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. 发明申请

WO2007076892A1 EDGE COMPARISON IN SEGMENTATION OF VIDEO SEQUENCES 审中-公开
标题翻译：视频序列分段的边缘比较
公开(公告)号：WO2007076892A1
公开(公告)日：2007-07-12
申请号：PCT/EP2005/057228
申请日：2005-12-30
申请人： TELECOM ITALIA S.P.A. , ROSSATO, Luca , VARESIO, Andrea
发明人： ROSSATO, Luca , VARESIO, Andrea
IPC分类号： G06T5/00
CPC分类号： G06K9/38 , G06T7/12 , G06T7/155 , G06T7/194 , G06T2207/10016 , G06T2207/20081
摘要： A method of image processing, comprising: receiving at least one video frame of a video sequence, the at least one video frame comprising at least one foreground subject and a background; and processing the at least one video frame so as to separate the at least one foreground subject from said background. The processing includes: obtaining a reference image including the background; comparing the at least one video frame to the reference image; and generating a pixel mask as a result of the comparison, the pixel mask indicating whether a pixel of the at least one video frame belongs to the foreground subject or to the background. The method further comprises at least partially determining edges of the at least one foreground subject in the at least one video frame, and modifying the pixel mask based on the determined foreground subject edges.
摘要翻译：一种图像处理方法，包括：接收视频序列的至少一个视频帧，所述至少一个视频帧包括至少一个前景对象和背景; 以及处理所述至少一个视频帧，以将所述至少一个前景对象与所述背景分离。该处理包括：获得包括背景的参考图像; 将所述至少一个视频帧与所述参考图像进行比较; 以及作为所述比较的结果生成像素掩模，所述像素掩码指示所述至少一个视频帧的像素是否属于前景对象或背景。该方法还包括至少部分地确定至少一个视频帧中的至少一个前景对象的边缘，以及基于所确定的前景对象边缘来修改像素掩码。

2. 发明申请

WO2007076891A1 AVERAGE CALCULATION IN COLOR SPACE, PARTICULARLY FOR SEGMENTATION OF VIDEO SEQUENCES 审中-公开
标题翻译：颜色空间中的平均值计算，特别是视频序列的分割
公开(公告)号：WO2007076891A1
公开(公告)日：2007-07-12
申请号：PCT/EP2005/057225
申请日：2005-12-30
申请人： TELECOM ITALIA S.P.A. , ROSSATO, Luca , VARESIO, Andrea , PORTA, Alessandro
发明人： ROSSATO, Luca , VARESIO, Andrea , PORTA, Alessandro
IPC分类号： G06T5/00 , H04N5/272
CPC分类号： H04N5/272 , G06T7/12 , G06T7/155 , G06T7/194 , G06T7/90 , G06T2207/10016 , G06T2207/20081
摘要： A method of image processing, comprises providing a plurality of image frames and processing the at least one image frame. A description of a plurality of pixels of the plurality of image frames is provided in a color space (e.g. HSV) including at least an angular coordinate (e.g. the Hue). A method is disclosed for reliably calculating the average of the angular coordinate.
摘要翻译：一种图像处理方法，包括提供多个图像帧并处理所述至少一个图像帧。多个图像帧中的多个像素的描述被提供在至少包括角坐标（例如，色调）的颜色空间（例如，HSV）中。公开了一种用于可靠地计算角坐标的平均值的方法。

