Abstract
Motion analysis involves the interpretation of image data over time. It is crucial for a range of vision tasks such as obstacle detection, depth estimation, video analysis, scene interpretation, video compression, etc. Motion analysis is difficult because it requires modeling of the complicated relationships between the observed image data and the motion of objects and motion patterns in the visual scene.
This chapter focuses on critical aspects of motion analysis, including statistical optical flow, model-based motion analysis, and joint motion estimation and segmentation. There exist many different techniques for performing various motion tasks; these techniques can be subsumed within a statistical and geometrical framework. We choose to focus on statistical approaches to classifying motion patterns in an observed image sequence.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Adiv G (1985) Determining three dimensional motion and structure from optical flow generated by several objects. IEEE Transactions on Pattern Analysis and Machine Intelligence 7:384–401
Aloimonos Y, Duric Z (1992) Active egomotion estimation: a qualitative approach. In: Proceedings of European Conference on Computer Vision Ligure, Italy, Springer, pp 497–510
Ayer S, Schroeter P, Bigun J (1994) Segmentation of moving objects by robust motion parameter estimation over multiple frames. In: Proceedings of European Conference on Computer Vision, Springer, Berlin, pp 316–327
Baker S, Matthews I (2004) Lucas-Kanade 20 Years On: a unifying framework. International Journal of Computer Vision 56(3):221–255
Barron J, Fleet D, Beauchemins (1994) Performance of optical flow techniques. International Journal of Computer Vision 12(1):43–77
Black M, Jepson A (1996) Estimating optical flow in segmented images using variable-orderparametric models with local deformations. IEEE Transactions on Pattern Analysis and Machine Intelligence 18(10):972–986
Brox T, Bruhn A, Papenberg N, Weickert J (2004) High accuracy optical flow estimation based on a theory for warping. Lecture Notes in Computer Science pp 25–36
Bruhn A, Weickert J, Schnörr C (2005) Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. International Journal of Computer Vision 61(3):211–231
Darrell T, Pentland A (1995) Cooperative robust estimation using layers of support. IEEE Transactions on Pattern Analysis and Machine Intelligence pp 474–487
Fleet D, Weiss Y (2005) Optical flow estimation. In: Mathematical Models for Computer Vision: The Handbook, ed O Faugeras, Springer, Newyork, pp 239–258
Fleet D, Black M, Yacoob Y, Jepson A (2000) Design and use of linear models for image motion analysis. International Journal of Computer Vision 36(3):171–193
Foroosh H, Zerubia J, Berthod M (2002) Extension of phase correlation to subpixel registration. IEEE Transactions on Image Processing 11(3):188–200
Geman S, Geman D (1987) Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images. Readings in Computer Vision: Issues, Problems, Principles, and Paradigms pp 564–584
Jepson A, Black M (1993) Mixture models for optical flow computation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 760–761
Konrad J, Dubois E (1992) Bayesian estimation of motion vector fields. IEEE Transactions on Pattern Analysis and Machine Intelligence 14(9):910–927
Liu C, Freeman W, Adelson E, Weiss Y (2008) Human-assisted motion annotation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 1–8
Liu J (2001) Monte Carlo Strategies in Scientific Computing. Springer, New york
Perona P (1995) Deformable kernels for early vision. IEEE Transactions on Pattern Analysis and Machine Intelligence pp 488–499
Roth S, Black M (2007) On the spatial statistics of optical flow. International Journal of Computer Vision 74(1):33–50
Tekalp A (1995) Digital Video Processing. Prentice Hall, Upper Saddle River, NJ
Verri A, Poggio T (1987) Against quantitative optical flow. In: Proceedings of the First Internaional Conference on Computer Vision, pp 171–180. Computer Society Press, New york
Wang J, Adelson E (1994) Representing moving images with layers. IEEE Transactions on Image Processing3(5):625–638
Wechsler H, Duric Z, Li F, Cherkassky V (2004) Motion estimation using statistical learning theory. IEEE Transactions on Pattern Analysis and Machine Intelligence pp 466–478
Weiss Y (1997) Smoothness in layers: motion segmentation using nonparametricmixture estimation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 520–526
Weiss Y, Adelson E (1996) A unified mixture framework for motion segmentation: incorporatingspatial coherence and estimating the number of models. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 321–326
Zhang J, Hanauer G (1995) The application of mean field theory to image motion estimation. IEEE Transactions on Image Processing 4(1):19–33
Zhao H, Chan T, Merriman B, Osher S (1996) A variational level set approach to multiphase motion. Journal of Computational Physics 127(1):179–195
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2009 Springer-Verlag London Limited
About this chapter
Cite this chapter
Zheng, N., Xue, J. (2009). Statistical Motion Analysis. In: Statistical Learning and Pattern Analysis for Image and Video Processing. Advances in Pattern Recognition. Springer, London. https://doi.org/10.1007/978-1-84882-312-9_7
Download citation
DOI: https://doi.org/10.1007/978-1-84882-312-9_7
Publisher Name: Springer, London
Print ISBN: 978-1-84882-311-2
Online ISBN: 978-1-84882-312-9
eBook Packages: Computer ScienceComputer Science (R0)