利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

562 条记录 (耗时 0.026 秒)

    TECHNIQUES FOR DISPARITY ESTIMATION USING CAMERA ARRAYS FOR HIGH DYNAMIC RANGE IMAGING
    72.
    发明申请
    TECHNIQUES FOR DISPARITY ESTIMATION USING CAMERA ARRAYS FOR HIGH DYNAMIC RANGE IMAGING 有权
    使用摄像机阵列进行高动态范围成像的差分估计技术

    公开(公告)号：US20150161797A1

    公开(公告)日：2015-06-11

    申请号：US14101061

    申请日：2013-12-09

    申请人： SUNG HEE PARK ,  KALPANA SESHADRINATHAN

    发明人： SUNG HEE PARK ,  KALPANA SESHADRINATHAN

    IPC分类号： G06T7/00 ,  H04N13/00 ,  H04N5/235 ,  H04N13/02 ,  G06T5/00 ,  G06T5/50

    CPC分类号： G06T7/55 ,  G06T5/007 ,  G06T5/009 ,  G06T5/50 ,  G06T2200/04 ,  G06T2207/10012 ,  G06T2207/20208 ,  G06T2207/20216 ,  G06T2207/20228 ,  H04N5/2355 ,  H04N13/128 ,  H04N13/243 ,  H04N13/271

    摘要： Techniques for improved focusing of camera arrays are described. In one embodiment, a system may include a processor circuit, a camera array, and an imaging management module for execution on the processor circuit to capture an array of images from the camera array, the array of images comprising first and second images taken with first and second values of an exposure parameter, respectively, the first value different than the second value, to estimate a noise level, to normalize an intensity of each image based upon the noise level of the respective image, to produce a respective normalized image, to identify candidate disparities in each of the respective normalized images, to estimate a high dynamic range (HDR) image patch for each candidate disparity, and to compute an error from the HDR image patch and an objective function, to produce a disparity estimate. Other embodiments are described and claimed.

    摘要翻译： 描述了改进相机阵列聚焦的技术。 在一个实施例中，系统可以包括处理器电路，相机阵列和成像管理模块，用于在处理器电路上执行以从相机阵列捕获图像阵列，所述图像阵列包括第一和第二图像 和曝光参数的第二值分别是与第二值不同的第一值，以估计噪声电平，以基于各个图像的噪声电平对每个图像的强度进行归一化，以产生相应的标准化图像，以产生相应的标准化图像 识别每个相应标准化图像中的候选差异，以估计每个候选视差的高动态范围（HDR）图像块，并计算来自HDR图像块和目标函数的误差，以产生视差估计。 描述和要求保护其他实施例。

    IMAGE PROCESSING APPARATUS AND IMAGE PROCESSING METHOD
    73.
    发明申请
    IMAGE PROCESSING APPARATUS AND IMAGE PROCESSING METHOD 有权
    图像处理装置和图像处理方法

    公开(公告)号：US20150154460A1

    公开(公告)日：2015-06-04

    申请号：US14619364

    申请日：2015-02-11

    申请人： FUJITSU LIMITED

    发明人： Kozo Baba ,  Kunikazu Takahashi

    IPC分类号： G06K9/00 ,  G06K9/46 ,  G06T7/00

    CPC分类号： G06K9/00805 ,  G06K9/4661 ,  G06T7/12 ,  G06T7/246 ,  G06T7/254 ,  G06T2207/10016 ,  G06T2207/20068 ,  G06T2207/20216 ,  G06T2207/20224 ,  G06T2207/30252 ,  G06T2207/30261

    摘要： An image processing apparatus includes a processor. The processor is configured to execute a process including creating an average image of difference images in moving picture data based on a difference between a first frame and a second frame adjacent to the first frame, the first frame and the second frame included in the moving picture data, calculating a sum total of luminance values arranged in a lateral direction of the average image for each point in a longitudinal direction of the average image, selecting a predetermined number of points that are higher in value of a secondary differential value of the sum total of luminance values, from among points located in a downward direction from a position of a vanishing point in the average image, and firstly specifying a point that is on a boundary between a hood and a road from among the predetermined number of selected points.

    摘要翻译： 图像处理装置包括处理器。 处理器被配置为执行处理，该处理包括基于与第一帧相邻的第一帧和第二帧之间的差异创建运动图像数据中的差分图像的平均图像，包括在运动图像中的第一帧和第二帧 数据，计算在平均图像的纵向方向上的每个点的平均图像的横向方向上布置的亮度值的总和，选择在总和的二次微分值的值中较高的预定数量的点 从位于平均图像中的消失点的位置的向下方向的点中，从预定数量的选择点中首先指定位于罩和道路之间的边界上的点的亮度值。

    Post-render motion blur
    74.
    发明授权
    Post-render motion blur 有权
    后渲染运动模糊

    公开(公告)号：US09025902B2

    公开(公告)日：2015-05-05

    申请号：US14036664

    申请日：2013-09-25

    申请人： Lucasfilm Entertainment Company, Ltd.

