Abstract: State-of-the-art video coding schemes supports splitting a picture into smaller rectangular units called tiles units. Each tile units can be independently encoded and decoded by separate encoders and decoders, respectively. The primary purpose of tiles units is to allow parallel processing of the picture to reduce implementation cost and complexity. The present disclosure provides additional functionality to define flexible partitioned tile regions and to allow partial decoding and reconstruction of tile regions.

Abstract: An image processing apparatus includes an image inputting unit for inputting a plurality of facial images; a detecting unit for detecting a facial region of each of the facial images; a correction ratio calculating unit for calculating a correction ratio of the facial region of each of the facial images; a position calculating unit for calculating a positional deviation of the facial region of each of the facial images; and a correcting unit for correcting a layout of each of the facial images through enlarging or reducing each of the facial images according to the correction ratio and moving each of the facial images according to the positional deviation.

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: In one embodiment, a method of predicting a motion vector for a current block in a current picture by a moving picture decoding device includes obtaining, by the moving picture decoding device, a direction of a reference picture of the current picture, based on comparison of a display order of the reference picture and a display order of the current picture, obtaining, by the moving picture decoding device, at least three motion vectors for at least three other blocks than the current block based on the direction of the reference picture, predicting, by the moving picture decoding device, a motion vector for the current block by using a median operation of the at least three motion vectors and decoding the current block in the current picture using the predicted motion vector for the current block.

Abstract: A motion vector generation apparatus which generates a motion vector utilized to execute motion-compensated encoding based on comparison between a block to be encoded in an image to be encoded and a reference block in a reference image. The apparatus sequentially selects a candidate from a plurality of motion vector candidates, sequentially calculates differences between pixel values of the block to be encoded and pixel values of the reference block corresponding to respective motion vector candidates, calculates, as an average difference, differences between an average pixel value obtained by averaging the pixel values of the block to be encoded and respective pixel values of the block to be encoded, decides a weighting coefficient based on a ratio between a minimum difference and the average difference, and calculates, for each selected motion vector candidate, an evaluation value for deciding a motion vector candidate having a minimum evaluation value.

Abstract: One embodiment of the present invention provides a system that automatically produces a summary of a video. During operation, the system partitions the video into scenes and then determines similarities between the scenes. Next, the system selects representative scenes from the video based on the determined similarities, and combines the selected scenes to produce the summary for the video.

Abstract: In one exemplary embodiment, a tracking system for region-of-interest (ROI) performs a feature-point detection locally on an ROI of an image frame at an initial time via a feature point detecting and tracking module, and tracks the detected features. A linear transformation module finds out a transform relationship between two ROIs of two consecutive image frames, by using a plurality of corresponding feature points. An estimation and update module predicts and corrects a moving location for the ROI at a current time. Based on the result corrected by the estimation and update module, an outlier rejection module removes at least an outlier outside the ROI.

Abstract: A lossless image compression method for a high definition image is provided. The image compression method generates a minimum value of values produced by subtracting a current virtual pixel value from an average of neighbor pixels designated by a plurality of directions, as the prediction value of a current pixel. Thus, the image compression more efficient than the current JPEG-LS can be achieved.

Abstract: A method of processing video data includes: receiving a first video frame with first blocks of pixels associated with a known motion vector and a second video frame with second blocks of pixels, the second blocks corresponding to the first blocks, and uncovered blocks adjacent to the first frame boundary not corresponding to the first blocks in the first video frame; determining a first block for each line segment in the second video frame corresponding to a block in the first video frame, wherein the first block has the known motion vector from the first video frame; and assigning a motion vector for at least one of the line segments in the second video frame to the uncovered blocks in the line segment of the second video frame between first block and the first frame boundary.

Abstract: Described herein are a method and system for frame rate adaptation. There may be conditions that require the rate of a video sequence to be dynamically controlled, and a frame interval may be adaptively selected every frame. A frame within the video sequence may contain, for example, a time stamp that is transmitted to a decoder to indicate the change in temporal spacing between frames.

Abstract: It is a task to provide a mobile electronic device with high operability and high safety. The mobile electronic device includes an image projector that projects an image, a cabinet, an input unit that is disposed on the cabinet and detects an operation input by an operator, and a control unit that controls the operation of the image projector and the state of the input unit. The task is solved in such a manner that when a predetermined operation is detected by the input unit, the control unit stops emission of light from the image projector or reduces an amount of light emitted from the image projector.

