Abstract: Automatic tracking by a camera of an object such as on-air talent appearing in a television show commences by first determining whether the object lies within the camera field of view matches a reference object. If so, tracking of the object then occurs to maintain the object in fixed relationship to a pre-set location in the camera's field of view, provided the designated object has moved more than a threshold distance from the pre-set location.

Abstract: Automatic tracking by a camera of an object such as on-air talent appearing in a television show commences by first determining whether the object lies within the camera field of view matches a reference object. If so, tracking of the object then occurs to maintain the object in fixed relationship to a pre-set location in the camera's field of view, provided the designated object has moved more than a threshold distance from the pre-set location.

Abstract: A method and an apparatus for determining an orientation of a video are suggested. The method comprises the steps of: estimating a motion of the video; extracting translation-based parameters from the estimated motion of the video; and computing at least one feature giving the evolution of the horizontal translation over time against the evolution of the vertical translation according to the translation based parameters, the feature being used for determining the orientation of the video.

Abstract: A method for controlling tracking using a color model is disclosed. The method includes obtaining a window in a second frame of a video image corresponding to a window in a first frame of the video image using a tracking algorithm in a tracking mode, wherein each pixel in the video image has at least one color component. The method further includes defining a background area around the window in the first frame, assigning a pixel confidence value for each pixel in the second frame according to a color model, assigning a window confidence value for the window in the second frame according to the pixel confidence values of pixels in the window in the second frame, if the window confidence value is greater than a first confidence threshold, selecting the tracking mode, and if the window confidence value is not greater than the first confidence threshold, selecting a mode different from the tracking mode.

Abstract: A method and a system of audio retrieval and source separation are described. The method comprises the steps of: receiving a textual query; retrieving a preliminary audio sample from an auxiliary audio database; retrieving a target audio sample from a target audio database; and separating the retrieved target audio sample into a plurality of audio source signals. The corresponding system comprises an input unit, a storing unit and a processing unit to implement the method.

Abstract: A method, performed by a touch screen device, for delineating an object in an image is disclosed. The method comprises obtaining, from a user input, a band around the object wherein at least one characteristic of the band depends on the presence of artifacts in the neighborhood of the object to delineate. A device for implementing the method and a computer program product are further disclosed.

Abstract: A device performs a method for tracking an object in a video sequence with a bounding box for display on the device by selecting at least one point that belongs to the object, then motion processing an area of points around the selected at least one point to determine an estimated bounding box; and then color processing the points in the estimated bounding box to determine the bounding box for display on the device. The colour processing comprises computing averages of scores from pixel differences to the background model minus pixel differences from the foreground model per line as long as such average is above a threshold.

Abstract: Objects in an image sequence are tracked within a bounding box such that the object is assured to some extent of being contained within the bounding box. The location of the object within the bounding box is less important than knowing with some certainty that the object is within the bounding box, unlike previous methods that attempt to center an object within a bounding box. The approach, which uses histograms of image features such as color indices, is suited to applications such as zooming and is robust to occlusions, out-of-plane rotations, illumination changes and long-term tracking drift.

Abstract: The invention relates to a method for browsing a collection of P video frames through a user interface comprising N cells disposed along a time line with N<P. The method comprises the steps of: —determining (S1) a subset of N key frames by uniformly subsampling the collection of P video frames, —displaying (S2) the N key frames in the N cells according to a chronological order, the N cells being classified as current cell, past cells and future cells, —receiving (S3) an input command requesting to transfer a selected key frame displayed in a cell Ci to a cell Cj of the UI, —in response to the input command, updating (S4) the key frame displayed in the cell Cj by the selected key frame and updating accordingly the key frames displayed in the other cells by updating key frames while maintaining the chronological order of the key frames in the N cells and adjusting the subsampling interval by pieces.

Abstract: The application concerns a method for transmitting video data in a data stream and associated metadata, said metadata representing associated video data structure. The method comprises the steps of—determining the structure of the video data, —splitting said structure into chunks in an incremental manner, —transmitting said chunks in the data stream at time intervals before the video data it is related to. The application concerns also a method for transmitting fingerprint information associated with video data into a video data stream. The method comprises the steps of: —determining fingerprint associated with at least one frame of said video data, —inserting at least a message into the video stream comprising said fingerprint information.

