Abstract: This application relates to a video coding method and apparatus, a computer device, and a storage medium. The method includes: obtaining a current coding unit; obtaining target pixel gradient data through calculation according to a pixel value of a pixel in the current coding unit, the target pixel gradient data being obtained according to a difference between the pixel value of the pixel and a reference pixel value; determining a target division decision result corresponding to the current coding unit according to the target pixel gradient data; and performing video coding on the current coding unit according to the target division decision result.

Abstract: Shake correction is performed using posture information corresponding to each frame of image data constituting a moving image on each frame, the frame having been subjected to processing of pasting to a celestial sphere model. Further, protrusion prevention processing for correcting an effective cropping area from each frame so that the effective cropping area does not protrude from a movable area in which the effective shake correction is maintained is performed on a requested cropping area to set an effective cropping area applied to each frame. Processing for generating an effective cropping area image is performed, the effective cropping area image being an image subjected to the shake correction and then projected onto a plane model from the celestial sphere model and being an image of the set effective cropping area.

Abstract: A method and apparatus for converting a picture into a video, and a device and a storage medium. The method for converting a picture into a video includes: partitioning an original picture to obtain a foreground region and a background region; performing an iterative transformation for visual depth on the background region, and storing an image obtained through each transformation as a picture frame to obtain multiple frames of images; and splicing the multiple frames of images to obtain a target video. The iterative transformation includes at least two transformations for visual depth.

Abstract: An image processing apparatus includes a separation unit configured to separate luminance information of each pixel in a processing area of an input image into an intrusion component and an object component, a determination unit configured to determine whether each of intrusion components is a first component or a second component, a processing unit configured to generate first information based on the first component, and an image generating unit configured to generate an output image based on the first information, the second component, and the object component.

Abstract: According to an aspect, there is provided a system (200) comprising: an image projection unit (210) configured to project an illumination pattern onto at least a portion of a scene, an imaging unit (220) configured to capture a plurality of images of the scene while the illumination pattern is projected onto the scene, and a processing unit (230) configured to: demodulate the plurality of images based on the illumination pattern and with respect to a target section in the plurality of captured images, wherein the target section corresponds to one of: a portion of the scene on which the illumination pattern is selectively projected while the plurality of images were captured, a portion of the scene at which the projected illumination pattern is resolvable, a portion of the scene with pixel depth values which satisfy a predetermined range; and generate an ambient light suppressed image of the scene based on results of the demodulation.

Abstract: In various embodiments, a method for processing video streams is described. A plurality of video streams for transmission to a display device are received. The plurality of video streams have respective initial image quality levels. An estimated gaze location of a user of the display device is estimated. At least one video stream of the plurality of video streams is processed to have a modified image quality level based on the estimated gaze location. The modified image quality level is less than a corresponding initial image quality level. The plurality of video streams are transmitted to the display device.

Abstract: This disclosure involves executing artificial intelligence models that infer image editing operations from natural language requests spoken by a user. Further, this disclosure performs the inferred image editing operations using inferred parameters for the image editing operations. Systems and methods may be provided that infer one or more image editing operations from a natural language request associated with a source image, locate areas of the source that are relevant to the one or more image editing operations to generate image masks, and performing the one or more image editing operations to generate a modified source image.

Abstract: A display device includes a plurality of pixels arranged in m rows and n columns, where the pixels receive write scan signals, data voltages and compensation scan signals, a plurality of write scan lines which provides the write scan signals to the pixels, a plurality of data lines which provides the data voltages to the pixels, and a plurality of compensation scan lines which provides the compensation scan signals to the pixels, wherein in h-th to p-th frames, the data voltages are applied to pixels arranged in first to i-th rows, and in h-th to (h+k)-th frames, the data voltages are applied to pixels of a row unit by increasing sequentially the number of the row unit to which the data voltages are applied in at least one row unit from an i-th row to an (i+1)-th row.

