A closed-form solution for optical flow by imposing temporal constraints

We present a well-constrained formulation for estimation of optical flow in a video sequence, which yields a closed-form solution. Unlike other existing closed-form approaches, our solution does not require second order spatial derivatives. It relies only on first order and cross-space-time derivatives which can be computed more reliably. Instead of the commonly used spatial smoothness constraint, we propose a temporal smoothness constraint which has a clear physical interpretation. Our formulation also allows for accurate analysis of sources of error and ill-conditioning, leading to a more tractable implementation and mathematically justifiable thresholding values.

[1]  Michael J. Black,et al.  A framework for the robust estimation of optical flow , 1993, 1993 (4th) International Conference on Computer Vision.

[2]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[3]  Steven S. Beauchemin,et al.  The computation of optical flow , 1995, CSUR.

[4]  Hans-Hellmut Nagel,et al.  Displacement vectors derived from second-order intensity variations in image sequences , 1983, Comput. Vis. Graph. Image Process..

[5]  Stephen J. Maybank Optical flow and the Taylor expansion , 1986, Pattern Recognit. Lett..

[6]  Hidetoshi Miike,et al.  Determining optical flow from sequential images , 1988, Systems and Computers in Japan.

[7]  Michael J. Black,et al.  Estimating Optical Flow in Segmented Images Using Variable-Order Parametric Models With Local Deformations , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Keith Langley,et al.  Recursive Filters for Optical Flow , 1995, IEEE Trans. Pattern Anal. Mach. Intell..