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

US20090103810A1 CONTENT GENERATION, EXTRACTION AND DISTRIBUTION OF IMAGE REGION SEGMENTS FROM VIDEO IMAGES 失效
标题翻译：图像区域的内容生成，提取和分配从视频图像
公开(公告)号：US20090103810A1
公开(公告)日：2009-04-23
申请号：US11964033
申请日：2007-12-25
申请人： Tomio Echigo , Ken Masumitsu , Masayoshi Teraguchi , Takaaki Murao
发明人： Tomio Echigo , Ken Masumitsu , Masayoshi Teraguchi , Takaaki Murao
IPC分类号： G06K9/46 , H04N5/93
CPC分类号： G06K9/00711 , G06F17/30905 , G06K9/3233 , G06T7/20
摘要： The present invention provides methods for extracting an image region segment from a video image, a system for extracting an image region segment, a program for extracting an image region segment, a method for distributing an extracted video image, and a method for generating content. Motion compensation data is calculated using sequential video images captured by a video camera, and the sequential video images are employed to prepare an estimation of the video camera operation. Based on the estimated camera operation, the center position (xc, yc) of an area that is aimed at in a video image is estimated under predetermined conditions (rules), an image feature is designated in the vicinity of the center position of the target area, and an image segment is specified that includes this image feature.
摘要翻译：本发明提供了从视频图像提取图像区域片段的方法，用于提取图像区域片段的系统，用于提取图像区域片段的节目，分发提取的视频图像的方法以及用于产生内容的方法。使用由摄像机拍摄的顺序视频图像来计算运动补偿数据，并且使用顺序视频图像来准备摄像机操作的估计。基于估计的摄像机操作，在预定条件（规则）下估计针对视频图像的区域的中心位置（xc，yc），在目标的中心位置附近指定图像特征区域，并且指定包括该图像特征的图像片段。

2. 发明授权

US07492944B2 Extraction and tracking of image regions arranged in time series 失效
标题翻译：以时间序列排列的图像区域的提取和跟踪
公开(公告)号：US07492944B2
公开(公告)日：2009-02-17
申请号：US11457829
申请日：2006-07-17
申请人： Ajith Kumar Narayanan , Alberto Tomita, Jr. , Takaaki Murao , Tomio Echigo
发明人： Ajith Kumar Narayanan , Alberto Tomita, Jr. , Takaaki Murao , Tomio Echigo
IPC分类号： G06K9/34 , G06K9/46
CPC分类号： H04N19/20 , G06T7/246 , G06T7/251 , G06T2207/10016 , G06T2207/30221 , G06T2207/30236 , G06T2207/30241 , H04N19/503 , H04N19/553
摘要： Methods and apparatus for effectively identifying the occlusion of objects, such as persons, having a high degree of freedom. In an example embodiment, after initialization, an image is input, and an image region is extracted from image data. The distance is employed that is obtained when the shape of a two-dimensional histogram in the color space is transformed into the feature space. A graph is formed by using the regions between the frames. A confidence factor is provided and image features are provided as weights to the edges that connect the nodes. Processing is performed and the confidence factor is examined. A connection judged less possible to be a path is removed. When there is only one available connection for the occlusion point, this connection is selected.
摘要翻译：用于有效地识别具有高度自由度的物体（例如人）的遮挡的方法和装置。在示例实施例中，在初始化之后，输入图像，并且从图像数据中提取图像区域。当将颜色空间中的二维直方图的形状变换为特征空间时，采用距离。通过使用帧之间的区域形成图形。提供置信因子，并且图像特征被提供为连接节点的边缘的权重。执行处理并检查置信因子。取消不太可能成为路径的连接。当遮挡点只有一个可用连接时，选择此连接。

