中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

38 records (took 0.038 seconds)

    Principal component analysis based seed generation for clustering analysis
    21.
    发明授权
    Principal component analysis based seed generation for clustering analysis 有权
    基于主成分分析的种子生成用于聚类分析

    公开(公告)号：US08660370B1

    公开(公告)日：2014-02-25

    申请号：US13755373

    申请日：2013-01-31

    Applicant: Google Inc.

    Inventor： Sangho Yoon ,  Jay N. Yagnik ,  Mei Han ,  Vivek Kwatra

    IPC: G06K9/62

    CPC classification number: G06K9/6247 ,  G06K9/6223

    Abstract: Clustering algorithms such as k-means clustering algorithm are used in applications that process entities with spatial and/or temporal characteristics, for example, media objects representing audio, video, or graphical data. Feature vectors representing characteristics of the entities are partitioned using clustering methods that produce results sensitive to an initial set of cluster seeds. The set of initial cluster seeds is generated using principal component analysis of either the complete feature vector set or a subset thereof. The feature vector set is divided into a desired number of initial clusters and a seed determined from each initial cluster.

    Abstract translation: 诸如k均值聚类算法的聚类算法被用于处理具有空间和/或时间特征的实体的应用中，例如表示音频，视频或图形数据的媒体对象。 使用产生对初始集群种子集合敏感的结果的聚类方法对代表实体特征的特征向量进行分区。 使用完整特征向量集或其子集的主成分分析来生成初始簇种子集合。 特征向量集合被分为期望数量的初始簇和从每个初始簇确定的种子。

    CASCADED CAMERA MOTION ESTIMATION, ROLLING SHUTTER DETECTION, AND CAMERA SHAKE DETECTION FOR VIDEO STABILIZATION
    26.
    发明申请
    CASCADED CAMERA MOTION ESTIMATION, ROLLING SHUTTER DETECTION, AND CAMERA SHAKE DETECTION FOR VIDEO STABILIZATION 有权
    CASCADED CAMERA运动估计，滚动快门检测和视频稳定的相机SHAKE检测

    公开(公告)号：US20160269642A1

    公开(公告)日：2016-09-15

    申请号：US15150069

    申请日：2016-05-09

    Applicant: Google Inc.

    Inventor： Matthias Grundmann ,  Vivek Kwatra ,  Irfan Essa

    IPC: H04N5/232 ,  G06T7/20

    CPC classification number: H04N5/23267 ,  G06K9/00718 ,  G06K9/00744 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/30244 ,  H04N5/23248 ,  H04N5/23254 ,  H04N5/2329

    Abstract: An easy-to-use online video stabilization system and methods for its use are described. Videos are stabilized after capture, and therefore the stabilization works on all forms of video footage including both legacy video and freshly captured video. In one implementation, the video stabilization system is fully automatic, requiring no input or parameter settings by the user other than the video itself. The video stabilization system uses a cascaded motion model to choose the correction that is applied to different frames of a video. In various implementations, the video stabilization system is capable of detecting and correcting high frequency jitter artifacts, low frequency shake artifacts, rolling shutter artifacts, significant foreground motion, poor lighting, scene cuts, and both long and short videos.

    Abstract translation: 描述了一种易于使用的在线视频稳定系统及其使用方法。 视频在拍摄后稳定，因此稳定性适用于所有形式的视频素材，包括传统视频和新鲜捕获的视频。 在一个实现中，视频稳定系统是全自动的，除了视频本身之外，不需要用户的输入或参数设置。 视频稳定系统使用级联运动模型来选择应用于视频的不同帧的校正。 在各种实施方案中，视频稳定系统能够检测和校正高频抖动伪像，低频抖动伪影，滚动快门伪像，显着的前景运动，差的照明，场景切换以及长视频和短视频。

    Systems and methods for resizing an image
    27.
    发明授权
    Systems and methods for resizing an image 有权
    调整图像大小的系统和方法

    公开(公告)号：US09424479B2

    公开(公告)日：2016-08-23

    申请号：US14517423

    申请日：2014-10-17

    Applicant: Google Inc.

