Abstract: The process performing a calculation of a motion vector field associated with an image, defining, for an image element with coordinates xi, yi, one or more motion vectors with components ui, vi, is characterized in that it also performs the following steps; modelling of the motion on the basis of a simplified parametric representation: ui=tx+k.xi vi=ty+k.yi with tx, ty components of a vector representing the translation component of the motion, k divergence factor characterizing the zoom component of the motion, robust linear regression in each of the two motion representation spaces defined by the planes and, x, y, u and v representing respectively the axes of the variables xi, yi, ui and vi, to give regression lines, calculation of the parameters tx, ty, and k on the basis of the slopes and ordinates at the origin of the regression lines. Applications relate to the selection of key images for video indexing or the generation of metadata.

Abstract: A device and a method for measuring visual similarity between two images. One image (Q) being referred to as the model and one image (T) being referred to as the target, the method comprises a prior step (E2) of segmenting the images into regions (Qi, Ti), with each region there being associated at least one attribute (F) representative of at least one characteristic of the region. It furthermore comprises the steps of calculating (E3) the visual similarity between the pairs (Qi, Ti) of possible regions of the two images (Q, T), by taking into account the distance (D(Qi, Ti)) between the said attributes (F) of the regions (Qi, Ti) matched and the areas of the regions (Qi, Ti) matched; selecting (E4) a certain number of pairs (Qi, Ti) of regions whose similarity is greater than a first fixed threshold (?), calculating (E9) the global similarity between the two images, based on the pairs (Qi, Ti) of regions selected.

Abstract: The invention relates to a method of processing audiovisual programs so as to display a summary thereof. The method comprises a prior step of recording an audiovisual program, and a step of searching for slow motion sequences within the program recorded and a step of displaying the sequences found. User commands make it possible to navigate among the various sequences found.

Abstract: The process is characterized in that it stores a position of the write pointer PW on receipt of the synchronization signal S1 relating to the input signal so as to provide a value PW-IN, and on receipt of the synchronization signal S2 relating to the output signal so as to provide a value PW-OUT, in that it dynamically calculates an interpolation phase &agr; (12, 13, 14, 15) such that: α = P W ⁢   ⁢ _OUT - P W ⁢   ⁢ _IN Δ ⁢  

Abstract: The present invention is a method for detecting static areas in a sequence of digital video pictures. The method includes computing pixel differences between corresponding pixels of consecutive frames or consecutive fields with identical parities and accumulating the magnitudes of the pixel differences over blocks of pixels of the video frames. Next, thresholds T(i,j) for pixel blocks are computed. The threshold for each block is adapted to an estimated noise level &sgr; for the current field or frame and the amount of a block gradient g(i,j), and the threshold levels T(i,j) are calculated according to a disclosed formula. Then, the thresholds T(i,j) are applied to the accumulated pixel differences of the corresponding blocks thus providing a preliminary map of static areas and the preliminary map of static areas are modified by eliminating isolated static blocks or small groups of adjacent static blocks.

Abstract: The process is characterized in that it stores a position of the write pointer PW on receipt of the synchronization signal S1 relating to the input signal so as to provide a value PW-IN, and on receipt of the synchronization signal S2 relating to the output signal so as to provide a value PW-OUT, in that it dynamically calculates an interpolation phase &agr; (12, 13, 14, 15) such that: 1 α = P W ⁢   ⁢ _ ⁢   ⁢ OUT - P W ⁢   ⁢ _ ⁢   ⁢ IN Δ ⁢   ⁢ P W ⁢   ⁢ _ ⁢   ⁢ FIELD ⁢   ⁢ if ⁢   ⁢ P W ⁢   ⁢ _ ⁢   ⁢ OUT ≥ P W ⁢   ⁢ _ ⁢   ⁢ IN or α = P W ⁢   ⁢ _ ⁢   ⁢ OUT + N CAP · Δ ⁢   ⁢ P W ⁢   ⁢ _ ⁢   ⁢ FIELD - P W ⁢   ⁢ _ ⁢   ⁢ IN Δ ⁢   ⁢

Abstract: In noise measurement for video sequences it is difficult to distinguish between picture content and noise. In order to improve the measurement reliability the results of two different noise level computing methods are combined. One computation relies on the analysis of displaced field or frame differences, the other is based on the values of the field or frame differences over static picture areas.