公开(公告)号：US09330476B2

公开(公告)日：2016-05-03

申请号：US12454666

申请日：2009-05-21

申请人： Eli Shechtman ,  Dan Goldman

发明人： Eli Shechtman ,  Dan Goldman

IPC分类号： G06K9/40 ,  G06T11/00

CPC分类号： G06T11/00

摘要： An image is displayed in a computer system. The image includes contents having a feature visible therein. The contents have a region thereof defined to be provided with additional content in generating a modified image. An input is received comprising a semantic mark to be placed on the image. The semantic mark indicates an inside-region part inside the region and an outside-region part outside the region. The additional content for the region is determined using a patch-based optimization algorithm applied to the image. The patch-based optimization algorithm (i) identifies the additional content for the inside-region part based on the outside-region part and not on an area of the image that the semantic mark does not indicate, and (ii) identifies the additional content for a remainder of the region without being restricted to the outside-region part. The modified image having the additional content in the region is stored.

摘要翻译： 图像显示在计算机系统中。 该图像包括其中具有可见特征的内容。 内容的区域被定义为在生成修改图像时提供附加内容。 接收包括要放置在图像上的语义标记的输入。 语义标记表示区域内的区域内部分和区域外部的外部区域部分。 使用应用于图像的基于补丁的优化算法来确定该区域的附加内容。 基于补丁的优化算法（i）基于外部区域部分识别内部区域部分的附加内容，而不是语义标记未指示的图像区域，以及（ii）识别附加内容 对于该区域的其余部分而不限于外部区域部分。 存储具有该区域中的附加内容的修改图像。

公开(公告)号：US20100296748A1

公开(公告)日：2010-11-25

申请号：US12454666

申请日：2009-05-21

申请人： Eli Shechtman ,  Dan Goldman

发明人： Eli Shechtman ,  Dan Goldman

IPC分类号： G06K9/40

CPC分类号： G06T11/00

摘要： An image is displayed in a computer system. The image includes contents having a feature visible therein. The contents have a region thereof defined to be provided with additional content in generating a modified image. An input is received comprising a semantic mark to be placed on the image. The semantic mark indicates an inside-region part inside the region and an outside-region part outside the region. The additional content for the region is determined using a patch-based optimization algorithm applied to the image. The patch-based optimization algorithm (i) identifies the additional content for the inside-region part based on the outside-region part and not on an area of the image that the semantic mark does not indicate, and (ii) identifies the additional content for a remainder of the region without being restricted to the outside-region part. The modified image having the additional content in the region is stored.

摘要翻译： 图像显示在计算机系统中。 该图像包括其中具有可见特征的内容。 内容的区域被定义为在生成修改图像时提供附加内容。 接收包括要放置在图像上的语义标记的输入。 语义标记表示区域内的区域内部分和区域外部的外部区域部分。 使用应用于图像的基于补丁的优化算法来确定该区域的附加内容。 基于补丁的优化算法（i）基于外部区域部分识别内部区域部分的附加内容，而不是语义标记未指示的图像区域，以及（ii）识别附加内容 对于该区域的其余部分而不限于外部区域部分。 存储具有该区域中的附加内容的修改图像。

公开(公告)号：US08355592B1

公开(公告)日：2013-01-15

申请号：US12454661

申请日：2009-05-21

申请人： Eli Shechtman ,  Dan Goldman

发明人： Eli Shechtman ,  Dan Goldman

IPC分类号： G06K9/40

CPC分类号： G06T3/0093

摘要： A computer-implemented method for generating a modified image includes initiating, in a computer device, a patch-based optimization algorithm for using a first image to generate a second image. The method includes identifying, in a computer device, a first feature of a first image. The identification corresponds to a constraint on the first feature for generating a second image, The constraint restricts at least one of location and geometric orientation in the second image of patches representing the first feature. The method includes identifying, using the computer device, contents for the second image by processing patches in the image in iterations of the patch-based optimization algorithm. The patch-based optimization complies with the constraint, The method includes generating the second image from the identified contents based on the iterations of the patch-based optimization algorithm. The second image includes a second feature generated to represent the first feature and complying with the constraint.

摘要翻译： 用于生成修改的图像的计算机实现的方法包括在计算机设备中启动用于使用第一图像生成第二图像的基于块的优化算法。 该方法包括在计算机设备中识别第一图像的第一特征。 识别对应于用于生成第二图像的第一特征的约束。约束限制表示第一特征的补丁的第二图像中的位置和几何取向中的至少一个。 该方法包括通过在基于补丁的优化算法的迭代中处理图像中的补丁来识别使用计算机设备的第二图像的内容。 基于补丁的优化符合约束。该方法包括基于基于补丁的优化算法的迭代从所识别的内容生成第二图像。 第二图像包括生成以表示第一特征并遵守约束的第二特征。

