专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09025880B2 Visual saliency estimation for images and video 有权
标题翻译：图像和视频的视觉显着性估计
公开(公告)号：US09025880B2
公开(公告)日：2015-05-05
申请号：US13598084
申请日：2012-08-29
申请人： Federico Perazzi , Alexander Hornung , Philipp Krähenbühl , Yael Pritch
发明人： Federico Perazzi , Alexander Hornung , Philipp Krähenbühl , Yael Pritch
IPC分类号： G06K9/46 , H04N19/117
CPC分类号： G06K9/4676 , G06K9/4652 , G06K9/4671 , G06K9/6212 , G06K9/6215 , G06T7/11 , G06T7/194 , G06T7/246 , G06T7/44 , G06T7/90 , G06T2207/10004 , G06T2207/10016 , G06T2207/10024 , H04N19/117
摘要： Methods and apparatus for visual saliency estimation for images and video are described. In an embodiment, a process includes decomposing, by a processor, an image into elements, wherein each element includes at least one pixel. The processor then calculates a first image measure indicative of each element's uniqueness in the image on a per element basis, and a second image measure indicative of each element's spatial distribution in the image on a per element basis. A per element saliency measure is provided by combining the first image measure and the second image measure, or by utilizing the first image measure, or by utilizing the second image measure.
摘要翻译：描述了用于图像和视频的视觉显着性估计的方法和装置。在一个实施例中，过程包括由处理器将图像分解为元素，其中每个元素包括至少一个像素。然后，处理器计算指示每个元素基于每个元素的每个元素在图像中的唯一性的第一图像测量，以及基于每个元素的图像中的每个元素的空间分布的第二图像测量。通过组合第一图像测量和第二图像测量，或通过利用第一图像测量，或通过利用第二图像测量来提供每个元素显着性度量。

2. 发明授权

US06831677B2 System and method for facilitating the adjustment of disparity in a stereoscopic panoramic image pair 有权
标题翻译：用于促进立体全景图像对中的视差调整的系统和方法
公开(公告)号：US06831677B2
公开(公告)日：2004-12-14
申请号：US09792638
申请日：2001-02-24
申请人： Shmuel Peleg , Moshe Ben-Ezra , Yael Pritch
发明人： Shmuel Peleg , Moshe Ben-Ezra , Yael Pritch
IPC分类号： H04N700
CPC分类号： G06T3/4038 , G06T2207/10012 , H04N2013/0088
摘要： A system for generating a stereoscopic panoramic image pair having left and right panoramic mosaic images for use in facilitating stereoscopic viewing of a panoramic scene, the system comprising a panoramic image generator and a strip separation value generation module. The panoramic image generator is configured to mosaic together respective left and right image strips from respective ones of a plurality of images to form the respective left and right panoramic images. The panoramic image generator is configured to use strip separation values for the respective images to determine the separation of the respective left and right image strips in generating the respective left and right panoramic images. The strip separation value generation module is configured to generate, for respective ones of said images, the strip separation values so as to provide at least one selected disparity for objects in the panoramic scene.
摘要翻译：一种用于产生具有用于促进全景场景的立体观看的左和右全景马赛克图像的立体全景图像对的系统，所述系统包括全景图像生成器和条带分离值生成模块。全景图像生成器被配置为将来自多个图像中的相应的左图像条和右图像条拼接在一起以形成相应的左和右全景图像。全景图像生成器被配置为对各个图像使用条带分离值来确定在生成相应的左和右全景图像时相应的左和右图像条的分离。条带分离值生成模块被配置为针对相应的所述图像生成条带分离值，以便为全景场景中的对象提供至少一个选择的视差。