Abstract: Provided are an enhanced inter-layer reference picture designating method and apparatus and an enhanced inter-layer reference picture recovering method and apparatus capable of increasing coding efficiency by allowing different blocks in an upper spatial layer picture of a current to-be-decoded or to-be-encoded picture to refer to blocks in different lower spatial layer pictures.

Abstract: An array encoding system and method for use with high definition digital video data streams includes method and means for analyzing the incoming data stream, splitting the data stream in accordance with video complexity or other criteria, encoding each of the subsidiary data streams in accordance with a desired encoding standard, and combining the data streams to generate an output. The encoding system and method is particularly suited to encoding data streams to provide an output with is substantially consistent with the H.264 video communications standard. The system and method are scalable.

Abstract: A method is provided for encoding a multi-layer video signal by using an extended macro-block skip mode. The method includes generating a bit stream of a base layer; generating a bit stream of an enhanced layer by referring to a frame of the base layer; setting a syntax item for an extended macro-block skip mode in an area of the bit stream of the enhanced layer, wherein the syntax item indicates if information of the base layer is used as it is while a frame of the enhanced layer is skipped.

Abstract: In principle, an I-frame is inserted every 50 frames and other frames are made P-frames. If the maximum amount of data that can be received by a terminal device to which a transmission is to be made is 300 KB, then frames up to a 144th frame for which the amount of data after compression will not exceed 300 KB is adopted as a first partitioned moving picture file. Since the 145th frame is the leading frame of the next partitioned moving picture file, it is made an I-frame. Frames from the 145th frame to a 289th frame are made a second partitioned moving picture file, and frames from a 290th frame to a 411th frame are made a third partitioned moving picture file. Since the leading frame of a partitioned moving picture file represents one complete frame, the moving picture can be reproduced and the number of partitions can be reduced.

Abstract: A method and apparatus for predicting reference data transfer scheme for motion estimation. The method includes computing, via the processor, hypothetical rectangle region in reference frame containing all the predicting and reference data for doing motion estimation search around the region, if the macroblock is not the first in a row, utilizing overlap with previously fetched reference data, computing overlap with previously fetched reference data, and transferring needed data, invalidating any predictor, wherein the predictor is not part of the fetched data, and regulating the motion estimation and setting the motion vector to an effective value based on the fetched and computed data.

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: This disclosure describes techniques for processing motion vectors such that the resulting motion vectors better correlate with the true motion of a video frame. In one example, the techniques may include comparing a block motion vector corresponding to a video block to a sub-block motion vector corresponding to a sub-block contained within the video block. The techniques may further include selecting one of the block motion vector and the sub-block motion vector as a spatially-estimated motion vector for the sub-block based on the comparison. Motion vectors that better correlate with true motion may be useful in applications such as motion compensated frame interpolation (MCI), moving object tracking, error concealment, or other video post-processing that requires the true motion information.

Abstract: The present invention provides a method and a system for video stabilization in real time. The method comprises the steps of: estimating an optical flow from an previous image, Ii, to a current image, Ii+1; determining an Euclidean transformation, Fi, from the previous image, Ii to the current image, Ii+1, wherein the Euclidean transformation, Fi, comprises a product of rotation, Ri, and scaling, si, and translation, Ti; and transforming the current image, Ii+1, by applying the inverse of the Euclidean transformation, Fi, to the current image, Ii+1, in order to obtain stabilization. The transformation of the current image, Ii+1, is restricted by using Euclidean matrices Ai and Bi, wherein: Ai is used to store absolute frame transformation relative world frame coordinates, Ao is the identity matrix and Ai+1 is equal to AiFi?1 for i?0 and Bi is used to store visualization window coordinate transformation.

Abstract: According to an embodiment, an encoding device includes an index setting unit and an encoding unit. The index setting unit generates a common index in which reference indices of one or more reference images included in a first index and a second index are sorted in a combination so as not to include a same reference image in accordance with a predetermined scanning order. The first index representing a combination of the one or more reference images referred to by a first reference image. The second index representing a combination of the one or more reference images referred to by a second reference image. The encoding unit encodes the common index.

