Abstract: A method and apparatus for variable accuracy inter-picture timing specification for digital video encoding is disclosed. Specifically, the present invention discloses a system that allows the relative timing of nearby video pictures to be encoded in a very efficient manner. In one embodiment, the display time difference between a current video picture and a nearby video picture is determined. The display time difference is then encoded into a digital representation of the video picture. In a preferred embodiment, the nearby video picture is the most recently transmitted stored picture. For coding efficiency, the display time difference may be encoded using a variable length coding system or arithmetic coding. In an alternate embodiment, the display time difference is encoded as a power of two to reduce the number of bits transmitted.

Abstract: A method of noise filtering of a digital video sequence is provided that includes computing a motion image for a frame, wherein the motion image includes a motion value for each pixel in the frame, and wherein the motion values are computed as differences between pixel values in a luminance component of the frame and corresponding pixel values in a luminance component of a reference frame, applying a first spatial noise filter to the motion image to obtain a final motion image, computing a blending factor image for the frame, wherein the blending factor image includes a blending factor for each pixel in the frame, and wherein the blending factors are computed based on corresponding motion values in the final motion image, generating a filtered frame, wherein the blending factors are applied to corresponding pixel values in the reference frame and the frame, and outputting the filtered frame.

Abstract: The present invention relate to an image generating apparatus for generating an image from a viewpoint specified by a user. According to the invention, the apparatus has a storage unit that stores data of a plurality of images, and a disparity map generating unit that generates a disparity map. The disparity map is associated with a pair of images including a first image and a second image, and indicates corresponding pixels in the first and second images.

Abstract: A frame rate conversion may be done using a target image between a current and a previous image. A first motion field is estimated between the target image and the current image. A second motion field is estimated between the target image and the previous image. The motion fields are then used for motion compensation in the frame rate conversion.

Abstract: Scalable Video Coding is recently attracting attentions due to its high flexibility. The current H.264/AVC scalable extension has adopted the Motion Compensated Temporal Filter (MCTF) framework to provide temporal scalability. In this paper, described is another fast motion estimation (ME) algorithm based on the MCTF framework. Simulation results show that the herein described algorithm can reduce the encoding complexity significantly while maintaining similar bit rate and PSNR, comparing with existing fast ME algorithms implemented in the reference software.

Abstract: A machine-implementable method for uniquely watermarking a content object according to end user identity includes transcoding an original content object to a format that is compatible with end user systems, and storing the transcoded content object where it is accessible by one or more points of presence (POPs) of a content delivery network. One of the POPs receives identifying information associated with a specific one of the end user systems. A digital watermark engine adds uncorrected digital watermark information correlating to the end user system, to the content object, to form a uniquely watermarked content object. The uncorrected digital watermark information is correctable by error correction capability of the specific end user system to deliver a version of the content object that is indistinguishable by a human from the original content object. The method further includes transmitting the uniquely watermarked content object to the specific end user system.

Abstract: An image decoding method is an image decoding method of decoding coded image data, including selecting, based on a type of a decoding target signal, an arithmetic decoding method that is used to decode the decoding target signal, from among a plurality of arithmetic decoding methods that include: a first arithmetic decoding method which is performed based on a symbol occurrence probability obtained according to a context, and which involves update of the symbol occurrence probability according to a decoding symbol; and a second arithmetic decoding method which is performed based on a symbol occurrence probability obtained according to a context, and which maintains the symbol occurrence probability that is other than 50%.

Abstract: A method for encoding pictures within a groups of pictures using prediction, where a first reference picture from a group of pictures and a second reference pictures from the subsequent group of pictures are used in predicting pictures in the group of pictures associated with the first reference picture. A plurality of anchor pictures in the group of pictures associated with the first reference picture may be predicted using both the first and second reference pictures to ensure a smooth transition between different groups of pictures within a video frame.

Abstract: A system and method for encoding dynamic image information for an image generated by a computer application executing on a processor. Various aspects of the present invention may comprise determining a first set of information describing a reference image. A second set of information may be determined for describing an image, wherein the second set of information comprises information indicative of movement between the image and the reference image. For example, a set of primary movement directions may be determined based at least in part on the computer application generating the image. Such set of primary movement directions may be utilized for analyzing the image relative to the reference images. The difference between the image and the reference image may, for example, be analyzed using at least one of the set of primary movement directions. A movement direction may, for example, be utilized to describe the image.

