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

WO2004097737A1 SEGMENTATION REFINEMENT 审中-公开
标题翻译：分类改良
公开(公告)号：WO2004097737A1
公开(公告)日：2004-11-11
申请号：PCT/IB2004/050525
申请日：2004-04-27
申请人： KONINKLIJKE PHILIPS ELECTRONICS N.V. , SETHURAMAN, Ramanathan , VAREKAMP, Christiaan , ERNST, Fabian, E.
发明人： SETHURAMAN, Ramanathan , VAREKAMP, Christiaan , ERNST, Fabian, E.
IPC分类号： G06T5/00
CPC分类号： H04N19/85 , G06T7/11 , G06T2207/10016 , G06T2207/20021
摘要： A method of converting of a first set (100a) of initial segments of an image into a second set of updated segments (A',B',C',D') is disclosed. The method comprises iterative updates of intermediate segments (A,B,C,D) being derived from respective initial segments. Each update comprises determining whether a pixel (300) should be moved from a first intermediate segment (A) to a second intermediate segment (B), on basis of a pixel value of the pixel, on basis of a first parameter of the intermediate segment (A) and on basis of a second parameter of the second intermediate segment (B). The iterative updates are performed on block base. That means that first a number of iterative updates are performed for pixels of a first two-dimensional block of pixels (200) of the image and after that the number of iterative updates are performed for pixels of a second two-dimensional block of pixels (204) of the image.
摘要翻译：公开了将图像的初始段的第一组（100a）转换为第二组更新段（A'，B'，C'，D'）的方法。该方法包括从相应的初始段导出的中间段（A，B，C，D）的迭代更新。每个更新包括基于中间片段的第一参数来确定像素（300）是否应当从第一中间片段（A）移动到第二中间片段（B），基于像素的像素值（A）并且基于第二中间段（B）的第二参数。迭代更新以块为基础进行。这意味着首先对图像的第一二维像素块（200）的像素执行多次迭代更新，然后针对第二二维像素块的像素执行迭代更新次数（ 204）的图像。

2. 发明申请

WO2003067868A2 UNIT FOR AND METHOD OF SEGMENTATION 审中-公开
标题翻译：单位和分组方法
公开(公告)号：WO2003067868A2
公开(公告)日：2003-08-14
申请号：PCT/IB2003/000186
申请日：2003-01-23
申请人： KONINKLIJKE PHILIPS ELECTRONICS N.V. , ERNST, Fabian, E. , VAREKAMP, Christiaan
发明人： ERNST, Fabian, E. , VAREKAMP, Christiaan
IPC分类号： H04N
CPC分类号： G06T7/215 , G06T2207/10016
摘要： The segmentation unit (100,200,300) for assigning a first pixel of a first image of a sequence of images to a segment comprises an assignment unit (102) for assigning a first homogeneity value to the first pixel on basis of the first image; an averaging unit (103) for calculating an average homogeneity value for the first pixel by means of averaging the first homogeneity value and a second homogeneity value being determined for a second pixel of a second image of the sequence of images, with the first pixel and the second pixel related by means of a motion vector; and a comparing unit (106) for comparing the average homogeneity value with a threshold in order to assign the first pixel to the segment.
摘要翻译：用于将图像序列的第一图像的第一像素分配给片段的分割单元（100,200,300）包括用于基于第一图像将第一均匀性值分配给第一像素的分配单元（102）平均单元（103），用于通过对第一像素序列的第二图像的第二像素确定的第一均匀性值和第二均匀性值进行平均来计算第一像素的平均均匀性值，以及通过运动矢量相关的第二像素; 以及用于将平均均匀性值与阈值进行比较以便将第一像素分配给该段的比较单元（106）。

