| Hi-index | 0.00 |
Scale space is a natural way to handle multi-scale problem. Yang and Ma considered the correspondence between scales, and proposed optical flow in the scale space. In this paper, we generalized Yang and Ma's work to generic images. We first genralize the Horn-Schunck algorithm to multidimentional multichannel image sequence. Since the global smothness constraint for regularization is no longer suitable in general cases, we introduced localized smoothness weight regularization. At last, we apply the proposedmethod in color image scale-space pullback, together with another localized smoothness trick considering flow density.