Abstract: Disclosed herein is an image processing apparatus, including: a representative-point storing section; an evaluation-value table generation section; a peak detection section; and a correlation determination section, wherein an operation carried out by the evaluation-value table generation section to generate the evaluation-value table on the basis of representative points stored in the representative-point storing section, an operation carried out by the peak detection section to detect the candidate vector, an operation carried out by the correlation determination section to determine the correlation between the representative point and the referenced point as well as an operation carried out by the correlation determination section to update the representative-point storing section in accordance with a result of the operation to determine a correlation between the representative point and the referenced point are repeated as long as existence of a significant candidate vector is determined.

Abstract: There is provided an image processing method includes: separating an image taken at a predetermined frame rate into a first frame and at least one second frame other than the first frame at intervals of 1/n, where n is an integer of 2 or larger; calculating a low-frequency-component difference between the separated at least one second frame and first frame; performing signal processing designated by a user on the first frame; decompressing, using a low-frequency component in the first frame being subjected to the signal processing and the low-frequency-component difference, a low-frequency component in the at least one second frame being approximately subjected to the signal processing; and decompressing, using the decompressed low-frequency component in the at least one second frame and a high-frequency component therein, the at least one second frame being approximately subjected to the signal processing.

Abstract: An apparatus and method for encoding and decoding a multi-view image including a stereoscopic image are provided. The apparatus for encoding a multi-view image includes a base layer encoding unit that encodes a base layer image to generate a base layer bit stream, a view-based conversion unit that performs view-based conversion of the base layer image to generate a view-converted base layer image, a subtractor obtaining a residual between a enhancement layer image and the view-converted base layer image, and an enhancement layer encoding unit that encodes the obtained residual to generate an enhancement layer bit stream.

Abstract: A method for transcoding from an H.264 format to an MPEG-2 format is disclosed. The method generally comprises the steps of (A) decoding an input video stream in the H.264 format to generate a picture having a plurality of macroblock pairs that used an H.264 macroblock adaptive field/frame coding; (B) determining a mode indicator for each of the macroblock pairs; and (C) coding the macroblock pairs into an output video stream in the MPEG-2 format using one of (i) an MPEG-2 field mode coding and (ii) an MPEG-2 frame mode coding as determined from the mode indicators.

Abstract: A method of improving accuracy and reliability of motion estimation is described herein. In one aspect, a 2D neighborhood of phase correlation peak is approximated with an outer-product of two 1D vectors to eliminate the sub-pixel error. In another aspect, estimation of reliability is improved. In yet another aspect, two-pass phase correlation is implemented to eliminate sub-pel motion bias.

Abstract: A data structure for use by a computer system for processing medical image data and representing at least one first region of a patient includes at least one computer-detected feature of interest. The data structure includes a first computer code that is executable to detect first data representing at least one second region included within a respective first region. At least one said feature of interest in said second region has a significant likelihood of representing a computer-detected false positive. The second computer code is executable to provide second data for enabling at least one said first region to be displayed on a display device, such that at least one said second region is displayed on the display apparatus differently from part of said first region not containing features of interest having a significant likelihood of representing computer-detected false positives.

Abstract: Spatial domain directional intra prediction has been shown to be very effective to remove the correlation between the pixels in the current block and reconstructed neighbors. In AVC, 8 directional prediction modes (plus the DC prediction mode) are defined. The prediction mode number is signaled to the decoder using a simple predictive coding method. The previous intra prediction methods have two major disadvantages: lack of precision for arbitrary directional patterns and accuracy lack of accuracy to exploit geometric dependency between blocks. To address these issues, a new method accurately predicts the intra directions from reconstructed neighboring pixels and differentially encode the intra directions. This allows a more precise directional prediction without the significant increase in the cost for transmitting the side information.

Abstract: This invention is directed to a method for decoding coded video data in which decoder performance is regulated based on perceptual masking. The method includes, upon receipt of coded video data, applying the coded video data to a multi-stage decoding process; computing perceptual masking measures for the coded video data; and switching a stage of the decoding process to a lower performance level based on the computed perceptual masking measures. The method may be applied to non-reference frames and reference frames with low numbers of dependent frames. The method provides scalability among decoders to allow for various decoder and/or coded data complexity.

