Motion compensating interpolation considering covered and uncovered background

摘要

An improved algorithm for motion compensating interpolation of images in digital television sequences is presented. The algorithm is applicable to the interpolation of skipped images in the environment of a low bit rate codec. It is based on the assumption of pure translatorily moving objects. A low complex hierarchical blockmatching algorithm is used to estimate displacement vector fields, which are a close approximation of the true motion. The estimated displacement vector fields are evaluated in combination with the information of a change detector, in order to derive a segmentation of the images into moving objects, static background, covered, and uncovered background. Especially in the case of interpolating more than one image between every two transmitted images, it has to be taken into account that for each of these images an individual displacement vector field and an individual segmentation is required. This is achieved through a transformation of motion information based on the estimation of one displacement vector field for each pair of transmitted images, only. A spatio-temporal filter, controlled by the displacement and segmentation information, is used to interpolate the desired number of images. Computer simulations confirm, that the presented algorithm provides a remarkably improved rendition of motion, even if video sequences are strongly distorted with coding noise caused by a low bit rate coding process.