中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

17 records (took 0.019 seconds)

    TWO WAY LOCAL FEATURE MATCHING TO IMPROVE VISUAL SEARCH ACCURACY
    2.
    发明申请
    TWO WAY LOCAL FEATURE MATCHING TO IMPROVE VISUAL SEARCH ACCURACY 审中-公开
    两路本地功能匹配提高视觉搜索精度

    公开(公告)号：US20140195560A1

    公开(公告)日：2014-07-10

    申请号：US14060314

    申请日：2013-10-22

    Applicant: Samsung Electronics Co., LTD

    Inventor： Xin Xin ,  Zhu Li ,  Abhishek Nagar ,  Gaurav Srivastava ,  Zhan Ma ,  Kong Posh Bhat ,  Felix Carlos Fernandes

    IPC: G06F17/30

    CPC classification number: G06F16/583

    Abstract: To improve precision of visual search processing, SIFT points within a query image are forward matched to features in each of a plurality of repository images and SIFT points within each repository image are backward matched to features within the query image. Forward-only, backward-only and forward-and-backward matches may be weighted differently in determining an image match. Two way matching may be triggered by query image bit rate in excess of a threshold or by a sum of weighted distances between matching points exceeding a threshold. Significant performance gains in eliminating false positive matches are achieved.

    Abstract translation: 为了提高视觉搜索处理的精度，查询图像内的SIFT点与多个存储库图像中的每一个中的特征向前匹配，并且每个储存库图像内的SIFT点与查询图像内的特征反向匹配。 在确定图像匹配时，仅向前，向后和向前和向后的匹配可以被不同地加权。 可以通过超过阈值的查询图像比特率或超过阈值的匹配点之间的加权距离之和来触发双向匹配。 实现消除假阳性匹配的显着性能提升。

    VISUAL SEARCH ACCURACY WITH HAMMING DISTANCE ORDER STATISTICS LEARNING
    4.
    发明申请
    VISUAL SEARCH ACCURACY WITH HAMMING DISTANCE ORDER STATISTICS LEARNING 审中-公开
    可视化搜索精度与汉堡距离订单统计学习

    公开(公告)号：US20140201200A1

    公开(公告)日：2014-07-17

    申请号：US14153907

    申请日：2014-01-13

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Zhu Li ,  Abhishek Nagar ,  Kong Posh Bhat ,  Xin Xin ,  Gaurav Srivastava ,  Felix Carlos Fernandes

    IPC: G06F17/30

    CPC classification number: G06F16/532 ,  G06F16/583 ,  G06K9/4676 ,  G06K9/6212 ,  G06K9/6215

    Abstract: Global descriptors for images within an image repository accessible to a visual search server are compared based on order statistics processing including sorting (which is a non-linear transform) and heat kernel matching. Affinity scores are computed for Hamming distances between Fisher vector components corresponding to different clusters of global descriptors from a pair of images and normalized to [0, 1], with zero affinity scores assigned to non-active cluster pairs. Linear Discriminant Analysis is employed to determine a sorted vector of affinity scores to obtain a new global descriptor. The resulting global descriptors produce significantly more accurate matching.

    Abstract translation: 基于包括排序（其是非线性变换）和热核心匹配的顺序统计处理来比较可视搜索服务器可访问的图像存储库内的图像的全局描述符。 计算对应于来自一对图像的全局描述符的不同簇的Fisher向量分量之间的汉明距离的归一化分数，并归一化为[0,1]，其中零亲和度分数分配给非活动簇对。 线性判别分析用于确定亲和度分数的排序向量以获得新的全局描述符。 所产生的全局描述符产生明显更准确的匹配。

    Method and system for complexity adaptive streaming
    6.
    发明授权
    Method and system for complexity adaptive streaming 有权

    公开(公告)号：US09967302B2

    公开(公告)日：2018-05-08

    申请号：US14076998

    申请日：2013-11-11

    Applicant: Samsung Electronics Co., LTD

    Inventor： Youngkwon Lim ,  Zhan Ma ,  Kong Posh Bhat ,  Felix C. A. Fernandes

    IPC: H04N21/2381 ,  H04L29/06

    CPC classification number: H04L65/4084 ,  H04L65/602 ,  H04L65/80

    Abstract: A method includes calculating a complexity value for each segment or version of multimedia content. The multimedia content has multiple versions associated with common content and different encoding parameters, and each version is divided into segments. The method also includes adaptively streaming the multimedia content to a client device based on at least some of the calculated complexity values. The complexity value for each segment or version is calculated by summing multiple operation complexity values defining complexities of operations for decoding the segment or version. The operation complexity values could include values for a bit parsing operation, a buffer initialization operation, an intra-prediction operation, an inverse quantization and transform operation, a reference block fetch operation, a fractional interpolation operation, and in-loop deblocking operation, a sample adaptive offset correction operation, an adaptive loop filtering operation, and a de-ringing filtering operation.