Abstract: A method for processing graphical data representing a sequence of images prior to compression, including analyzing a plurality of adjacent areas of an image from the sequence to determine: (i) a first set of areas, each of which includes changes when compared with a corresponding area in a previous image from the sequence; and (ii) a second set of areas, each of which does not include a change when compared with a corresponding area in the previous image. For each area of the second set, a section of the area is replaced with a block chosen to reduce the size of the graphical data once compressed, while leaving the original image of the area of the second set adjacent any part of the perimeter that adjoins an area of the first set. A dataset is provided to allow identification of the areas of the second set. On decompression of the compressed graphical data, the dataset is accessed and the image is processed by replacing each area of the second set with the corresponding area from a previous image.

Abstract: Disclosed herein is a method for decoding a video signal having at least one frame with a plurality of blocks including a current block, including generating, for at least a selected pixel in the current block, a predicted value for at least one pixel located in a row i and a column j of the current block using a processor and according to the following equation: Xij=Li+Aj?C; wherein Xij is the predicted value, Li is the value of a pixel to the left of the current block, Aj is the value of a pixel in a row above the current block and C is the value of a pixel in the row above and the column to the left of the current block and decoding the current block using the predicted value.

Abstract: Disclosed is an apparatus for decoding motion information in merge mode for reconstructing a moving picture signal coded at a low data rate while maintaining a high quality of an image. The apparatus for decoding motion information in merge mode discloses the position of a merge mode candidate and the configuration of a candidate in order to predict motion information in merge mode efficiently. Furthermore, a merge candidate indicated by the merge index of a current block can be efficiently reconstructed irrespective of a network environment by adaptively generating a merge candidate based on the number of valid merge candidate.

Abstract: Systems, apparatus, articles, and methods are described including operations for coder based partial image storage and retrieval.

Abstract: The present invention relates to an image enhancement apparatus for enhancing an input image of a sequence of input images. To provide the ability to increase the resolution of an input image and/or to temporally reduce artifacts and/or noise in an input image, the apparatus comprises a motion compensation unit, a weighted selection unit, a feature analysis unit, an image model unit configured to generate a modelled image by applying an image model on said input image and/or said weighted selection image, a spatio-temporal detail signal generation unit configured to generate a detail signal from said input image and said weighted selection image, and a combination unit configured to generate said enhanced output image from said input image, said detail signal and said modelled image.

Abstract: A system and method for the identification and analysis of cadence pattern is disclosed. The method uses previous and current fields to generate the difference between the field values. The difference of these values along with the field relations is passed to the state machine to generate the state of the top and bottom fields. Based on the top and bottom state the cadence signature is generated and by using the Fourier analysis the principle frequency of repeated cadence pattern signature sequence is identified. Each of the cadence signatures present in the cadence pattern signature sequence is decoded to calculate the pull-down value of the cadence pattern. The pull down value then gives the actual cadence pattern.

Abstract: Encoding input data includes: generating a first block of coefficients based on a transform performed on a residual block of data for multiple pixels; generating reference information based on a reference block of data corresponding to the residual block of data; and determining losslessly decodable code values representing the first block of coefficients based on the reference information.

Abstract: A system (100) and method (200) for efficient video adaptation of an input video (102) is provided. The method can include segmenting (210) the input video into a plurality of video shots (142) using a video trace (111) to exploit a temporal structure of the input video, selecting (220) a subset of frames (144) for the video shots that minimizes a distortion of adapted video (152) using the video trace, and selecting transcoding parameters (122) for the subset of frames to produce an optimal video quality of the adapted video under constraints of frame rate, bit rate, and viewing time constraint. The video trace is a compact representation for temporal and spatial distortions for frames in the input video. A spatio-temporal rate-distortion model (320) provides selection of the transcoding parameters during adaptation.

Abstract: An image processing apparatus reduces image data on a first rank to generate image data on a second rank, and acquires an evaluation value of sharpness from the image data on the second rank. When the evaluation value is equal to or more than a threshold value, the image processing apparatus acquires a motion vector from the image data on the second rank. The image processing apparatus, based on the acquired motion vector, sets a detection area of correlation between the image data on the first rank, to detect the motion vector on the first rank. When the evaluation value of the image data on the second rank is less than the threshold value, the image processing apparatus does not need to acquire the motion vector in the image data on the second rank but detects the motion vector in the image data on the first rank.