3. 发明授权

US08249394B2 Method and system for shift-map image editing 有权
标题翻译：移位图图像编辑的方法和系统
公开(公告)号：US08249394B2
公开(公告)日：2012-08-21
申请号：US12723248
申请日：2010-03-12
申请人： Shmuel Peleg , Yael Pritch , Eitam Kav Venaki
发明人： Shmuel Peleg , Yael Pritch , Eitam Kav Venaki
IPC分类号： G06K9/32 , G06K9/36 , G09G5/00
CPC分类号： G06T11/60
摘要： Natural looking output images are computed from input images based on given user constraints. Pixels in the output images are assigned a shift such that the respective output pixel value is derived from the value of the input pixel whose location is related to that of the output pixel by the shift, at least one shift being non-zero. The shift is determined by an optimization process adapted to minimize a cost function that includes a data term on the shifts of single pixels and a smoothness term on the shifts of pixel pairs. The output image is computed by applying the optimized shift-map between the input and output pixels. The data term can include shift constraints that limit the location in the output images of selected input pixels, and saliency constraints, indicating a preference that selected pixels in the input images will or will not appear in the output image.
摘要翻译：基于给定的用户约束，从输入图像计算自然观察输出图像。输出图像中的像素被赋予移位，使得相应的输出像素值是通过偏移从位置与输出像素的位置相关的输入像素的值导出的，至少一个移位不为零。移位由适于最小化成本函数的优化过程确定，该成本函数包括单个像素的偏移上的数据项和像素对的偏移上的平滑项。通过在输入和输出像素之间应用优化的移位图来计算输出图像。数据项可以包括限制所选输入像素的输出图像中的位置的偏移约束和显着约束，指示输入图像中的选定像素将会或不会出现在输出图像中的偏好。

4. 发明申请

US20100232729A1 METHOD AND SYSTEM FOR SHIFT-MAP IMAGE EDITING 有权
标题翻译：用于移位图像编辑的方法和系统
公开(公告)号：US20100232729A1
公开(公告)日：2010-09-16
申请号：US12723248
申请日：2010-03-12
申请人： Shmuel Peleg , Yael Pritch , Eitam Kav Venaki
发明人： Shmuel Peleg , Yael Pritch , Eitam Kav Venaki
IPC分类号： G06K9/36 , G06K9/32
CPC分类号： G06T11/60
摘要： Natural looking output images are computed from input images based on given user constraints. Pixels in the output images are assigned a shift such that the respective output pixel value is derived from the value of the input pixel whose location is related to that of the output pixel by the shift, at least one shift being non-zero. The shift is determined by an optimization process adapted to minimize a cost function that includes a data term on the shifts of single pixels and a smoothness term on the shifts of pixel pairs. The output image is computed by applying the optimized shift-map between the input and output pixels. The data term can include shift constraints that limit the location in the output images of selected input pixels, and saliency constraints, indicating a preference that selected pixels in the input images will or will not appear in the output image.
摘要翻译：基于给定的用户约束，从输入图像计算自然观察输出图像。输出图像中的像素被赋予移位，使得相应的输出像素值是通过偏移从位置与输出像素的位置相关的输入像素的值导出的，至少一个移位不为零。移位由适于最小化成本函数的优化过程确定，该成本函数包括单个像素的偏移上的数据项和像素对的偏移上的平滑项。通过在输入和输出像素之间应用优化的移位图来计算输出图像。数据项可以包括限制所选输入像素的输出图像中的位置的偏移约束和显着约束，指示输入图像中的选定像素将会或不会出现在输出图像中的偏好。

5. 发明授权

US08949235B2 Methods and systems for producing a video synopsis using clustering 有权
标题翻译：使用聚类制作视频概要的方法和系统
公开(公告)号：US08949235B2
公开(公告)日：2015-02-03
申请号：US12623217
申请日：2009-11-20
申请人： Shmuel Peleg , Yael Pritch , Sarit Ratovitch , Avishai Hendel
发明人： Shmuel Peleg , Yael Pritch , Sarit Ratovitch , Avishai Hendel
IPC分类号： G06F17/30 , G06K9/00 , G06F7/00
CPC分类号： G06K9/00751 , G06F17/30811 , G06F17/30814 , G06F17/30843 , Y10S707/914
摘要： Computer-implemented method, system, and techniques for summarization, searching, and indexing of video are provided, wherein data related to objects detected in the video in a selected time interval is received and the objects are clustered into clusters such that each cluster includes objects that are similar in respect to a selected feature or a combination of features. A video summary is generated based on the computed clusters.
摘要翻译：提供了计算机实现的方法，系统和用于视频的摘要，搜索和索引的技术，其中接收与在选定时间间隔内在视频中检测到的对象相关的数据，并且将对象聚类成群集，使得每个群集包括对象相对于所选择的特征或特征的组合是相似的。基于计算的集群生成视频摘要。