    发明人： Victor Schutz ,  Patrick Conran

    IPC分类号： G06K9/40 ,  G06T5/00 ,  G06T13/80

    CPC分类号： G06T5/50 ,  G06T5/002 ,  G06T11/001 ,  G06T13/20 ,  G06T13/80 ,  G06T15/50 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/20201 ,  G06T2207/20216

    摘要： A method of applying a post-render motion blur to an object may include receiving a first image of the object. The first image need not be motion blurred, and the first image may include a first pixel and rendered color information for the first pixel. The method may also include receiving a second image of the object. The second image may be motion blurred, and the second image may include a second pixel and a location of the second pixel before the second image was motion blurred. The method may additionally include locating the first pixel in the first image using the location of the second pixel before the second image was motion blurred. The method may further include coloring the second pixel using the rendered color information for the first pixel.

    摘要翻译： 将后渲染运动模糊应用于对象的方法可以包括接收对象的第一图像。 第一图像不需要运动模糊，并且第一图像可以包括用于第一像素的第一像素和渲染颜色信息。 该方法还可以包括接收对象的第二图像。 第二图像可以是运动模糊的，并且第二图像可以包括第二像素和第二像素在第二图像运动模糊之前的位置。 该方法可以另外包括在第二图像被运动模糊之前使用第二像素的位置来定位第一图像中的第一像素。 该方法还可以包括使用所渲染的第一像素的颜色信息着色第二像素。

    METHOD AND APPARATUS FOR PERFORMING HIERARCHICAL SUPER-RESOLUTION OF AN INPUT IMAGE
    76.
    发明申请
    METHOD AND APPARATUS FOR PERFORMING HIERARCHICAL SUPER-RESOLUTION OF AN INPUT IMAGE 有权
    用于执行输入图像的分层超分辨率的方法和装置

    公开(公告)号：US20150093045A1

    公开(公告)日：2015-04-02

    申请号：US14382569

    申请日：2013-03-04

    申请人： THOMSON LICENSING

    发明人： Mehmet Turkan ,  Dominique Thoreau ,  Philippe Guillotel

    IPC分类号： G06T3/40 ,  G06T5/50

    CPC分类号： G06T3/4076 ,  G06T3/4053 ,  G06T3/4084 ,  G06T5/50 ,  G06T2207/20052 ,  G06T2207/20216

    摘要： Super-resolution refers to a process of recovering the missing high-frequency details of a given low-resolution image. Known single image SR algorithms are often computationally intractable or unusable for most of the practical applications. The invention relates to a method for performing hierarchical super-resolution based on self content neighboring patches information is based on pyramidal decomposition. The intrinsic geometric property of an input LR patch neighborhood is obtained from the input LR patch and its K nearest neighbors taken from different down-scaled versions of the LR image.

    摘要翻译： 超分辨率是指恢复给定低分辨率图像的缺失高频细节的过程。 已知的单一图像SR算法通常在大多数实际应用中对于计算上难于处理或不可用。 本发明涉及一种基于自身内容的相邻补丁信息执行分级超分辨率的方法，其基于锥体分解。 输入LR补丁邻域的固有几何属性从输入LR补丁获得，并且从LR图像的不同缩小版本中获取其K个最近邻。

    HIGH DYNAMIC RANGE AND TONE MAPPING IMAGING TECHNIQUES
    77.
    发明申请
    HIGH DYNAMIC RANGE AND TONE MAPPING IMAGING TECHNIQUES 有权
    高动态范围和色调成像技术

    公开(公告)号：US20150078661A1

    公开(公告)日：2015-03-19

    申请号：US14469191

    申请日：2014-08-26

    申请人： DISNEY ENTERPRISES, INC.

    发明人： MIGUEL GRANADOS ,  JOSE RAFAEL TENA ,  TUNC OZAN AYDIN ,  JEAN FRANCOIS LALONDE ,  CHRISTIAN THEOBALT ,  IAIN MATTHEWS

    IPC分类号： G06T5/00

    CPC分类号： G06T5/009 ,  G06T5/003 ,  G06T5/50 ,  G06T2207/10024 ,  G06T2207/20208 ,  G06T2207/20216 ,  G06T2207/20221

    摘要： Algorithms for improving the performance of conventional tone mapping operators (TMO) by calculating both a contrast waste score and a contrast loss score for a first tone-mapped image produced by the TMO. The two contrast scores can be used to optimize the performance of the TMO by reducing noise and improving contrast. Algorithms for generating an HDR image by converting non-linear color space images into linear color space format, aligning the images to a reference, de-ghosting the aligned images if necessary, and merging the aligned (and potentially de-ghosted) images to create an HDR image. The merging can be performed with exposure fusion, HDR reconstruction, or other suitable techniques.

