Abstract: A method of parametrizing a video surveillance system comprising a current video content analytics module, a reference video content analytics module, and a video streaming component, the reference video content analytics module having higher performance than the current video content analytics module, the current video content analytics module processing video data transmitted by the video streaming component, includes the steps of obtaining, by the current video analytics module, first video data having first characteristics and analysing the first video data so as to obtain a first performance value, obtaining, by the reference video content analytics module, second video data having second characteristics and analysing the second video data so as to obtain a second performance value, comparing the first performance value with the second performance value, and, adapting configuration parameters of the video surveillance system based on the comparison result.

Abstract: The present invention relates to determining a trajectory of a target from two streams of images obtained from two sources of images, a sub-image of each of the images of the two streams of images representing an overlapping area of a real scene. After having obtained a target path for each of a plurality of targets, from images of the sources of images, for each of the two streams of images, each target path being obtained from a target tracker associated with a source of image, each of the obtained target paths is split into a plurality of target path portions as a function of each potential target switch along the obtained target path. Then, the trajectory is generated as a function of a plurality of the target path portions.

Abstract: The present invention relates in particular to a method for re-identification of a target object in images obtained from several image sources, wherein each of the image sources obtains images representing an area associated with the corresponding image source. After having identified a target object in images obtained from one of a pair of image sources, a relative velocity of the target object in comparison with other objects previously identified in images obtained from the one of the pair of image sources is estimated. Then, based on the estimated relative velocity of the target object, a correspondence between the target object identified in images obtained from the one of the pair of image sources and a candidate object represented in images obtained from the other image source of the pair of image sources is established.

Abstract: A sound source separation method comprising the steps of determining at least one location of at least one sound source based on video data, determining initial estimates of at least two parameters characterizing an audio signal emitted by said sound source, said initial estimates being determined based on said at least one location, performing an expectation-maximization method for determining final estimates of said parameters, and separating the audio signal from a combination of audio signals based on said final estimates of said parameters.

Abstract: A direction of at least one sound source from an array of microphones is determined by obtaining a plurality of solutions sets from audio signals acquired from the microphones array, each solutions set being obtained by applying a sound source localization method to the audio signals, each solution defining a sound direction candidate. Then, solutions are grouped into groups of solutions and at least one of the groups is removed, based on a criterion of disparity between the solutions sets. The direction of the at least one sound source from directions associated with the remaining groups is obtained.

Abstract: A direction of at least one sound source from an array of microphones is determined by obtaining a plurality of solutions sets from audio signals acquired from the microphones array, each solutions set being obtained by applying a sound source localization method to the audio signals, each solution defining a sound direction candidate. Then, solutions are grouped into groups of solutions and at least one of the groups is removed, based on a criterion of disparity between the solutions sets. The direction of the at least one sound source from directions associated with the remaining groups is obtained.

Abstract: This invention concerns a loudspeaker driver includes at least one actuator connected to a vibrating support to impart excitation to the latter when caused to move, wherein the loudspeaker driver further includes a plurality of sensing members arranged to move with the at least one actuator, each sensing member providing output sensing data dependent on the velocity of said at least one actuator, and means for determining the position of the at least one actuator based on at least one ratio (X/Y) of output sensing data or of linear combinations of output sensing data provided from the plurality of sensing members, said at least one ratio being independent of the velocity of the at least one actuator.