知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

1174 条记录 (耗时 0.032 秒)

    METHOD AND APPARATUS TO CORRECT DIGITAL VIDEO TO COUNTERACT EFFECT OF CAMERA SHAKE
    72.
    发明申请
    METHOD AND APPARATUS TO CORRECT DIGITAL VIDEO TO COUNTERACT EFFECT OF CAMERA SHAKE 有权
    将数字视频校正到相机拍摄对策效果的方法和装置

    公开(公告)号：US20160255275A1

    公开(公告)日：2016-09-01

    申请号：US15149481

    申请日：2016-05-09

    申请人： Fatih M. Ozluturk

    发明人： Fatih M. Ozluturk

    IPC分类号： H04N5/232 ,  G06T5/00 ,  G06T7/20 ,  H04N5/265

    CPC分类号： H04N5/23287 ,  G02B27/646 ,  G06T5/002 ,  G06T5/003 ,  G06T7/20 ,  G06T2207/10004 ,  G06T2207/10016 ,  G06T2207/20024 ,  G06T2207/20201 ,  G06T2207/20212 ,  H04N5/23216 ,  H04N5/23229 ,  H04N5/23248 ,  H04N5/23251 ,  H04N5/23254 ,  H04N5/23258 ,  H04N5/23267 ,  H04N5/23293 ,  H04N5/265

    摘要： The effect of camera shake in digital video is corrected using signal processing techniques. The digital video is a sequence of digital images. When the sequence of digital images are being captured, movement of the imaging device causes the images to shift on the image sensor of the imaging device and affects the quality of the eventual video. Movement of the imaging device is detected while the video is being captured, and a motion information representing the motion is recorded. A processor determines a correcting filter based on the motion information and user input. The processor modifies the sequence of images captured according to the correcting filter and obtains a final corrected video. Corrected video is displayed in a viewfinder.

    摘要翻译： 使用信号处理技术来校正数字视频中相机抖动的影响。 数字视频是一系列数字图像。 当捕获数字图像的序列时，成像装置的移动导致图像在成像装置的图像传感器上移动并影响最终视频的质量。 在捕获视频时检测成像装置的运动，并且记录表示运动的运动信息。 处理器基于运动信息和用户输入来确定校正滤波器。 处理器修改根据校正滤波器捕获的图像序列，并获得最终校正的视频。 更正的视频显示在取景器中。

    METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR REDUCING CHROMATIC ABERRATIONS IN DECONVOLVED IMAGES
    73.
    发明申请
    METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR REDUCING CHROMATIC ABERRATIONS IN DECONVOLVED IMAGES 有权
    方法，装置和计算机程序产品，用于减少解压缩图像中的色度偏差

    公开(公告)号：US20160253790A1

    公开(公告)日：2016-09-01

    申请号：US15051616

    申请日：2016-02-23

    申请人： Nokia Technologies Oy

    发明人： Gururaj Putraya ,  Krishna Annasagar Govindarao ,  Mithun Uliyar ,  Basavaraja S V

    IPC分类号： G06T5/00 ,  G06T5/50 ,  G06T5/20

    CPC分类号： G06T5/003 ,  G06T5/006 ,  G06T5/20 ,  G06T5/50 ,  G06T2207/10024 ,  G06T2207/20024 ,  G06T2207/20028 ,  G06T2207/20201

    摘要： In an example embodiment, method, apparatus and computer program product are provided. The method includes facilitating receipt of a deconvolved image including a plurality of component images. A guide image is selected from the component images and a cross-filtering is performed of component images other than the guide image to generate filtered component images. The cross-filtering is performed of a component image by iteratively performing, selecting a pixel and a set of neighboring pixels around the pixel in the guide image, computing a set of weights corresponding to the set of neighboring pixels based at least on spatial differences between the pixel and the set of neighboring pixels, and cross-filtering a corresponding pixel of the pixel in the component image based on the set of weights to generate a filtered corresponding pixel in the component image. The filtered component images form a filtered deconvolved image with reduced chromatic aberration.