6. 发明授权

US08520060B2 Method and a system for calibrating and/or visualizing a multi image display and for reducing ghosting artifacts 有权
标题翻译：用于校准和/或可视化多图像显示并减少重影伪像的方法和系统
公开(公告)号：US08520060B2
公开(公告)日：2013-08-27
申请号：US12528328
申请日：2008-02-25
申请人： Assaf Zomet , Dan Elharrar , Yael Pritch , Chanoch Havlin , Yaron Tadmor
发明人： Assaf Zomet , Dan Elharrar , Yael Pritch , Chanoch Havlin , Yaron Tadmor
IPC分类号： G06T15/00 , G09G5/02 , G09G5/10 , H04N13/02 , H04N13/04 , H04N5/232 , G03H1/02 , G02B21/00 , G02B27/22 , G02B27/26 , G02B27/10 , G02B13/06 , G02B5/08 , G06K9/00 , G06K9/74 , G06K9/40 , G03F1/00 , A61M21/00
CPC分类号： G03B25/02 , G03B35/14 , G03B35/24 , H04N13/305 , H04N13/327
摘要： A method for identifying a blur profile of a multi image display with a first image separating mask. The method comprises displaying a calibration pattern through a second image separating mask, allowing an evaluator to provide a visual estimation indicating a blur brought about to the calibration pattern by the second image separating mask, and generating a blur profile of at least the first image separating mask according to the visual estimation. The first and second image separating masks having a substantially similar optical profile.
摘要翻译：一种用于利用第一图像分离掩模来识别多图像显示器的模糊轮廓的方法。该方法包括通过第二图像分离掩模显示校准图案，允许评估器提供指示通过第二图像分离掩模带来的对模糊的模糊的视觉估计，并且产生至少第一图像分离的模糊轮廓面具根据视觉估计。第一和第二图像分离掩模具有基本相似的光学轮廓。

7. 发明授权

US07477284B2 System and method for capturing and viewing stereoscopic panoramic images 有权
标题翻译：拍摄和观看立体全景图像的系统和方法
公开(公告)号：US07477284B2
公开(公告)日：2009-01-13
申请号：US09861859
申请日：2001-04-19
申请人： Shmuel Peleg , Moshe Ben-Ezra , Yael Pritch
发明人： Shmuel Peleg , Moshe Ben-Ezra , Yael Pritch
IPC分类号： H04N13/00
CPC分类号： H04N13/282 , H04N13/194
摘要： Method and apparatus for generating images of a scene from image data of the scene and displaying the images to provide a sense of depth. In some embodiments of the method and apparatus the generated images are mosaics.
摘要翻译：用于从场景的图像数据生成场景的图像并显示图像以提供深度感的方法和装置。在方法和装置的一些实施例中，生成的图像是马赛克。

8. 发明申请

US20140063275A1 VISUAL SALIENCY ESTIMATION FOR IMAGES AND VIDEO 有权
标题翻译：图像和视频的视觉平均估计
公开(公告)号：US20140063275A1
公开(公告)日：2014-03-06
申请号：US13598084
申请日：2012-08-29
申请人： Philipp Krähenbühl , Yael Pritch , Federico Perazzi , Alexander Hornung
发明人： Philipp Krähenbühl , Yael Pritch , Federico Perazzi , Alexander Hornung
IPC分类号： G06K9/36 , H04N5/228 , G06K9/46
CPC分类号： G06K9/4676 , G06K9/4652 , G06K9/4671 , G06K9/6212 , G06K9/6215 , G06T7/11 , G06T7/194 , G06T7/246 , G06T7/44 , G06T7/90 , G06T2207/10004 , G06T2207/10016 , G06T2207/10024 , H04N19/117
摘要： Methods and apparatus for visual saliency estimation for images and video are described. In an embodiment, a process includes decomposing, by a processor, an image into elements, wherein each element includes at least one pixel. The processor then calculates a first image measure indicative of each element's uniqueness in the image on a per element basis, and a second image measure indicative of each element's spatial distribution in the image on a per element basis. A per element saliency measure is provided by combining the first image measure and the second image measure, or by utilizing the first image measure, or by utilizing the second image measure.
摘要翻译：描述了用于图像和视频的视觉显着性估计的方法和装置。在一个实施例中，过程包括由处理器将图像分解为元素，其中每个元素包括至少一个像素。然后，处理器计算指示每个元素基于每个元素的每个元素在图像中的唯一性的第一图像测量，以及基于每个元素的图像中的每个元素的空间分布的第二图像测量。通过组合第一图像测量和第二图像测量，或通过利用第一图像测量，或通过利用第二图像测量来提供每个元素显着性度量。

