Abstract
This paper presents a dense optic flow algorithm based on quite simple local probability assumptions. Due to the explicit derivation of the correspondence concept in a probability-theoretical framework, occlusion probability evolves straight-forwardly from the model for each pixel. Initialized with a similarity measure based on single pixels, an iterated diffusion step propagates local information across the image, while occlusion probability is used to inhibit flow information transfer across depth discontinuities, which prevents flow smoothing at 3d object boundaries. The inhibition is thereby not artificially modelled by some heuristically chosen parameters, but arises directly from the Bayesian correspondence model. The algorithm structure can be interpreted as a recurrent neural network, where matched points have reached a stable state, while others (e.g. those in homogeneous areas) keep receiving information from regions more and more far away until they converge, this way overcoming the aperture problem. The massive parallel structure allows for and demands a real hardware implementation of the system.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Kanade, T., Okutomi, M.: A stereo matching algorithm with an adaptive window: Theory and experiment. IEEE Transactions on PAMI 16, 920–932 (1994)
Horn, B., Schunck, B.: Determining optical flow. AI 17, 185–204 (1981)
Marroquin, J., Velasco, F., Rivera, M., Nakamura, M.: Gauss-markov measure field models for low-level vision. IEEE Transactions on PAMI 23, 337–348 (2001)
Scharstein, D., Szeliski, R.: Stereo matching with nonlinear diffusion. International Journal of Computer Vision 28, 155–174 (1998)
Zitnick, C., Kanade, T.: A cooperative algorithm for stereo matching and occlusion detection. IEEE Transactions on PAMI 22, 675–684 (2000)
Vasconcelos, N., Lippman, A.: Empirical bayesian motion segmentation. IEEE Transactions on PAMI 23, 217–221 (2001)
Torr, P., Szeliski, R., Anandan, P.: An integrated bayesian approach to layer extraction from image sequences. IEEE Transactions on PAMI 23, 297–303 (2001)
Black, M., Rangarajan, A.: On the unification of line processes, outlier rejection, and robust statistics with applications in early vision. IJCV 19(1), 57–91 (1996)
Konrad, J., Dubois, E.: Bayesian estimation of motion vector fields. IEEE Transactions on PAMI 14, 910–927 (1992)
Belhumeur, P.N.: A Bayesian approach to binocular stereopsis. International Journal of Computer Vision 19, 237–262 (1996)
Memin, E., Perez, P.: Dense estimation and object-based segmentation of the optical flow with robust techniques. IEEE Transactions on IP 7, 703–719 (1998)
Perwass, C., Sommer, G.: An iterative bayesian technique for dense image point matching. In: Proceedings of Dynamic Perception, pp. 283–288 (2002)
Egnal, G., Wildes, R.: Detecting binocular half-occlusions: Empirical comparisons of four approaches. In: IEEE Conference CVPR, pp. 466–473 (2000)
Koeser, K.: Dense image point matching with explicit occlusion detection for stereo disparity and optic flow. Master’s thesis, CAU Kiel (2003), available at http://www.ks.informatik.uni-kiel.de
Galvin, B., McCane, B., Novins, K., Mason, D., Mills, S.: Recovering motion fields: An evaluation of eight optical flow algorithms. In: Proc. of BMVC, pp. 195–204 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Koeser, K., Perwass, C., Sommer, G. (2006). Dense Optic Flow with a Bayesian Occlusion Model. 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_11
Download citation
DOI: https://doi.org/10.1007/11676959_11
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)