    Robust keypoint feature selection for visual search with self matching score
    7.
    发明授权
    Robust keypoint feature selection for visual search with self matching score 有权
    强大的关键点特征选择用于自我匹配得分的视觉搜索

    公开(公告)号：US09235780B2

    公开(公告)日：2016-01-12

    申请号：US14101047

    申请日：2013-12-09

    Applicant: Samsung Electronics Co., LTD

    Inventor： Zhu Li ,  Xin Xin ,  Abhishek Nagar ,  Gaurav Srivastava ,  Kong Posh Bhat ,  Felix Carlos Fernandes

    IPC: G06K9/68 ,  G06K9/62 ,  G06K9/46

    CPC classification number: G06K9/6211 ,  G06K9/4671

    Abstract: To improve feature selection accuracy during a visual search, interest points within a query image are two-way matched to features in an affine transformed image or otherwise transformed version of the query image. A user device implements a method for selecting local descriptors in the visual search. The method includes: detecting a first set of interest points for the original image; computing an affine transform matrix; computing a new image as a transformation of the original image using the affine transform matrix; detecting a second set of interest points from the and new image; performing a two-way matching between the first set of interest points and the second set of interest points; sorting matching pairs according to a specified self-matching score (SMS); assigning an infinite value to SMS of unmatched interest points from the original image; selecting the interest points based on SMS. Significant performance gains reduce false positive matches.

    Abstract translation: 为了在视觉搜索期间提高特征选择精度，查询图像内的兴趣点与仿射变换图像中的特征或查询图像的其他变换版本进行双向匹配。 用户设备实现在视觉搜索中选择本地描述符的方法。 该方法包括：检测原始图像的第一组兴趣点; 计算仿射变换矩阵; 使用仿射变换矩阵计算新图像作为原始图像的变换; 从新图像检测第二组兴趣点; 执行第一组兴趣点与第二组兴趣点之间的双向匹配; 根据指定的自匹配分数（SMS）对匹配对进行排序; 从原始图像向无缝匹配的兴趣点的SMS分配无限值; 基于短信选择兴趣点。 显着的业绩增益减少假阳性匹配。

    METHOD AND APPARATUS FOR ENFORCING BEHAVIOR OF DASH OR OTHER CLIENTS
    8.
    发明申请
    METHOD AND APPARATUS FOR ENFORCING BEHAVIOR OF DASH OR OTHER CLIENTS 审中-公开
    执行DASH或其他客户行为的方法和装置

    公开(公告)号：US20140201368A1

    公开(公告)日：2014-07-17

    申请号：US14153803

    申请日：2014-01-13

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Imed Bouazizi ,  Mark Edward Trayer ,  Kong Posh Bhat ,  Zhu Li ,  Youngkwon Lim

    IPC: H04L29/08

    CPC classification number: H04L67/02 ,  H04L65/4092 ,  H04L65/602 ,  H04L65/80

    Abstract: A method for obtaining content includes determining that a playout of one or more other pieces of content is dependent upon a playout of a first piece of content. The method also includes obtaining the first piece of content and identifying a forced content token associated with the first piece of content. The method further includes obtaining an access token using the forced content token. In addition, the method includes using the access token to obtain the one or more other pieces of content. The forced content token could be identified as a hash of the first piece of content or as a watermark extracted from the first piece of content. The forced content token could also be identified by creating a thumbnail for each of one or more frames in the first piece of content and calculating a differential trace signature for each of the one or more frames.