Abstract: Automatic tracking by a camera of an object such as on-air talent appearing in a television show commences by first determining whether the object lies within the camera field of view matches a reference object. If so, tracking of the object then occurs to maintain the object in fixed relationship to a pre-set location in the camera's field of view, provided the designated object has moved more than a threshold distance from the pre-set location.

Abstract: Automatic tracking by a camera (16) of an object (12) such as on-air talent appearing in a television show commences by first determining whether the object lies within the camera field of view matches a reference object. If so, tracking of the object then occurs to maintain the object in fixed relationship to a pre-set location in the camera's field of view, provided the designated object has moved more than a threshold distance from the pre-set location.

Abstract: Methods and an apparatus for locally sharpening a video using a spatial indication of blurring in a video signal are described. A method includes obtaining the spatial indication of blurring associated with the video signal, wherein the spatial indication of blurring is provided to locally adjust the sharpness of a video image of the video signal, the strength of sharpening being locally decreased for blurred area. Another method includes obtaining a video signal, obtaining a spatial indication of blurring, adjusting the sharpness of the video signal using the indication of the blurring, and providing the adjusted video signal for display on a display device.

Abstract: A method for estimating the position, on a sensor of a light-field acquisition device of a projection of a chief ray, corresponding to an optical axis of the light-field acquisition device is described. The method includes determining a coarse estimate of the position of the chief ray projection through shape-matching of the micro-images formed on the sensor by cross-correlation computation and optionally refining the coarse estimate by illumination fall-off analysis of the raw image formed on the sensor.

Abstract: A method for selecting sequences in a signal including a plurality of audio and/or video frames is described. According to an embodiment, the selecting takes into account a value of a quantified indicator assigned to one of said frame and a time slot of said sequences. An electronic device, computer readable program product and computer readable storage medium are also described.

Abstract: Objects in an image sequence are tracked within a bounding box such that the object is assured to some extent of being contained within the bounding box. The location of the object within the bounding box is less important than knowing with some certainty that the object is within the bounding box, unlike previous methods that attempt to center an object within a bounding box. The approach, which uses histograms of image features such as color indices, is suited to applications such as zooming and is robust to occlusions, out-of-plane rotations, illumination changes and long-term tracking drift.

Abstract: A method for controlling tracking using a color model is disclosed. The method includes obtaining a window in a second frame of a video image corresponding to a window in a first frame of the video image using a tracking algorithm in a tracking mode, wherein each pixel in the video image has at least one color component. The method further includes defining a background area around the window in the first frame, assigning a pixel confidence value for each pixel in the second frame according to a color model, assigning a window confidence value for the window in the second frame according to the pixel confidence values of pixels in the window in the second frame, if the window confidence value is greater than a first confidence threshold, selecting the tracking mode, and if the window confidence value is not greater than the first confidence threshold, selecting a mode different from the tracking mode.

Abstract: A method and an apparatus for determining an orientation of a video are suggested. The method comprises the steps of: estimating a motion of the video; extracting translation-based parameters from the estimated motion of the video; and computing at least one feature giving the evolution of the horizontal translation over time against the evolution of the vertical translation according to the translation based parameters, the feature being used for determining the orientation of the video.

Abstract: The invention relates to a method and a device for synchronising metadata associated by a first signature to a first version of an audiovisual document, with a second version of this audiovisual document. The method is characterised in that it synchronises the metadata with the second version of the audiovisual document from a second signature detected in the portion of the second version of the audiovisual document, said portion of the second version of the audiovisual document being obtained by detecting the first signature in the second version of the audiovisual document. In this way, the precision of the synchronisation between the two items of video content carried out by the first signature is improved by the second signature, and new, more accurate metadata is created.

Abstract: Methods and apparatuses for automatic animation are suggested. An example method can include: detecting one or more regions of interest (ROIs) in an image at least partially based on saliency values of the one or more ROIs; determining a sequence of presenting the one or more ROIs; and generating an animation based on the ROIs and the sequence, wherein an animation path, along which a display area is moved between adjacent ROIs in the sequence, is determined to maximize the sum of the saliency values of the one or more ROIs along the path.