Abstract: An optical-flow calculating unit (122) detects the amount of movement of an image capturing apparatus at the time of shooting a shot moving image. A camerawork-parameter calculating unit (123) calculates transformation parameters on the basis of the amount of movement. An image transforming unit (160) transforms a captured image on the basis of the transformation parameters. An image combining unit (180) combines the transformed captured image with a history image. A display unit (260) displays, as a representative image, the history image generated by the image combining unit (180) from a certain number of images among captured images. When a selecting operation of selecting a position in the displayed representative image is accepted, a selecting unit (240) selects a recording position of the moving image on the basis of the selected position. A display control unit (250) plays the moving image, starting from the selected recording position of the moving image.

Abstract: There is provided an image processing apparatus including a local-motion-compensation-processing unit which generates a local-motion-compensation image by detecting a local motion vector, which is a motion vector for each block forming an image, from a standard image and a reference image, and performing motion compensation on the reference image using the local motion vector, a global-motion-compensation-processing unit which generates a global-motion-compensation image by calculating a global motion vector, which is a motion vector for an entire image between the standard image and the reference image, using the local motion vector, and performing motion compensation on the reference image using the global motion vector, and a blend processing unit which generates a blend-motion-compensation image by combining a pixel value of a pixel in the local-motion-compensation image and a pixel value of a pixel in the global-motion-compensation image based on a noise intensity for a luminance value of an image.

Abstract: Provided herein is a technique by which a user may interact with an apparatus configured to provide for display of an image, such as with augmented reality glasses. An example embodiment may provide a method including receiving an indication of a first motion event initiated on a first side of a device from a motion sensor, determining a first motion event pattern based on one or more directional components of the first motion event, distinguishing the first motion event from a motion event initiated on a second side of the device, correlating a first operation with the first motion event pattern, and causing the first operation to be performed. The first operation may include causing the opacity of an image presented on a substantially transparent display to be increased.

Abstract: A motion analysis apparatus is provided that enables an analysis result presentation quantity to be easily adjusted. A motion analysis apparatus is an apparatus that performs analysis of motion subject to comparison (compared motion) by means of comparison with standard motion, and has a motion feature extraction section and motion extraction section that determine a location where a degree of difference between a motion subject to comparison and a standard motion satisfies a predetermined condition, a presentation quantity input section that receives a specification of a presentation quantity of locations that satisfy the predetermined condition, and a motion extraction degree adjustment section that adjusts the predetermined condition so that a quantity of locations satisfying the predetermined condition becomes the specified presentation quantity.

Abstract: Embodiments of the invention may include generating a description of a monitored scene and creating a plurality of rules related to the monitored scene by using common language. The description of the monitored scene and the plurality of rules may be converted into system parameters and an analysis of the video data may be performed based on the system parameters. The results of the analysis may be converted into one or more output terms from the plurality of predefined terms and may be displayed to a user in a common language.

Abstract: A method and apparatus for variable accuracy inter-picture timing specification for digital video encoding is disclosed. Specifically, the present invention discloses a system that allows the relative timing of nearby video pictures to be encoded in a very efficient manner. In one embodiment, the display time difference between a current video picture and a nearby video picture is determined. The display time difference is then encoded into a digital representation of the video picture. In a preferred embodiment, the nearby video picture is the most recently transmitted stored picture. For coding efficiency, the display time difference may be encoded using a variable length coding system or arithmetic coding. In an alternate embodiment, the display time difference is encoded as a power of two to reduce the number of bits transmitted.

Abstract: A method and an apparatus providing a visual indication of the occurrence of video recording operations on an electronic device. The video recording operations including recording a plurality of frames according to a number of characteristics. The method comprising providing a time interval between the recording of two consecutive frames by modifying at least one of the characteristics of the video recording operations and providing the visual indication of video recording operations during the time interval.