3. 发明申请

WO2005015497A1 DETERMINING DEPTH INFORMATION 审中-公开
标题翻译：确定深度信息
公开(公告)号：WO2005015497A1
公开(公告)日：2005-02-17
申请号：PCT/IB2004/051359
申请日：2004-08-02
申请人： KONINKLIJKE PHILIPS ELECTRONICS N.V. , VAREKAMP, Christiaan , ERNST, Fabian, E.
发明人： VAREKAMP, Christiaan , ERNST, Fabian, E.
IPC分类号： G06T7/60
CPC分类号： G06T7/564
摘要： The invention relates to a method and apparatus of determining depth information of an image by use of T -junctions. An apparatus comprises a segmentation processor (201) which receives an image and segments it into a plurality of image segments having similar characteristics. The segments are fed to a junction extraction processor (203) which determines T -junction candidates. The image segments and T -junction candidates are fed to a depth information processor (205) which determines depth information associated with objects of the image in response to the T-junction candidates. Specifically, predetermined junction models are fitted to the T junction candidates and the model having the closest fit is selected. Depth information for the T -junction is then determined from known depth information of the junction model. In addition certainty measures are determined for the T-junction candidates and the associated depth information.
摘要翻译：本发明涉及一种通过使用T形结构确定图像的深度信息的方法和装置。一种装置包括分割处理器（201），其接收图像并将其分割成具有相似特征的多个图像片段。这些段被馈送到确定T型连接候选的结提取处理器（203）。图像段和T结候选被馈送到深度信息处理器（205），深度信息处理器（205）响应于T连接候选来确定与图像的对象相关联的深度信息。具体地说，将预定的结型号拟合到T结候选中，并且选择具有最接近的拟合的模型。然后，从连接模型的已知深度信息确定T形结的深度信息。另外确定T连接候选者和相关深度信息的确定度量。

4. 发明申请

WO2005027523A1 METHOD AND APPARATUS FOR SCALABLE SIGNAL PROCESSING 审中-公开
标题翻译：可扩展信号处理的方法和装置
公开(公告)号：WO2005027523A1
公开(公告)日：2005-03-24
申请号：PCT/IB2004/051573
申请日：2004-08-26
申请人： KONINKLIJKE PHILIPS ELECTRONICS N.V. , SETHURAMAN, Ramanathan , ERNST, Fabian, E.
发明人： SETHURAMAN, Ramanathan , ERNST, Fabian, E.
IPC分类号： H04N7/24
CPC分类号： H04N19/428 , H04N19/39 , H04N21/2343 , H04N21/2662 , H04N21/4402 , H04N21/4621
摘要： The invention relates to content signal processing and in particular to processing of a video content signal. An apparatus (100) for content signal processing comprises a scalable encoder (101) for encoding a content signal to generate scalable encoded data comprising data associated with a plurality of compression rates. A compression processor (105) determines compression factor indicators indicating data associated with the plurality of compression rates. Thus, the compression factor indicators indicate which data of the scalable encoded data corresponds to the different compression rates. Combined data comprising the scalable encoded data and the compression factor indicators are stored in a frame memory (105). An application having a given compression factor requirement may use the compression factor indicators to access the scalable encoded data of the frame memory (105) which is required for processing. A plurality of applications may access the same frame memory (105) thereby allowing for scalable encoded data which can be used with a plurality of applications having different compression factor requirements.
摘要翻译：本发明涉及内容信号处理，特别涉及视频内容信号的处理。用于内容信号处理的装置（100）包括可缩放编码器（101），用于对内容信号进行编码以产生包括与多个压缩率相关联的数据的可分级编码数据。压缩处理器（105）确定指示与多个压缩率相关联的数据的压缩因子指示符。因此，压缩因子指示符指示可缩放编码数据的哪个数据对应于不同的压缩率。包括可缩放编码数据和压缩因子指示符的组合数据被存储在帧存储器（105）中。具有给定压缩因子要求的应用可以使用压缩因子指示符来访问处理所需的帧存储器（105）的可缩放编码数据。多个应用可以访问相同的帧存储器（105），从而允许可以与具有不同压缩因子要求的多个应用使用的可缩放编码数据。

5. 发明申请

WO2003067868A3 UNIT FOR AND METHOD OF SEGMENTATION 审中-公开
公开(公告)号：WO2003067868A3
公开(公告)日：2003-08-14
申请号：PCT/IB2003/000186
申请日：2003-01-23
申请人： KONINKLIJKE PHILIPS ELECTRONICS N.V. , ERNST, Fabian, E. , VAREKAMP, Christiaan
发明人： ERNST, Fabian, E. , VAREKAMP, Christiaan
IPC分类号： G06T5/00
摘要： The segmentation unit (100,200,300) for assigning a first pixel of a first image of a sequence of images to a segment comprises an assignment unit (102) for assigning a first homogeneity value to the first pixel on basis of the first image; an averaging unit (103) for calculating an average homogeneity value for the first pixel by means of averaging the first homogeneity value and a second homogeneity value being determined for a second pixel of a second image of the sequence of images, with the first pixel and the second pixel related by means of a motion vector; and a comparing unit (106) for comparing the average homogeneity value with a threshold in order to assign the first pixel to the segment.

