Probability distributions of optical flow
作者： E.P. Simoncelli , E.H. Adelson , D.J. Heeger
关键词:
摘要: Gradient methods are widely used in the computation of optical flow. The authors discuss extensions these which compute probability distributions use allows representation uncertainties inherent flow computation, facilitating combination with information from other sources. Distributed for a synthetic image sequence is computed, and it demonstrated that probabilistic model accounts errors estimates. distributed real computed. >
sci-hub.se 参考文章(8)
Lynn H. Quam, Hierarchical warp stereo Morgan Kaufmann Publishers Inc.. pp. 80- 86 ,(1987) , 10.1016/B978-0-08-051581-6.50015-5
David J. Heeger, Optical flow using spatiotemporal filters International Journal of Computer Vision. ,vol. 1, pp. 279- 302 ,(1988) , 10.1007/BF00133568
Peter J Burt, Fast filter transform for image processing Computer Graphics and Image Processing. ,vol. 16, pp. 20- 51 ,(1981) , 10.1016/0146-664X(81)90092-7
Richard Stephen Szeliski, Bayesian Modeling of Uncertainty in Low-Level Vision ,(2011)
Bruce D. Lucas, Takeo Kanade, An iterative image registration technique with an application to stereo vision international joint conference on artificial intelligence. pp. 674- 679 ,(1981)
P. Anandan, A Computational Framework and an Algorithm for the Measurement of Visual International Journal of Computer Vision. ,vol. 2, pp. 283- 310 ,(1987) , 10.1007/BF00158167
Berthold K. P. Horn, Brian G. Schunck, Determining optical flow Shape recovery. ,vol. 17, pp. 389- 407 ,(1992)
P. J. Burt, Fast Filter Transforms for Image Processing Comput. Vision, Graphics & Image Processing. ,vol. 16, pp. 20- 51 ,(1981)