Abstract: A method and apparatus for variable accuracy inter-picture timing specification for digital video encoding is disclosed. Specifically, the present invention discloses a system that allows the relative timing of nearby video pictures to be encoded in a very efficient manner. In one embodiment, the display time difference between a current video picture and a nearby video picture is determined. The display time difference is then encoded into a digital representation of the video picture. In a preferred embodiment, the nearby video picture is the most recently transmitted stored picture. For coding efficiency, the display time difference may be encoded using a variable length coding system or arithmetic coding. In an alternate embodiment, the display time difference is encoded as a power of two to reduce the number of bits transmitted.

Abstract: A method and apparatus for variable accuracy inter-picture timing specification for digital video encoding is disclosed. Specifically, the present invention discloses a system that allows the relative timing of nearby video pictures to be encoded in a very efficient manner. In one embodiment, the display time difference between a current video picture and a nearby video picture is determined. The display time difference is then encoded into a digital representation of the video picture. In a preferred embodiment, the nearby video picture is the most recently transmitted stored picture. For coding efficiency, the display time difference may be encoded using a variable length coding system or arithmetic coding. In an alternate embodiment, the display time difference is encoded as a power of two to reduce the number of bits transmitted.

Abstract: A method and apparatus for variable accuracy inter-picture timing specification for digital video encoding is disclosed. Specifically, the present invention discloses a system that allows the relative timing of nearby video pictures to be encoded in a very efficient manner. In one embodiment, the display time difference between a current video picture and a nearby video picture is determined. The display time difference is then encoded into a digital representation of the video picture. In a preferred embodiment, the nearby video picture is the most recently transmitted stored picture. For coding efficiency, the display time difference may be encoded using a variable length coding system or arithmetic coding. In an alternate embodiment, the display time difference is encoded as a power of two to reduce the number of bits transmitted.

Abstract: A method and apparatus for variable accuracy inter-picture timing specification for digital video encoding is disclosed. Specifically, the present invention discloses a system that allows the relative timing of nearby video pictures to be encoded in a very efficient manner. In one embodiment, the display time difference between a current video picture and a nearby video picture is determined. The display time difference is then encoded into a digital representation of the video picture. In a preferred embodiment, the nearby video picture is the most recently transmitted stored picture. For coding efficiency, the display time difference may be encoded using a variable length coding system or arithmetic coding. In an alternate embodiment, the display time difference is encoded as a power of two to reduce the number of bits transmitted.

Abstract: There is provided an information processing apparatus including: a characteristic amount extracting unit extracting a plurality of characteristic amounts, which are information expressing characteristics of a video, from the video; a labeling unit associating the extracted characteristic amounts with a person or a background; a matching degree judging unit judging a degree of matching between the associated characteristic amounts and the characteristic amounts of at least one other video; a comparing unit comparing the plurality of characteristic amounts of one scene in the video from which the characteristic amounts have been extracted and the plurality of characteristic amounts of one scene in the at least one other video; and a relationship inferring unit inferring a relationship between the one scene in the video and the one scene in the at least one other video based on a comparison result of the comparing unit.

Abstract: Gain Saturation (GS) for MRFME is where searching in more previous frames offers very limited or even no performance gain. Similarly, gain aggregation (GA) is where significant gain can be obtained by searching more frames. By dynamically determining, while encoding, if either condition applies, and changing the search range accordingly, complexity is reduced and speed can be increased.

Abstract: An image stabilization system includes: a region vector detection unit configured to detect a motion vector of each of a plurality of regions in an image; a reliability determination unit configured to determine reliability of the motion vector of each of the regions; a region indicator configured to indicate, to the region vector detection unit, a new detection target region instead of a region whose motion vector is determined to have low reliability; an image vector computing unit configured to compute a motion vector of the entire image using a motion vector determined to have high reliability; and a stabilization unit configured to move an entire image to be output according to the motion vector of the entire image to compensate for sway of the image.

Abstract: A method for transcoding that includes (A) generating a decoded frame by decoding an MPEG-2 input video stream, the decoded frame including decoded macroblocks; (B) determining a search center for encoding a current macroblock corresponding to a pair of the decoded macroblocks on consecutive macroblock rows, when (i) the encoding uses a predictive field mode and (ii) a current field being encoded is a second field of a current frame that has a first field as a reference field, the search center is a temporally scaled version of a decoded motion vector from an upper or a lower macroblock in the pair; (C) generating a refined motion vector by searching in a temporal search direction about the search center; and (D) generating an H.264 output video stream by encoding the current macroblock based on the refined motion vector.