Abstract: Method for real time video processing for retouching an object in a video, comprising: providing an object in the video steam, the object being at least partially and at least occasionally presented in frames of the video; setting a degree of retouching; generating a list of at least one element of the object selected based on a request of retouching and the degree of retouching; detecting the at least one element of the object in the video and parameters of the at least one element; calculating new parameters of the at least one element according to the degree of retouching; detecting characteristic points for each of the at least one element of the object; generating a mesh based on the characteristic points for each of the at least one element of the object; tracking the at least one element of the object in the video, wherein the tracking comprises aligning the mesh for each of the at least one element with a position of the corresponding each of the at least one element; and transforming the frames of th

Abstract: The disclosed system modifies luminance of a display associated with a selective screen. The display provides a camera with an image having resolution higher than the resolution of the display by presenting multiple images while the selective screen enables light from different portions of the multiple images to reach the camera. The resulting luminance of the recorded image is lower than a combination of luminance values of the multiple images. The processor obtains a criterion indicating a property of the input image where image detail is unnecessary. The processor detects a region of the input image satisfying the criterion, and determines a region of the selective screen corresponding to the region of the input image. The processor increases the luminance of the display by disabling the region of the selective screen corresponding to the region of the input image.

Abstract: Disclosed here are various techniques to increase dynamic range of an image recorded from a display. A processor performing preprocessing splits an input image containing both bright and dark regions into two images, image A containing bright regions, and image B containing dark regions. The display presents image A and image B in alternating fashion. Camera is synchronized with the display to record image A and image B independently. In postprocessing, a processor obtains the recorded images A and B. The processor increases the pixel value of the recorded image A to obtain image A with increased pixel value. Finally, the processor increases pixel value of the image recorded from the display by combining the first recorded image with increased pixel value and the second recorded image.

Abstract: Systems and methods may provide for occlusion detection in frame rate conversion. Detecting the occlusion allows frame rate conversion to be more accurately performed. In some embodiments, one or more stereoscopic depth cameras may be used to determine the depth of a moving object to more accurately determine the occlusion. In some embodiments, the compression ratio may be adjusted to balance the frame rate and power to help ensure compliance with a power budget. In at least some embodiments, the motion of a camera may be passed from a 3D render pipe to an encoder to avoid motion calculation and thereby saving power.

Abstract: A method, device, and non-transitory computer-readable medium for decoding an encoded video bitstream using at least one processor, including obtaining a coded picture from the encoded video bitstream; decoding the coded picture to generate a decoded picture; obtaining a first flag indicating whether reference picture resampling is enabled; obtaining a second flag indicating whether reference pictures have a constant reference picture size; obtaining a third flag indicating whether output pictures have a constant output picture size indicated in the encoded video bitstream; generating a reference picture by resampling the decoded picture to have the constant reference picture size, and storing the reference picture in a decoded picture buffer; and generating an output picture by resampling the decoded picture to have the constant output picture size, and outputting the output picture.

Abstract: 3D mapping statistics are generated for a first image of a first dynamic range and a second image of a second dynamic range different from the first dynamic range. Multivariate multiple regression (MMR) coefficients are generated by solving an optimization problem formulated using an MMR matrix built with the 3D mapping statistics without a letterbox constraint, and used to generate chroma mappings for predicting chroma codeword values of the second image. It is determined whether a letterbox exists in the images. If so, it is determined whether the chroma mappings accurately predict chroma codeword values in the second image. A reconstructed image generated by a recipient device by backward reshaping one of the images is rendered by a display device operating in conjunction with the recipient device.

Abstract: This invention provides a process which allows better quality rendering of video on any display. The process proposes encoding, video data and additional data. The additional data includes a change time instant. The change time instant can be used to indicate a change in time of a characteristic luminance. The characteristic luminance summarizes the set of luminances of pixels in an image of the video data. The process includes generating on descriptive data based on the video data and encoding and outputting the descriptive data as additional data.