Abstract: A method for evaluating video quality of a video stream comprising the steps of a) calculating, for at least a first frame of a series of frames from said video stream, a true value of at least one video quality-related parameter associated to said first frame; b) calculating a predicted value of said video quality-related parameter for at least a second frame from said series of frames based on said true value associated to said first frame; c) calculating a true value of said video quality-related parameter associated to said second frame; and d) judging the video quality of said second frame based on a difference between true and predicted values of the at least one video quality-related parameter associated to said second frame.

Abstract: A Method and apparatus for encoding and decoding a multi-view image are provided. The method of encoding a multi-view image includes determining whether each of pictures included in multi-view image sequences is a reference picture referred to by other pictures included in the multi-view image sequences for inter-view prediction, and encoding the pictures using at least one of inter-view prediction and temporal prediction based on the determination result, thereby efficiently encoding and decoding the multi-view image at high speed.

Abstract: Apparatus and methods are presented for estimating the velocity field based on a multi-image frame sequence having an integer number M frames, M is greater than two, in which a set of M?1 displaced frame difference (DFD) equations is solved including a motion compensated prediction (MCP) equation, M?2 motion compensated interpolation (MCI) equations for solving a velocity field at a first time using a set of iteration equations to determine a velocity field, and 2×(M?2) conservative velocity constraint (CVC) equations for solving a velocity field at times t2, . . . , tM?1.

Abstract: An image processing apparatus extracts still images from a moving image and performs an image process. A parameter indicating characteristics of moving image data is extracted, and the number of still images is determined based on the parameter indicating characteristics of the moving image data. Then, based on a determined number of still images, still images are extracted from the moving image, the extracted still images are saved as a single file, and the image process is carried out using saved still images.

Abstract: A video encoding method and apparatus are provided. The video encoding method includes determining whether a current block includes an affine-transformation object having an affine transformation; if the current block includes an affine-transformation object, generating a prediction block by performing affine transformation-based motion compensation on the current block in consideration of an affine transformation of the affine-transformation object; and if the current block does not include any affine-transformation object, generating a prediction block by performing motion vector-based motion compensation on the current block using a motion vector of the current block. Therefore, it is possible to achieve high video encoding/decoding efficiency even when a block to be encoded or decoded includes an affine transformation.

Abstract: Embodiments of an apparatus and method for decoding an encoded bitstream to generate a video signal are taught. A decoder receives the bitstream and decodes a portion thereof to obtain at least a portion of a predictive reference frame. The reference frame is generated by, for example, selecting a filter set including a target frame with a block having a plurality of pixels and at least one adjacent frame, determining a coding mode associated with the block, determining a block-specific factor derived from the coding mode, determining weighted averages of pixels in the filter set and using the weighted averages to generate the predictive reference frame. The decoder also generates a residual from another portion of the encoded bitstream that represents a portion of a frame of the plurality of frames and reconstructs the portion of the frame by adding the residual to the predictive reference frame.

Abstract: A video codec having a modular structure for encoding/decoding a digitized sequence of video frames in a multi-core system is described. The video codec comprises a memory unit; a multithreading engine. and a plurality of control and task modules organized in a tree structure, each module corresponding to a coding operation. The modules communicate with each other by control messages and shared memory. The control modules control all coding logic and workflow, and lower level task modules perform tasks and provide calculations upon receiving messages from the control task modules. The multithreading engine maintains context of each task and assigns at least one core to each task for execution. The method of coding/decoding comprises an error resilient algorithm.

Abstract: An apparatus performs efficient coding techniques to more efficiently resolve geometric relationships between video data units and thereby determine neighboring video data units for a current video data unit. The apparatus comprises a geometric resolution unit that obtains video data defining a plurality of video data units, and determines, for the current one of the plurality of video data units to be processed, a partition width and a video unit number of the current video data unit. The geometric resolution unit accesses, using the determined partition width and video unit number, a plurality of look-up tables (LUTs) to output one or more indices identifying one or more of the plurality of video data units that neighbor the current video data unit.

Abstract: A method of receiving video data comprising the steps of: receiving at least one chunk of video data comprising a number of sequential key video frames where the number is at least two and, constructing at least one delta frame between a nearest preceding key frame and a nearest subsequent key frame from data contained in the either or each of the nearest preceding and subsequent frames.

Abstract: A method for transcoding from an MPEG-2 format to a VC-1 format is disclosed. The method generally comprises the steps of (A) decoding an input video stream in the MPEG-2 format to generate a picture; (B) determining a mode indicator for the picture; and (C) coding the picture into an output video stream in the VC-1 format using one of (i) a VC-1 field mode coding and (ii) a VC-1 frame mode coding as determined from the mode indicator.