3. 发明授权

US07971217B2 Content digest system, video digest system, user terminal, video digest generation method, video digest reception method and program therefor 有权
标题翻译：内容摘要系统，视频摘要系统，用户终端，视频摘要生成方法，视频摘要接收方法及其程序
公开(公告)号：US07971217B2
公开(公告)日：2011-06-28
申请号：US10081274
申请日：2002-02-21
申请人： Ken Masumitsu , Tomio Echigo , Takaaki Murao , Masayoshi Teraguchi
发明人： Ken Masumitsu , Tomio Echigo , Takaaki Murao , Masayoshi Teraguchi
IPC分类号： H04N5/445
CPC分类号： H04N21/84 , G06F17/30817 , H04N5/445 , H04N7/173 , H04N21/252 , H04N21/25891 , H04N21/4532 , H04N21/4755 , H04N21/6131 , H04N21/8549
摘要： Meta data about content is converted into characteristic values. Each characteristic value is associated with one or more content segments of content. The content can be audio, video, or other data or combinations of data. Importance levels for content segments are determined from content scores. Content scores are generally an indication of how one person would rate a particular characteristic value. The content scores may be estimated by using previously determined scores of similar content segments. The similarity is preferably determined by a particular metric. A user may also supply his or her own content scores for content segments. The user profile content scores can be combined with the determined content scores or completely supplant these scores. Based on the importance levels for content scores for content segments, content segments may be packaged into a content digest that a user may view.
摘要翻译：有关内容的元数据被转换为特征值。每个特征值与内容的一个或多个内容片段相关联。内容可以是音频，视频或其他数据或数据组合。内容分段的重要性水平是根据内容分数确定的。内容分数通常表示一个人如何评估特定特征值。可以通过使用预先确定的类似内容片段的分数来估计内容分数。相似度优选地由特定度量来确定。用户还可以为内容片段提供他或她自己的内容分数。用户简档内容分数可以与确定的内容分数相结合或完全取代这些分数。基于内容分段的内容分数的重要性级别，内容片段可以被打包成用户可以查看的内容摘要。

4. 发明授权

US07796781B2 Content generation, extraction and distribution of image region segments from video images 失效
标题翻译：图像区域片段的内容生成，提取和分配
公开(公告)号：US07796781B2
公开(公告)日：2010-09-14
申请号：US11964033
申请日：2007-12-25
申请人： Tomio Echigo , Ken Masumitsu , Masayoshi Teraguchi , Takaaki Murao
发明人： Tomio Echigo , Ken Masumitsu , Masayoshi Teraguchi , Takaaki Murao
IPC分类号： G06K9/00 , G06K9/34 , G06K9/66 , H04N5/225
CPC分类号： G06K9/00711 , G06F17/30905 , G06K9/3233 , G06T7/20
摘要： The present invention provides methods for extracting an image region segment from a video image, a system for extracting an image region segment, a program for extracting an image region segment, a method for distributing an extracted video image, and a method for generating content. Motion compensation data is calculated using sequential video images captured by a video camera, and the sequential video images are employed to prepare an estimation of the video camera operation. Based on the estimated camera operation, the center position (xc, yc) of an area that is aimed at in a video image is estimated under predetermined conditions (rules), an image feature is designated in the vicinity of the center position of the target area, and an image segment is specified that includes this image feature.
摘要翻译：本发明提供了从视频图像提取图像区域片段的方法，用于提取图像区域片段的系统，用于提取图像区域片段的节目，分发提取的视频图像的方法以及用于产生内容的方法。使用由摄像机拍摄的顺序视频图像来计算运动补偿数据，并且使用顺序视频图像来准备摄像机操作的估计。基于估计的摄像机操作，在预定条件（规则）下估计针对视频图像的区域的中心位置（xc，yc），在目标的中心位置附近指定图像特征区域，并且指定包括该图像特征的图像片段。

5. 发明授权

US07313278B2 Content generation, extraction and distribution of image region segments from video images 失效
标题翻译：图像区域片段的内容生成，提取和分配
公开(公告)号：US07313278B2
公开(公告)日：2007-12-25
申请号：US10094896
申请日：2002-03-08
申请人： Tomio Echigo , Ken Masumitsu , Masayoshi Teraguchi , Takaaki Murao
发明人： Tomio Echigo , Ken Masumitsu , Masayoshi Teraguchi , Takaaki Murao
IPC分类号： G06K9/46 , G06K9/00
CPC分类号： G06K9/00711 , G06F17/30905 , G06K9/3233 , G06T7/20
摘要： The present invention provides methods for extracting an image region segment from a video image, a system for extracting an image region segment, a program for extracting an image region segment, a method for distributing an extracted video image, and a method for generating content. Motion compensation data is calculated using sequential video images captured by a video camera, and the sequential video images are employed to prepare an estimation of the video camera operation. Based on the estimated camera operation, the center position (xc, yc) of an area that is aimed at in a video image is estimated under predetermined conditions (rules), an image feature is designated in the vicinity of the center position of the target area, and an image segment is specified that includes this image feature.
摘要翻译：本发明提供了从视频图像提取图像区域片段的方法，用于提取图像区域片段的系统，用于提取图像区域片段的节目，分发提取的视频图像的方法以及用于产生内容的方法。使用由摄像机拍摄的顺序视频图像来计算运动补偿数据，并且使用顺序视频图像来准备摄像机操作的估计。基于估计的摄像机操作，在预定条件（规则）下估计针对视频图像的区域的中心位置（xc，yc），在目标的中心位置附近指定图像特征区域，并且指定包括该图像特征的图像片段。

