Abstract: Summarization of video content including football.

Abstract: A upscaling (upsampling) technique for digital images and video for presentation on a display.

Abstract: A mosaic image construction system includes at least one of a decoder receiving or an encoder transmitting a sequence of pixel data frames. The sequence includes at least a first pixel data frame and a second pixel data frame. The second pixel data frame is preferably temporally later than the first pixel data frame. The second pixel data frame has an associated parameter indicating the motion of the second frame with respect to the first frame and is used in the construction of the sequence of the pixel data frames. The mosaic image is constructed using at least the first and second pixel data frames together with the associated parameter.

Abstract: Summarization of video content including football.

Abstract: A transmission systems suitable for video.

Abstract: A video image processing system includes an image sensor for sensing an image and generating an image signal therefor; and a histogram computation mechanism for generating, on-line, a histogram from said image signal. A method of analyzing a video image includes sensing an image; generating an image signal therefor; and computing, on-line, a histogram for the image from the image signal.

Abstract: A system for viewing audio-video content together with temporal information.

Abstract: Summarization of video content including football.

Abstract: A mosaic image construction system includes at least one of a decoder receiving or an encoder transmitting a sequence of pixel data frames. The sequence includes at least a first pixel data frame and a second pixel data frame. The second pixel data frame is preferably temporally later than the first pixel data frame. The second pixel data frame has an associated parameter indicating the motion of the second frame with respect to the first frame and is used in the construction of the sequence of the pixel data frames. The mosaic image is constructed using at least the first and second pixel data frames together with the associated parameter.

Abstract: A method of estimating a motion field includes estimating a first motion vector component from a source average vector and a target average vector; displacing the search area according to the first motion vector component; and estimating a second motion vector component from the displaced search area.

Abstract: Providing at least one description scheme. For audio and/or video programs a program description scheme provides information regarding the associated program. For the user a user description scheme provides information regarding the user's preferences. For the system a system description scheme provides information regarding the system. The description schemes are independent of one another. Preferably, the program description scheme, user description scheme, and system description scheme are independent of one another.

Abstract: Providing at least one description scheme. For audio and/or video programs a program description scheme provides information regarding the associated program. For the user a user description scheme provides information regarding the user's preferences. For the system a system description scheme provides information regarding the system. The description schemes are independent of one another. Preferably, the program description scheme, user description scheme, and system description scheme are independent of one another.

Abstract: A hierarchical system for object-based audiovisual descriptive tagging of images for information retrieval, editing, and manipulation, includes: an object-based selection mechanism for selecting an object of interest in said image; hierarchical data structure generation means for generating a hierarchical data structure for said image and for associating auxiliary information with said image; and a transmission/storage mechanism for storing the image and the hierarchical data structure. A hierarchical method for object-based audiovisual descriptive tagging of images for information retrieval, editing, and manipulation, includes: selecting an object of interest in said image with an object-based selection mechanism; generating a hierarchical data structure for said image and for associating auxiliary information with said image; and transmitting/storing the image and the hierarchical data structure.

Abstract: A method for content-scalable shape representation is described. In content-scalable shape representation, the more important parts of the image are encoded using a larger number of bits within a single hierarchical layer, or within one or more layers of multiple hierarchical layers. This representation may be used with the framework of a hierarchical vertex-based shape representation technique. The method described herein provides for the representation of shapes either by selected verticles along a contour, or by binary bit maps. The resulting representation facilitates content-scalable coding.

Abstract: A method for coding multiple layer, vertex-based shape representation and bit stream scalable shape includes selecting vertices in a hierarchical scheme; defining multiple layers of vertices; arranging M layers of vertices in order, from the most salient layer to the least salient layer; placing vertices in their natural order along their image contour within each layer; storing vertices from each layer separately; and recording vertex order information for each vertex in each layer of vertices. Four variations of the method for multiple layer vertex representation and coding are disclosed where the correct order information is coded for correct reconstruction of the shape information.

Abstract: A method of vertex-based hierarchical shape representation and coding includes selecting an image of interest, defining a boundary about an object of interest within the image of interest, wherein the boundary is defined by a set of contour points, selecting a number of layers, each layer having a predefined saliency parameter associated therewith, wherein the saliency parameter defines a range of layers from a most salient layer to a least salient layer, identifying the most salient contour points in the boundary and placing the most salient contour points in the most salient layer, identifying the next most salient contour points in the boundary and placing the next most salient contour points in the next most salient layer until all of the selected layers have contour points placed therein, and hierarchically storing the layers in a database.

Abstract: A robust system, adaptive to motion estimation accuracy, for creating a high resolution image from a sequence of lower resolution motion images produces a mapping transformation for each low resolution image to map pixels in each low resolution image into locations in the high resolution image. A combined point spread function (PSF) is computed for each pixel in each lower resolution image employing the mapping transformations provided that they describe accurate motion vectors. The high resolution image is generated from the lower resolution images employing the combined PSF's by projection onto convex sets (POCS), where sets and associated projections are defined only for those pixels whose motion vector estimates are accurate.

Abstract: A process and apparatus for generating a deinterlaced digital output image from a plurality of sequential interlaced image fields processes selected ones (a pair of immediately successive fields of the same polarity) of the plurality of sequential interlaced image fields, so as to produce a global motion vector estimate of global translational motion between the selected image fields. An accuracy map representative of accuracy of motion compensation is then generated in accordance with the global motion vector estimate. An adaptive deinterlacer selectively deinterlaces one of the image fields in accordance with the accuracy map. The selectively deinterlaced image field is subjected to postprocessing in order to remove judder artifacts that may be present in the deinterlaced image field as a result of a misclassification of the global motion vector estimate as being accurate in one or more image regions of the deinterlaced image field.

Abstract: The present invention is a two-step, contour-sensitive deinterlacing technique. The first step of the technique determines for each missing pixel of an interlaced frame of image pixels whether the absolute difference between the pixels above and below the missing pixel is greater than a preselected threshold value. If it is decided that the missing pixel lies at a low-vertical frequency location, its value is estimated via vertical interpolation. Otherwise, the second step is carried out. The goal of the second step is to determine whether or not there is a well-defined contour passing through the missing pixel, and to determine its direction if there is one. In the presence of a well-defined contour, the missing pixel is obtained by averaging the intensity values along the direction of the contour in the field lines immediately above and below the missing field line. Otherwise the process effectively falls back to vertical interpolation.

Abstract: A system and method for creating a high quality still image from a series of interlaced video fields of the type employing local motion detection between first and third fields of the series, merging the first and second fields in areas of no motion and performing spatial interpolation on the first field in areas containing local motion, including removing dominant motion from the second and third fields prior to local motion detection.