知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

211 records (took 0.034 seconds)

    BASE ANCHORED MODELS AND INFERENCE FOR THE COMPRESSION AND UPSAMPLING OF VIDEO AND MULTIVIEW IMAGERY
    22.
    发明申请
    BASE ANCHORED MODELS AND INFERENCE FOR THE COMPRESSION AND UPSAMPLING OF VIDEO AND MULTIVIEW IMAGERY 审中-公开

    公开(公告)号：US20200021824A1

    公开(公告)日：2020-01-16

    申请号：US16335297

    申请日：2017-09-21

    Applicant: KAKADU R & D PTY LTD

    Inventor： David Scott TAUBMAN ,  Dominic Patric RUEFENACHT

    IPC: H04N19/31 ,  H04N19/597 ,  H04N19/177 ,  H04N19/172 ,  H04N19/54

    Abstract: A method of representing displacement information between the frames of a video and/or multiview sequence, comprising the steps of assigning a plurality of the frames to a Group of Pictures (GOPs), providing a base displacement model for each GOP, the base displacement model describing a displacement field that carries each location in a designated base frame of the GOP to a corresponding location in each other the frame of the GOP, and inferring other displacement relationships between the frames of the GOP from the base displacement model. Embodiments include a piecewise smooth displacement field, deformable mesh, reverse displacement field, double mapping, synthesize optical blur and foreground-background discrimination process.

    Feature based high resolution motion estimation from low resolution images captured using an array source
    23.
    发明授权
    Feature based high resolution motion estimation from low resolution images captured using an array source 有权

    公开(公告)号：US10462362B2

    公开(公告)日：2019-10-29

    申请号：US15804149

    申请日：2017-11-06

    Applicant: FotoNation Limited

    Inventor： Dan Lelescu ,  Ankit K. Jain

    IPC: H04N5/232 ,  G06T3/40 ,  H04N19/53 ,  H04N19/54 ,  H04N19/59 ,  G06K9/46 ,  G06K9/62 ,  G06T11/60 ,  G06T7/13 ,  G06T7/246

    Abstract: Systems and methods in accordance with embodiments of the invention enable feature based high resolution motion estimation from low resolution images captured using an array camera. One embodiment includes performing feature detection with respect to a sequence of low resolution images to identify initial locations for a plurality of detected features in the sequence of low resolution images, where the at least one sequence of low resolution images is part of a set of sequences of low resolution images captured from different perspectives. The method also includes synthesizing high resolution image portions, where the synthesized high resolution image portions contain the identified plurality of detected features from the sequence of low resolution images. The method further including performing feature detection within the high resolution image portions to identify high precision locations for the detected features, and estimating camera motion using the high precision locations for said plurality of detected features.

    Method and system for global motion estimation and compensation
    24.
    发明授权
    Method and system for global motion estimation and compensation 有权

    公开(公告)号：US10453207B2

    公开(公告)日：2019-10-22

    申请号：US15748576

    申请日：2016-08-01

    Applicant: VERSITECH LIMITED

    Inventor： Shing Chow Chan ,  Zhong Liu

    IPC: H04N19/00 ,  G06T7/579 ,  H04N19/54 ,  H04N19/527 ,  G06T7/529

    Abstract: It is proposed a Method and System for Global Motion Estimation and Compensation. The system operates on two depth maps which contain a reference depth map and a current depth map as well as their associated texture images if available. The system executes four major steps which are feature detection (step 1), global motion compensation (GMC) (step 2), major moving objects (MMO) detection and the estimation of their motion parameters denoted as major motion parameters (MMPs) (step 3), and local motion compensation (LMC) of macroblocks or other coding/prediction units (step 4). The output of the system is the global motion parameters (GMPs), major moving objects (MMOs) and MMPs, the local motion vectors (LMVs), and the coding modes.

    VIDEO ENCODING AND DECODING BY INHERITANCE OF A FIELD OF MOTION VECTORS
    27.
    发明申请
    VIDEO ENCODING AND DECODING BY INHERITANCE OF A FIELD OF MOTION VECTORS 审中-公开
    通过影像运动矢量的视频编码和解码

    公开(公告)号：US20160219299A1

    公开(公告)日：2016-07-28

    申请号：US15024753

    申请日：2014-09-23

    Applicant: ORANGE

    Inventor： Elie Gabriel Mora ,  Joel Jung ,  Beatrice Pesquet-Popescu ,  Marco Cagnazzo

    IPC: H04N19/52 ,  H04N19/54 ,  H04N19/96 ,  H04N19/597

    CPC classification number: H04N19/52 ,  H04N19/54 ,  H04N19/597 ,  H04N19/96

    Abstract: A method is provided for coding a current image. The method includes determining, in a first image, different from the current image, a group of k′ pixels corresponding to a current group of k pixels (k′≦k) to be coded of the current image; calculating a motion vector between each of the k′ pixels of the first image and a corresponding pixel of a second image different from the current image, on completion of which a field of k′ motion vectors is obtained; and predicting the pixels or of the motion of the current group of k pixels of the current image on the basis of the field of k′ motion vectors which is obtained.

