Abstract
Transparent motions are additive or multiplicative superpositions of moving patterns and occur due to reflections, semi-transparencies, and partial occlusions. The estimation of transparent motions remained a challenging nonlinear problem. We here first linearize the problem in a way which makes it accessible to the known methods used for the estimation of single motions, such as structure tensor, regularization, block matching, Fourier methods, etc. We present the results for two motion layers but there is no limit to the number of layers. Finally, we present a way to categorize different transparent-motion patterns based on the rank of a generalized structure tensor.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Badino, H.: A robust approach for ego-motion estimation using a mobile stereo platform. In: Jähne, B., Mester, R., Barth, E., Scharr, H. (eds.) IWCM 2004. LNCS, vol. 3417, pp. 198–208. Springer, Heidelberg (2007)
Sühling, M., Arigovindan, M., Jansen, C., Hunziker, P., Unser, M.: Myocardial motion and strain rate analysis from ultrasound sequences. In: Jähne, B., Mester, R., Barth, E., Scharr, H. (eds.) IWCM 2004. LNCS, vol. 3417, pp. 177–189. Springer, Heidelberg (2007)
Sigal, L., Zhu, Y., Comaniciu, D., Black, M.J.: Tracking Complex Objects Using Graphical Object Models. In: Jähne, B., Mester, R., Barth, E., Scharr, H. (eds.) IWCM 2004. LNCS, vol. 3417, pp. 223–234. Springer, Heidelberg (2007)
Shizawa, M., Mase, K.: Simultaneous multiple optical flow estimation. In: IEEE Conf. Computer Vision and Pattern Recognition. vol. 1, Atlantic City, NJ, pp. 274–278. IEEE Computer Press, Los Alamitos (1990)
Wang, J.Y.A., Adelson, E.H.: Representing moving images with layers. IEEE Transactions on Image Processing 3, 625–638 (1994)
Darrell, T., Simoncelli, E.: Separation of transparent motion into layers using velocity-tuned mechanisms. Technical Report 244, MIT Media Laboratory (1993)
Darrell, T., Simoncelli, E.: Nulling filters and the separation of transparent motions. In: IEEE Conf. Computer Vision and Pattern Recognition, New York, pp. 738–739. IEEE Computer Society Press, Los Alamitos (1993)
Vernon, D.: Decoupling Fourier components of dynamic image sequences: a theory of signal separation, image segmentation and optical flow estimation. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 68–85. Springer, Heidelberg (1998)
Szeliski, R., Avidan, S., Anandan, P.: Layer extraction from multiple images containing reflections and transparency. In: IEEE Conf. Computer Vision and Pattern Recognition, vo. 1, Hilton Head Island, pp. 246–253. IEEE Computer Society Press, Los Alamitos (2000)
Anandan, P.: Motion estimation and optical flow computation: a personalized view. In: Anandan, P. (ed.) Complex Motion, 1st Int. Workshop, Günzburg, Oct. 12–14, Invited talk (2004)
Mota, C., Stuke, I., Barth, E.: Analytic solutions for multiple motions. In: Proc. IEEE Int. Conf. Image Processing. vol. 2, Thessaloniki, Greece, pp. 917–920. IEEE Signal Processing Soc. (2001)
Mota, C., Dorr, M., Stuke, I., Barth, E.: Categorization of transparent-motion patterns using the projective plane. International Journal of Computer & Information Science 5, 129–140 (2004)
Stuke, I., Aach, T., Barth, E., Mota, C.: Multiple-motion estimation by block-matching using markov random fields. International Journal of Computer & Information Science 5, 141–152 (2004)
Stuke, I., Aach, T., Mota, C., Barth, E.: Estimation of multiple motions: regularization and performance evaluation. In: Vasudev, B., Hsing, T.R., Tescher, A.G., Ebrahimi, T. (eds.) Image and Video Communications and Processing 2003. Proceedings of SPIE, vol. 5022, pp. 75–86 (2003)
Cremers, D.: Bayesian approaches to motion-based image and video segmentation. In: Jähne, B., Mester, R., Barth, E., Scharr, H. (eds.) IWCM 2004. LNCS, vol. 3417, pp. 104–123. Springer, Heidelberg (2007)
Nordberg, K., Vikstén, F.: Motion based estimation and representation of 3D surfaces and boundaries. In: Jähne, B., Mester, R., Barth, E., Scharr, H. (eds.) IWCM 2004. LNCS, vol. 3417, pp. 146–164. Springer, Heidelberg (2007)
Horn, B., Schunck, B.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)
Langley, K., Fleet, D.J.: A logarithmic transformation applied to multiplicative transparencies and motion discontinuities. Opthalmology Physiology and Optics 14, 441 (1994)
Haußecker, H., Spies, H.: Motion. In: Jähne, B., Haußecker, H., Geißler, P. (eds.) Handbook of Computer Vision and Applications, vol. 2, pp. 309–396. Academic Press, London (1999)
Stuke, I., Aach, T., Mota, C., Barth, E.: Linear and regularized solutions for multiple motion. In: Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing, vol. 3, Hong Kong, pp. 157–160. IEEE Signal Processing Soc. (2003)
Scharr, H.: Optimal filters for extended optical flow. In: Jähne, B., Mester, R., Barth, E., Scharr, H. (eds.) IWCM 2004. LNCS, vol. 3417, pp. 14–29. Springer, Heidelberg (2007)
Fleet, D.J., Jepson, A.D.: Computation of component image velocity from local phase information. International Journal of Computer Vision 5, 77–104 (1990)
Aach, T., Kaup, A.: Bayesian algorithms for adaptive change detection in image sequences using Markov random fields. Signal Processing: Image Communication 7, 147–160 (1995)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Mota, C., Stuke, I., Aach, T., Barth, E. (2007). Divide-and-Conquer Strategies for Estimating Multiple Transparent Motions. In: Jähne, B., Mester, R., Barth, E., Scharr, H. (eds) Complex Motion. IWCM 2004. Lecture Notes in Computer Science, vol 3417. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69866-1_6
Download citation
DOI: https://doi.org/10.1007/978-3-540-69866-1_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69864-7
Online ISBN: 978-3-540-69866-1
eBook Packages: Computer ScienceComputer Science (R0)