Abstract: A method for analyzing recurrent streams of digital data to detect anomalies. The digital data streams are acquired by an explorer having a sensor and processed by a digital data processing center. A knowledge base and a statistical model representing a set of the digital data having same context of obtainment are generated from the stream of digital data acquired by the sensor. Another stream of digital data is acquired by the sensor and the digital data processing center detects anomalies by comparing the statistical model to the statistical data of the other stream of digital data.

Abstract: A system for locating at least one object in a real space by image processing, comprises a computation center (center), with a database of a virtual environment, a virtual representation of the real space, and computing the position of a point from which the virtual environment appears on a real space image obtained by an image acquisition device borne by the object. The center is sited remotely from the object. A data transmission device transfers the image data from the object to the center and the location data from the center to the object. The center processes the image data to determine a position from which the image was acquired, and stores, in a complementary database, data of the processed image to complement and/or to correct an initial database. The locating system implements a locating method for locating and transmitting the location data to a plurality of real environment objects.

Abstract: A method for projecting information issued from a digital design model. Calibration is performed by acquiring characteristic data originating from a surface of interest and comparing the characteristic data with virtual data issued from the digital design model. A spatial position of a projecting device is determined. The projecting device comprises a video projector and at least two separate image-capturing devices. Depending on the spatial position, information issued from the digital design model is projected by the video projector onto the surface of interest.

Abstract: A method for processing local information acquired by a virtual representation and a device having an inertial unit and an image sensor. At least one image of a real environment of the device is captured. The localization of the device in the virtual representation, corresponding to the localization of the device in the real environment, is obtained by correlating the portions of the captured image and portions of the virtual representation, The inertial unit determines the displacement of the device. The localization of the device in the virtual representation is modified as a function of the displacement so that the real position of the device corresponds, during the displacement, to the localization of the device in the virtual representation.

Abstract: A method of searching for a scene based on a stream of images archived in a video surveillance database including: a first phase of preprocessing prior to archiving of the images including extracting generic information from the images of the stream, systematically annotating the scenes of the images by at least one indication defined as a function of the generic information, and indexing the scenes of the images based on information extracted from the indications originating from one or more streams; a second phase of investigation by preselecting video segments from the stream of images including the annotation indications associated with the images; and a third phase of searching for a particular scene based on at least one additional characteristic not forming part of the annotations associated with the preselected video segments.

Abstract: A method for generating a digital mockup in three dimensions using computer-aided design (CAD) software. The digital mockup is integrated into a spatialization environment for the digital mockup allowing visualization of the digital mockup from various angles of view. The digital mockup is produced to obtain a semi-finished product. A plurality of pieces of production information is acquired. For each piece of production information, a spatial position linked to the production information is measured, and the production information is integrated into the spatialization environment on the digital mockup at a position in the digital mockup corresponding to the measured spatial position.

Abstract: A method for projecting information issued from a digital design model. Calibration is performed by acquiring characteristic data originating from a surface of interest and comparing the characteristic data with virtual data issued from the digital design model. A spatial position of a projecting device is determined. The projecting device comprises a video projector and at least two separate image-capturing devices. Depending on the spatial position, information issued from the digital design model is projected by the video projector onto the surface of interest.

Abstract: A method for processing local information acquired by a virtual representation and a device having an inertial unit and an image sensor. At least one image of a real environment of the device is captured. The localization of the device in the virtual representation, corresponding to the localization of the device in the real environment, is obtained by correlating the portions of the captured image and portions of the virtual representation, The inertial unit determines the displacement of the device. The localization of the device in the virtual representation is modified as a function of the displacement so that the real position of the device corresponds, during the displacement, to the localization of the device in the virtual representation.

Abstract: A method for analyzing geographical regions and detecting areas of interest by a exploration system comprising a sensor and a digital data processing center. The method includes a first phase of learning the intrinsic appearance of each geographical region, in which a database of knowledge comprising groups of digital data is generated. The method further includes a second phase of detecting areas of interest in the geographical regions. The phases includes acquiring a piece of digital data corresponding to a geographical region by the sensor, transmitting the acquired digital data to the digital data processing center, and processing the digital data by the digital data processing center.

Abstract: The invention relates to a method for virtually expanding and enriching the field of view of the current image of a scene described by a video including several images. This method includes the following steps of: a—expanding said field of view by at least one mosaic obtained from said images and by inserting at least one contextual datum in the reference frame of the current image of said scene, b—enriching said field of view by at least one piece of information referenced in said contextual datum.

Abstract: The invention relates to a method for virtually expanding and enriching the field of view of the current image of a scene described by a video including several images. This method includes the following steps of: a—expanding said field of view by at least one mosaic obtained from said images and by inserting at least one contextual datum in the reference frame of the current image of said scene, b—enriching said field of view by at least one piece of information referenced in said contextual datum.

Abstract: A method of searching for a scene based on a stream of images archived in a video surveillance database including: a first phase of preprocessing prior to archiving of the images including extracting generic information from the images of the stream, systematically annotating the scenes of the images by at least one indication defined as a function of the generic information, and indexing the scenes of the images based on information extracted from the indications originating from one or more streams; a second phase of investigation by preselecting video segments from the stream of images including the annotation indications associated with the images; and a third phase of searching for a particular scene based on at least one additional characteristic not forming part of the annotations associated with the preselected video segments.