6. 发明申请

US20050261884A1 Unified modeling language (UML) design method 失效
标题翻译：统一建模语言（UML）设计方法
公开(公告)号：US20050261884A1
公开(公告)日：2005-11-24
申请号：US11126614
申请日：2005-05-11
申请人： Masaharu Sakamoto , Takaaki Murao , Naoto Sato , Shin Saito
发明人： Masaharu Sakamoto , Takaaki Murao , Naoto Sato , Shin Saito
IPC分类号： G06F17/50 , G06F9/44
CPC分类号： G06F17/5022
摘要： To provide a UML design method by which architecture design pursuing optimal design parameters while viewing the overall target system on the UML model can be performed. A UML design method of the present invention is a UML design method for performing design by modeling a target system based on Unified Modeling Language (UML), using a profile storing a design parameter, the method including the steps of: storing a stereotype and a tagged value in the profile as the design parameters; annotating a UML model of the target system with the stored stereotype and tagged value; and associating the added stereotype and tagged value with each class constituting the UML model, and displaying the stereotype and tagged value and the UML model, which are associated, on a graphical user interface.
摘要翻译：提供一种UML设计方法，通过该方法可以在UML模型上查看整个目标系统的同时追求最佳设计参数的架构设计。本发明的UML设计方法是一种用于通过使用统一建模语言（UML）对目标系统进行建模来执行设计的UML设计方法，其使用存储设计参数的简档，所述方法包括以下步骤：存储刻板印象和在配置文件中标记值作为设计参数; 用存储的原型和标记值注释目标系统的UML模型; 并将添加的原型和标记的值与构成UML模型的每个类相关联，并且在图形用户界面上显示相关联的原型和标记值以及UML模型。

7. 发明授权

US06512995B2 Shape analysis, difference detection, and search for three-dimensional models 失效
标题翻译：形状分析，差异检测和三维模型搜索
公开(公告)号：US06512995B2
公开(公告)日：2003-01-28
申请号：US09839088
申请日：2001-04-20
申请人： Takaaki Murao
发明人： Takaaki Murao
IPC分类号： G01B322
CPC分类号： G06T19/00 , G06F17/30241 , G06F17/50 , G06T17/005 , G06T2210/12
摘要： Through comparison of electronic shape data for parts, the invention automatically detects a difference in shapes of products due to the design change, and/or searches for a product that is similar in shape. A shape analysis system comprises: an analysis tree node generator; a neighbor graph generator, for creating an edge between the nodes that are generated by the analysis tree node generator and that are geometrically adjacent, so as to produce a neighbor graph; and an analysis tree generator, for merging nodes in the neighbor graph that are generated by the neighbor graph generator and that are connected by the edge, for generating a new node in correlation with a 3d-shape that encloses patches included in the merged nodes and a shape analysis tree wherein the node acquired by merging is defined as a parent node and the other nodes, before being merged, are defined as child nodes.
摘要翻译：通过比较零件的电子形状数据，本发明可以自动检测由于设计变化而产生的形状差异，和/或搜索形状相似的产品。形状分析系统包括：分析树节点发生器; 邻居图生成器，用于在由分析树节点生成器生成并且几何相邻的节点之间创建边缘，以便产生邻居图; 以及分析树生成器，用于合并由邻居图生成器生成并且由边缘连接的邻居图中的节点，用于生成与包含在合并节点中的补丁相关的3d形状相关联的新节点;以及形状分析树，其中通过合并获取的节点被定义为父节点，并且在被合并之前的其他节点被定义为子节点。