    Abstract translation: 提供了一种用于编码当前图像的方法。 该方法包括：在与第一图像不同的当前图像中确定与当前图像要编码的当前k个像素组（k'≤k）相对应的k个像素组; 计算第一图像的k个像素的每一个与不同于当前图像的第二图像的对应像素之间的运动矢量，其中，获得k个运动矢量的场; 并且基于获得的k个运动矢量的场来预测当前图像的当前k个像素组的像素或运动。

    Method and system for encoding collections of images and videos
    28.
    发明授权
    Method and system for encoding collections of images and videos 有权
    用于编码图像和视频集合的方法和系统

    公开(公告)号：US09338461B2

    公开(公告)日：2016-05-10

    申请号：US13758348

    申请日：2013-02-04

    Applicant: Mitsubishi Electric Research Laboratories, Inc

    Inventor： Dong Tian ,  Anthony Vetro ,  Shantanu Rane

    IPC: H04N7/12 ,  H04N11/02 ,  H04N11/04 ,  H04N19/134 ,  H04N19/54 ,  H04N19/573

    CPC classification number: H04N19/134 ,  H04N19/54 ,  H04N19/573

    Abstract: An input segment of an input video is encoded by first extracting and storing, for each segment of previously encoded videos, a set of reference features. The set of input features are matched with each set of the reference features to produce a set of scores. The reference segments having largest scores are selected to produce a first reduced set of reference segments. A rate-distortion cost for each reference segment in the first reduced set of reference segments is estimated. The reference segments in the first reduced set of reference segments is selected to produce a second reduced set of reference segments. Then, the input segment are encoded based on second reduced set of reference segments.

    Abstract translation: 通过首先对先前编码的视频的每个段提取和存储一组参考特征来编码输入视频的输入段。 输入特征的集合与每组参考特征相匹配以产生一组分数。 选择具有最大分数的参考分段以产生第一缩减的参考分组集合。 估计第一组缩减的参考段中每个参考段的速率失真成本。 选择第一缩减的参考段集合中的参考段以产生第二缩减的参考段集合。 然后，基于第二缩减的参考片段编码输入片段。

    System and method for exploiting scene graph information in construction of an encoded video sequence
    29.
    发明授权
    System and method for exploiting scene graph information in construction of an encoded video sequence 有权
    用于在编码视频序列的构造中利用场景图信息的系统和方法

    公开(公告)号：US09219922B2

    公开(公告)日：2015-12-22

    申请号：US13911948

    申请日：2013-06-06

    Applicant: ActiveVideo Networks, Inc.

    Inventor： Ronald Alexander Brockmann ,  Anuj Dev ,  Maarten Hoeben

    IPC: G06K9/36 ,  H04N19/54 ,  H04N19/56

    CPC classification number: H04N19/54 ,  H04N19/56

    Abstract: A system method and computer program product for creating a composited video frame sequence for an application. A current scene graph state for the application is compared to a previous scene graph state wherein each scene graph state includes a plurality of hierarchical nodes that represent one or more objects at each node. A video construction engine determines if one or more objects have moved based upon a comparison of the scene graph states. If one or more objects have moved based upon the scene graph comparison, motion information about the objects is determined and the motion information is forwarded to a stitcher module. The motion information is used to define motion vectors for use by the stitcher module in construction of the composited video frame sequence.

    Abstract translation: 一种用于为应用创建合成视频帧序列的系统方法和计算机程序产品。 将应用的当前场景图状态与先前的场景图状态进行比较，其中每个场景图状态包括表示每个节点处的一个或多个对象的多个分层节点。 视频构造引擎基于场景图状态的比较来确定一个或多个对象是否已经移动。 如果一个或多个对象已经基于场景图比较移动，则确定关于对象的运动信息，并将运动信息转发到拼接模块。 运动信息用于定义运动矢量供拼接模块在合成视频帧序列的构造中使用。

Patent Agency Ranking