Abstract: A method and apparatus for performing a predictive motion search in a video encoder system using motion vectors representing the difference in coordinates of a macroblock of data in a current frame of video data and coordinates of a related macroblock of data in a reference frame of video data. A plurality of motion vector predictors is obtained where the motion vector predictors represent approximations of possible motion vectors for a current macroblock. A search pattern is defined. Each motion vector predictor of the plurality of motion vector predictors is searched around using the search pattern. A final motion vector is then determined.

Abstract: A method and apparatus for performing a predictive motion search in a video encoder system using motion vectors representing the difference in coordinates of a macroblock of data in a current frame of video data and coordinates of a related macroblock of data in a reference frame of video data. A plurality of motion vector predictors is obtained where the motion vector predictors represent approximations of possible motion vectors for a current macroblock. A search pattern is defined. Each motion vector predictor of the plurality of motion vector predictors is searched around using the search pattern. A final motion vector is then determined.

Abstract: A method and apparatus for determining if a first video segment matches a second video segment is provided herein. Each video segment to be compared has an associated metric (HR), which is a function over time as the conditional entropy between frame fk and previous frame fk?1. A comparison of each video segment's HR vectors determines if the video segments match.

Abstract: A method and apparatus for reducing error propagation in digital video signals using random forced intra-refresh of macroblocks. One or more predetermined regions are defined for each digital video frame. Within each predetermined region, a number of macroblocks are selected according to a random permutation of the macroblocks within the region. The selected macroblocks are intra-coded, while the remaining macroblocks are coded according to a standard video compression protocol. This approach provides an efficient method for mitigating error propagation in a decoder. Interior regions may be smaller than exterior regions, providing higher quality for the interior regions, where sensitivity to errors is higher.

Abstract: The disclosed invention is a method to detect candidate errors within the picture start code, picture header, and picture timestamp. Upon detection, these errors may be confirmed and the impacts mitigated. An error within the timestamp bit field is adaptively detected by the use of a threshold comparison, and a mechanism for concealing the timestamp information leaves only a small timestamp anomaly. An error within the picture start code (PSC) is determined by adaptively analyzing the number of bits and the macro-block location of the next slice or GOB. If a PSC is suspected to have been overrun due to an error, this method allows for data beyond the first GOB or slice to be recovered in the frame. Depending on the extent of use of slices and GOBs, the method can recover a majority of the frame that otherwise would have been completely lost.

Abstract: A processor (10) utilizes information regarding one or more physical dimensions of an individual (14) to better inform a personal identification process. In one embodiment, the measured physical dimensions are utilized to influence the conduct of a face recognition process. In one embodiment, a Bayesian Belief Network can be utilized to facilitate such processes.

Abstract: A search system (200) for a database (224) including records having a multiple disparate types of media is provided. The search system supports queries, that include different types of search criteria, including content based retrieval search criteria. A fuzzy logic method (400) is provided for effectively combining the results of different types of search criteria. The fuzzy logic method also allows confidence levels entered by the user for search criteria to be considered in combining results. Retrieval relevance values for documents for at least some search criteria are used in the fuzzy logic method. For content based image retrieval searches, the retrieval relevance values are computed by mapping a distance between quantitative characterizations of a search basis image, and other images into a finite range.

Abstract: At least one visual significance metric is determined (12) for at least some frames belonging to an original series of frames (11). Key frames are identified (13) as a function, at least in part, of the visual significance metric. Cumulative visual significance values are then determined (14) for at least some of the frames that intervene between each pair of key frames. These cumulative visual significance values are then used to identify (15) frames of additional content interest. Various frames are then selected (16) for use in a visual summary. In one embodiment, all of the key frames and frames of additional content interest are selected for inclusion in the visual summary.

Abstract: A method and apparatus for determining the quality of a block match for a candidate motion vector in a video encoder system using motion vectors representing the difference in coordinates of a macroblock of data in a current frame of video data and coordinates of a related macroblock of data in a reference frame of video data. The method can include defining a search pattern, searching a region based on the search pattern for a candidate motion vector for evaluation, calculating a difference metric, calculating a bias based on the difference between a predictor motion vector and a candidate motion vector, determining a modified difference metric by adding the difference metric to the bias, and defining a final motion vector based on the modified difference metric.

Abstract: A method and apparatus for performing a predictive motion search in a video encoder system using motion vectors representing the difference in coordinates of a macroblock of data in a current frame of video data and coordinates of a related macroblock of data in a reference frame of video data. A plurality of motion vector predictors is obtained where the motion vector predictors represent approximations of possible motion vectors for a current macroblock. A search pattern is defined. Each motion vector predictor of the plurality of motion vector predictors is searched around using the search pattern. A final motion vector is then determined.

Abstract: The disclosed invention is a method to detect candidate errors within the picture start code, picture header, and picture timestamp. Upon detection, these errors may be confirmed and the impacts mitigated. An error within the timestamp bit field is adaptively detected by the use of a threshold comparison, and a mechanism for concealing the timestamp information leaves only a small timestamp anomaly. An error within the picture start code (PSC) is determined by adaptively analyzing the number of bits and the macro-block location of the next slice or GOB. If a PSC is suspected to have been overrun due to an error, this method allows for data beyond the first GOB or slice to be recovered in the frame. Depending on the extent of use of slices and GOBs, the method can recover a majority of the frame that otherwise would have been completely lost.

Abstract: A method and apparatus for reducing error propagation in digital video signals using random forced intra-refresh of macroblocks. One or more predetermined regions are defined for each digital video frame. Within each predetermined region, a number of macroblocks are selected according to a random permutation of the macroblocks within the region. The selected macroblocks are intra-coded, while the remaining macroblocks are coded according to a standard video compression protocol. This approach provides an efficient method for mitigating error propagation in a decoder. Interior regions may be smaller than exterior regions, providing higher quality for the interior regions, where sensitivity to errors is higher.

Abstract: A method and device for detecting errors in a digital video signal comprising a sequence of image frames, each image frame comprising a sequence of image slices, each image slice comprising a sequence of macroblocks and each macroblock comprising a plurality of pixels. A macroblock decoder includes an error detection unit that operates to calculate an error metric between pixel values on at least part of the boundary between a current macroblock and one or more adjoining macroblocks and to label the current macroblock as suspicious if the error metric is greater than a threshold level. The threshold level is adjusted according to a weighted average error metric from one or more previous image frames. Suspicious macroblocks and subsequent inter-coded macroblocks may be regenerated according to a concealment strategy if a syntax error is found within the current image slice.