-
公开(公告)号：US20140146370A1
公开(公告)日：2014-05-29
申请号：US13825793
申请日：2010-09-24
申请人： Ron Banner , Omer Barkol , Daniel Freedman
发明人： Ron Banner , Omer Barkol , Daniel Freedman
IPC分类号： H04N1/00
CPC分类号： H04N1/00047 , G06K9/6232 , G06T7/001 , G06T7/33 , G06T2207/20072 , G06T2207/30144 , H04N1/00005 , H04N1/00015 , H04N1/00039 , H04N1/0005 , H04N1/00063 , H04N1/00082 , H04N1/2307
摘要： An image registration method to register a target image with a reference image is provided, including to determine a target set of features present in the target image, to determine a reference set of features present in the reference image, to generate respective signatures for each feature in the target and reference sets, to match features from the target set to corresponding features in the reference set using the signatures, to generate respective transformations to map pairs of features in the target set to corresponding pairs of features in the reference set, and determine a similarity transformation for the target image using a measure of the accuracy of the transformations.
摘要翻译： 提供了一种用参考图像注册目标图像的图像注册方法，包括确定目标图像中存在的特征的目标集合，以确定参考图像中存在的特征的参考集合，以生成每个特征的各个签名 在目标和参考集中，使用特征将来自目标集的特征与参考集中的对应特征相匹配，以产生相应的变换以将目标集中的特征对映射到参考集中的相应特征对，并且确定 使用测量转换精度的目标图像的相似度变换。
-
公开(公告)号：US20120301028A1
公开(公告)日：2012-11-29
申请号：US13114736
申请日：2011-05-24
申请人： Daniel Freedman , Pavel Kisilev
发明人： Daniel Freedman , Pavel Kisilev
IPC分类号： G06K9/00
摘要： A technique includes using a processor-based machine to determine a discrete color flow transformation to map target colors of a target object to source colors of a source object based at least in part on a first histogram indicating a color distribution of the target object and a second histogram of a color distribution indicating the source object. The technique includes determining a continuous color flow transformation to map the target colors to the source colors based at least in part on the discrete color flow transformation; and transforming the target colors of the target object to generate a third object based at least in part on the continuous color flow transformation.
摘要翻译： 一种技术包括使用基于处理器的机器来至少部分地基于指示目标对象的颜色分布的第一直方图来确定离散颜色流变换以将目标对象的目标颜色映射到源对象的源颜色， 指示源对象的颜色分布的第二直方图。 该技术包括：至少部分地基于离散的颜色流变换来确定连续的颜色流变换以将目标颜色映射到源颜色; 以及至少部分地基于所述连续色彩流转换来转换所述目标对象的目标颜色以生成第三对象。
-
公开(公告)号：US20110123069A1
公开(公告)日：2011-05-26
申请号：US12622779
申请日：2009-11-20
申请人： Pavel Kisilev , Daniel Freedman
发明人： Pavel Kisilev , Daniel Freedman
IPC分类号： G06K9/00
摘要： A computer implemented method of mapping values of source pixels (c(x)s) of a source image 2 onto target pixels (c(x)t) of a target image 4. In one image (2) or in respective images (2, 4) two different groups (Rs, Rt) of pixels are selected to be representative of target and source pixels according to their property values. Within the image or images, target pixels (xεT) and source pixels (xεS) are selected which match the selected representative target and source pixels according to the property values thereof. The distributions of values of properties associated with the source pixels and target pixels are calculated. New property values are mapped onto the target pixels according to a transform which minimises an overall closeness measure between the source distribution and the target distribution.
摘要翻译： 一种计算机实现的方法，用于将源图像2的源像素（c（x）s）的值映射到目标图像4的目标像素（c（x）t）上。在一个图像（2）或相应图像（2 ，4）根据它们的属性值，选择两个不同的像素组（Rs，Rt）来代表目标像素和源像素。 在图像或图像内，根据其特性值选择与所选择的代表性目标和源像素匹配的目标像素（x＆amp; T）和源像素（x＆amp; S）。 计算与源像素和目标像素相关联的属性值的分布。 根据最小化源分布和目标分布之间的整体接近度量度的变换，将新属性值映射到目标像素上。
-
公开(公告)号：US20070260968A1
公开(公告)日：2007-11-08
申请号：US11106278
申请日：2005-04-13
IPC分类号： G06F17/00
CPC分类号： G11B27/034 , G11B27/329
摘要： To address needs of journalists and other editors, an audiovisual editing system associates segments of audiovisual materials with segments of related text. The editing system permits an editor to edit both the audiovisual materials of the segments and to edit the related text. The data structure representing the story includes a list of media segments and a list a text segments and a correspondence among the segments. Each media segment has a type, such as script, SOT and voice, and includes a list of video clips. These data structures enable the editing system to provide a simple and intuitive interface for editing a story, and can be transformed in a straightforward manner into a conventional, multitrack sequence used to represent an audiovisual composition. The editing system automatically defines parameters, such as designating the correct audio tracks, which minimize the chance for errors and speeds the workflow. Automatic ducking of these tracks also can be provided. For media segments with associated script in a corresponding text segment, an estimated time for reading the related script aloud by the newscaster may be determined. This estimated time for reading the text related a script segment may be compared to the actual duration of the audiovisual material of the script segment. The difference in the duration of the audiovisual material and the duration of the related text may be displayed to the editor, ma king it easier for the editor to match video to a script. Similarly, the duration of voice and SOT clips can be compared to the duration of video clips in a media segment. The difference in the duration of the video clips and the voice and SOT clips may be displayed to the editor, making it easier for the editor to match the video to the audio. Stories can be stored as text documents in a markup language. Data representing the audiovisual segments can be embedded in these stories. The editing system also may be interconnected through a computer network in a newsroom to a variety of other systems including an asset management system, shared storage for media and a story database. By having the editing system store stories in the story database and sequences in the asset management system, both sequences and stories are made available to other editing systems.
-
-
-
搜索结果
14 条记录 (耗时 0.036 秒)
