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: A method for analysis of an intrinsic facial feature of a face presented (2) in a field of acquisition of an imager (3) comprising the following steps: the imager (3) acquires a first image of a face, and then acquires a second image of the face, based on the first image and the second image, a processing unit determines a variation of an intrinsic facial feature between the first image and the second image, without determining a value quantifying an absolute state of the intrinsic facial feature in the first image and/or in the second image; based on the variation of the intrinsic facial feature, the processing unit determines a state of the face presented (2) in the field of acquisition of an imager (3) and performs an action depending on the state of the face presented.

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: Method for collaborative observation between a local targeting device and a distant targeting device located at different geographical positions and able to acquire images. The method including: when it is implemented by the local targeting device, execution of a procedure for determining a position of an observed object, referred to as the local targeted object, including application of a method for matching points of interest, determined on a local image by the local targeting device, representing a distant image obtained from the distant targeting device. If matching is successful, the local targeting device determines the position of the local targeted object according to information representing a position of a distant targeted object supplied by the distant targeting device and a transformation law allowing to pair the distant and local points of interest obtained when said matching method is applied and controls display of an image comprising the local targeted object.

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: 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: 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: 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: Method for collaborative observation between a local targeting device and a distant targeting device located at different geographical positions and able to acquire images, respectively referred to as local images and distant images, the method comprising, when it is implemented by the local targeting device, an execution of a procedure for determining a position of an observed object, referred to as the local targeted object, comprising an application (403) of a method for matching points of interest representing a distant image obtained (400, 401) from the distant targeting device with points of interest (402) determined on a local image by the local targeting device.

Abstract: The invention relates to a method for analyzing a multispectral image (10), which includes designing a detection image from the values of a revealing function that quantifies a content shift in the multispectral image between two areas. The revealing function is applied between a target area and a background area, inside a window which is determined around each pixel. The revealing function values are determined from integral images of order one, and optionally also of order two, which in turn are calculated only once initially, so that the total amount of calculations is reduced. The analysis method is compatible with a real-time implementation during a capture of consecutive multispectral images which form a video stream, in particular for an environment-monitoring task.

Abstract: The invention relates to a method for analyzing a multispectral image (10), which includes designing a detection image from signal-to-noise ratio values. The signal-to-noise ratio values relate to the content of the multispectral image inside a window which is determined around each pixel, when the contrast in the window is maximized by a Fischer projection. The signal-to-noise ratio values at calculated from integral images of order one and two, which in turn are calculated only once initially, so that the total amount of calculations is reduced. The analysis method is compatible with a real-time implementation during a capture of consecutive multispectral images which form a video stream, in particular for an environment-monitoring task.

Abstract: The invention relates to a method for analysing a multispectral image (10), which includes designing a detection image from signal-to-noise ratio values. The signal-to-noise ratio values relate to the content of the multispectral image inside a window which is determined around each pixel, when the contrast in the window is maximised by a Fischer projection. The signal-to-noise ratio values are calculated from integral images of order one and two, which in turn are calculated only once initially, so that the total amount of calculations is reduced. The analysis method is compatible with a real-time implementation during a capture of consecutive multispectral images which form a video stream, in particular for an environment-monitoring task.

Abstract: The invention relates to a method for analysing a multispectral image (10), which includes designing a detection image from the values of a revealing function that quantifies a content shift in the multispectral image between two areas. The revealing function is applied between a target area and a background area, inside a window which is determined around each pixel. The revealing function values are determined from integral images of order one, and optionally also of order two, which in turn are calculated only once initially, so that the total amount of calculations is reduced. The analysis method is compatible with a real-time implementation during a capture of consecutive multispectral images which form a video stream, in particular for an environment-monitoring task.

Abstract: The inventive method for viewing of a multi-spectral image by an operator uses contrast optimization by Fisher projection. The Fisher projection is determined and applied within a window (F1, F2, F3, . . . ) that is smaller than a display screen matrix (1) used by the operator. The window is moved for successive updates of a depiction of the image that is displayed, while creating a remanence of the positions of the earlier windows and elements that were exposed in some of said earlier windows. The implementation of the method is particularly simple and intuitive for the operator, so as to improve the reliability and effectiveness of his or her monitoring.

Abstract: The inventive method for viewing of a multi-spectral image by an operator uses contrast optimisation by Fisher projection. The Fisher projection is determined and applied within a window (F1, F2, F3, . . . ) that is smaller than a display screen matrix (1) used by the operator. The window is moved for successive updates of a depiction of the image that is displayed, while creating a remanence of the positions of the earlier windows and elements that were exposed in some of said earlier windows. The implementation of the method is particularly simple and intuitive for the operator, so as to improve the reliability and effectiveness of his or her monitoring.