-
公开(公告)号：US08477149B2
公开(公告)日：2013-07-02
申请号：US12752238
申请日：2010-04-01
IPC分类号： G09G5/00 , G09G5/02 , G03F3/08 , H04N1/38 , H04N1/40 , H04N9/74 , H04N9/75 , H04N5/445 , G06K9/40 , G06K9/62 , G06K9/38 , G06K9/32
CPC分类号： G06K9/4652 , G06K9/6247 , H04N9/75
摘要： A method, system and computer readable media for real-time chromakey matting using image statistics. To identify the chroma key spectrum, the system/method executes in three stages. In an off-line training stage, the system performs semi-automatic calibration of the chroma key parameterization. In the real-time classification stage, the system estimates the alpha matte on a GPU. Finally, an optional error minimization stage improves the estimated matte, accounting for misclassifications and signal noise. Given the resulting matte, standard alpha blending composites the virtual scene with the video feed to create the illusion that both worlds coexist.
摘要翻译： 一种使用图像统计的实时色卡消光的方法，系统和计算机可读介质。 为了识别色度键谱，系统/方法分三个阶段执行。 在离线训练阶段，系统对色度键参数化进行半自动校准。 在实时分类阶段，系统估计了GPU上的Alpha哑光。 最后，可选的错误最小化阶段提高了估计的消光，考虑到错误分类和信号噪声。 鉴于最终的哑光，标准的Alpha混合将虚拟场景与视频馈送相结合，创造出两个世界并存的幻觉。
-
92.发明授权Apparatus and method for outputting image using a plurality of chroma-key colors 有权使用多个色键颜色输出图像的装置和方法公开(公告)号：US08363164B2
公开(公告)日：2013-01-29
申请号：US11656371
申请日：2007-01-23
申请人： Seung-taek Oh , Jung-khun Byun
发明人： Seung-taek Oh , Jung-khun Byun
IPC分类号： H04N9/75
CPC分类号： H04N9/75
摘要： An apparatus which outputs an image using a plurality of chroma-key colors is provided. The apparatus includes a chroma-key-color-storage unit that stores multiple chroma-key colors; a microprocessor unit (MPU) that sets a block where the chroma-key color is applied using a pixel address of a foreground image; and a video controller that composes a background image and the foreground image using the block set by the MPU, and displays the composed image in the display unit.
摘要翻译： 提供了使用多个色键颜色输出图像的装置。 该装置包括存储多个色键颜色的色键存储单元; 微处理器单元（MPU），其使用前景图像的像素地址来设置应用色度色彩的块; 以及使用由MPU设定的块构成背景图像和前景图像的视频控制器，并将合成图像显示在显示单元中。
-
公开(公告)号：US07528890B2
公开(公告)日：2009-05-05
申请号：US10836729
申请日：2004-04-30
IPC分类号： H04N9/75
摘要： An interactive video compositing device includes a chroma-key mixer, video switcher and control circuitry. The chroma-key mixer generates a composite image by combining a real-time image, such as one captured by a video recorder, with a prerecorded video image, such as a movie. The composite image includes the modified real-time image superimposed, or overlaid, onto the prerecorded image. The video switcher automatically selects either the composite image or the prerecorded image to be output to a display. The control circuitry controls the video switcher and other outputted signals based on data file information that corresponds to content of the prerecorded image or media. For example, the data files may contain information relating to the presence (or absence) of a particular character in a movie scene, thus allowing for the output and display, at appropriate times, of the real-time composite image instead of the prerecorded image.
摘要翻译： 交互式视频合成装置包括色键混合器，视频切换器和控制电路。 色度键混合器通过将诸如由视频记录器捕获的实时图像与诸如电影的预先记录的视频图像组合在一起来生成合成图像。 合成图像包括叠加或重叠在预先记录的图像上的经修改的实时图像。 视频切换器自动选择要输出到显示器的合成图像或预先记录的图像。 控制电路基于与预先记录的图像或介质的内容相对应的数据文件信息来控制视频切换器和其它输出信号。 例如，数据文件可以包含与电影场景中的特定字符的存在（或不存在）有关的信息，从而允许在适当的时间输出和显示实时合成图像而不是预先记录的图像 。
-
公开(公告)号：US07212248B2
公开(公告)日：2007-05-01
申请号：US10654836
申请日：2003-09-04
申请人： Leon J. Stanger
发明人： Leon J. Stanger
CPC分类号： H04N21/8547 , H04N5/04 , H04N21/4305 , H04N21/4307 , H04N21/4394 , H04N21/44
摘要： A method and apparatus for synchronizing audio and video portions of a media program signal is disclosed. The method comprises the steps of detecting an audio event in the audio portion of the media program signal, measuring the timing interval from the audio event to a subsequent video synchronization pulse in the video portion of the media program signal, and storing the timing interval in a third portion of the media program signal. The apparatus comprises a voice detector for detecting an audio event in the audio portion of the media program signal, a timer for measuring the timing interval from the audio event to a subsequent video synchronization pulse in the video portion of the media program signal, and a processor for storing the timing interval in a third portion of the media program signal.