    摘要翻译： 通过计算TMO产生的第一个色调映射图像的对比度浪费评分和对比度损失分数来提高常规色调映射算子（TMO）的性能的算法。 两个对比度分数可用于通过降低噪音和改善对比度来优化TMO的性能。 用于通过将非线性颜色空间图像转换为线性颜色空间格式来生成HDR图像的算法，将图像对准参考，如果需要，将对齐的图像对焦，并合并对齐（并且可能去重影）的图像以创建 HDR图像。 可以通过曝光融合，HDR重建或其它合适的技术进行合并。

    IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD, AND PROGRAM
    78.
    发明申请
    IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD, AND PROGRAM 有权
    图像处理设备，图像处理方法和程序

    公开(公告)号：US20150054970A1

    公开(公告)日：2015-02-26

    申请号：US14446829

    申请日：2014-07-30

    申请人： OLYMPUS CORPORATION

    发明人： Yusuke HAMADA

    IPC分类号： H04N5/262 ,  H04N5/76 ,  G06T11/60 ,  G06T7/20 ,  H04N5/232 ,  H04N5/357

    CPC分类号： G06T5/50 ,  G06T5/001 ,  G06T5/002 ,  G06T2207/10016 ,  G06T2207/20216 ,  G06T2207/20221 ,  H04N5/217 ,  H04N5/23254 ,  H04N5/23277

    摘要： A frame memory stores a plurality of captured images. An image selection unit selects a reference image, which is a standard for composition, from images other than an image which is captured earliest and an image which is captured latest among the plurality of images stored in the frame memory and selects images to be combined with the reference image from a group of images which are captured earlier and later than the reference image among the plurality of images. A composition processing unit composes the images to be combined selected by the image selection unit with the reference image selected by the image selection unit to generate a composite image.

    摘要翻译： 帧存储器存储多个捕获的图像。 图像选择单元从除了最早拍摄的图像之外的图像和存储在帧存储器中的多个图像中最近被捕获的图像之外的图像中选择作为组合的标准的参考图像，并且选择要与 来自在所述多个图像中比所述参考图像更早且晚于所述图像组的参考图像。 合成处理单元将由图像选择单元选择的要组合的图像与由图像选择单元选择的参考图像组合以生成合成图像。

    METHOD FOR MINIMIZING SCINTILLATION IN DYNAMIC IMAGES
    79.
    发明申请
    METHOD FOR MINIMIZING SCINTILLATION IN DYNAMIC IMAGES 审中-公开
    在动态图像中最小化扫描的方法

    公开(公告)号：US20140341470A1

    公开(公告)日：2014-11-20

    申请号：US14287984

    申请日：2014-05-27

    申请人： DRS RSTA, INC.

    发明人： Harry Charles Lee ,  Teresa Lorae Pace ,  Marlon Javier Fuentes

    IPC分类号： G06T5/00 ,  G06T5/50 ,  G06T7/00 ,  G06T5/40

    CPC分类号： G06T5/003 ,  G06K9/40 ,  G06T5/00 ,  G06T5/008 ,  G06T5/40 ,  G06T5/50 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/20192 ,  G06T2207/20208 ,  G06T2207/20216 ,  G06T2207/20221 ,  G06T2207/20224 ,  G06T2207/30181

    摘要： A method for reducing scintillation in an image of a scene includes receiving an input sequence of images of the scene and grouping a first plurality of images of the sequence of images into a first subset of images comprising a first number of images that occur in sequence within the input sequence of images of the scene. The method also includes grouping a second plurality of images of the sequence of images into a second subset of images comprising a second number of images that occur in sequence within the input sequence of images of the scene. The method further includes generating a set of averaged images comprising an averaged image for the first subset of images and an averaged image for the second subset of image and outputting a composite image based at least the set of averaged images.

    摘要翻译： 一种用于减少场景图像中的闪烁的方法包括：接收场景的图像的输入序列，并将图像序列的第一多个图像分组成第一图像子集，其包括第一数量的图像， 场景图像的输入序列。 该方法还包括将图像序列的第二多个图像分组成图像的第二子集，其包括在场景的图像的输入序列内依次发生的第二数量的图像。 该方法还包括生成一组平均图像，其包括图像的第一子集的平均图像和图像的第二子集的平均图像，并且至少基于平均图像集合输出合成图像。