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: Modified compression/decompression and metadata in burst mode images reduce the storage space consumed by burst mode images. Metadata is added to image files (e.g., EXIF files) to establish links between images in a burst mode image series. A series of linked burst mode images can include delta images representing a temporal difference between the image data (e.g., pixel data) for two burst images captured at different time instances. Difference information can be compressed. A root image for a linked burst mode series can be identified and used as a reference for other burst images. Metadata can be added to image files to link burst images prior to compression, after compression, or at an intermediate stage of compression of image data. Difference information for delta image files can be derived prior to compression, after compression, or at an intermediate stage of compression of image data.

Abstract: According to one embodiment an image encoder encodes original image data using reference image data stored in a frame memory. The image encoder includes a controller, a memory, a motion controller, and a motion compensation module. The controller generates control information including a starting point coordinate and an ending point coordinate of a necessary area in the reference image data stored in the frame memory. The memory includes a storage area in which at least part of the reference image data is stored. The motion controller determines whether the necessary area is a transfer-necessary area or a transfer-unnecessary area based on the control information, and transfers the reference image data of the transfer-necessary area from the frame memory to the storage area. The motion compensation module generates prediction image data using the reference image data stored in the storage area.

Abstract: There are provided an encoding device, a decoding device, an encoding method, and a decoding method that enhance optimality in a case of encoding moving image signals having no sample ratio distinction between color components such as a 4:4:4 format. In a case of conducting compression encoding by inputting digital moving image signals of the 4:4:4 format, there are prepared a first encoding process of encoding three color component signals of the input moving image signals in a common encoding mode, and a second encoding process of encoding the three color component signals of the input moving image signals in respective independent encoding modes. The encoding process is executed by selecting any one of the first encoding process and the second encoding process, and the compression data contains an identification signal for specifying which process is selected.

Abstract: In one embodiment, the apparatus includes a decoder. The decoder is configured to obtain first and second motion vectors of a block other than the current block. The other block neighbors the current block at one of a left, top and top right position. The decoder is configured to determine first and second motion vectors of the current block using the first and second motion vectors of the other block such that the first motion vector of the current block has a same direction as the first motion vector of the other block and the second motion vector of the current block has a same direction as the second motion vector of the other block.

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, devices and methods are described including applying nonlinear scaling to a current image frame and a reference image frame to generate at least a corresponding current image layer and a corresponding reference image layer. Hierarchical motion estimation may then be performed using the nonlinearly scaled image layers. Further, source block size may be adaptively determined in a downsampled image layer and hierarchical motion estimation may be performed using the adaptively sized source blocks.

Abstract: When removing a block distortion occurring in a local decoded image, a loop filtering part 11 of an image coding device carries out a filtering process on each of signal components (a luminance signal component and color difference signal components) after setting the intensity of a filter for removing the block distortion for each of the signal components according to a coding mode (an intra coding mode or an inter coding mode) selected by a coding controlling part 1.

Abstract: In one embodiment, an apparatus includes a decoder. The decoder is configured to obtain first and second motion vectors of a block other than the current block. The other block neighbors the current block at one of a left, top and top right position. The decoder is configured to determine first and second motion vectors of the current block using the first and second motion vectors of the other block such that the first motion vector of the current block has a same direction as the first motion vector of the other block and the second motion vector of the current block has a same direction as the second motion vector of the other block.

Abstract: In one embodiment, the apparatus includes a decoder. The decoder is configured to obtain first and second motion vectors of a block other than the current block. The other block neighbors the current block at one of a left, top and top right position. The decoder is configured to determine first and second motion vectors of the current block using the first and second motion vectors of the other block such that the first motion vector of the current block has a same direction as the first motion vector of the other block and the second motion vector of the current block has a same direction as the second motion vector of the other block.

Abstract: A moving picture compression coding apparatus divides a screen into at least three regions and performs compression coding for the at least three regions by encoding units. The moving picture compression coding apparatus includes a coding control unit configured to control the encoding units to encode the data for different regions in parallel and to control the encoding such that the data for an upper region out of two adjacent upper and lower regions in the vicinity of the center of the screen of the at least three regions is encoded prior to the encoding of the data for the lower region or such that the data for a left region of two adjacent left and right regions in the vicinity of the center of the screen of the at least three regions is encoded prior to the encoding of the data for the right region.