摘要翻译： 公开了一种用于同步媒体节目信号的音频和视频部分的方法和装置。 该方法包括以下步骤：检测媒体节目信号的音频部分中的音频事件，测量从音频事件到媒体节目信号的视频部分中的后续视频同步脉冲的定时间隔，并将定时间隔存储在 媒体节目信号的第三部分。 该装置包括用于检测媒体节目信号的音频部分中的音频事件的语音检测器，用于测量媒体节目信号的视频部分中从音频事件到后续视频同步脉冲的定时间隔的定时器，以及 处理器，用于将定时间隔存储在媒体节目信号的第三部分中。
-
公开(公告)号：US06950130B1
公开(公告)日：2005-09-27
申请号：US09225189
申请日：1999-01-05
申请人： Richard J. Qian
发明人： Richard J. Qian
摘要： A method for background replacement. The method takes an input image of one or more frames of video, or a still image, and performs an initial classification of the pixels (14) as foreground or background pixels. The classification is refined (16) using one of several techniques, including anisotropic diffusion or morphological filtering. After the refined classification is completed, a feathering process (18) is used to overlay the foreground pixels from the original image on the pixels of the new background, resulting in a new output image (20).
摘要翻译： 背景替换方法。 该方法获取一个或多个视频帧或静止图像的输入图像，并且将像素（14）的初始分类执行为前景或背景像素。 使用几种技术之一进行分类（16），包括各向异性扩散或形态滤波。 在精细分类完成之后，使用羽化处理（18）将来自原始图像的前景像素重叠在新背景的像素上，从而产生新的输出图像（20）。
-
公开(公告)号：US20050057663A1
公开(公告)日：2005-03-17
申请号：US10893446
申请日：2004-07-16
申请人： Graham Thomas , Richard Russell
发明人： Graham Thomas , Richard Russell
摘要： A method and apparatus for keying foreground and background areas of an image or objects within an image is described. The selected object or area is differentially lit with key light having a selected characteristic, such as a selected colour property or temporal variation. A first image is formed of the scene, and a key signal is derived from the image based on detection of the key light. A second image of the scene may also be formed in which the effect of the key light on the object or area is reduced. The method may allow objects or areas to be keyed into or out of an image.
摘要翻译： 描述了用于对图像中的图像或对象的前景和背景区域进行键控的方法和装置。 所选择的对象或区域与具有所选择的特性（例如所选颜色属性或时间变化）的键光不同地点亮。 第一图像由场景形成，并且基于关键光的检测从图像导出关键信号。 也可以形成场景的第二图像，其中键光对物体或区域的影响减小。 该方法可以允许将对象或区域键入或移出图像。
-
公开(公告)号：US6438508B2
公开(公告)日：2002-08-20
申请号：US73699600
申请日：2000-12-14
发明人： TAMIR MICHAEL , SHARIR AVI
摘要： A position detecting device for an object within virtual set comprises providing the object with an emitting device and using the device in conjunction with a plain or patterned chroma-key background to provide the exact position of a TV camera or alone to provide a position for another object or actor.
摘要翻译： 用于物体在虚拟集合内的位置检测装置包括向对象提供发射装置，并且使用该装置结合平面或图案化色键背景来提供电视摄像机的精确位置或单独提供另一个位置 对象或演员。
-
公开(公告)号：US6167167A
公开(公告)日：2000-12-26
申请号：US886076
申请日：1997-07-02
申请人： Masakazu Matsugu , Hideo Takiguchi , Koji Hatanaka
发明人： Masakazu Matsugu , Hideo Takiguchi , Koji Hatanaka
CPC分类号： H04N19/503 , H04N19/20
摘要： There is disclosed an image extraction method for extracting, from a subject image that records both the background and the object to be extracted, image data of the object using a mask. An initial mask used for extracting the subject region is generated on the basis of difference data between the subject image and the background image that records the background alone, the region of the initial mask is grown on the basis of the similarity between the features of a first region and its neighboring second region in the subject image corresponding to the initial mask, and the image data of the object is extracted from the first image on the basis of the grown mask region.