3. 发明申请

WO2007076893A1 EDGE-GUIDED MORPHOLOGICAL CLOSING IN SEGMENTATION OF VIDEO SEQUENCES 审中-公开
标题翻译： EDGE指导的视频序列分割中的形态闭合
公开(公告)号：WO2007076893A1
公开(公告)日：2007-07-12
申请号：PCT/EP2005/057230
申请日：2005-12-30
申请人： TELECOM ITALIA S.P.A. , ROSSATO, Luca , VARESIO, Andrea
发明人： ROSSATO, Luca , VARESIO, Andrea
IPC分类号： G06T5/30 , G06T5/00
CPC分类号： G06K9/38 , G06T7/12 , G06T7/155 , G06T2207/10016 , G06T2207/20081
摘要： A method of image processing, comprising receiving at least one video frame of a video sequence, the at least one video frame comprising at least one foreground subject and a background, and processing the at least one video frame so as to separate said at least one foreground subject from said background. The processing includes: generating a pixel mask indicating whether a pixel of the at least one video frame belongs to the foreground subject or to the background, applying morphological closing to the pixel mask, wherein the applying morphological closing comprises, for each pixel of the pixel mask, conditioning a pixel value in the mask to values of neighboring pixels. The conditioning comprises: determining at least edges of the at least one foreground subject in the at least one video frame; and, for the generic pixel under processing, determining the neighboring pixels based on the determined edges.
摘要翻译：一种图像处理方法，包括：接收视频序列的至少一个视频帧，所述至少一个视频帧包括至少一个前景主题和背景，以及处理所述至少一个视频帧，以便分离所述至少一个前景主题从所述背景。所述处理包括：生成指示所述至少一个视频帧的像素是否属于所述前景对象或所述背景的像素掩码，对所述像素掩模应用形态关闭，其中所述应用形态关闭包括对于所述像素的每个像素掩模，将掩模中的像素值调整为相邻像素的值。所述条件包括：至少确定所述至少一个视频帧中的所述至少一个前景对象的边缘; 并且对于正在处理的通用像素，基于所确定的边缘来确定相邻像素。

4. 发明申请

WO2007076894A1 CONTOUR FINDING IN SEGMENTATION OF VIDEO SEQUENCES 审中-公开
标题翻译：在视频序列分段中的轮廓发现
公开(公告)号：WO2007076894A1
公开(公告)日：2007-07-12
申请号：PCT/EP2005/057232
申请日：2005-12-30
申请人： TELECOM ITALIA S.P.A. , ROSSATO, Luca , VARESIO, Andrea
发明人： ROSSATO, Luca , VARESIO, Andrea
IPC分类号： G06T5/00
CPC分类号： G06T7/155 , G06T7/12 , G06T7/194 , G06T2207/10016
摘要： A method of image processing comprises: receiving at least one video frame of a video sequence, the at least one video frame comprising at least one foreground subject and a background; and processing the at least one video frame so as to separate the at least one foreground subject from said background. The processing includes: generating a pixel mask containing information indicating, for each pixel of the at least one video frame, whether the pixel belongs to the foreground subject or to the background ; and determining contours of the at least one foreground subject on the pixel mask. The determining of the contours comprises, for each pixel in the at least one video frame: based on the information included in the pixel mask, determining whether at least one pixel border belongs to a contour of the at least one foreground subject, the at least one pixel border separating the pixel from a respective at least one adjacent pixel.
摘要翻译：一种图像处理方法包括：接收视频序列的至少一个视频帧，所述至少一个视频帧包括至少一个前景主题和背景; 以及处理所述至少一个视频帧，以将所述至少一个前景对象与所述背景分离。该处理包括：生成包含用于指示至少一个视频帧的每个像素的像素是否属于前景对象或背景的信息的像素掩码; 以及确定所述像素掩模上的所述至少一个前景物体的轮廓。轮廓的确定对于至少一个视频帧中的每个像素包括：基于包括在像素掩模中的信息，确定至少一个像素边界是否属于至少一个前景对象的轮廓，至少将像素与相应的至少一个相邻像素分开的一个像素边界。

