The motion models are supposed to capture known, expected or learned properties of the motion field, and this implies to somehow introduce spatial coherence or more generally contextual information. The latter can be formalized in a probabilistic way with local conditional densities as in Markov models. It can also rely on predefined spatial supports (e.g., blocks or pre-segmented regions). The classic mathematical expressions associated with the visual motion information are of two types. Some are continuous variables to represent velocity vectors or parametric motion models. The other are discrete variables or symbolic labels to code motion detection output (binary labels) or motion segmentation output (numbers of the motion regions or layers). We introduce new models, called mixed-state auto-models, whose variables belong to a domain formed by the union of discrete and continuous values, and which include local spatial contextual information. We describe how such models can be specified and exploited in the motion recognition problem. Finally, we present a new way of investigating the motion detection problem with spatial coherence being associated to a perceptual grouping principle.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Aach, T., Kaup, A.: Bayesian algorithms for change detection in image sequences using Markov random fields. Signal Processing: Image Communication 7(2), 147–160 (1995)

    Article  Google Scholar 

  2. Alvarez, L., Weickert, J., Sánchez, J.: Reliable estimation of dense optical flow fields with large displacements. International Journal of Computer Vision 39(1), 41–56 (2000)

    Article  MATH  Google Scholar 

  3. Besag, J.: Spatial interactions and the statistical analysis of lattice systems. Journal Royal Statistical Society, B 148, 1–36 (1974)

    Google Scholar 

  4. Bigün, J., Granlund, G.H., Wiklund, J.: Multidimensional orientation estimation with applications to texture analysis and optical flow. IEEE Trans. on Pattern Analysis and Machine Intelligence 13(8), 775–790 (1991)

    Article  Google Scholar 

  5. Black, M.J., Anandan, P.: The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields. Computer Vision and Image Understanding 63(1), 75–104 (1996)

    Article  Google Scholar 

  6. Black, M.J., Jepson, A.D.: Estimating optical flow in segmented images using variable-order parametric models with local deformations. IEEE Trans. on Pattern Analysis and Machine Intelligence 18(10), 972–986 (1996)

    Article  Google Scholar 

  7. Bouthemy, P., François, E.: Motion segmentation and qualitative dynamic scene analysis from an image sequence. Int. Journal of Computer Vision 10(2), 157–182 (1993)

    Article  Google Scholar 

  8. Cohen, I., Herlin, I.: Non uniform multiresolution method for optical flow and phase portrait models: Environmental application. IJCV 33(1), 29–49 (1999)

    Article  Google Scholar 

  9. Corpetti, T., Mémin, E., Pérez, P.: Dense estimation of fluid flows. IEEE Trans. on Pattern Analysis and Machine Intelligence 24(3), 365–380 (2002)

    Article  Google Scholar 

  10. Cremers, D., Kohlberger, T., Schnörr, C.: Nonlinear Shape Statistics in Mumford-Shah Based Segmentation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. 93–108. Springer, Heidelberg (2002)

    Chapter  Google Scholar 

  11. Cremers, D., Soatto, S.: Variational space-time motion segmentation. In: Proc. 9th IEEE Int. Conf. on Computer Vision, ICCV 2003, Nice (October 2003)

    Google Scholar 

  12. Desolneux, A., Moisan, L., Morel, J.-M.: A grouping principle and four applications. IEEE Trans. on Pattern Analysis and Machine Intelligence 25(4), 508–513 (2003)

    Article  Google Scholar 

  13. Fablet, R., Bouthemy, P.: Non-parametric scene activity analysis for statistical retrieval with partial query. Journal of Mathematical Imaging and Vision 14(3), 257–270 (2001)

    Article  MATH  Google Scholar 

  14. Fablet, R., Bouthemy, P., Pérez, P.: Non-parametric motion characterization using causal probabilistic models for video indexing and retrieval. IEEE Trans. on Image Processing 11(4), 393–407 (2002)

