Gradient-based approaches to the computation of optical flow often use a minimization technique incorporating a smoothness constraint on the optical flow field. The author derives the most general form of such a smoothness constraint which is quadratic in first or second derivatives of the grey-level image intensity function, based on three simple assumptions about the smoothness constraint: (1) that it be expressed in a form which is independent of the choice of Cartesian coordinate system in the image; (2) that it be positive definite; and (3) that it not couple different components of the optical flow. It is shown that there are essentially only four such constraints; any smoothness constraint satisfying all three assumptions must be a linear combination of these four, possibly multipled by certain quantities of these four, possibly multipled by certain quantities invariant under a change in the Cartesian coordinate system. Beginning with the three assumptions mentioned above, the author mathematically demonstrates that all the best-known smoothness constraints appearing in the literature are special cases of this general form, and, in particular, that the 'weight matrix' introduced by H.-H. Nagel (1983) is essentially the only physically plausible such constraint.<<ETX>>
[1]
Berthold K. P. Horn,et al.
Determining Optical Flow
,
1981,
Other Conferences.
[2]
Eric L. W. Grimson,et al.
From Images to Surfaces: A Computational Study of the Human Early Visual System
,
1981
.
[3]
Michael Brady,et al.
Rotationally symmetric operators for surface interpolation
,
1983,
Comput. Vis. Graph. Image Process..
[4]
Ellen C. Hildreth,et al.
Measurement of Visual Motion
,
1984
.
[5]
Hans-Hellmut Nagel,et al.
An Investigation of Smoothness Constraints for the Estimation of Displacement Vector Fields from Image Sequences
,
1983,
IEEE Transactions on Pattern Analysis and Machine Intelligence.
[6]
Hans-Hellmut Nagel,et al.
On the Estimation of Optical Flow: Relations between Different Approaches and Some New Results
,
1987,
Artif. Intell..