Abstract: A display apparatus includes a display; an optical sensor; and a processor configured to: obtain a current illumination value detected by the optical sensor while the display displays an image, identify a first illumination level corresponding to the obtained current illumination value, the first illumination level being previously obtained at a time when the display is displaying a preset image, identify an ambient brightness based on a second illumination level, the second illumination level corresponding to the identified first illumination level and being previously obtained at a time when the display is not displaying any image, and perform an operation based on the identified ambient brightness.

Abstract: Provided is a method of executing content, the method including: recognizing an external electronic device connected to an electronic device; determining a type of the content provided from the external electronic device to the electronic device based on a user interface (UI) displayed on a screen of the electronic device, as the external electronic device is recognized; and determining an image quality control mode for the content based on the determined type of the content.

Abstract: A method of determining a quality measure for a processed video signal generated from an original video signal. A statistical metric for a value for a set of pixels of the original video signal is determined, and the statistical metric for the value for a corresponding set of pixels of the processed video signal is also determined. The quality measure for the processed video signal is then determined by comparing the statistical metrics for the original video signal and the processed video signal.

Abstract: A method, device, and non-transitory computer-readable medium for decoding an encoded video bitstream using at least one processor, including obtaining a coded picture from the encoded video bitstream; decoding the coded picture to generate a decoded picture; obtaining a first flag indicating whether reference picture resampling is enabled; obtaining a second flag indicating whether reference pictures have a constant reference picture size; obtaining a third flag indicating whether output pictures have a constant output picture size indicated in the encoded video bitstream; generating a reference picture by resampling the decoded picture to have the constant reference picture size, and storing the reference picture in a decoded picture buffer; and generating an output picture by resampling the decoded picture to have the constant output picture size, and outputting the output picture.

Abstract: A system and method of processing video data: produce, on the basis of the video data, descriptive data regarding a variation in a characteristic luminance of the video data, wherein the characteristic luminance summarizes the set of luminances of pixels in an image of the video data, wherein the descriptive data identifies the at least one change time instant, wherein the change time instant indicates a time at which a change of the characteristic luminance occurs; and encode and output the descriptive data.

Abstract: Methods and apparatus to implement aging compensation for emissive displays with subpixel rendering are disclosed. An example apparatus includes a converter to convert red-green-blue (RGB) data to subpixel rendering (SPR) data. The RGB data is indicative of an image to be rendered on an emissive display screen. The apparatus includes a compensator to apply pixel correction values to the SPR data to generate corrected SPR data to compensate for pixel degradation. The apparatus further includes a usage accumulator to track pixel usage based on the corrected SPR data. The apparatus also includes a correction calculator to calculate the pixel correction values based on the pixel usage.

Abstract: Images of user drawn virtual characters, virtual objects, or virtual scenes may be used in providing display of animations. The animations may be displayed over other images or in a virtual world of video game play.

Abstract: A three-dimensional around view monitoring system of a vehicle includes a fisheye image correction setting module, configured to receive fisheye image data generated by photographing a correction plate; correct the fisheye image data into corrected image data to generate a fisheye correction lookup table and rotate and translate radiate vertical reference lines presented as straight lines in the corrected image data in a neighborhood into overlaps having a same radiation angle to generate a rotation and translation lookup table; and a static three-dimensional stitched image generation module, configured to generate a stitched image lookup table according to the rotation and translation lookup table and the fisheye correction lookup table, calculate a pixel value of each pixel in the corrected image data by using a pixel value of each pixel in fisheye image data, and perform image stitching on the neighboring corrected image data to generate static stitched image data.

Abstract: A display device and a display signal input system and a display signal input method thereof are provided. The display signal input method includes: receiving sub-images; grouping the sub-images into a plurality of sub-image groups of a base level; judging information of edge matching between sub-image units in each sub-image group of a current level; if edge matching between the sub-image units in each sub-image group of the current level is correct, grouping respective sub-image groups of the current level as sub-image units to form sub-image groups of a new level, and performing judgment again till edge matching between any two adjacent sub-images in an image formed by splicing the sub-images is correct; and outputting information of the respective sub-images arranged in sequence to the display device.