    Article  Google Scholar 

  15. Fablet, R., Bouthemy, P.: Motion recognition using non parametric image motion models estimated from temporal and multiscale cooccurrence statistics. IEEE Trans. on Pattern Analysis and Machine Intelligence 25(12), 1619–1624 (2003)

    Article  Google Scholar 

  16. Fleet, D.J., Jepson, A.D.: Computation of component image velocity from local phase information. International Journal of Computer Vision 5(1), 77–104 (1990)

    Article  Google Scholar 

  17. Gelgon, M., Bouthemy, P.: A region-level motion-based graph representation and labeling for tracking a spatial image partition. Pattern Recognition 33(4), 725–745 (2000)

    Article  Google Scholar 

  18. Guyon, X., Hardouin, C., Yao, J.-F.: Markovian auto-models with mixed states (preprint, 2004)

    Google Scholar 

  19. Haussecker, H.W., Fleet, D.J.: Estimating optical flow with physical models of brightness variation. IEEE Trans. on Pattern Analysis and Machine Intelligence 23(6), 661–673 (2001)

    Article  Google Scholar 

  20. Heitz, F., Bouthemy, P.: Multimodal estimation of discontinuous optical flow using Markov random fields. IEEE Trans. on PAMI 15(12), 1217–1232 (1993)

    Google Scholar 

  21. Heitz, F., Pérez, P., Bouthemy, P.: Multiscale minimization of global energy functions in some visual recovery problems. CVGIP: Image Understanding 59(1), 125–134 (1994)

    Article  Google Scholar 

  22. Horn, B.K.P., Schunck, B.G.: Determing optical flow. Art. Intelligence 17, 185–203 (1981)

    Article  Google Scholar 

  23. Irani, M., Rousso, B., Peleg, S.: Computing occluding and transparent motion. International Journal of Computer Vision 12(1), 5–16 (1994)

    Article  Google Scholar 

  24. Konrad, J.: Motion detection and estimation. In: Bovik, A.C. (ed.) Handbook of Image and Video Processing, Academic Press, London (2000)

    Google Scholar 

  25. Kornprobst, P., Deriche, R., Aubert, G.: Image sequence analysis via partial differential equations. Journal of Mathematical Imaging and Vision 11(1), 5–26 (1999)

    Article  MathSciNet  Google Scholar 

  26. Mansouri, A.-R., Konrad, J.: Multiple motion segmentation with level sets. IEEE Trans. Image Processing 12, 201–220 (2003)

    Article  Google Scholar 

  27. Marroquin, J.-L., Santana, E.A., Botello, S.: Hidden Markov measure field models for image segmentation. IEEE Trans. on PAMI 25(11), 1380–1387 (2003)

    Google Scholar 

  28. Mémin, E., Pérez, P.: Optical flow estimation and object-based segmentation with robust techniques. IEEE Trans. on Image Processing 7(5), 703–719 (1998)

    Article  Google Scholar 

  29. Mémin, E., Pérez, P.: Hierarchical estimation and segmentation of dense motion fields. Int. Journal of Computer Vision 46(2), 129–155 (2002)

    Article  MATH  Google Scholar 

  30. Mitiche, A., Bouthemy, P.: Computation and analysis of image motion: A synopsis of current problems and methods. International Journal of Computer Vision 19(1), 29–55 (1996)

    Article  Google Scholar 

  31. Murray, D.W., Buxton, B.F.: Scene segmentation from visual motion using global optimization. IEEE Trans. on Pattern Analysis and Machine Intelligence 9(2), 220–228 (1987)

    Article  Google Scholar 

  32. Nagel, H.-H.: On the estimation of optic flow: Relations between different approaches and some new results. Artificial Intelligence 33, 299–324 (1987)

    Article  Google Scholar 

  33. Nagel, H.-H., Gehrke, A.: Spatiotemporally Adaptive Estimation and Segmentation of OF-fields. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, Springer, Heidelberg (1998)

