Abstract: The method produces three dimensional cartographic data of a scene from n two-dimensional images of the scene, n being an integer higher than 2. The images are delivered by n respective detectors seeing the scene from different points of view. In a first step, each detector i is calibrated for estimating parameters identifying n affine models Fi (x, y, z) each defining a relation between coordinates x, y, z of any point in the scene and coordinates (p, q)i of a projection of said any point in an image i among said n images. Each of (n−1) couples of images, (each couple consisting of a same reference image selected among said n images) is matched, each match being made by searching an homolog of each of pixels or zones constituting the reference image along a corresponding epipolar line of the other image of the couple.

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.

Abstract: Classification method implemented in a layered neural network, comprising learning steps during which at least one layer is constructed by the addition of the successive neurons necessary for operating, by successive dichotomies, a classification of examples distributed over classes. In order to create at least one layer starting with a group of examples distributed over more than two classes, each successive neuron tends to distinguish its input data according to two predetermined sub-groups of classes peculiar to the said neuron according to a principal components analysis of the distribution of the said input data subjected to the learning of the neuron of the layer in question.

Abstract: Classification procedure implemented in a tree-like neural network which, in the course of learning steps, determines with the aid of a tree-like structure the number of neurons and their synaptic coefficients required for the processing of problems of classification of multi-class examples. Each neuron tends to distinguish, from the examples, two groups of examples approximating as well as possible to a division into two predetermined groups of classes. This division can be obtained through a principal component analysis of the distribution of examples. The neural network comprises a directory of addresses of successor neurons which is loaded in learning mode then read in exploitation mode. A memory stores example classes associated with the ends of the branches of the tree.

Abstract: A neural network system comprises a memory for storing in binary code the synaptic coefficients indicative of the interconnections among the neurons. Means are provided for simultaneously supplying all the synaptic coefficients associated with a given neuron. Digital multipliers are provided for determining the product of the supplied synaptic coefficients and the relevant neuron states of the neurons connected to said given neuron. The multipliers deliver their results into an adder tree for determining the sum of the products. As a result of the parallel architecture of the system high operating speeds are attainable. The modular architecture enables extension of the system.