知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

56 条记录 (耗时 0.03 秒)

    Comparison of visual information
    3.
    发明授权
    Comparison of visual information 有权
    视觉信息的比较

    公开(公告)号：US08712156B2

    公开(公告)日：2014-04-29

    申请号：US12987290

    申请日：2011-01-10

    申请人： Alexander Bronstein ,  Michael Bronstein

    发明人： Alexander Bronstein ,  Michael Bronstein

    IPC分类号： G06K9/00 ,  G06K1/00

    CPC分类号： G06K1/00 ,  G06K9/6289 ,  G06T7/33 ,  G06T2207/20164

    摘要： A method determines similarity of objects depicted in images when the images pertain to different modalities. The method includes obtaining images that depict the objects and that pertain to the different modalities. An embedding function is applied to each of the images. The embedding function is selected from a set of two or more embedding functions, each of the embedding functions corresponding to a modality of the different modalities, the selected embedding function corresponding to the modality of the image to which it is applied. Application of the embedding function maps that image to a representation in a representation space such that when the images are mapped to the representation space, a distance between the representations of the images is indicative of a similarity of their depicted objects. The similarity of the depicted objects is determined based on the location of the corresponding representations in the representation space.

    摘要翻译： 当图像与不同的模态有关时，一种方法确定在图像中描绘的对象的相似性。 该方法包括获得描绘对象并涉及不同模态的图像。 嵌入功能被应用于每个图像。 嵌入函数从一组两个或多个嵌入函数中选择，每个嵌入函数对应于不同模态的模态，所选择的嵌入函数对应于应用于其的图像的模态。 嵌入函数的应用将该图像映射到表示空间中的表示，使得当图像被映射到表示空间时，图像的表示之间的距离指示它们描绘的对象的相似性。 所描绘的对象的相似性基于表示空间中相应表示的位置来确定。

    Three-Dimensional Data Acquisition
    5.
    发明申请
    Three-Dimensional Data Acquisition 有权
    三维数据采集

    公开(公告)号：US20130063559A1

    公开(公告)日：2013-03-14

    申请号：US13604724

    申请日：2012-09-06

    申请人： Sagi Ben Moshe ,  Ron Kimmel ,  Michael Bronstein ,  Alex Bronstein

    发明人： Sagi Ben Moshe ,  Ron Kimmel ,  Michael Bronstein ,  Alex Bronstein

    IPC分类号： G06K9/36 ,  H04N13/02

    CPC分类号： G01B11/25 ,  G06T7/521 ,  G06T2207/10028 ,  H04N13/207 ,  H04N13/363

    摘要： A projector illuminates an object, within the field of view of a camera, with a sequence of code patterns. The camera captures the illuminated object and provides object images to a decoder to convert the code patterns into code. A transition locator locates discontinuities in the code pattern images. A dequantizer reconstructs a range image from those discontinuities and said code.

    摘要翻译： 投影机在摄像机的视野内用一系列代码模式照亮物体。 照相机拍摄照明物体，并将对象图像提供给解码器，以将代码模式转换为代码。 过渡定位器定位代码图像图像中的不连续性。 去量化器从这些不连续性和所述代码重建范围图像。

    Facial recognition and the open mouth problem
    7.
    发明授权
    Facial recognition and the open mouth problem 有权
    面部识别和开嘴问题

    公开(公告)号：US08155400B2

    公开(公告)日：2012-04-10

    申请号：US12076830

    申请日：2008-03-24

    申请人： Michael Bronstein ,  Alexander Bronstein ,  Ron Kimmel

    发明人： Michael Bronstein ,  Alexander Bronstein ,  Ron Kimmel

    IPC分类号： G06K9/00

    CPC分类号： G06K9/00214 ,  G01S17/89 ,  G06K9/00288 ,  G06T17/00

    摘要： A method of cropping a representation of a face for electronic processing, said method comprising: selecting a first geodesic contour about an invariant reference point on said face, setting a region within said first geodesic contour as a first mask, selecting a second geodesic contour about a boundary of said identified first region, setting a region within said second geodesic contour as a second mask, and forming a final mask from a union of said first mask and said second mask.