Abstract: An image processing apparatus includes: a storage means for storing a decoded image in which pictures of a first image and a second image each having a disparity are alternately arranged, and performing local decoding, and a storage control means for performing storage control to control the storage of a reference picture in the storage means such that, from among the pictures which are encoded temporally earlier than a current picture in encoding process which is a picture to be encoded, and are capable of becoming reference pictures, a picture which is a picture of an image at the same viewpoint as the current picture in encoding process from among the first image and the second image and is closest to the current picture in encoding process in a display order is stored in the storage means.

Abstract: A method for transcoding from an H.264 format to a VC-1 format. 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 VC-1 format using one of (i) a VC-1 field motion compensation mode coding and (ii) a VC-1 frame motion compensation mode coding as determined from the mode indicator.

Abstract: In one embodiment, a method of predicting a motion vector for a current block in a current picture by a moving picture decoding device includes obtaining, by the moving picture decoding device, a direction of a reference picture of the current picture, based on comparison of a display order of the reference picture and a display order of the current picture, obtaining, by the moving picture decoding device, at least three motion vectors for at least three other blocks than the current block based on the direction of the reference picture and predicting, by the moving picture decoding device, a motion vector for the current block by using a median operation of the at least three motion vectors.

Abstract: In one embodiment, the apparatus includes a decoder. The decoder is configured to obtain first and second motion vectors of a block other than the current block. The other block neighbors the current block at one of a left, top and top right position. The decoder is configured to determine first and second motion vectors of the current block using the first and second motion vectors of the other block such that the first motion vector of the current block has a same direction as the first motion vector of the other block and the second motion vector of the current block has a same direction as the second motion vector of the other block.

Abstract: An intraprediction/inter prediction method and apparatus is provided. In a method of intrapredicting an image processing unit of a current picture, the image processing unit including a plurality of sub blocks, a first prediction value of the image processing unit is generated by intrapredicting each of the sub blocks using pixels neighboring each of the sub blocks. A second prediction value of the image processing unit is generated by intrapredicting each of the sub blocks using pixels neighboring each of the sub blocks included in the first prediction value. Accordingly, an intrapredicted value or an intrapredicted motion vector can be more accurately obtained, so that the compression rate of image encoding is improved.

Abstract: In one embodiment, the method includes selecting a list 0 motion vector of the first block in the first picture as the motion vector for deriving list 0 and list 1 motion vectors of the bi-predictive block if the first block has both a list 1 motion vector and the list 0 motion vector, the first picture being permitted to be located temporally before the current picture and permitted to be located temporally after the current picture, deriving a first temporal distance between the current picture and a reference picture of the current picture, deriving a second temporal distance between the first reference picture and a reference picture of the first picture, scaling the selected motion vector based on the first and the second temporal distances and deriving at least one motion vector of the bi-predictive block by applying a bit operation to the scaled motion vector.

Abstract: In one embodiment, an apparatus includes a decoder. The decoder is configured to obtain first and second motion vectors of a block other than the current block. The other block neighbors the current block at one of a left, top and top right position. The decoder is configured to determine first and second motion vectors of the current block using the first and second motion vectors of the other block such that the first motion vector of the current block has a same direction as the first motion vector of the other block and the second motion vector of the current block has a same direction as the second motion vector of the other block.

Abstract: In one embodiment, the apparatus includes a decoder. The decoder is configured to obtain first and second motion vectors of a block other than the current block. The other block neighbors the current block at one of a left, top and top right position. The decoder is configured to determine first and second motion vectors of the current block using the first and second motion vectors of the other block such that the first motion vector of the current block has a same direction as the first motion vector of the other block and the second motion vector of the current block has a same direction as the second motion vector of the other block.

Abstract: In one embodiment, a method of predicting a motion vector for a current block in a current picture by a moving picture decoding device includes obtaining, by the moving picture decoding device, a direction of a reference picture of the current picture, based on comparison of a display order of the reference picture and a display order of the current picture, obtaining, by the moving picture decoding device, at least three forward motion vectors for at least three other blocks than the current block based on the direction of the reference picture, and predicting, by the moving picture decoding device, a forward motion vector for the current block by using median operation of the at least three forward motion vectors.