    Abstract translation: 一种用于获得内容的方法包括确定一个或多个其他内容的播出取决于第一内容的播出。 该方法还包括获取第一内容并且识别与第一内容相关联的强制内容令牌。 该方法还包括使用强制内容令牌来获得访问令牌。 此外，该方法包括使用访问令牌来获得一个或多个其他内容片段。 强制内容令牌可以被识别为第一内容片段的散列或作为从第一片内容提取的水印。 还可以通过为第一段内容中的一个或多个帧中的每一个创建缩略图并且为一个或多个帧中的每个帧计算差分跟踪签名来识别强制内容令牌。

    METHOD AND APPARATUS FOR ENCAPSULATION OF MOTION PICTURE EXPERTS GROUP MEDIA TRANSPORT ASSETS IN INTERNATIONAL ORGANIZATION FOR STANDARDIZATION BASE MEDIA FILES
    9.
    发明申请
    METHOD AND APPARATUS FOR ENCAPSULATION OF MOTION PICTURE EXPERTS GROUP MEDIA TRANSPORT ASSETS IN INTERNATIONAL ORGANIZATION FOR STANDARDIZATION BASE MEDIA FILES 审中-公开
    运动图片专家的方法和装置集团媒体资产在国际标准化基地媒体文件组织

    公开(公告)号：US20140149545A1

    公开(公告)日：2014-05-29

    申请号：US14091243

    申请日：2013-11-26

    Applicant: Samsung Electronics Co., LTD

    Inventor： Imed Bouazizi ,  Youngkwon Lim ,  Kong Posh Bhat

    IPC: H04L29/06

    CPC classification number: H04L65/607 ,  H04L65/4084 ,  H04N21/85406

    Abstract: An apparatus includes receive path circuitry configured to receive a Motion Picture Experts Group (MPEG) Media Transport (MMT) container and a processing device configured to identify locations of one or more media fragment units (MFUs) in the MMT container using a hint track within the MMT container. Another apparatus includes transmit path circuitry configured to transmit an MMT container and a processing device configured to identify locations of one or more MFUs in the MMT container using a hint track within the MMT container.

    Abstract translation: 一种装置包括：接收路径电路，其被配置为接收运动图像专家组（MPEG）媒体传输（MMT）容器;以及处理设备，其被配置为使用所述MMT容器内的提示轨道来识别所述MMT容器中的一个或多个媒体片段单元（MFU）的位置 MMT容器。 另一种装置包括被配置成传输MMT容器的发送路径电路和被配置为使用MMT容器内的提示轨迹来识别MMT容器中的一个或多个MFU的位置的处理设备。

    METHOD AND SYSTEM FOR COMPLEXITY ADAPTIVE STREAMING
    10.
    发明申请
    METHOD AND SYSTEM FOR COMPLEXITY ADAPTIVE STREAMING 有权
    用于复杂自适应流的方法和系统

    公开(公告)号：US20140136727A1

    公开(公告)日：2014-05-15

    申请号：US14076998

    申请日：2013-11-11

    Applicant: Samsung Electronics Co., LTD

    Inventor： Youngkwon Lim ,  Zhan Ma ,  Kong Posh Bhat ,  Felix C.A. Fernandes

    IPC: H04L29/06

    CPC classification number: H04L65/4084 ,  H04L65/602 ,  H04L65/80

    Abstract: A method includes calculating a complexity value for each segment or version of multimedia content. The multimedia content has multiple versions associated with common content and different encoding parameters, and each version is divided into segments. The method also includes adaptively streaming the multimedia content to a client device based on at least some of the calculated complexity values. The complexity value for each segment or version is calculated by summing multiple operation complexity values defining complexities of operations for decoding the segment or version. The operation complexity values could include values for a bit parsing operation, a buffer initialization operation, an intra-prediction operation, an inverse quantization and transform operation, a reference block fetch operation, a fractional interpolation operation, and in-loop deblocking operation, a sample adaptive offset correction operation, an adaptive loop filtering operation, and a de-ringing filtering operation.

    Abstract translation: 一种方法包括计算多媒体内容的每个段或版本的复杂度值。 多媒体内容具有与通用内容和不同编码参数相关联的多个版本，并且每个版本被分成多个段。 该方法还包括基于所计算的复杂度值中的至少一些来自适应地将多媒体内容流式传输到客户端设备。 通过对定义用于对段或版本进行解码的操作的复杂性的多个操作复杂度求和来计算每个段或版本的复杂度值。 操作复杂度值可以包括位解析操作，缓冲器初始化操作，帧内预测操作，逆量化和变换操作，参考块提取操作，分数内插操作和循环中去块操作的值， 采样自适应偏移校正操作，自适应环路滤波操作和解除振铃滤波操作。

Patent Agency Ranking