    Chapter  Google Scholar 

  34. Nicolescu, M., Medioni, G.: Layered 4D representation and voting for grouping from motion. IEEE Trans. on Pattern Analysis and Machine Intelligence 25(4), 492–501 (2003)

    Article  Google Scholar 

  35. Odobez, J.-M., Bouthemy, P.: Robust multiresolution estimation of parametric motion models. Journal of Visual Communication and Image Representation 6(4), 348–365 (1995)

    Article  Google Scholar 

  36. Odobez, J.M., Bouthemy, P.: Separation of moving regions from background in an image sequence acquired with a mobile camera. In: Li, H.H., Sun, S., Derin, H. (eds.) Video Data Compression for Multimedia Computing, ch.8, pp. 283–311. Kluwer, Dordrecht (1997)

    Google Scholar 

  37. Odobez, J.-M., Bouthemy, P.: Direct incremental model-based image motion segmentation for video analysis. Signal Processing 6(2), 143–155 (1998)

    Article  Google Scholar 

  38. Papin, C., Bouthemy, P., Mémin, E., Rochard, G.: Tracking and Characterization of Highly Deformable Cloud Structures. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 428–442. Springer, Heidelberg (2000)

    Chapter  Google Scholar 

  39. Paragios, N., Deriche, R.: Geodesic active contours and level sets for the detection and tracking of moving objects. IEEE Trans. on PAMI 22(3), 266–280 (2000)

    Google Scholar 

  40. Piriou, G., Bouthemy, P., Yao, J.-F.: Extraction of semantic dynamic content from videos with probabilistic motion models. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, Springer, Heidelberg (2004)

    Google Scholar 

  41. Sawhney, H.S., Ayer Compact, S.: representations of videos through dominant and multiple motion estimation. IEEE Trans. on PAMI 18(8), 814–830 (1996)

    Google Scholar 

  42. Smith, P., Drummond, T., Cipolla, R.: Layered motion segmentation and depth ordering by tracking edges. IEEE Trans. on PAMI 26(4), 479–494 (2004)

    Google Scholar 

  43. Stiller, C., Konrad, J.: Estimating motion in image sequences (A tutorial on modeling and computation of 2D motion). IEEE Signal Processing Magazine 16, 70–91 (1999)

    Article  Google Scholar 

  44. Veit, T., Cao, F., Bouthemy, P.: Probabilistic parameter-free motion detection. In: IEEE Conf. Computer Vision and Pattern Recognition, CVPR 2004, Washington DC (June 2004)

    Google Scholar 

  45. Wang, Y., Zhu, S.-C.: Modeling textured motion: Particle, wave and sketch. In: IEEE Int. Conf. on Computer Vision, ICCV 2003, Nice (October 2003)

    Google Scholar 

  46. Weickert, J., Bruhn, A., Papenberg, N., Brox, T.: Variational optic flow computation: From continuous models to algorithms. In: Alvarez, L. (ed.) International Workshop on Computer Vision and Image Analysis, IWCVIA 2003, Las Palmas de Gran Canaria (December 2003)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. IRISA / INRIA, Campus universitaire de Beaulieu, 35042 cedex, Rennes, France

    P. Bouthemy

Authors
  1. P. Bouthemy
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. University of Toronto, M5S 3G4, Toronto, ON, Canada

    W. James MacLean

Rights and permissions

Reprints and permissions

Copyright information

© 2006 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Bouthemy, P. (2006). 2D Motion Description and Contextual Motion Analysis: Issues and New Models. In: MacLean, W.J. (eds) Spatial Coherence for Visual Motion Analysis. SCVMA 2004. Lecture Notes in Computer Science, vol 3667. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11676959_1

Download citation

  • DOI: https://doi.org/10.1007/11676959_1

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-32533-8

  • Online ISBN: 978-3-540-32534-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation