公开(公告)号：US20170359559A1

公开(公告)日：2017-12-14

申请号：US15181653

申请日：2016-06-14

申请人： Personify, Inc.

发明人： Sanjay Patel ,  Elad Yarkony

IPC分类号： H04N9/73 ,  H04N5/272 ,  H04N9/12

CPC分类号： H04N9/73 ,  H04N5/275 ,  H04N9/12 ,  H04N9/76

摘要： Disclosed herein are methods and systems for combining foreground video and background video using chromatic matching. In an embodiment, a system obtains foreground video data. The system obtains background video data. The system determines a color-distribution dimensionality of the background video data to be either high-dimensional chromatic or low-dimensional chromatic. The system selects a chromatic-adjustment technique from a set of chromatic-adjustment techniques based on the determined color-distribution dimensionality of the background video data. The system adjusts the foreground video data using the selected chromatic-adjustment technique. The system generates combined video data at least in part by combining the background video data with the adjusted foreground video data. The system outputs the combined video for display.

公开(公告)号：US20150070467A1

公开(公告)日：2015-03-12

申请号：US14285905

申请日：2014-05-23

申请人： VENTANA 3D LLC

发明人： Ashley Crowder ,  Benjamin Conway

IPC分类号： H04N13/02 ,  G06T5/10 ,  H04N5/33

CPC分类号： G06T5/10 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/10028 ,  G06T2207/10048 ,  H04N5/2226 ,  H04N5/275 ,  H04N13/271 ,  H04N2013/0092

摘要： According to embodiments herein, depth key compositing is the process of detecting specific desired portionsobjects of a digital image using mathematical functions based on depth, in order to separate those specific portionsobjects for further processing. In one particular embodiment, a digital visual image is captured from a video capture device, and one or more objects are determined within the digital visual image that are within a particular depth range of the video capture device. From there, the one or more objects may be isolated from portions of the digital visual image not within the particular depth range, and the isolated objects are processed for visual display apart from the portions of the digital visual image not within the particular depth range. Also, in certain embodiments, the detected portion of the digital image (isolated objects) may be layered with another image, such as for film production, or used for holographic projection.

摘要翻译： 根据本文的实施例，深度密钥合成是使用基于深度的数学函数来检测数字图像的特定期望部分对象的过程，以便分离这些特定部分对象以用于进一步处理。 在一个特定实施例中，从视频捕捉设备捕获数字视觉图像，并且在视频捕捉设备的特定深度范围内的数字视觉图像内确定一个或多个对象。 从那里，一个或多个对象可以与数字视觉图像的不在特定深度范围内的部分隔离，并且除了不在特定深度范围内的数字视觉图像的部分之外，处理孤立对象以进行视觉显示。 此外，在某些实施例中，数字图像（孤立物体）的检测部分可以与另一图像分层，例如用于胶片制作或用于全息投影。

公开(公告)号：US20140104314A1

公开(公告)日：2014-04-17

申请号：US14136044

申请日：2013-12-20

申请人： Clifford R. DAVID

发明人： Clifford R. DAVID

IPC分类号： G06T11/00

CPC分类号： G06T11/00 ,  G06Q30/0241 ,  G06Q30/0601 ,  G06Q30/0621 ,  G06T11/60 ,  G08B13/19684 ,  G08B13/19689 ,  H04N1/00132 ,  H04N1/0019 ,  H04N5/2628 ,  H04N5/272 ,  H04N5/275

摘要： Systems and methods for creating and distributing professional quality pictorial souvenirs giving the illusion that guests of a facility were imaged at other locations, including making initial arrangements with guests, showing selections of background scene images at video displays and flashing chroma key images interspersed with frames of the scene images, taking key guest images in synch with the flashed key images, extracting guest image content from the key guest images and merging into selecting scene images, showing initial merges images for guest selection and providing souvenir portfolios that include merged images to guests or designees after making financial arrangements, including for payment to third parties for copyright content included in the souvenirs and with advertisers for promotional material included in the souvenirs.

摘要翻译： 制作和分发专业质量图形纪念品的系统和方法，给予设施客人在其他地方成像的幻觉，包括与客人进行初步安排，显示视频显示器上的背景场景图像的选择以及散布有帧 场景图像，与闪烁的关键图像同步的主要客人图像，从主要客人图像中提取客人图像内容并合并到选择场景图像中，显示初始合并用于客人选择的图像，并提供包括合并图像的纪念品组合给客人或 指定人员在作出财务安排后，包括向第三方支付包含在纪念品中的版权内容，以及向广告商收取包含在纪念品中的宣传材料。

公开(公告)号：US08599316B2

公开(公告)日：2013-12-03

申请号：US12786471

申请日：2010-05-25

申请人： Aaron T. Deever

发明人： Aaron T. Deever

IPC分类号： H04N9/64 ,  H04N5/275

CPC分类号： H04N5/275 ,  G06F17/30784 ,  G11B27/28 ,  H04N21/44008 ,  H04N21/8549

摘要： A method for determining key video frames for a digital video having a time sequence of video frames, comprising using a processor to perform the steps of: analyzing the digital video to determine an importance value as a function of time; forming a warped time representation by temporal relocation of the video frames responsive to the importance value as a function of time; subdividing the warped time digital video sequence representation into a set of equal intervals; selecting a key video frame for each interval by analyzing the video frames within each interval; and storing an indication of the key video frames in a processor-accessible memory.