Abstract: A method of identifying and scaling a region of interest on a display device is presented. The region of interest is detected based on the rate of change between frames. A size of the display area of the display device and aspect ratio are determined. The detected region of interest is scaled to fit the display area in full screen mode based on the display area and the aspect ratio. The region of interest may be, for example, an active video region. In full screen mode, any static or slow-moving images are hidden.

Abstract: Techniques related to tracking regions of interest across video frames with corresponding depth maps are discussed. Such techniques may include motion tracking feature points of a region of interest, filtering the tracked feature points, determining a center of the region of interest, verifying a depth consistency of the center, and, if the number of tracked feature points falls below a threshold or the center fails depth consistency for a current frame, re-initializing the region of interest in a prior frame.

Abstract: A method and an apparatus for dividing an image area are provided. The method includes: a reading step: reading a pixel value of a current pixel and pixel values of multiple adjacent pixels adjacent to the current pixel in an image; a calculation step: calculating a difference between the pixel values of the current pixel and each adjacent pixel, so as to obtain a pixel difference value set, the pixel difference value set including multiple pixel difference values; a processing step: comparing each pixel difference value with a corresponding dynamic threshold in sequence, and determining all adjacent pixels in a same sub-image area as the current pixel, the current pixel and all the adjacent pixels of the current pixel in the same sub-image area constituting one sub-image area; and a traversal step: traversing each pixel in the image, and performing the reading step, the calculation step, and the processing step on each pixel in sequence, so as to acquire multiple sub-image areas of the image.

Abstract: A determination device according to the present embodiment, detects a center line from video that is obtained by capturing a match-up type game for going into a goal that is provided on an opposing team's territory, conducted in a field, where one of territories is separated from other one of the territories by using the center line and outputs an index as to which team is more superior in the game in accordance with a determination result as to which one of the territories, separated by using the detected center line, mainly appears in the video.

Abstract: A method and apparatus for emulation of Bi predicted B pictures is described where a B picture is constructed only from information from one preceding and successive frame without pixel averaging or motion vector computation. In the case of H.264 or analogous codecs, a top field of a B picture is formed from the successive I or P picture top field, and the bottom field formed from the previous P picture bottom field. B picture emulation may reverse the previous and successive pictures. For interlaced pictures, the odd and ever interlacing fields are treated as top and bottom fields, and also use information from both one preceding and successive frame. The resulting Bi predicted B pictures reduce inter-GOP flicker.

Abstract: Techniques for enabling an augmented reality system to complement operation of existing output devices in an environment are described herein. An augmented reality system may include one or more augmented reality functional nodes (ARFNs) that are configured to project content onto different non-powered and/or powered display mediums. The ARFN may identify existing output devices, as well as any content that these content output devices currently output. The ARFN may then either take over the display of the content when appropriate, or may project related content.

Abstract: A method and an apparatus for scanning in a wireless LAN are disclosed. The method for scanning in a wireless LAN comprises the steps of: enabling a station (STA) to receive, from a first access point (AP) operated in a first channel, a detection frame comprising identifier information of a second AP operated in a second channel and beacon frame transmission time information of the second AP, and enabling the STA to scan a beacon frame of the second AP on the basis of the beacon frame transmission time information of the second AP. Thus, the present invention can rapidly perform a scanning operation.

Abstract: There is provided an image processing apparatus including an image processing unit which performs image processing on each of a plurality of images of a same subject having different resolutions, and an image combining unit which combines an image processing result of each of the plurality of images obtained by the image processing unit.