6. 发明申请

WO2005116925A3 METHOD FOR ELECTRONIC IMAGE PROCESSING 审中-公开
公开(公告)号：WO2005116925A3
公开(公告)日：2005-12-08
申请号：PCT/IB2005/051682
申请日：2005-05-24
申请人： KONINKLIJKE PHILIPS ELECTRONICS N.V. , MEUWISSEN, Patrick, P., E. , SETHURAMAN, Ramanathan , PETERS, Harm, J., A., M. , ERNST, Fabian, E.
发明人： MEUWISSEN, Patrick, P., E. , SETHURAMAN, Ramanathan , PETERS, Harm, J., A., M. , ERNST, Fabian, E.
IPC分类号： G06T7/00 , G06T7/20 , H04N7/26
摘要： A method for electronic image processing wherein a calculation is performed on groups of pixels. Each group comprises a center pixel (21) and a group of surrounding pixels. The calculation is performed on a number of center pixels in parallel, a group of displacement vectors is associated with each centre pixel, and during each step of the calculation for the number of pixels a same displacement vector ((-2,-2);(-2,-1)) is used, wherein for each of the displacement vectors for each of the center pixels a function value is calculated and the displacement vectors are processed sequentially within the group of displacement vectors. Preferably use is made of a footprint cache wherein for each pixel the results of calculations are stored. Preferably the displacement vectors are dealt with line-byline.

7. 发明申请

WO2005052858A1 DETERMINING DEPTH INFORMATION FOR A VIDEO IMAGE 审中-公开
标题翻译：确定视频图像的深度信息
公开(公告)号：WO2005052858A1
公开(公告)日：2005-06-09
申请号：PCT/IB2004/052501
申请日：2004-11-22
申请人： KONINKLIJKE PHILIPS ELECTRONICS N.V. , VAREKAMP, Christiaan , ERNST, Fabian, E.
发明人： VAREKAMP, Christiaan , ERNST, Fabian, E.
IPC分类号： G06T7/00
CPC分类号： G06T7/543
摘要： The invention relates to a system for determining depth information for a video image. The video image is segmented (703) to determine a plurality of image segments. A plurality of junction points associated with the plurality of image segments are determined (705). The junction points may be between three different objects, between two different objects or within a single object. For each junction point, independent depth information data is determined (707, 709, 711) assuming that the junction point corresponds to each of the three possible object associations. The reliability of the assumption is determined in response to a fit of a corresponding model and a depth characteristic is derived (713) by selecting the most reliable information. The depth characteristics of a multiplicity of junction points are then used to determine a depth map. By determining and using depth information of all junction points and not just object T-junctions, additional and improved depth information is obtained.
摘要翻译：本发明涉及一种用于确定视频图像的深度信息的系统。视频图像被分割（703）以确定多个图像片段。确定与多个图像片段相关联的多个连接点（705）。连接点可以在三个不同的对象之间，两个不同的对象之间或一个对象内。对于每个连接点，假设连接点对应于三个可能的对象关联中的每一个，确定独立的深度信息数据（707,709,711）。根据相应模型的拟合来确定假设的可靠性，并通过选择最可靠的信息导出深度特征（713）。然后使用多个连接点的深度特征来确定深度图。通过确定和使用所有连接点的深度信息，而不仅仅是对象T形接头，获得额外和改进的深度信息。

8. 发明申请

WO2004061765A2 METHOD AND APPARATUS FOR DEPTH ORDERING OF DIGITAL IMAGES 审中-公开
标题翻译：数字图像深度订购的方法和装置
公开(公告)号：WO2004061765A2
公开(公告)日：2004-07-22
申请号：PCT/IB2004/000017
申请日：2004-01-05
申请人： KONINKLIJKE PHILIPS ELECTRONICS N.V. , U.S. PHILIPS CORPORATION , ERNST, Fabian, E. , VAREKAMP, Christiaan , WILINSKI, Piotr
发明人： ERNST, Fabian, E. , VAREKAMP, Christiaan , WILINSKI, Piotr
IPC分类号： G06T
CPC分类号： H04N19/20 , G06T7/13 , G06T7/215 , G06T7/579 , G06T2207/10016 , H04N19/543
摘要： In a method for relative depth of parts of one or more digital images, the digital images are regularized by segmentation, and at least part of the pixels of the images are assigned to respective segments. The realtive motion of the segments for successive images is estimated by image matching. The image features of the segments are regularized by dual segmetation, in which the edges of the segments are found, pixels are assigned to the edges, and dual segments are defined. The relative motion of the dual segments for successive images is estimated by image segment matching in order to determine the relative depth order of the image segments.
摘要翻译：在一种或多种数字图像的部分相对深度的方法中，通过分割对数字图像进行规则化，并且将图像的至少部分像素分配给相应的片段。通过图像匹配来估计连续图像的段的实体运动。段的图像特征通过双重分段进行规则化，其中发现段的边缘，将像素分配给边缘，并且定义双段。通过图像段匹配来估计用于连续图像的双段的相对运动，以便确定图像段的相对深度顺序。