公开(公告)号：US20130124951A1

公开(公告)日：2013-05-16

申请号：US12324345

申请日：2008-11-26

申请人： Eli Shechtman ,  Shai Bagon ,  Aseem O. Agarwala

发明人： Eli Shechtman ,  Shai Bagon ,  Aseem O. Agarwala

IPC分类号： G06F17/00 ,  G06K9/36 ,  G06K9/00

CPC分类号： G06T7/38 ,  G06K9/00718 ,  G06T3/0006 ,  G06T3/0056 ,  G06T13/80 ,  G06T2207/20036

摘要： A method, system, and computer-readable storage medium for performing content based transitions between images. Image content within each image of a set of images are analyzed to determine at least one respective characteristic metric for each image. A respective transition score for each pair of at least a subset of the images is determined with respect to each transition effect of a plurality of transition effects based on the at least one respective characteristic metric for each image. Transition effects implementing transitions between successive images for a sequence of the images are determined based on the transition scores. An indication of the determined transition effects is stored. The determined transition effects are useable to present the images in a slideshow or other image sequence presentation.

摘要翻译： 一种用于在图像之间执行基于内容的转换的方法，系统和计算机可读存储介质。 分析一组图像的每个图像内的图像内容以确定每个图像的至少一个相应的特征度量。 基于每个图像的至少一个相应的特征度量，针对每个图像的至少一个子集对于多个过渡效应的每个过渡效应来确定每对图像的相应过渡分数。 基于转换分数来确定针对图像序列的连续图像之间的转换的转换效果。 存储确定的过渡效果的指示。 确定的过渡效果可用于以幻灯片或其他图像序列呈现来呈现图像。

公开(公告)号：US08811771B2

公开(公告)日：2014-08-19

申请号：US12324345

申请日：2008-11-26

申请人： Eli Shechtman ,  Shai Bagon ,  Aseem O. Agarwala

发明人： Eli Shechtman ,  Shai Bagon ,  Aseem O. Agarwala

IPC分类号： G06K9/32

CPC分类号： G06T7/38 ,  G06K9/00718 ,  G06T3/0006 ,  G06T3/0056 ,  G06T13/80 ,  G06T2207/20036

摘要： A method, system, and computer-readable storage medium for performing content based transitions between images. Image content within each image of a set of images are analyzed to determine at least one respective characteristic metric for each image. A respective transition score for each pair of at least a subset of the images is determined with respect to each transition effect of a plurality of transition effects based on the at least one respective characteristic metric for each image. Transition effects implementing transitions between successive images for a sequence of the images are determined based on the transition scores. An indication of the determined transition effects is stored. The determined transition effects are useable to present the images in a slideshow or other image sequence presentation.

摘要翻译： 一种用于在图像之间执行基于内容的转换的方法，系统和计算机可读存储介质。 分析一组图像的每个图像内的图像内容以确定每个图像的至少一个相应的特征度量。 基于每个图像的至少一个相应的特征度量，针对每个图像的至少一个子集对于多个过渡效应的每个过渡效应来确定每对图像的相应过渡分数。 基于转换分数来确定针对图像序列的连续图像之间的转换的转换效果。 存储确定的过渡效果的指示。 确定的过渡效果可用于以幻灯片或其他图像序列呈现来呈现图像。

公开(公告)号：US08189866B1

公开(公告)日：2012-05-29

申请号：US12317340

申请日：2008-12-19

申请人： Chunhui Gu ,  Eli Shechtman

发明人： Chunhui Gu ,  Eli Shechtman

IPC分类号： G06K9/00

CPC分类号： G06K9/00335

摘要： The present disclosure includes, among other things, systems, methods and program products applying a plurality of low-level feature detectors to an image where each low-level feature detector produces a respective low-level feature vector that represents a detection result. The low-level feature vectors are provided to a plurality of higher-level feature detectors where each higher-level feature detector produces a respective higher-level feature vector that represents a detection result based on a distribution of features in one or more of the low-level feature vectors. The higher-level feature vectors are then provided to a classifier in order to classify a human-action in the image.

摘要翻译： 本公开尤其包括将多个低级特征检测器应用于图像的系统，方法和程序产品，其中每个低级特征检测器产生表示检测结果的相应的低级特征向量。 低级特征向量被提供给多个较高级别的特征检测器，其中每个较高级特征检测器产生相应的较高级特征向量，该特征向量表示基于一个或多个低位特征中的特征分布的检测结果 级特征向量。 然后将较高级特征向量提供给分类器，以便对图像中的人为动作进行分类。

公开(公告)号：US08244063B2

公开(公告)日：2012-08-14

申请号：US11401449

申请日：2006-04-11

申请人： Eli Shechtman ,  Michal Irani

发明人： Eli Shechtman ,  Michal Irani

IPC分类号： G06K9/64

CPC分类号： G06K9/64 ,  G06K9/00335

摘要： A method includes measuring the likelihood that two different space-time video segments could have resulted from a similar underlying motion field without computing the field. The method may be employed to identify locations in a video sequence where at least one behavioral phenomenon similar to that demonstrated in the video segment occurs. For example, the phenomenon might be a dynamic behavior, an action, a rigid motion, and/or a non-rigid motion.

