Adaptive mixed norm optical flow estimation
This work addresses motion estimation challenges in computer vision, offering an incremental improvement by integrating adaptive regularization into existing pel-recursive methods.
The paper tackles the problem of robust optical flow estimation by proposing an adaptive regularized approach using a Mixed Norm (MN) functional, which handles outliers, motion discontinuities, and occlusion without requiring prior knowledge of noise distribution, resulting in robust estimates as indicated by experiments.
The pel-recursive computation of 2-D optical flow has been extensively studied in computer vision to estimate motion from image sequences, but it still raises a wealth of issues, such as the treatment of outliers, motion discontinuities and occlusion. It relies on spatio-temporal brightness variations due to motion. Our proposed adaptive regularized approach deals with these issues within a common framework. It relies on the use of a data-driven technique called Mixed Norm (MN) to estimate the best motion vector for a given pixel. In our model, various types of noise can be handled, representing different sources of error. The motion vector estimation takes into consideration local image properties and it results from the minimization of a mixed norm functional with a regularization parameter depending on the kurtosis. This parameter determines the relative importance of the fourth norm and makes the functional convex. The main advantage of the developed procedure is that no knowledge of the noise distribution is necessary. Experiments indicate that this approach provides robust estimates of the optical flow.