Abstract: The invention discloses a method for editing propagation of video and image content based on local feature structure preservation, comprising: mapping all pixels in the input original image and/or video key frames to a selected feature space; finding K nearest neighbor pixels for each pixel according to feature vectors' Euclidean distance in the selected feature space; using Locally Linear Embedding (LLE) dimension reduction to construct the locally linear relationship between each pixel and its K nearest neighbor pixels in the selected feature space; According to the present invention, it is possible to accurately perform such image or video processing as automatic color transformation, interactive color editing, gray image colorization, video cloning and image matting.

Abstract: A video processing device (100) includes: an edge histogram generating section (141) and a noise reducing section (150). The generating section (141) generates an edge histogram of a decoded image obtained from a video signal. The noise reducing section (150) (i) determines whether or not a ratio of a sum of frequencies of classes higher than a predetermined class of an edge histogram to a sum of all frequencies the edge histogram is equal to or greater than a predetermined threshold value and (ii) performs a smoothing process on the decoded image with a smoothing intensity adjusted in accordance with whether or not the ratio is equal to or greater than the predetermined threshold value.

Abstract: A method of displaying images, which includes displaying a first image in a first display portion, receiving a first image-quality condition for setting a first image quality of the first image displayed in the first display portion, generating, via a first display controller of the first display portion, a first image-quality setting image by applying the first image-quality condition to the first image displayed in the first display portion, transmitting the generated first image-quality setting image from the first display controller to a second display controller of a second display portion, and displaying the transmitted first image-quality setting image on the second display portion.

Abstract: A method includes predicting, through a processor of a data processing device communicatively coupled to a memory, a portion of a video frame on which a user of the data processing device is likely to focus on during rendering thereof on a display unit associated with the data processing device. The video frame is part of decoded video data. The method also includes rendering, through the processor, the portion of the video frame on the display unit at an enhanced level compared to other portions thereof following the prediction of the portion of the video frame.

Abstract: A video transmission apparatus includes a video data transmission unit configured to transmit video data to an external apparatus, an image quality parameter acquisition unit configured to acquire an image quality parameter to be used for display of the video data, an image quality parameter generation unit configured to generate, from the image quality parameter acquired by the image quality parameter acquisition unit, image quality parameter information to be used in the external apparatus, and an image quality parameter transmission unit configured to transmit the image quality parameter information generated by the image quality parameter generation unit to the external apparatus.

Abstract: Devices and methods are disclosed for detecting a focus of at least one viewer as being directed to a particular region of a video display. A first portion of a frame of video for presentation in the region of the viewer's focus is processed differently than another portion of the frame of video related to a region that is not part of the viewer's focus.

Abstract: A control device controls a television. The control device includes a touch module. The control device displays a menu containing a number of soft keys on a screen. The soft keys are activated to control the television to carry out corresponding functions. All positions on the menu are associated with all positions on the touch module correspondingly. As a result, a user can select desired soft keys to carry out corresponding functions by viewing the menu on the television and touching the touch module, rather than viewing the touch module.

Abstract: A method to correct for temporal variability in incoming streams of media and data to optimize the performance of a pattern recognition system includes the steps of receiving from one of the incoming streams a point in time when an event is announced, applying a probability distribution about the point in time, shifting a point of highest probability of the probability distribution back in time by an amount effective to accommodate for a delay between the event and the announcement, comparing a detected pattern of the event to a stored pattern of similar events and applying a confidence value to the comparison, and confirming to the pattern recognition system that the event occurred at the point of highest probability when the confidence score exceeds a predefined threshold. The method is useful to determine the time at which a particular play occurs during a sporting event, such as the time of a shot-on-goal in a soccer match.

Abstract: A video processing system receives left and right 3D video and/or graphics frames and generates noise reduced left 3D video, right 3D video and/or graphics frames based on parallax compensated left and right frames. Displacement of imagery and/or pixel structures is determined relative to opposite side left and/or right frames. Parallax vectors are determined for parallax compensated left 3D video, right 3D video and/or graphics frames. A search area for displacement may be bounded by parallax limitations. Left 3D frames may be blended with the parallax compensated right 3D frames. Right 3D frames may be blended with the parallax compensated left 3D frames. The left 3D video, right 3D video and/or graphics frames comprise images that are captured, representative of and/or are displayed at a same time instant or at different time instants. Motion estimation, motion adaptation and/or motion compensation techniques may be utilized with parallax techniques.