摘要翻译： 一种方法包括测量在不计算场的情况下两个不同的时空视频段可能由类似的底层运动场产生的可能性。 可以采用该方法来识别视频序列中的位置，其中发生与视频段中示出的类似的至少一个行为现象。 例如，该现象可能是动态行为，动作，刚性运动和/或非刚性运动。

公开(公告)号：US20070237419A1

公开(公告)日：2007-10-11

申请号：US11401449

申请日：2006-04-11

申请人： Eli Shechtman ,  Michal Irani

发明人： Eli Shechtman ,  Michal Irani

IPC分类号： G06K9/64

CPC分类号： G06K9/64 ,  G06K9/00335

摘要： A method includes measuring the likelihood that two different space-time video segments could have resulted from a similar underlying motion field without computing the field. The method may be employed to identify locations in a video sequence where at least one behavioral phenomenon similar to that demonstrated in the video segment occurs. For example, the phenomenon might be a dynamic behavior, an action, a rigid motion, and/or a non-rigid motion.

摘要翻译： 一种方法包括测量在不计算场的情况下两个不同的时空视频段可能由类似的底层运动场产生的可能性。 可以采用该方法来识别视频序列中的位置，其中发生与视频段中示出的类似的至少一个行为现象。 例如，该现象可能是动态行为，动作，刚性运动和/或非刚性运动。

公开(公告)号：US20100104158A1

公开(公告)日：2010-04-29

申请号：US12519522

申请日：2007-12-20

申请人： Eli Shechtman ,  Michal Irani

发明人： Eli Shechtman ,  Michal Irani

IPC分类号： G06K9/46

CPC分类号： G06K9/46

摘要： A method includes matching at least portions of first, second signals using local self-similarity descriptors of the signals. The matching includes computing a local self-similarity descriptor for each one of at least a portion of points in the first signal, forming a query ensemble of the descriptors for the first signal and seeking an ensemble of descriptors of the second signal which matches the query ensemble of descriptors. This matching can be used for image categorization, object classification, object recognition, image segmentation, image alignment, video categorization, action recognition, action classification, video segmentation, video alignment, signal alignment, multi-sensor signal alignment, multi-sensor signal matching, optical character recognition, image and video synthesis, correspondence estimation, signal registration and change detection. It may also be used to synthesize a new signal with elements similar to those of a guiding signal synthesized from portions of the reference signal. Apparatus is also included.

摘要翻译： 一种方法包括使用信号的局部自相似性描述符来匹配第一，第二信号的至少一部分。 所述匹配包括为所述第一信号中的至少一部分点中的每一个计算一个局部自相似性描述符，形成所述第一信号的所述描述符的查询集合，并且寻找与所述查询匹配的所述第二信号的描述符的整体 描述符集合 该匹配可用于图像分类，对象分类，对象识别，图像分割，图像对齐，视频分类，动作识别，动作分类，视频分割，视频对齐，信号对齐，多传感器信号对齐，多传感器信号匹配 ，光学字符识别，图像和视频合成，对应估计，信号配准和变化检测。 它也可以用于合成具有与参考信号的部分合成的引导信号类似的元件的新信号。 还包括装置。

公开(公告)号：US07428019B2

公开(公告)日：2008-09-23

申请号：US10498345

申请日：2002-12-26

申请人： Michal Irani ,  Yaron Caspi ,  Eli Shechtman

发明人： Michal Irani ,  Yaron Caspi ,  Eli Shechtman

IPC分类号： H04N5/262 ,  H04N5/225

CPC分类号： G06T3/4069 ,  H04N5/217 ,  H04N5/225 ,  H04N5/77 ,  H04N7/01 ,  H04N7/0125 ,  H04N7/12

摘要： A system and method for increasing space or time resolution of an image sequence by combination of a plurality input sources with different space-time resolutions such that the single output displays increased accuracy and clarity without the calculation of motion vectors. This system of enhancement may be used on any optical recording device, including but not limited to digital video, analog video, still pictures of any format and so forth. The present invention includes support for example for such features as single frame resolution increase, combination of a number of still pictures, the option to calibrate spatial or temporal enhancement or any combination thereof, increased video resolution by using high-resolution still cameras as enhancement additions and may optionally be implemented using a camera synchronization method.

摘要翻译： 通过组合具有不同空间 - 时间分辨率的多个输入源来增加图像序列的空间或时间分辨率的系统和方法，使得单个输出在不计算运动矢量的情况下显示增加的精度和清晰度。 该增强系统可以用于任何光学记录装置，包括但不限于数字视频，模拟视频，任何格式的静止图像等。 本发明包括例如对于诸如单帧分辨率增加，多个静止图像的组合，校准空间或时间增强的选项或其任何组合的特征的支持，通过使用高分辨率静态相机作为增强添加来增加视频分辨率 并且可以可选地使用相机同步方法来实现。