5. 发明申请

WO2007076890A1 SEGMENTATION OF VIDEO SEQUENCES 审中-公开
标题翻译：视频序列分段
公开(公告)号：WO2007076890A1
公开(公告)日：2007-07-12
申请号：PCT/EP2005/057224
申请日：2005-12-30
申请人： TELECOM ITALIA S.P.A. , ROSSATO, Luca , VARESIO, Andrea , PORTA, Alessandro
发明人： ROSSATO, Luca , VARESIO, Andrea , PORTA, Alessandro
IPC分类号： G06T5/00
CPC分类号： G06T7/155 , G06T7/12 , G06T7/194 , G06T2207/10016 , G06T2207/20081
摘要： A method of image processing, comprising: providing a data processing apparatus, comprising a central processing unit and a graphics processing unit; feeding at least one video frame of a video sequence to the data processing apparatus, the at least one video frame comprising at least one foreground subject and a background; processing the at least one video frame in the data processing apparatus so as to separate the at least one foreground subject from the background. The processing is at least partially performed by the processors of the graphics processing unit.
摘要翻译：一种图像处理方法，包括：提供数据处理装置，包括中央处理单元和图形处理单元; 将至少一个视频序列的视频帧馈送到所述数据处理设备，所述至少一个视频帧包括至少一个前景主题和背景; 处理所述数据处理装置中的所述至少一个视频帧，以将所述至少一个前景对象与所述背景分离。处理至少部分地由图形处理单元的处理器执行。

6. 发明申请

WO2006111179A1 METHOD AND APPARATUS FOR DIGITAL IMAGE CODING 审中-公开
标题翻译：数字图像编码方法与装置
公开(公告)号：WO2006111179A1
公开(公告)日：2006-10-26
申请号：PCT/EP2005/004167
申请日：2005-04-19
申请人： TELECOM ITALIA S.p.A. , ROSSATO, Luca , VARESIO, Andrea
发明人： ROSSATO, Luca , VARESIO, Andrea
IPC分类号： H04N7/50
CPC分类号： H04N19/136 , H04N19/103 , H04N19/105 , H04N19/132 , H04N19/176 , H04N19/196 , H04N19/61
摘要： A method of coding a digital image comprises subdividing the image into image blocks formed by a plurality of pixels, and processing each image block of the image, by determining a skip-mode prediction block in respect of the current image block being processed, calculating a difference between the image block being processed and the skip-mode prediction block, comparing the calculated difference to a predetermined threshold. The calculation of the difference between the current image block being processed and the skip-mode prediction block includes: calculating a plurality of pixel-by-pixel differences between a pixel of the current image block and a corresponding pixel of the skip-mode prediction image block; associating a respective quantized value to each pixel-by-pixel difference; and cumulating the quantized values.
摘要翻译：一种对数字图像进行编码的方法包括：将图像细分成由多个像素形成的图像块，并通过对正在处理的当前图像块确定一个跳过模式预测块，计算一个图像块，正在处理的图像块和跳过模式预测块之间的差异，将计算出的差值与预定阈值进行比较。正在处理的当前图像块和跳过模式预测块之间的差的计算包括：计算当前图像块的像素与跳过模式预测图像的对应像素之间的多个像素像素差异块; 将各个量化值与逐像素差分相关联; 并累积量化值。

7. 发明申请

WO2013171182A8 DECODING AND RECONSTRUCTION OF TIME-BASED AND/OR MULTIDIMENSIONAL SIGNALS IN A TIERED TEMPORAL HIERARCHY 审中-公开
公开(公告)号：WO2013171182A8
公开(公告)日：2013-11-21
申请号：PCT/EP2013/059880
申请日：2013-05-14
申请人： ROSSATO, Luca , MEARDI, Guido
发明人： ROSSATO, Luca , MEARDI, Guido
IPC分类号： H04N7/26
摘要： Computer processor hardware receiving encoded data and reconstructing samples of a signal which are encoded in a tiered hierarchy that comprises a first tier having a lower level of quality and at least a second tier having a higher level of quality, wherein each of these tiers has a distinct level of quality, and comprises one or more of the samples encoded in the tiered hierarchy. The computer processor hardware computes samples of the second tier through reconstruction operations by starting from at least one of the samples of the first tier.

