Abstract: Provided is a method derives a reference picture index and a motion vector of a current prediction unit, generates a prediction block of the current prediction unit using the reference picture index and the motion vector, generating a residual block by inverse-scan, inverse-quantization and inverse transform, and generates reconstructed pixels using the prediction block and the residual block. Prediction pixels of the prediction block is generated using an interpolation filter selected based on the motion vector. Accordingly, the coding efficiency of the motion information is improved by including various merge candidates. Also, the computational complexity of an encoder and a decoder is reduced by selecting different filter according to location of the prediction pixels determined by the motion vector.

Abstract: An electronic apparatus having at least two camera devices and a processing device. The processing device: determines a first length between an object positioned at a first time and a surface formed by the two camera devices, determines a second length between the object positioned at a second time and the surface, determines a third length between the object positioned at a third time and the surface, and determines a depth in a virtual space corresponding to the object positioned at the third time according to the first length, the second length, and the third length. In operation, the third time is later than the first time and the second time, and the third length is longer than the first length and shorter than the second length.

Abstract: An imaging apparatus includes a first detector configured to detect an elapsed time after starting to shoot an image in a specific shooting mode for shooting the image by moving the imaging apparatus in a predetermined shooting direction, a second detector configured to detect amount of movement of the imaging apparatus, and a controller configured to control display of a display unit to display, in the specific shooting mode, a first indicator fixedly positioned on the display unit and a second indicator movably positioned on the display unit. The controller decides a first amount of movement in the predetermined shooting direction according to the detected elapsed time and a second amount of movement in an opposite direction according to the detected amount of movement of the imaging apparatus, and controls a display position of the second indicator based on the first and second amounts of movement.

Abstract: Provided is a method derives a reference picture index and a motion vector of a current prediction unit, generates a prediction block of the current prediction unit using the reference picture index and the motion vector, generating a residual block by inverse-scan, inverse-quantization and inverse transform, and generates reconstructed pixels using the prediction block and the residual block. Prediction pixels of the prediction block is generated using an interpolation filter selected based on the motion vector. Accordingly, the coding efficiency of the motion information is improved by including various merge candidates. Also, the computational complexity of an encoder and a decoder is reduced by selecting different filter according to location of the prediction pixels determined by the motion vector.

Abstract: Video analytics systems and methods are described that typically comprise a video encoder operable to generate macroblock video analytics metadata (VAMD) from a video frame. Functional modules receive the VAMD and an encoded version of the video frame is configured to generate video analytics information related to the frame using the VAMD and the encoded video frame. The downstream decoder can use the VAMD to obtain a global motion vector related to the frame, detect and track motion of an object within the frame and monitor a line provided or found within the frame. Traversals of the line by a moving object can be detected and counted using information in the VAMD and the line may be part of a polygon that delineates an area to be monitored within the encoded frame. The VAMD can comprise macroblock level and video frame level information.

Abstract: Embodiments of the invention receive videos and feedback data associated with the videos from a client device and adaptively encode the videos based on the feedback data. The encoded videos are suitable to be transmitted over a network and displayed on the client device. Embodiments of an encoding server adaptively changes resolution of a video on the fly or scale the video quality up or down based on the factors described by the feedback data, including network condition for transmitting the encoded video, network delay, encoder and decoder processing capacity and feedback from viewers of the decoded video. Furthermore, the encoding server adaptively encodes the video based on a combination of various factors described by the feedback data.

Abstract: A computer-implemented method includes detecting, at a wearable computing device, a first direction of a first stare, wherein the wearable computing device includes a head-mountable display unit, identifying a target based on the detected first direction, and based on a determination that a first time duration of the first stare is greater than or equal to a first predetermined time threshold, identifying information relevant to the target and displaying the identified information on the display unit. Subsequent to displaying the identified information, the method includes detecting a second stare that is directed at the target or at the displayed information, and based on a determination that a second time duration of the second stare is greater than or equal to a second predetermined time threshold, identifying additional information relevant to the target, and displaying the additional information on the display unit.

Abstract: An image processing device includes: a memory; and a processor coupled to the memory and configured to: obtain image data regarding an image captured by an image capture device that moves along with a moving body and of which image capture direction is a certain traveling direction of the moving body, and detect a feature caused by a reflection from features based on information regarding positions of the features in the image data at a time when the moving body has moved in a direction different from the image capture direction.

Abstract: An imaging apparatus includes: a first imaging device including a first filter, and configured to output a first image signal, and the first filter preventing light in a predetermined wavelength band of wavelengths longer than visible light; a second imaging device arranged at a different position and configured to perform photoelectric conversion on subject light containing a wavelength component of the light in the predetermined wavelength band to output a second image signal; a correlation detection unit configured to detect a correlation between the first and second image signals; a luminance signal generation unit configured to generate a luminance signal; a color signal generation unit configured to generate a color signal; and a three-dimensional image generation unit configured to generate a three-dimensional image by the correlation, the luminance signal, and the color signal.

Abstract: Techniques are provided for tracking objects in an encoded video stream based on data directly extracted from the video stream, thus eliminating any need for the stream to be fully or partially decoded. Extracted motion vector and DC coefficient data can be used to provide a rough estimation of which macro-blocks are be associated with a background motion model and which macro-blocks correspond to a foreground object which is moving with respect to the background motion model. Macro-blocks which are associated with a moving foreground object can be grouped based on connectivity and a similarity measure derived from the extracted DC coefficient data. The grouped macro-blocks can be tracked from frame to frame to identify and eliminate groups having only negligible motion. The resulting validated macro-block groups will correspond to a rough object mask associated with a moving region in the analyzed frame.

