Abstract: The present invention relates to a method for processing a plurality of candidate annotations of a given instance of an image, each candidate annotation being defined as a closed shape matching the instance, characterized in that the method comprises performing, by a processing unit (21) of a server (2), steps of: (a) segregating said candidate annotations into a set of separate groups of at least overlapping candidate annotations; (b) selecting a subset of said groups as a function of the number of candidate annotations in each group; (c) building a final annotation of the given instance of said image as a combination of regions of the candidate annotations of said selected groups where at least a second predetermined number of the candidate annotations of said selected groups overlap.

Abstract: This invention concerns a method of learning parameters of a convolutional neural network (CNN) through data processing means (11a, 11b, 11c) of at least one server (1a, 1b, 1c), for detecting items of interest visible in images, from at least one image learning database in which said items of interest, as well as characteristic geometric structures are already annotated, the CNN comprising an encoding layer for generating a representation vector of the detected items of interest, the method being characterized in that said representation vector comprises, for at least a first item of interest category to be detected, at least one descriptive value of at least a characteristic geometric structure of said first item of interest category. The present invention also relates to a process for detecting items of interest visible in an image and a method for associating items of interest visible in an image.

Abstract: A parameter training method for a convolutional neural network, CNN, for detecting items of interest visible in images by a data processor of at least one server. The method is implemented based on a plurality of training image databases. The items of interest are already annotated, the CNN being a CNN common to the plurality of training image databases and having a common core and a plurality of encoding layers, each one specific to one of the plurality of training image databases. The method is also for detecting items of interest visible in an image.

Abstract: The present invention relates to a method for association of items of interest visible in a video consisting of a sequence of K images, characterized in that it comprises the implementation by data processing means of a terminal of steps of: association of each item of interest from a first category visible in a kth image of said video with an item of interest from a second category, different from the first category, visible in said kth image; calculation of an association cost for a plurality of pairs of an item of interest from the first category visible in at least one image of the video with an item of interest from the second category visible in at least one image of the video, depending on at least the counters of association of pairs of one item of interest from the first category with one item of interest from the second category; use of a combinatorial optimization algorithm depending on the calculated association costs so as to reassociate each item of interest from the first category visible in sa

Abstract: The present invention relates to a method for processing a plurality of candidate annotations of a given instance of an image, each candidate annotation being defined as a closed shape matching the instance, characterized in that the method comprises performing, by a processing unit (21) of a server (2), steps of: (a) segregating said candidate annotations into a set of separate groups of at least overlapping candidate annotations; (b) selecting a subset of said groups as a function of the number of candidate annotations in each group; (c) building a final annotation of the given instance of said image as a combination of regions of the candidate annotations of said selected groups where at least a second predetermined number of the candidate annotations of said selected groups overlap.

Abstract: A method for processing a stream of video images to search for information therein, in particular detect predefined objects and/or a motion, comprising the steps of: a) supplying at least one attention map in at least one space of the positions and of the scales of at least one image of the video stream, b) selecting, in this space, points to be analyzed by making the selection depend at least on the values of the coefficients of the attention map at these points, at least some of the points to be analyzed being selected by random draw with a probability of selection in the draw at a point depending on the value of the attention map at that point, a bias being introduced into the map to give a non-zero probability of selection at any point, c) analyzing the selected points to search therein for said information, d) updating the attention map at least for the processing of the subsequent image, from at least the result of the analysis performed in c), e) reiterating the steps a) to d) for each new image of

Abstract: The present invention relates to a parameter training method for a convolutional neural network, CNN, for detecting items of interest visible in images by data processing means (11a, 11b, 11c) of at least one server (1a, 1b, 1c), the method being characterized in that it is implemented based on a plurality of training image databases, wherein said items of interest are already annotated, the CNN being a CNN common to said plurality of training image databases and having a common core and a plurality of encoding layers, each one specific to one of said plurality of training image databases. The present invention also relates to a method for detecting items of interest visible in an image.

Abstract: The present invention relates to a method for association of items of interest visible in a video consisting of a sequence of K images, characterized in that it comprises the implementation by data processing means (21) of a terminal (2), of steps of: (a) Association of each item of interest from a first category visible in a kth image of said video with an item of interest from a second category, different from the first category, visible in said kth image; (b) Calculation of an association cost for a plurality of pairs of an item of interest from the first category visible in at least one image of the video with an item of interest from the second category visible in at least one image of the video, depending on at least the counters of association of pairs of one item of interest from the first category with one item of interest from the second category; (c) Use of a combinatorial optimization algorithm depending on the calculated association costs so as to reassociate each item of interest from the firs

Abstract: This invention concerns a method of learning parameters of a convolutional neural network (CNN) through data processing means (11a, 11b, 11c) of at least one server (1a, 1b, 1c), for detecting items of interest visible in images, from at least one image learning database in which said items of interest, as well as characteristic geometric structures are already annotated, the CNN comprising an encoding layer for generating a representation vector of the detected items of interest, the method being characterized in that said representation vector comprises, for at least a first item of interest category to be detected, at least one descriptive value of at least a characteristic geometric structure of said first item of interest category. The present invention also relates to a process for detecting items of interest visible in an image and a method for associating items of interest visible in an image.

Abstract: A method for processing a stream of video images to search for information therein, in particular detect predefined objects and/or a motion, comprising the steps of: a) supplying at least one attention map in at least one space of the positions and of the scales of at least one image of the video stream, b) selecting, in this space, points to be analyzed by making the selection depend at least on the values of the coefficients of the attention map at these points, at least some of the points to be analyzed being selected by random draw with a probability of selection in the draw at a point depending on the value of the attention map at that point, a bias being introduced into the map to give a non-zero probability of selection at any point, c) analyzing the selected points to search therein for said information, d) updating the attention map at least for the processing of the subsequent image, from at least the result of the analysis performed in c), e) reiterating the steps a) to d) for each new image of