9. 发明申请

WO2006075304A2 DEPTH PERCEPTION 审中-公开
标题翻译：深度知觉
公开(公告)号：WO2006075304A2
公开(公告)日：2006-07-20
申请号：PCT/IB2006/050114
申请日：2006-01-12
申请人： KONINKLIJKE PHILIPS ELECTRONICS N.V. , ERNST, Fabian, E. , OP DE BEECK, Marc, J., R. , VAREKAMP, Christiaan
发明人： ERNST, Fabian, E. , OP DE BEECK, Marc, J., R. , VAREKAMP, Christiaan
CPC分类号： H04N13/111 , H04N13/282
摘要： A method of rendering a multi-view image comprising a first output image and a second output image on basis of an input image (102) is disclosed. The method comprises: creating a modulation image (100) comprising irregular shaped objects (106-112); modulating pixel values of a portion of the input image (102) on basis of further pixel values of the modulation image (100), resulting into an intermediate image (104); and generating the multi-view image by means of warping the intermediate image on basis of the disparity data.
摘要翻译：公开了一种基于输入图像（102）渲染包括第一输出图像和第二输出图像的多视图图像的方法。该方法包括：创建包括不规则形状物体（106-112）的调制图像（100）; 基于调制图像（100）的其他像素值调制输入图像（102）的一部分的像素值，得到中间图像（104）; 并且通过基于视差数据扭曲中间图像来生成多视点图像。

10. 发明申请

WO2004057460A2 SEGMENT-BASED MOTION ESTIMATION 审中-公开
标题翻译：基于分段的运动估计
公开(公告)号：WO2004057460A2
公开(公告)日：2004-07-08
申请号：PCT/IB2003/005474
申请日：2003-11-20
申请人： KONINKLIJKE PHILIPS ELECTRONICS N.V. , SETHURAMAN, Ramanathan , ERNST, Fabian, E. , MEUWISSEN, Patrick, P., E. , PETERS, Harm, J., A., M. , PESET LLOPIS, Rafael
发明人： SETHURAMAN, Ramanathan , ERNST, Fabian, E. , MEUWISSEN, Patrick, P., E. , PETERS, Harm, J., A., M. , PESET LLOPIS, Rafael
IPC分类号： G06F7/00
CPC分类号： G06T7/20 , G06T7/223 , H04N19/20 , H04N19/51
摘要： A method to determine motion vectors for respective segments (S11-S14) of a segmented image (100) comprises: creating sets of candidate motion vectors for the respective segments (S11-S14); dividing the segmented image (100) into a grid of blocks (b11-b88) of pixels; determining for the blocks (b11-b88) of pixels which of the candidate motion vectors belong to the blocks (b11-b88), on basis of the segments (S11-S14) and the locations of the blocks (b11-b88) within the segmented image (100); computing partial match errors for the blocks (b11-b88) on basis of the determined candidate motion vectors and on basis of pixel values of a further image (102); combining the partial match errors into a number of match errors per segment; selecting for each of the sets of candidate motion vectors respective candidate motion vectors on basis of the match errors; and assigning the selected candidate motion vectors as the motion vectors for the respective segments (S11-S14).
摘要翻译：确定分段图像（100）的各个分段（S11-S14）的运动矢量的方法包括：为各个分段创建多组候选运动矢量（S11-S14）; 将分割图像（100）分割成像素块（b11-b88）的网格; 基于区段（S11-S14）和区块（b11-b88）中的区块（b11-b88）的位置，确定像素的块（b11-b88）中的哪些候选运动矢量属于区块分段图像（100）; 基于所确定的候选运动向量并基于另一图像（102）的像素值计算块（b11-b88）的部分匹配误差; 将部分匹配错误组合成每段的大量匹配错误; 基于匹配误差为候选运动矢量的集合中的每一个选择相应的候选运动矢量; 并将所选择的候选运动矢量分配为各个段的运动矢量（S11-S14）。

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