-
99.发明授权Key signal generating apparatus and picture synthesis apparatus, and key signal generating method and picture synthesis method 失效关键信号发生装置和图像合成装置，以及按键信号生成方法和图像合成方法
公开(公告)号：US6128046A
公开(公告)日：2000-10-03
申请号：US765286
申请日：1997-01-06
申请人： Takashi Totsuka , Taku Yokoyama , Tomoo Mitsunaga
发明人： Takashi Totsuka , Taku Yokoyama , Tomoo Mitsunaga
CPC分类号： H04N5/2622 , H04N5/275
摘要： In this invention, when the portion from which a key signal .alpha. is to be generated of picture is caused to be foreground F, the portion except for the above is caused to be background B, and pixel value of pixels constituting that picture is designated at C, the key signal .alpha. is generated so as to satisfy the relational expression C'=(F-B).alpha.'('(prime) represents differentiation). In more practical sense, a change detecting section 10 calculates change C' of pixel value between pixels constituting picture, and an F-B detecting section 30 calculates difference F-B between the foreground and the background. In addition, an integral value calculating section 40 divides the change C' by the difference F-B to integrate the result obtained by divisional operation to thereby determine key signal .alpha.. As a result, precise key signal can be obtained in this invention.
摘要翻译： PCT No.PCT / JP96 / 01251 Sec。 371日期1997年1月6日 102（e）日期1997年1月6日PCT提交1996年5月10日PCT公布。 出版物WO96 / 36168 日期：1996年11月14日在本发明中，当将要产生图像的键信号α的部分设为前景F时，将除上述之外的部分设为背景B，构成像素的像素值 该图像在C处被指定，产生关键信号α，以满足关系式C'=（FB）α'（'（素数）表示微分）。 在更实际的意义上，变化检测部分10计算构成图像的像素之间的像素值的变化C'，并且F-B检测部分30计算前景和背景之间的差F-B。 此外，积分值计算部分40将变化C'除以差分F-B以对通过分割操作获得的结果进行积分，从而确定键信号α。 结果，在本发明中可以获得精确的关键信号。
-
100.发明授权
公开(公告)号：US6035060A
公开(公告)日：2000-03-07
申请号：US801717
申请日：1997-02-14
摘要： A method and apparatus for generating region frames from video frames are disclosed which employs an industry standard encoder to lessen the negative impact on the quality of the transmitted video sequence while consuming fewer bits. The invention utilizes image segmentation and color replacement techniques to create the region frames. Each region frame includes a subject region, zero or more previously segmented regions and zero or more non-subject regions. The subject region is defined by the pixels of the original video frame. The previously segmented regions and non-subject regions are assigned replacement pixels P.sub.n,y and C.sub.n, respectively. The replacement pixel C.sub.n is chosen to indicate a color that is not likely to be confused with any color in the subject region R.sub.n. The replacement pixels P.sub.n,y are chosen such that the compression ratio of the region frame data is maximized. Using the region frames, content based scalability can be provided without the need for special encoders and/or channels having a wider bandwidth. Also, color artifacts associated with the segmenting process are removed by color clipping or gray-level erosion.
摘要翻译： 公开了一种用于从视频帧产生区域帧的方法和装置，其采用工业标准编码器来减少对所发送的视频序列的质量的负面影响，同时消耗较少的比特。 本发明利用图像分割和颜色替换技术来创建区域框架。 每个区域帧包括主题区域，零个或多个先前分割的区域和零个或多个非对象区域。 主题区域由原始视频帧的像素定义。 先前分割的区域和非对象区域分别被分配替换像素Pn，y和Cn。 选择替换像素Cn以指示不可能与对象区域Rn中的任何颜色混淆的颜色。 选择替换像素Pn，y使得区域帧数据的压缩比最大化。 使用区域帧，可以提供基于内容的可扩展性，而不需要具有更宽带宽的特殊编码器和/或信道。 此外，与分割过程相关联的颜色伪影通过颜色剪切或灰度侵蚀而被去除。
-
-
-
-
-
-
-
-
-
搜索结果
379 条记录 (耗时 0.027 秒)