Abstract: Approaches enable display of image content (e.g., still or video content), providing an appearance or view based at least in part upon a current relative position and/or orientation of the viewer with respect to the device, and changes in that relative position and/or orientation. Image content is rendered consistent with a viewing angle for the current relative position of the viewer. As that viewing angle changes, the content can be re-rendered or otherwise updated to display the image content from a perspective that reflects the change in viewing angle. Different adjustments can be applied to portions of the content based upon the change in viewing angle. These adjustments can include changes due to parallax or occlusion, which when added to the rendered content enhance the viewer experience and increase realism for content rendered on a two- or three-dimensional display screen.

Abstract: Multi-layered video structures are scaled over a range of perceived quality levels. An estimated Mean Opinion Score (eMOS)-based encoder control loop is utilized to determine one or more encoder key performance index (KPI) associated with a particular perceived quality level. A KPI-based encoder control loop is then utilized to guide generation of a hierarchical structure having quality and/or temporal and/or spatial enhancement layers, without recalculating eMOS for the scalable structure. In addition, eMOS is used to guide the generation of a hierarchical structure at best-perceived quality levels for a given bitrate budget. Rate adaptation may occur by dropping segments, changing hierarchical structure, or changing the KPI target values. With the structure scaled as a function of perceived quality, perceived quality is impacted predictably as the encoding rate is adapted.

Abstract: The disclosed apparatus, systems, and methods provide for a displacement sensor with a multi-position image sensor. The displacement sensor includes an optical lens. The displacement sensor includes an image sensor configured to view an object through the lens along a plane of focus that is not parallel to an image plane of the image sensor. The displacement sensor includes a laser for illuminating the object by the displacement sensor, wherein the laser is: spaced from the lens at a fixed distance, and configured to project a line of light along the plane of focus of the image sensor. The displacement sensor comprises a first configuration wherein the image sensor is at a first location along an image plane with a first field of view along the plane of focus, and a second configuration at a second location with a different field of view.

Abstract: In an example, a method of coding video data includes determining a location of a reference sample associated with a reference picture of video data based on one or more scaled offset values, where the reference picture is included in a first layer of a multi-layer bitstream and the one or more scaled offset values indicate a difference in scale between the first layer and a second, different layer. The method also includes determining a location of a collocated reference block of video data in the first layer based on the location of the reference sample, and coding a current block of video data in the second layer relative to the collocated reference block.

Abstract: A vehicle 1 towing a trailer 4 is fitted with three video cameras 5, 6, 7 fitted to the rear of the vehicle and on each door mirror. A view from any camera can be presented to the driver on a display 11. A predicted trailer path, calculated in a computing unit 10, is also presented to the driver on the display 11 as guide lines overlaid on the camera view. The computing unit 10 is also configured to calculate a hitch angle by tracking the position of a trailer-mounted marker in the camera view.

Abstract: Methods and apparatus are provided for video image pruning. An apparatus includes a data pruner for pre-processing a picture prior to, and in preparation for, compression by encoding. The data pruner selectively removes, in the spatial domain, at least one region within the picture. At the decoder end, an apparatus includes a data restorer for receiving a decompressed picture subsequent to decompression by decoding, and post-processing the decompressed picture by selectively restoring, in the spatial domain, at least one region in the decompressed picture based on information indicating a removal of the at least one region prior to a previously performed encoding process.

Abstract: The present invention relates to a method for signaling image information and to a decoding method using same. The method for signaling image information according to the present invention comprises: a step of performing inter-prediction for a current picture; and a step of signaling information including the result of said inter-prediction and reference picture information indicating reference pictures usable in said inter prediction, wherein said reference picture information contains pieces of picture order count (POC) information of said usable reference pictures. The POC information of said usable reference pictures in said reference picture information is configured such that POCs for the pictures existing before said current picture in terms of a POC sequence are located at the front, and POCs for the pictures existing after said current picture in terms of a POC sequence are located following the POCs located at the front.

Abstract: In palette-based coding, a video coder may form a so-called “palette” as a table of colors representing the video data of a given block. The video coder may code index values for one or more pixels values of a current block of video data, where the index values indicate entries in the palette that represent the pixel values of the current block. According to the techniques, a video coder determines one or more palette entries in a predictive palette that are copied to the current palette, and a number of new palette entries not in the predictive palette that are included in the current palette. The video coder calculates a size of the current palette equal to the sum of the number of the copied palette entries and the number of the new palette entries, and generates the current palette including the copied palette entries and the new palette entries.

Abstract: In a system that monitors the positions and movements of objects within an environment, a depth camera may be configured to produce depth images based on configurable measurement parameters such as illumination intensity and sensing duration. A supervisory component may be configured to roughly identify objects within an environment and to specify observation goals with respect to the objects. The measurement parameters of the depth camera may then be configured in accordance with the goals, and subsequent analyses of the environment may be based on depth images obtained using the measurement parameters.

Abstract: Relating to the field of video coding, a method and an apparatus for building a motion vector list for motion vector prediction, which solve a problem of building motion vector lists of at least two PUs in a same coding unit in a serial manner, and improve the parallel processing capability. The method includes: obtaining spatial neighboring blocks of a current prediction block, where the current prediction block is located inside a current coding unit; determining available neighboring blocks of the current prediction block according to a partition manner of the current coding unit, where the available neighboring blocks are located outside the current coding unit; and obtaining motion vector predictors from the available neighboring blocks in a preset sequence according to motion vector predictors of the available neighboring blocks, and adding the obtained motion vector predictors to the motion vector list.