    摘要翻译： 在示例实施例中，提供了方法，装置和计算机程序产品。 该方法包括促进接收包括多个分量图像的去卷积图像。 从分量图像中选择引导图像，并且对除了引导图像之外的分量图像进行交叉滤波以生成滤波分量图像。 通过迭代地执行，选择引导图像中的像素周围的像素和一组相邻像素来对分量图像进行交叉滤波，至少基于相邻像素集合之间的空间差异来计算对应于该组相邻像素的一组权重 像素和相邻像素的集合，并且基于权重集合对分量图像中的像素的对应像素进行交叉滤波，以在分量图像中生成滤波的对应像素。 滤波的分量图像形成具有减小的色差的经滤波的去卷积图像。

    Detecting glare in a frame of image data
    74.
    发明授权
    Detecting glare in a frame of image data 有权
    在一帧图像数据中检测眩光

    公开(公告)号：US09418407B2

    公开(公告)日：2016-08-16

    申请号：US14564424

    申请日：2014-12-09

    申请人： ABBYY Development LLC

    发明人： Konstantin Bocharov ,  Mikhail Kostyukov

    IPC分类号： G06T5/00 ,  G06K9/40

    CPC分类号： G06T5/005 ,  G06K9/18 ,  G06K9/40 ,  G06K2209/01 ,  G06T5/001 ,  G06T5/002 ,  G06T2207/20021 ,  G06T2207/20056 ,  G06T2207/20192 ,  G06T2207/20201

    摘要： Disclosed are systems, computer-readable mediums, and methods for detecting glare in a frame of image data. A frame of image data is preprocessed. A set of connected components in the preprocessed frame is determined. A set of statistics is calculated for one or more connected components in the set of connected components. A decision for the one or more connected components is made, using the calculated set of statistics, if the connected component is a light spot over text. Whether glare is present in the frame is determined.

    摘要翻译： 公开了用于在图像数据的帧中检测眩光的系统，计算机可读介质和方法。 一帧图像数据被预处理。 确定预处理帧中的一组连接的组件。 对一组连接的组件中的一个或多个连接的组件计算一组统计信息。 如果所连接的组件是文本上的一个亮点，则使用所计算的一组统计信息来决定一个或多个连接的组件。 确定是否存在眩光。

    Deblurring of an image from a sequence of images
    76.
    发明授权
    Deblurring of an image from a sequence of images 有权
    从图像序列中去除图像

    公开(公告)号：US09406108B2

    公开(公告)日：2016-08-02

    申请号：US14192850

    申请日：2014-02-27

    申请人： THOMSON LICENSING

    发明人： Jordi Salvador ,  Axel Kochale ,  Siegfried Schweidler

    IPC分类号： G06T5/00 ,  G06T7/20

    CPC分类号： G06T5/003 ,  G06T7/20 ,  G06T2207/20201

    摘要： A method and an apparatus for deblurring an image from a sequence of images are described. The image comprises pixels. A motion estimation stage estimates motion of the pixels of the image. A point spread function modeling stage models point spread functions for the pixels of the image using the motion estimates. A deconvolution stage determines a deblurred estimate of the image using the modeled point spread functions. A feedback loop allows iteratively improving the motion estimates for the pixels until the modeled point spread functions converge.

    摘要翻译： 描述了用于从图像序列去除图像的方法和装置。 图像包括像素。 运动估计阶段估计图像的像素的运动。 点扩散函数建模阶段模型使用运动估计的图像像素的点扩散函数。 解卷积阶段使用建模的点扩散函数确定图像的去模糊估计。 反馈循环允许迭代地改进像素的运动估计，直到建模的点扩散函数收敛。

    Image capturing apparatus
    78.
    发明授权
    Image capturing apparatus 有权
    图像捕获装置