摘要翻译： 一种用于确定具有视频帧的时间序列的数字视频的关键视频帧的方法，包括使用处理器执行以下步骤：分析数字视频以确定作为时间的函数的重要性值; 响应于作为时间的函数的重要性值，通过视频帧的时间重新定位来形成扭曲时间表示; 将翘曲时间数字视频序列表示细分成一组相等的间隔; 通过分析每个间隔内的视频帧，为每个间隔选择一个关键视频帧; 以及将关键视频帧的指示存储在处理器可访问的存储器中。

公开(公告)号：US07995121B2

公开(公告)日：2011-08-09

申请号：US12033506

申请日：2008-02-19

申请人： Atsushi Kobayashi ,  Takashi Mori

发明人： Atsushi Kobayashi ,  Takashi Mori

IPC分类号： H04N5/262

CPC分类号： H04N9/75 ,  H04N5/2621 ,  H04N5/275

摘要： The present invention provides an imaging unit, a portable terminal device, and a portable terminal system capable of performing a satisfactory key synthesizing process. An imaging unit mainly includes an imaging section, a conversion section, and a key signal generating section. The conversion section converts the format of the imaged image data output from the imaging section from YUV format to RGB format. The key signal generating section generates a key signal based on each pixel data configuring the imaged image data and the reference data for the imaged image data input from the imaging section. The key signal generating section also outputs foreground image data having the generated key signal and the corresponding pixel data of RGB format as minimum configuring unit. An image synthesizing section of a main unit generates synthesized image data by overlapping the foreground image data from the imaging unit and the background image data stored in a RAM based on the key signal contained in the foreground image data.

摘要翻译： 本发明提供了能够执行令人满意的密钥合成处理的成像单元，便携式终端装置和便携式终端系统。 成像单元主要包括成像部分，转换部分和键信号产生部分。 转换部分将从成像部分输出的成像图像数据的格式从YUV格式转换为RGB格式。 键信号产生部分基于构成成像图像数据的每个像素数据和从成像部分输入的成像图像数据的参考数据生成键信号。 键信号产生部分还输出具有生成的键信号的前景图像数据和RGB格式的相应像素数据作为最小配置单元。 主单元的图像合成部分基于前景图像数据中包含的键信号，通过将来自成像单元的前景图像数据和存储在RAM中的背景图像数据重叠来产生合成图像数据。

公开(公告)号：US07965885B2

公开(公告)日：2011-06-21

申请号：US11240555

申请日：2005-10-03

申请人： Yoshiaki Iwai

发明人： Yoshiaki Iwai

IPC分类号： G06K9/00

CPC分类号： H04N5/275

摘要： The invention aims at separating a background area of an image using a plurality of cameras by utilizing a method of estimating a background in combination with a stereo method. Data on input images, synchronous with one another, which are obtained by photographing images of a subject from different points of sight using at least two cameras is stored in a frame memory. A background area estimation processing unit performs global image superimposition for the input images, synchronous with one another, the data on which is stored in the frame memory on the assumption that a background area is in the distance and has a flat surface. Then, the background area estimation processing unit estimates the background area based on a degree of local similarity. A distance image generation processing unit performs distance measurement with respect to points other than those in the estimated background area by utilizing a stereo method to generate distance images. A background separated image generation processing unit removes the image of an area in a predetermined distance or more from the input images by referring to resulting distance images to generate a background removed image.

摘要翻译： 本发明的目的是通过利用与立体声方法组合来估计背景的方法，使用多个照相机分离图像的背景区域。 通过使用至少两个照相机从不同的视点拍摄被摄体的图像获得的彼此同步的输入图像的数据被存储在帧存储器中。 背景区域估计处理单元假设背景区域处于距离并且具有平坦表面的情况下，对输入图像进行全局图像叠加，彼此同步，存储在帧存储器中的数据。 然后，背景区域估计处理单元基于局部相似度来估计背景区域。 距离图像生成处理单元通过利用立体声方式对估计背景区域以外的点进行距离测量，以生成距离图像。 背景分离图像生成处理单元通过参照所得到的距离图像从输入图像中去除预定距离以上的区域的图像，生成背景去除图像。

公开(公告)号：US07724952B2

公开(公告)日：2010-05-25

申请号：US11434567

申请日：2006-05-15

申请人： Heung-Yeung Shum ,  Jian Sun ,  Sing Bing Kang ,  Yin Li

发明人： Heung-Yeung Shum ,  Jian Sun ,  Sing Bing Kang ,  Yin Li

IPC分类号： G06K9/34

CPC分类号： H04N5/275 ,  H04N5/2354

摘要： Foreground object matting uses flash/no-flash images pairs to obtain a flash-only image. A trimap is obtained from the flash-only image. A joint Bayesian algorithm uses the flash-only image, the trimap and one of the image of the scene taken without the flash or the image of the scene taken with the flash to generate a high quality matte that can be used to extract the foreground from the background.