    Inventor： Mayur Datar ,  Huei-Hung Christopher Liao ,  Vivek Kwatra ,  Allen Huang

    IPC: G06K9/32 ,  G06K9/18 ,  G06T3/00

    CPC classification number: G06K9/18 ,  G06T3/0012

    Abstract: In some instances, an image may have dimensions that do not correspond to a slot to display the image. For example, an image content item may have dimensions that do not correspond to a content item slot. The image may be resized using seam carving to add or remove pixels of the image. A saliency map for the image may be used having saliency scores for each pixel of the image. Evaluation metrics may be used before, during, and after, seam carving to determine whether salient content is affected by the seam carving. In some instances, a seam cost threshold value may be used for adaptive step size during the seam carving. The resized image may then be outputted, such as for an image content item to be served with a resource.

    Abstract translation: 在某些情况下，图像可能具有不对应于显示图像的时隙的尺寸。 例如，图像内容项目可以具有与内容项目时隙不对应的维度。 可以使用接缝雕刻来调整图像的大小，以添加或删除图像的像素。 可以使用图像的显着图，其具有图像的每个像素的显着性分数。 评估指标可以在缝合雕刻之前，之中和之后使用，以确定显着含量是否受到缝合雕刻的影响。 在一些情况下，在缝合雕刻期间可以使用接缝成本阈值用于自适应步长。 然后可以输出调整大小的图像，例如用于要与资源一起服务的图像内容项目。

    Cascaded camera motion estimation, rolling shutter detection, and camera shake detection for video stabilization
    28.
    发明授权
    Cascaded camera motion estimation, rolling shutter detection, and camera shake detection for video stabilization 有权
    级联相机运动估计，滚动快门检测和用于视频稳定的相机抖动检测

    公开(公告)号：US09374532B2

    公开(公告)日：2016-06-21

    申请号：US13854819

    申请日：2013-04-01

    Applicant: Google Inc.

    Inventor： Matthias Grundmann ,  Vivek Kwatra ,  Irfan Essa

    IPC: H04N5/232 ,  G06T7/20

    CPC classification number: H04N5/23267 ,  G06K9/00718 ,  G06K9/00744 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/30244 ,  H04N5/23248 ,  H04N5/23254 ,  H04N5/2329

    Abstract: An easy-to-use online video stabilization system and methods for its use are described. Videos are stabilized after capture, and therefore the stabilization works on all forms of video footage including both legacy video and freshly captured video. In one implementation, the video stabilization system is fully automatic, requiring no input or parameter settings by the user other than the video itself. The video stabilization system uses a cascaded motion model to choose the correction that is applied to different frames of a video. In various implementations, the video stabilization system is capable of detecting and correcting high frequency jitter artifacts, low frequency shake artifacts, rolling shutter artifacts, significant foreground motion, poor lighting, scene cuts, and both long and short videos.

    Abstract translation: 描述了一种易于使用的在线视频稳定系统及其使用方法。 视频在拍摄后稳定，因此稳定性适用于所有形式的视频素材，包括传统视频和新鲜捕获的视频。 在一个实现中，视频稳定系统是全自动的，除了视频本身之外，不需要用户的输入或参数设置。 视频稳定系统使用级联运动模型来选择应用于视频的不同帧的校正。 在各种实施方案中，视频稳定系统能够检测和校正高频抖动伪像，低频抖动伪影，滚动快门伪像，显着的前景运动，差的照明，场景切换以及长视频和短视频。

    Methods and systems for video retargeting using motion saliency
    29.
    发明授权
    Methods and systems for video retargeting using motion saliency 有权
    使用运动显着性进行视频重新定位的方法和系统

    公开(公告)号：US09167221B2

    公开(公告)日：2015-10-20

    申请号：US14058411

    申请日：2013-10-21

    Applicant: Google Inc.