8. 发明申请

WO2013171175A1 ENCODING AND RECONSTRUCTION OF RESIDUAL DATA BASED ON SUPPORT INFORMATION 审中-公开
标题翻译：基于支持信息编制和重建残留数据
公开(公告)号：WO2013171175A1
公开(公告)日：2013-11-21
申请号：PCT/EP2013/059853
申请日：2013-05-13
申请人： ROSSATO, Luca , MEARDI, Guido
发明人： ROSSATO, Luca , MEARDI, Guido
IPC分类号： H04N7/26 , H04N7/28 , H04N7/30 , H04N7/46
CPC分类号： H04N19/126 , G06T7/248 , H04N19/136 , H04N19/23 , H04N19/33 , H04N19/50 , H04N19/59 , H04N19/62 , H04N19/63 , H04N19/635 , H04N19/87 , H04N19/94
摘要： Computer processor hardware receives a sequence of sets of values. The computer processor hardware processes the sequence of sets of values and utilizes the values of the multiple sets in the sequence to produce a set of support values, wherein said set of support values are determined so as to form a baseline to substantially reproduce each of the original sets of values in the sequence. The computer processor hardware generates reconstruction data corresponding to said set of support values.
摘要翻译：计算机处理器硬件接收一组值的序列。计算机处理器硬件处理值序列的序列并且利用序列中的多个集合的值来产生一组支持值，其中确定所述一组支持值以便形成基线以基本上再现每个序列中的原始值集。计算机处理器硬件产生对应于所述一组支持值的重建数据。

9. 发明申请

WO2013011492A3 TIERED SIGNAL DECODING AND SIGNAL RECONSTRUCTION 审中-公开
公开(公告)号：WO2013011492A3
公开(公告)日：2013-01-24
申请号：PCT/IB2012/053722
申请日：2012-07-20
申请人： ROSSATO, Luca , MEARDI, Guido
发明人： ROSSATO, Luca , MEARDI, Guido
IPC分类号： H04N7/26 , H04N7/50
摘要： A decoder decodes a first set of data and utilizes the first set of decoded data to reconstruct the signal according to a first level of quality. The decoder further decodes a second set of data and identifies an upsample operation specified by the second set of decoded data. The decoder applies the upsample operation identified in the second set of decoded data to the reconstructed signal at the first level of quality to reconstruct the signal at a second, higher level of quality. To enhance the reconstructed signal, the decoder retrieves residual data from the second set of decoded data. The residual data indicates how to modify the reconstructed signal at the second level of quality subsequent to application of the upsampling operation as discussed above. The decoder then modifies the reconstructed signal at the second level of quality as specified by the residual data.

10. 发明申请

WO2013171184A1 MOTION COMPENSATION AND MOTION ESTIMATION LEVERAGING A CONTINUOUS COORDINATE SYSTEM 审中-公开
标题翻译：运动补偿和运动估计采用连续坐标系统
公开(公告)号：WO2013171184A1
公开(公告)日：2013-11-21
申请号：PCT/EP2013/059886
申请日：2013-05-14
申请人： ROSSATO, Luca , MEARDI, Guido
发明人： ROSSATO, Luca , MEARDI, Guido
IPC分类号： H04N7/36 , H04N7/26 , H04N7/30 , H04N7/28 , H04N7/46
CPC分类号： H04N19/126 , G06T7/248 , H04N19/136 , H04N19/23 , H04N19/33 , H04N19/50 , H04N19/59 , H04N19/62 , H04N19/63 , H04N19/635 , H04N19/87 , H04N19/94
摘要： Computer processor hardware receives settings information for a first image. The first image includes a set of multiple display elements. The computer processor hardware receives motion compensation information for a given display element in a second image to be created based at least in part on the first image. The motion compensation information indicates a coordinate location within a particular display element in the first image to which the given display element pertains. The computer processor hardware utilizes the coordinate location as a basis from which to select a grouping of multiple display elements in the first image. The computer processor hardware then generates a setting for the given display element in the second image based on settings of the multiple display elements in the grouping.
摘要翻译：计算机处理器硬件接收第一个图像的设置信息。第一个图像包括一组多个显示元素。计算机处理器硬件至少部分地基于第一图像，在要创建的第二图像中接收给定显示元素的运动补偿信息。运动补偿信息指示给定显示元件所属的第一图像内的特定显示元素内的坐标位置。计算机处理器硬件利用坐标位置作为选择第一图像中的多个显示元素的分组的基础。计算机处理器硬件然后基于分组中的多个显示元素的设置生成第二图像中的给定显示元素的设置。

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