摘要翻译： 前景对象消光使用闪光/非闪光图像对来获取闪光灯图像。 从闪光灯图像获得一个微调。 联合贝叶斯算法使用仅闪光图像，微调和没有闪光灯拍摄的场景中的一个图像或用闪光灯拍摄的场景的图像，以生成可用于从 的背景。

公开(公告)号：US20080174680A1

公开(公告)日：2008-07-24

申请号：US11939079

申请日：2007-11-13

申请人： Atsushi OGINO

发明人： Atsushi OGINO

IPC分类号： H04N5/76

CPC分类号： H04N5/772 ,  G11B27/034 ,  H04N5/272 ,  H04N5/275 ,  H04N5/91

摘要： An imaging device has an image compositing unit. The image compositing unit comprises: an edge extracting portion that extracts edges within an area containing a subject image in a captured image to generate edge information; an outline generating portion that generates an outline based on the edge information; an outline cutting portion that forms a partial image by cutting out an area in a captured image along the outline; and an image compositing portion that generates an image by combining a foreground image and a background image. The foreground image is a partial image formed by cutting out an area containing a subject image in a captured image either captured by an image sensor or selected from among captured images stored in memory. The background image is a captured image either captured by the image sensor or selected from among captured images stored in the memory.

摘要翻译： 成像装置具有图像合成单元。 图像合成单元包括：边缘提取部分，其在捕获的图像中提取包含被摄体图像的区域内的边缘以产生边缘信息; 轮廓生成部，其基于所述边缘信息生成轮廓; 轮廓切割部，其通过沿着轮廓切除拍摄图像中的区域而形成部分图像; 以及通过组合前景图像和背景图像来生成图像的图像合成部分。 前景图像是通过在由图像传感器捕获或从存储在存储器中的捕获图像中选择的捕获图像中切出包含被摄体图像的区域而形成的部分图像。 背景图像是由图像传感器捕获或从存储在存储器中的捕获图像中选择的捕获图像。

公开(公告)号：US20080018792A1

公开(公告)日：2008-01-24

申请号：US11458598

申请日：2006-07-19

申请人： Kiran Bhat ,  Kar-Han Tan ,  Anoop K. Bhattacharjya

发明人： Kiran Bhat ,  Kar-Han Tan ,  Anoop K. Bhattacharjya

IPC分类号： H04N9/74

CPC分类号： G06T13/40 ,  G06T2213/12 ,  H04N5/275

摘要： A surround visual field framework or system and methods are presented. In an embodiment, a surround visual field system comprises a control signal extractor that obtains a control signal that is related to the input stream. The control signal is provided to a coupling rule that links the control signal to an effect on an element of a surround visual field. The effect is applied to the element of the surround visual field thereby creating a surround visual field that has a characteristic or characteristics which relate to an input audio/visual stream presentation. In one embodiment, the surround visual field is displayed in an area partially surrounding or surrounding the input stream being displayed. In embodiments, the surround visual field may be a rendering of a three-dimensional environment. In embodiments, one or more otherwise idle display areas may be used to display a surround visual field.

摘要翻译： 提出了环绕视野框架或系统和方法。 在一个实施例中，环绕视场系统包括获取与输入流相关的控制信号的控制信号提取器。 控制信号被提供给将控制信号链接到对环绕视场的元件的影响的耦合规则。 该效果被应用于环绕视野的元素，从而创建具有与输入音频/视频流呈现相关的特征或特征的环绕视野。 在一个实施例中，环绕视野被显示在部分地围绕或围绕正在显示的输入流的区域中。 在实施例中，环绕视野可以是三维环境的渲染。 在实施例中，可以使用一个或多个否则空闲的显示区域来显示环绕视野。

公开(公告)号：US07295217B2

公开(公告)日：2007-11-13

申请号：US11281362

申请日：2005-11-18

申请人： Nobuyuki Matsumoto ,  Osamu Hori ,  Takashi Ida ,  Hidenori Takeshima

发明人： Nobuyuki Matsumoto ,  Osamu Hori ,  Takashi Ida ,  Hidenori Takeshima

IPC分类号： G09G5/00

CPC分类号： H04N5/275 ,  H04N5/272

摘要： A video object clipping method includes storing, in a storage unit, original images each including a video object to be clipped and reference alpha images representing objects prepared, determining a criteria original image and a criteria reference alpha image from the original images and the reference alpha images, determining a deformation parameter by deforming the criteria reference alpha image to correspond to the criteria original image, and deforming remaining ones of the reference alpha images according to the determined deformation parameter to generate output alpha images corresponding to the original images.