8. 发明授权

US10083542B1 Method and system to compare and search polyhedral shape 有权
公开(公告)号：US10083542B1
公开(公告)日：2018-09-25
申请号：US09616772
申请日：2000-07-14
申请人： Takaaki Murao
发明人： Takaaki Murao
IPC分类号： G06T17/00
CPC分类号： G06T17/00 , G06T2210/56
摘要： Polyhedral data is compared with limited information while keeping accuracy. A comparison of two polyhedrons is accomplished as follows. (1) A squared-sum of the difference of primary moment functions and a squared-sum of the difference of secondary moment functions are separately sought at sample points of polyhedron Ma, Mb, normalize them and compute the sum of both, or seek sum functions of the primary moment functions and the secondary moment functions to compute the squared-sum of the difference of the sum functions, the primary moment function all the sample points of polyhedral data that occupy central symmetry directions are blended in the same sign, which is the different sign in the case of the secondary moment function, the functions having variables representing points on a surface of a sphere of which center is the center of gravity of the polyhedron and a value which is an axial moment value, the axis defined as a line through the points and the center, and (2) in the case that the value of the sum is a certain threshold or less, it is determined that the polyhedrons are similar in shape.

9. 发明授权

US07509629B2 Method for system and architecture design using unified modeling language (UML) 失效
标题翻译：使用统一建模语言（UML）的系统和架构设计方法
公开(公告)号：US07509629B2
公开(公告)日：2009-03-24
申请号：US11126614
申请日：2005-05-11
申请人： Masaharu Sakamoto , Takaaki Murao , Naoto Sato , Shin Saito
发明人： Masaharu Sakamoto , Takaaki Murao , Naoto Sato , Shin Saito
IPC分类号： G06F9/44 , G06F9/45 , G06F3/048 , G06G7/48
CPC分类号： G06F17/5022
摘要： To provide a UML design method by which architecture design pursuing optimal design parameters while viewing the overall target system on the UML model can be performed. A UML design method of the present invention is a UML design method for performing design by modeling a target system based on Unified Modeling Language (UML), using a profile storing a design parameter, the method including the steps of: storing a stereotype and a tagged value in the profile as the design parameters; annotating a UML model of the target system with the stored stereotype and tagged value; and associating the added stereotype and tagged value with each class constituting the UML model, and displaying the stereotype and tagged value and the UML model, which are associated, on a graphical user interface.
摘要翻译：提供一种UML设计方法，通过该方法可以在UML模型上查看整个目标系统的同时追求最佳设计参数的架构设计。本发明的UML设计方法是一种用于通过使用统一建模语言（UML）对目标系统进行建模来执行设计的UML设计方法，其使用存储设计参数的简档，所述方法包括以下步骤：存储刻板印象和在配置文件中标记值作为设计参数; 用存储的原型和标记值注释目标系统的UML模型; 并将添加的原型和标记的值与构成UML模型的每个类相关联，并且在图形用户界面上显示相关联的原型和标记值以及UML模型。

10. 发明申请

US20060280335A1 EXTRACTION AND TRACKING OF IMAGE REGIONS ARRANGED IN TIME SERIES 失效
标题翻译：时间序列中图像区域的提取和跟踪
公开(公告)号：US20060280335A1
公开(公告)日：2006-12-14
申请号：US11457829
申请日：2006-07-17
申请人： Alberto Tomita , Takaaki Murao , Tomio Echigo , Ajith Narayanan
发明人： Alberto Tomita , Takaaki Murao , Tomio Echigo , Ajith Narayanan
IPC分类号： G06K9/00
CPC分类号： H04N19/20 , G06T7/246 , G06T7/251 , G06T2207/10016 , G06T2207/30221 , G06T2207/30236 , G06T2207/30241 , H04N19/503 , H04N19/553
摘要： The invention provide methods and apparatus for effectively identifying the occlusion of objects, such as persons, having a high degree of freedom. In an example embodiment, after initialization, an image is input, and an image region is extracted from image data. The distance is employed that is obtained when the shape of a two-dimensional histogram in the color space is transformed into the feature space. A graph is formed by using, the regions between the frames. A confidence factor is provided and image features are provided as weights to the edges that connect the nodes. Processing is performed, and the confidence factor is examined. A connection judged less possible to be a path is removed. When there is only one available connection for the occlusion point, this connection is selected.
摘要翻译：本发明提供了用于有效地识别具有高自由度的物体（例如人）的遮挡的方法和装置。在示例实施例中，在初始化之后，输入图像，并且从图像数据中提取图像区域。当将颜色空间中的二维直方图的形状变换为特征空间时，采用距离。通过使用帧之间的区域形成图形。提供置信因子，并且图像特征被提供为连接节点的边缘的权重。进行处理，并检查置信因子。取消不太可能成为路径的连接。当遮挡点只有一个可用连接时，选择此连接。

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