Abstract: The invention discloses a method for editing propagation of video and image content based on local feature structure preservation, comprising: mapping all pixels in the input original image and/or video key frames to a selected feature space; finding K nearest neighbor pixels for each pixel according to feature vectors' Euclidean distance in the selected feature space; using Locally Linear Embedding (LLE) dimension reduction to construct the locally linear relationship between each pixel and its K nearest neighbor pixels in the selected feature space; According to the present invention, it is possible to accurately perform such image or video processing as automatic color transformation, interactive color editing, gray image colorization, video cloning and image matting.

Abstract: A recording/reproducing apparatus includes an operating section having dual functions depending on being in an image capture mode or in a reproduction mode respectively. While one of the recording mode and the reproduction mode is being carried out, in response to start of the other mode, a controlling function of the operating section is switched to the function of the other mode, and in response to the completion of the other mode, the function of the operating section is switched to the function of the one mode.

Abstract: A projector projecting an image on an object by scanning the object with a light beam includes a light source; a divergence angle converter converting the divergence angle of the light beam; a light deflector deflecting the light beam in a light beam scanning direction and a direction perpendicular to the light beam scanning direction; alight deflector drive controller controlling the light deflector to form the focused light spots at the respective pixel positions of the object on the basis of positional data for the pixels; a light amount controller controlling light amount of the light beam on the basis of luminance data for the pixels; and an image processor correcting the luminance data on the basis of previously obtained deterioration data of the projected image and outputting the corrected luminance data to the light amount controller while outputting the positional data to the light deflector drive controller.

Abstract: A method and system for generating a cartoon are provided. The method includes receiving a digital image for processing at a server. The method includes executing a color structure coding procedure to produce a color-reduced interim image. The method includes generating a sketch from the digital image with a Difference of Gaussian procedure. The method includes combining the color-reduced interim image and the sketch into a processed cartoon.

Abstract: Provided are a digital video rescaling system, a method of rescaling video images, and a chip comprising a computer executable medium embedded therein computer executable instructions for rescaling video images.

Abstract: A signal processing apparatus includes a lower-level region data detecting section detecting, in luminance data of an input video signal, luminance data corresponding to a value in a set lower-level region, and a data converting section converting a value of the luminance data corresponding to the lower-level region to a set conversion value.

Abstract: An object-based system and method of directing visual attention by a subliminal cue is disclosed. An object detector detects an object in an input image, thereby resulting in a cued object served as an object-based subliminal cue. An enhancement unit enhances saliency of the cued object in the input image by respectively and differently adjusting image characteristic of the cued object and an area other than the cued object, thereby generating a cue image. A mixer selects between the cue image and the input image, thereby resulting in a sequence of output images composed of the input images and the cue images, each of which is interposed between the adjacent input images.

Abstract: The present disclosure includes, among other things, systems, methods and program products for generating a clean reference frame image. A method includes obtaining a color census of a color image. A color profile is selected based on the color census. One or more foreground areas of the image are identified, the foreground areas comprising image areas containing colors that do not fit the color profile. For each identified foreground area, a color is applied to the identified foreground area based on one or more colors of one or more non-identified image areas to create a clean reference image.

Abstract: The invention relates to a method for the continuous transmission of a video from a server to a number of client machines over a communication network, comprising the following steps: obtaining requests from client machines, at least some of the requests obtained each specifying at least one spatial zone of interest in one or more images of the video, a spatial zone representing a set of digital data, processing the requests obtained so as to determine one or more intersections defining common data between the spatial zones of interest of the video, creating a multipoint network session for each intersection thus determined.