    Inventor： Matthias Grundmann ,  Vivek Kwatra

    IPC: H04N5/93 ,  G11B27/00 ,  H04N9/80 ,  H04N9/87 ,  H04N21/2187 ,  H04N21/234 ,  H04N21/2343 ,  H04N21/854 ,  H04N9/64 ,  H04N5/14 ,  H04N5/225 ,  H04N21/4728

    CPC classification number: H04N9/87 ,  H04N5/145 ,  H04N5/225 ,  H04N21/2187 ,  H04N21/23418 ,  H04N21/234345 ,  H04N21/4728 ,  H04N21/854

    Abstract: Methods and systems for video retargeting and view selection using motion saliency are described. Salient features in multiple videos may be extracted. Each video may be retargeted by modifying the video to preserve the salient features. A crop path may be estimated and applied to a video to retarget each video and generate a modified video preserving the salient features. An action score may be assigned to portions or frames of each modified video to represent motion content in the modified video. Selecting a view from one of the given modified videos may be formulated as an optimization subject to constraints. An objective function for the optimization may include maximizing the action score. This optimization may also be subject to constraints to take into consideration optimal transitioning from a view from a given video to another view from another given video, for example.

    Abstract translation: 描述了使用运动显着的视频重定向和视图选择的方法和系统。 可以提取多个视频中的显着特征。 可以通过修改视频来重定向每个视频以保持显着特征。 可以估计裁剪路径并将其应用于视频以重新定位每个视频，并生成保留显着特征的修改的视频。 可以将动作得分分配给每个经修改的视频的部分或帧以表示经修改的视频中的运动内容。 从给定的修改的视频之一选择视图可以被制定为受约束的优化。 优化的目标函数可以包括最大化动作得分。 例如，这种优化也可能受到约束，以考虑从给定视频的视图到另一给定视频的另一视图的最佳转换。

    IMAGE DENOISING SYSTEM AND METHOD
    30.
    发明申请
    IMAGE DENOISING SYSTEM AND METHOD 有权
    图像吸收系统和方法

    公开(公告)号：US20140119664A1

    公开(公告)日：2014-05-01

    申请号：US13665449

    申请日：2012-10-31

    Applicant: Google Inc.

    Inventor： Sergey Ioffe ,  Troy Chinen ,  Vivek Kwatra ,  Hui Fang ,  Yichang Shih

    IPC: G06K9/40

    CPC classification number: G06T5/002 ,  G06K9/00221 ,  G06K9/00261 ,  G06K9/40 ,  G06T5/005 ,  G06T5/20 ,  G06T5/50 ,  G06T2207/10004 ,  G06T2207/10016 ,  G06T2207/20028 ,  G06T2207/20182 ,  G06T2207/20216 ,  G06T2207/30201

    Abstract: A method, computer program product, and computer system for identifying a first portion of a facial image in a first image, wherein the first portion includes noise. A corresponding portion of the facial image is identified in a second image, wherein the corresponding portion includes less noise than the first portion. One or more filter parameters of the first portion are determined based upon, at least in part, the first portion and the corresponding portion. At least a portion of the noise from the first portion is smoothed based upon, at least in part, the one or more filter parameters. At least a portion of face specific details from the corresponding portion is added to the first portion.

    Abstract translation: 一种用于识别第一图像中的面部图像的第一部分的方法，计算机程序产品和计算机系统，其中所述第一部分包括噪声。 面部图像的相应部分在第二图像中被识别，其中对应部分包括比第一部分少的噪声。 至少部分地基于第一部分和对应部分来确定第一部分的一个或多个过滤器参数。 至少部分地基于一个或多个过滤器参数来平滑来自第一部分的噪声的至少一部分。 来自相应部分的面部特定细节的至少一部分被添加到第一部分。

Patent Agency Ranking