    摘要翻译： 一种裁剪用于电子处理的面部表示的方法，所述方法包括：在所述面部上选择关于不变参考点的第一测地线轮廓，将所述第一测地线轮廓内的区域设置为第一掩模，选择第二测地线轮廓 所述识别的第一区域的边界，将所述第二测地线轮廓内的区域设置为第二掩模，以及从所述第一掩模和所述第二掩模的联合形成最终掩模。

    Method and System for Encoding Order and Frame Type Selection Optimization
    8.
    发明申请
    Method and System for Encoding Order and Frame Type Selection Optimization 有权
    用于编码顺序和帧类型选择优化的方法和系统

    公开(公告)号：US20100054329A1

    公开(公告)日：2010-03-04

    申请号：US12199741

    申请日：2008-08-27

    申请人： Alexander Bronstein ,  Michael Bronstein

    发明人： Alexander Bronstein ,  Michael Bronstein

    IPC分类号： H04N7/26

    CPC分类号： H04N19/192 ,  H04N19/109 ,  H04N19/115 ,  H04N19/147 ,  H04N19/149 ,  H04N19/154 ,  H04N19/157 ,  H04N19/162 ,  H04N19/17 ,  H04N19/172 ,  H04N19/179

    摘要： A method for resource allocation for video encoder to achieve the minimum sequence cost within given resource budgets. Optimal video encoder design by deriving the optimal sequence order and frame type selection is invented. In order to achieve computationally practical resource allocation, the current invention utilizes various encoder model and buffer model. The models allow the optimization procedure to assess the best encoding design without actually performing the computationally expensive encoding. Efficient optimization algorithm is also derived to substantially reduce the computations required to search for the optimal action sequence.

    摘要翻译： 一种用于视频编码器的资源分配方法，以在给定的资源预算内实现最小序列成本。 发明了优化的视频编码器设计，通过推导优化序列顺序和帧类型选择。 为了实现计算实际的资源分配，本发明利用各种编码器模型和缓冲模型。 这些模型允许优化过程来评估最佳的编码设计，而无需实际执行计算昂贵的编码。 还导出了有效的优化算法，以显着减少搜索最佳动作序列所需的计算。

    Resource Allocation for Frame-Based Controller
    10.
    发明申请
    Resource Allocation for Frame-Based Controller 有权
    基于帧的控制器的资源分配

    公开(公告)号：US20090219993A1

    公开(公告)日：2009-09-03

    申请号：US12040788

    申请日：2008-02-29

    申请人： Michael Bronstein ,  Alexander Bronstein

    发明人： Michael Bronstein ,  Alexander Bronstein

    IPC分类号： H04N11/02

    CPC分类号： H04N19/17 ,  H04N19/127 ,  H04N19/154 ,  H04N19/61

    摘要： A method for resource allocation for video encoder to achieve optimal picture quality within a given resource budget. Making a video encoder utilize the computational complexity, bitrate and other resources in an optimal way while maintaining optimal quality is a complicated optimization problem. A subset of this resource allocation problem, optimizing the tradeoff between bitrate versus quality is called rate-distortion optimization and is performed in most modern encoders. In order to achieve a computationally practical solution of the resource allocation problem, the current invention partitions the video content into a number of regions based on their characteristics and assesses resource allocation among regions to achieve the optimal quality within the resource budget limit. To maintain the computation tractable, the invention relies on bit production model and distortion model for the underlying video content to assess the quality and resource usage instead of actually conducting video compression. An iterative optimization algorithm has been developed to implement the invention.

    摘要翻译： 一种用于视频编码器的资源分配方法，以在给定的资源预算内实现最佳图像质量。 使视频编码器以最佳方式利用计算复杂度，比特率和其他资源，同时保持最优质量是一个复杂的优化问题。 这种资源分配问题的一个子集，优化了比特率与质量之间的权衡，称为速率失真优化，并在大多数现代编码器中执行。 为了实现资源分配问题的计算实用解决方案，本发明基于其特征将视频内容划分为多个区域，并评估区域之间的资源分配，以在资源预算限制内实现最优质量。 为了保持计算易于使用，本发明依赖于底层视频内容的位生产模型和失真模型来评估质量和资源使用，而不是实际进行视频压缩。 已经开发了迭代优化算法来实现本发明。