Abstract: In a method of estimating motion, at least two motion parameter sets are generated (PE1-PEn) from input video data (n, n−1), a motion parameter set being a set of parameters describing motion in an image, by means of which motion parameter set motion vectors can be calculated. One motion parameter set indicates a zero velocity for all image parts in an image, and each motion parameter set has corresponding local match errors. Output motion data are determined from the input video data (n, n−1) in dependence on the at least two motion parameter sets, wherein the importance of each motion parameter set in calculating the output motion data depends on the motion parameter sets' local match errors.

Abstract: In a method of estimating motion vectors, motion parameters (p1-p4) are determined (PC) for a given field (n−1) of a video signal; and motion vectors ( D(X, n) ) for a field (n) of said video signal are determined in dependence upon at least one predetermined motion vector ( D(x−X, y−Y, n), D(x+X, y−Y, n), D(x, y+2Y, n−1) ) and at least one additional motion vector (PV(X) derived (PG) from said motion parameters (p1-p4).

Abstract: In a method of furnishing output motion vectors (MV′), motion vectors (MV) are retrieved (DEC) from an encoded image signal (MPEG), and the retrieved motion vectors (MV) are post-processed to obtain the output motion vectors (MV′). The post-processing includes generating (CVG) candidate motion vectors, and selecting (CVS) the output motion vectors (MV′) in dependence upon the candidate motion vectors and the retrieved motion vectors (MV).

Abstract: An image data recursive noise filter wherein relatively high spatial frequency components of the image data are either not filtered at all or are filtered to a lesser degree than relatively low spatial frequency components of the image data. This minimizes blurring of fine low-contrast detail and also avoids "freezing" of noise in undetailed moving areas of the image.

Abstract: In a method of filtering data, including the steps of processing (7) data (O) to obtain reduced data, delaying (9) the reduced data to obtain delayed data, interpolating (11, 13) the delayed data to obtain interpolated data (R), and combining (1-5) the interpolated data (R) and input data (I) to obtain filtered data (O), the interpolating step (11, 13) includes the step (13) of providing one delayed data element out of several delayed data elements in dependence upon an input data element (p).