Abstract: Provided are methods and apparatus for tracking a head pose with online face template reconstruction. The method comprises the steps of retrieving a plurality of frames of images of the user; comparing each of the retrieved frames with a predetermined face template to determine one or more head poses that are monitored successfully and obtain head pose information of the determined one or more head poses; and reconstructing, during the step of comparing, the face template from the obtained head pose information; wherein the reconstructed face template is compared with subsequently retrieved images such that the head poses of the user are tracked in time.

Abstract: Provided are methods and apparatus for tracking a head pose with online face template reconstruction. The method comprises the steps of retrieving a plurality of frames of images of the user; comparing each of the retrieved frames with a predetermined face template to determine one or more head poses that are monitored successfully and obtain head pose information of the determined one or more head poses; and reconstructing, during the step of comparing, the face template from the obtained head pose information; wherein the reconstructed face template is compared with subsequently retrieved images such that the head poses of the user are tracked in time.

Abstract: Subject matter disclosed herein relates to foreground image extraction and image depth of video images.

Abstract: The present invention relates to method and apparatus for video coding by ABT-based just noticeable difference (JND). For building the just noticeable difference model, spatial content information (SCI) is used to represent the spatial appearance similarity between one macroblock and its sub-blocks and the motion characteristic distance (MCD) is used to represent the motion characteristics similarity between one macroblock and its sub-blocks. For intra frames, the balance strategy based on the obtained SCI of the macroblock is used to generate the ABT-based JND model. For inter frames, the balanced strategy based on the obtained SCI and MCD of the macroblock is used to generate the ABT-based JND model. Using the ABT-based JND model, the residual coefficients for each block in a frame is filtered to obtain a reduced set of residual coefficients for transmission without degradation in visual quality.

Abstract: In a motion compensated prediction process, a parametric interpolation filter (PIF) device is provided that takes into account the time-variant statistics of video sources, the filter being represented by a model determined by five parameters instead of by individual coefficients. The parameters are calculated and coded on a frame-by-frame basis to minimize the energy of the prediction error for each frame. The model design is based on the fact that high frequency energy of an HD video source is mainly distributed along the vertical and horizontal directions of a frame. A PIF device with the method according to the invention overcomes this obstacle because it represents each filter using only five parameters, all of which are encoded using sufficiently high precision without substantially increasing overhead.

Abstract: In a human feature recognition system that is intended to provide substantially real-time recognition of body segments, various methods and structures are provided to facilitate real-time recognition with reduced computation requirements, including a face detection module employing an active boosting procedure and a lazy boosting procedure on a hybrid cascade structure, a human body segmentation module and a boundary matting module. The hybrid cascade structure is in the form of a tree where one type of node represents a strong classifier learned from active boosting, another type of classifier is obtained by low-computation-load lazy boosting, and weak classifiers are obtained from the previous layers.

Abstract: The invention is used in video coding. Systems, apparatuses and methods for processing an order-16 integer transform from an order-8 transform are provided. The order-16 transform method involves expanding an order-8 transform by generating an order-16 integer matrix and a scaling matrix.

Abstract: Method and apparatus for recognizing landmark buildings in an image and then locating the recognized landmark buildings onto a map together with related information wherein a first database is employed to store models formed by mathematical set descriptions of landmark buildings which are learned from a set of training images of a model-learning module captured by an imaging device for each building, and a second database is employed to store the related information of each landmark building. The model of each landmark building is represented as a set of features and the geometric relationship between them by clustering the salient features extracted from a set of training images of the landmark building.

Abstract: The presently claimed invention adaptively selects a local de-interlacing method according to information from a compressed video bitstream. According to one embodiment, successive images from a video bitstream are first reconstructed. Syntax elements, selected from a macroblock type, a macroblock partition, a motion vector, a distance from a reference frame, the existence of non-zero transform coefficients and the distribution of transform coefficients, are then extracted from this bitstream. Based on the syntax elements, a de-interlacing algorithm is decided from an algorithm set for each image region in a video frame. Algorithms in the algorithm set include motion compensation, edge-based line averaging, and line averaging. Each image region is thereby interpolated using the de-interlacing algorithm and complementary motion compensation. The complementary motion compensation de-interlaces the image region using an inverse of motion vectors extracted from a bitstream clip representing neighboring frames.

Abstract: The present invention relates to method and apparatus for video coding by ABT-based just noticeable difference (JND). For building the just noticeable difference model, spatial content information (SCI) is used to represent the spatial appearance similarity between one macroblock and its sub-blocks and the motion characteristic distance (MCD) is used to represent the motion characteristics similarity between one macroblock and its sub-blocks. For intra frames, the balance strategy based on the obtained SCI of the macroblock is used to generate the ABT-based JND model. For inter frames, the balanced strategy based on the obtained SCI and MCD of the macroblock is used to generate the ABT-based JND model. Using the ABT-based JND model, the residual coefficients for each block in a frame is filtered to obtain a reduced set of residual coefficients for transmission without degradation in visual quality.

Abstract: Method and apparatus for recognizing landmark buildings in an image and then locating the recognized landmark buildings onto a map together with related information wherein a first database is employed to store models formed by mathematical set descriptions of landmark buildings which are learned from a set of training images of a model-learning module captured by an imaging device for each building, and a second database is employed to store the related information of each landmark building. The model of each landmark building is represented as a set of features and the geometric relationship between them by clustering the salient features extracted from a set of training images of the landmark building.

Abstract: In a motion compensated prediction process, a parametric interpolation filter (PIF) device is provided that takes into account the time-variant statistics of video sources, the filter being represented by a model determined by five parameters instead of by individual coefficients. The parameters are calculated and coded on a frame-by-frame basis to minimize the energy of the prediction error for each frame. The model design is based on the fact that high frequency energy of an HD video source is mainly distributed along the vertical and horizontal directions of a frame. A PIF device with the method according to the invention overcomes this obstacle because it represents each filter using only five parameters, all of which are encoded using sufficiently high precision without substantially increasing overhead.

Abstract: Methods of decoding video bitstreams and related devices are disclosed. The claimed methods include reconstructing video frames from a video bitstream 101; extracting a plurality of syntax elements from the video bitstream 101; deciding a de-interlacing algorithm from an algorithm set for each image region in a video frame based on the syntax elements where the algorithm set includes complementary motion compensation; and interpolating at least one of the macroblocks 532 using complementary motion compensation. The complementary motion compensation interpolates image pixels in a macroblock 532 by reference to immediately neighboring frames 520.

Abstract: In a human feature recognition system that is intended to provide substantially real-time recognition of body segments, various methods and structures are provided to facilitate real-time recognition with reduced computation requirements, including a face detection module employing an active boosting procedure and a lazy boosting procedure on a hybrid cascade structure, a human body segmentation module and a boundary matting module. The hybrid cascade structure is in the form of a tree where one type of node represents a strong classifier learned from active boosting, another type of classifier is obtained by low-computation-load lazy boosting, and weak classifiers are obtained from the previous layers.

Abstract: The invention is used in video coding. Systems, apparatuses and methods for processing an order-16 integer transform from an order-8 transform are provided. The order-16 transform method involves expanding an order-8 transform by generating an order-16 integer matrix and a scaling matrix.