    公开(公告)号：US09398218B2

    公开(公告)日：2016-07-19

    申请号：US14758209

    申请日：2013-12-19

    申请人： CANON KABUSHIKI KAISHA

    发明人： Keiichiro Ishihara

    IPC分类号： H04N5/232 ,  G06T7/00 ,  G01C3/08 ,  G06T7/20 ,  G06T7/40

    CPC分类号： H04N5/23248 ,  G01C3/08 ,  G06T7/11 ,  G06T7/187 ,  G06T7/215 ,  G06T7/571 ,  G06T7/90 ,  G06T2207/10004 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/10148 ,  G06T2207/20201 ,  G06T2207/20224 ,  H04N5/23212 ,  H04N5/23264

    摘要： To reduce the difference among a plurality of images acquired due to an object shake or hand shake. An image capturing apparatus 10 includes an imaging optical system 11 and an image sensor 14 that acquires an image of light coming from the imaging optical system 11. The imaging optical system 11 has an aperture stop 12 including a first aperture and a second aperture. The image sensor 11 has first pixels and second pixels. The central axis of the first aperture and the central axis of the second aperture are aligned with each other. The first aperture has a first optical filter that codes light passing therethrough with a first code. The first pixels receive first coded light coded with the first code. The second pixels do not receive the first coded light and receive light other than the first coded light.

    摘要翻译： 为了减少由于物体抖动或手抖动而获取的多个图像之间的差异。 摄像装置10包括摄像光学系统11和拍摄来自成像光学系统11的光的图像的图像传感器14.成像光学系统11具有包括第一孔和第二孔的孔径光阑12。 图像传感器11具有第一像素和第二像素。 第一孔的中心轴线和第二孔的中心轴线彼此对准。 第一光圈具有第一光学滤光器，用第一代码对穿过其中的光进行编码。 第一像素接收用第一码编码的第一编码光。 第二像素不接收第一编码光并接收第一编码光以外的光。

    IMAGE PROCESSING DEVICE, IMAGE-CAPTURING DEVICE, IMAGE PROCESSING METHOD, AND PROGRAM
    80.
    发明申请
    IMAGE PROCESSING DEVICE, IMAGE-CAPTURING DEVICE, IMAGE PROCESSING METHOD, AND PROGRAM 有权
    图像处理装置，图像捕获装置，图像处理方法和程序

    公开(公告)号：US20160055628A1

    公开(公告)日：2016-02-25

    申请号：US14933759

    申请日：2015-11-05

    申请人： FUJIFILM Corporation

    发明人： Kenkichi HAYASHI ,  Masahiko SUGIMOTO ,  Yousuke NARUSE

    IPC分类号： G06T5/00 ,  H04N5/357

    CPC分类号： G06T5/003 ,  G06T2207/20024 ,  G06T2207/20201 ,  H04N5/23212 ,  H04N5/3572 ,  H04N9/045

    摘要： An image processing device includes a point-image restoration processing unit 40 which receives a photographic image as input, and subjects the photographic image to a point-image restoration process based on point-image restoration information to generate a restored image, an area information output unit 45 which outputs area information relating to a specific area in the restored image where restoration strength of the point-image restoration process based on the point-image restoration information is equal to or greater than a threshold value, a display control unit 50 which receives the restored image and the area information as input and performs display control to highlight the specific area in the restored image based on the area information, and a display unit 55 which highlights at least the specific area based on the display control by the display control unit 50.

    摘要翻译： 图像处理装置包括点摄像恢复处理单元40，其接收摄影图像作为输入，并且基于点图像恢复信息对摄影图像进行点图像恢复处理，以生成恢复图像，区域信息输出 单元45，其输出与基于点图像恢复信息的点图像恢复处理的恢复强度等于或大于阈值的还原图像中的特定区域相关的区域信息;接收 恢复的图像和区域信息作为输入，并且基于区域信息执行显示控制以突出恢复的图像中的特定区域;以及显示单元55，其基于显示控制单元的显示控制至少突出显示特定区域 50。