Abstract: Images having a moving pattern against a fixed or quasi-fixed background are segmented by determining a silhouette of the moving pattern, and forming a segmentation image filling the silhouette. On a pixel-by-pixel basis, differences are determined between the current image and previous images of a sequence, and compared with a threshold to form a binary image of background and useful zone. The boundaries of the useful zone are regularized, and irregularities in the useful zone and in the background are suppressed. A segmentation image is then formed within the silhouette.

Abstract: A coding subassembly for images composed of at least one moving pattern against a fixed or quasi-fixed background, including circuits for constructing a base model representative of the useful zone of the said images, a coding circuit, and an associated decoding subassembly. The model constructing circuits include circuits for initial calibration and adaptation of the model and a circuit for determining the movement of characteristic points taken from the useful zone and a circuit for selecting at least one zone of particular interest inside the useful zone and determining its movement. The coding circuit includes a circuit for coding output signals from the initial calibration circuit, and a circuit for correcting any shifts in luminance or chrominance in zones alongside the borders of the said zone(s) of interest observed on either side of these borders.