Abstract: Systems and methods for rolling shutter artifact repair are disclosed.

Abstract: A computer-readable storage medium storing an image processing program that causes a computer to execute a process includes acquiring the same object identification information included in a plurality of image data items by referring to a storage unit that stores each of the image data items, object identification information that identifies an object included in the image data item, and a location information item that identifies a location of the object in the image data item in association with one another; acquiring the location of the object identified by the acquired object identification information in each of the image data items by referring to the storage unit; computing a difference between the acquired location information items; comparing the difference between the location information items with a predetermined location threshold value; and determining whether the image data items are to be in the same group.

Abstract: Systems and methods for region of interest background smoothing & compression enhancement in accordance with embodiments of the invention are disclosed. In one embodiment, preprocessing video with a smoothing filter includes identifying a region of interest in a frame of video, determining an importance value for the region of interest, when the importance value satisfies a criterion, applying an intra frame smoothing filter to pixels within the region of interest, which includes dividing the specified region of interest into pairs of pixel groupings, where the pixel groupings in each pair are the same size and are adjacent to each other, calculating the difference between the average luminance of the pixels within each pixel grouping, when the calculated difference is less than a predetermined amount: calculating the average luminance for all pixels in the pixel groupings, and assigning the calculated average luminance to all pixels within the pixel groupings.

Abstract: Methods and apparatus for robust video stabilization. A video stabilization technique applies a feature tracking technique to an input video sequence to generate feature trajectories. The technique applies a video partitioning technique to segment the input video sequence into factorization windows and transition windows. The technique smoothes the trajectories in each of the windows, in sequence. For factorization windows, a subspace-based optimization technique may be used. For transition windows, a direct track optimization technique that uses a similarity motion model may be used. The technique then determines and applies warping models to the frames in the video sequence. In at least some embodiments, the warping models may include a content-preserving warping model, a homography model, a similarity transform model, and a whole-frame translation model. The warped frames may then be cropped according to a cropping technique.

Abstract: An apparatus performs efficient coding techniques to more efficiently locate motion vector data within neighboring video data units. The apparatus comprises a motion vector (MV) location unit that includes a look-up table (LUT), where the MV location unit obtains video data defining a plurality of video data units and processes the plurality of video data units. The apparatus further includes a geometric resolution unit that determines, while processing a current one of the plurality of video data units, which of the plurality of video data units neighbor the current video data unit. The MV location unit then accesses, for each of the neighboring video data units, the LUT to determine a location of a motion vector within a section of the video data to which the neighboring video data unit is associated.

Abstract: A method for motion estimation with respect to a sequence of images. Respective updates are generated based on predictor vectors. The updates are distributed over a plurality of tables, which are organized in a plurality of table sets. Only a single table of updates, of a respective selected table set, is applied to a given predictor vector to generate a limited set of candidate vectors only. For a subsequent predictor vector, a further single table of the plurality of tables out of the plurality of table sets is applied.

Abstract: A stream condense unit coupled to a streaming server and a client player is provided. The stream condense unit includes a streaming data input unit, a stream content analysis unit, a frame timestamp adjust unit, and a streaming data output unit. The streaming data input unit is configured to receive a plurality of streaming content groups sent by the streaming server. The stream content analysis unit is configured to receive the plurality of streaming content groups, execute a content analysis to get importance scores of the source streaming contents. The frame timestamp adjust unit is configured to receive the condensed stream and adjust a timestamp of each frame in the condensed stream. The streaming data output unit is configured to receive the condensed stream and attach content identifying labels and tables to the condensed stream, and send the condensed stream to the client player to display.

Abstract: A technique for frame rate conversion that utilizes motion estimation and motion compensated temporal interpolation includes obtaining a first image and a second image, where the first and second images correspond to different instances in time, compressing the second image using multiple motion vectors that result from motion estimation between the first image and the second image to generate a compressed image, and generating an interpolated image using the compressed image.

Abstract: A technique for improving image compression by pre-processing the image frames. In particular, methods for de-interlacing and noise reduction using combinations of median filters, applied both spatially and temporally, with and without motion analysis, are described.