9. 发明申请

US20100066817A1 METHOD AND A SYSTEM FOR CALIBRATING AND/OR VISUALIZING A MULTI IMAGE DISPLAY AND FOR REDUCING GHOSTING ARTIFACTS 有权
标题翻译：用于校准和/或可视化多图像显示和减少激励作用的方法和系统
公开(公告)号：US20100066817A1
公开(公告)日：2010-03-18
申请号：US12528328
申请日：2008-02-25
申请人： Assaf Zomet , Dan Elharrar , Yael pritch , Chanoch Havlin , Yaron Tadmor
发明人： Assaf Zomet , Dan Elharrar , Yael pritch , Chanoch Havlin , Yaron Tadmor
IPC分类号： H04N13/04 , G06K15/02
CPC分类号： G03B25/02 , G03B35/14 , G03B35/24 , H04N13/305 , H04N13/327
摘要： A method for identifying a blur profile of a multi image display with a first image separating mask. The method comprises displaying a calibration pattern through a second image separating mask, allowing an evaluator to provide a visual estimation indicating a blur brought about to the calibration pattern by the second image separating mask, and generating a blur profile of at least the first image separating mask according to the visual estimation. The first and second image separating masks having a substantially similar optical profile.
摘要翻译：一种用于利用第一图像分离掩模来识别多图像显示器的模糊轮廓的方法。该方法包括通过第二图像分离掩模显示校准图案，允许评估器提供指示通过第二图像分离掩模带来的对模糊的模糊的视觉估计，并且产生至少第一图像分离的模糊轮廓面具根据视觉估计。第一和第二图像分离掩模具有基本相似的光学轮廓。

10. 发明申请

US20060215934A1 Online registration of dynamic scenes using video extrapolation 审中-公开
标题翻译：使用视频外推的动态场景的在线注册
公开(公告)号：US20060215934A1
公开(公告)日：2006-09-28
申请号：US11378635
申请日：2006-03-20
申请人： Shmuel Peleg , Alexander Rav-Acha , Yael Pritch
发明人： Shmuel Peleg , Alexander Rav-Acha , Yael Pritch
IPC分类号： G06K9/32
CPC分类号： G06T7/269
摘要： A computer-implemented method and system determines camera movement of a new frame relative to a sequence of frames of images containing at least one dynamic object and for which relative camera movement is assumed. From changes in color values of sets of pixels in different frames of the sequence for which respective locations of all pixels in each set are adjusted so as to neutralize the effect of camera movement between the respective frames in the sequence containing the pixels, corresponding color values of the pixels in the new frame are predicted and used to determine camera movement as a relative movement of the new frame and the predicted frame. An embodiment of the invention maintains an aligned space-time volume of frames for which camera movement is neutralized and adds each new frame to the aligned space-time volume after neutralizing camera movement in the new frame.
摘要翻译：计算机实现的方法和系统相对于包含至少一个动态对象的图像的帧序列来确定新帧的相机移动，并且假定相对相机移动。从序列的不同帧中的像素集合的颜色值的变化被调整到每一组中的所有像素的相应位置，以便中和在包含像素的序列中的相应帧之间的相机运动的影响，相应的颜色值预测新帧中的像素，并用于确定相机移动作为新帧和预测帧的相对移动。本发明的一个实施例保持对准的空间 - 时间体积的帧，相机移动被中和，并且在中和新帧中的相机运动之后将每个新帧添加到对齐的时空体积。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式