专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明授权

US07577294B2 Background maintenance of an image sequence 有权
标题翻译：图像序列的后台维护
公开(公告)号：US07577294B2
公开(公告)日：2009-08-18
申请号：US11382697
申请日：2006-05-10
申请人： Kentaro Toyama , John Krumm , Barry L. Brummitt , Brian R. Meyers
发明人： Kentaro Toyama , John Krumm , Barry L. Brummitt , Brian R. Meyers
IPC分类号： G06K9/34 , G06K9/46 , G06K9/66
CPC分类号： G06K9/38 , G06T7/11 , G06T7/174 , G06T7/194 , G06T2207/10016 , G06T2207/20016 , G06T2207/20081
摘要： A system and method for maintaining a background model of an image sequence by processing on multiple spatial scales. These multiple spatial scales include a pixel scale, a regional scale and a frame scale. The image sequence undergoes pixel processing that determines a current background model and provides an initial pixel assignment as either a background or a foreground pixel. Region processing further refines the initial pixel assignments by considering relationships between pixels and possibly reassigning pixels. Frame processing further refines the current background model by determining whether a substantial change has occurred in the actual background and, if so, providing a more accurate background model.
摘要翻译：一种用于通过在多个空间尺度上处理来维护图像序列的背景模型的系统和方法。这些多个空间尺度包括像素尺度，区域尺度和帧尺度。图像序列经历像素处理，其确定当前背景模型，并将初始像素分配提供为背景或前景像素。区域处理通过考虑像素之间的关系和可能重新分配的像素进一步优化初始像素分配。帧处理通过确定在实际背景中是否发生实质性变化而进一步优化当前背景模型，如果是，则提供更准确的背景模型。

52. 发明授权

US07551181B2 Image region filling by exemplar-based inpainting 失效
标题翻译：图像区域填充通过基于示例的修复
公开(公告)号：US07551181B2
公开(公告)日：2009-06-23
申请号：US11095138
申请日：2005-03-30
申请人： Antonio Criminisi , Patrick Perez , Kentaro Toyama , Michel Gangnet , Andrew Blake
发明人： Antonio Criminisi , Patrick Perez , Kentaro Toyama , Michel Gangnet , Andrew Blake
IPC分类号： G09G5/00
CPC分类号： G06T11/001 , G06T11/40
摘要： An example-based filling system identifies appropriate filling material to replace a destination region in an image and fills the destination region using this material, thereby alleviating or minimizing the amount of manual editing required to fill a destination region in image. Tiles of image data are borrowed from the proximity of the destination region or some other source to generate new image data to fill in the region. Destination regions may be designated by user input (e.g., selection of an image region by a user) or by other means (e.g., specification of a color or feature to be replaced). In addition, the order in which the destination region is filled by example tiles may be configured to emphasize the continuity of linear structures and composite textures using a type of isophote-driven image-sampling process.
摘要翻译：基于示例的填充系统识别适当的填充材料以替换图像中的目的地区域并使用该材料填充目的地区域，从而减少或最小化填充图像中的目的地区域所需的手动编辑量。从目的地区域或某些其他源的附近借用图像数据块以生成新的图像数据以填充该区域。目的地区域可以由用户输入（例如，用户选择图像区域）或通过其他方式（例如，要更换的颜色或特征的指定）来指定。此外，通过示例瓦片填充目的地区域的顺序可以被配置为使用一种类型的等轴驱动图像采样处理来强调线性结构和复合纹理的连续性。

53. 发明授权

US07489817B2 Background maintenance of an image sequence 有权
标题翻译：图像序列的后台维护
公开(公告)号：US07489817B2
公开(公告)日：2009-02-10
申请号：US11255447
申请日：2005-10-22
申请人： Kentaro Toyama , John C. Krumm , Barry L. Brumitt , Brian R. Meyers
发明人： Kentaro Toyama , John C. Krumm , Barry L. Brumitt , Brian R. Meyers
IPC分类号： G06K9/34 , G06K9/46 , G06K9/66
CPC分类号： G06K9/38 , G06T7/11 , G06T7/174 , G06T7/194 , G06T2207/10016 , G06T2207/20016 , G06T2207/20081
摘要： An image background maintenance system and method for maintaining a background model of an image sequence by processing on multiple spatial scales. These multiple spatial scales include a pixel scale, a regional scale and a frame scale. The image sequence undergoes pixel processing that determines a current background model and provides an initial pixel assignment as either a background or a foreground pixel. Region processing further refines the initial pixel assignments by considering relationships between pixels and possibly reassigning pixels. Frame processing further refines the current background model by determining whether a substantial change has occurred in the actual background and, if so, providing a more accurate background model.
摘要翻译：一种用于通过在多个空间尺度上处理来维护图像序列的背景模型的图像背景维护系统和方法。这些多个空间尺度包括像素尺度，区域尺度和帧尺度。图像序列经历像素处理，其确定当前背景模型，并将初始像素分配提供为背景或前景像素。区域处理通过考虑像素之间的关系和可能重新分配的像素进一步优化初始像素分配。帧处理通过确定在实际背景中是否发生实质性变化而进一步优化当前背景模型，如果是，则提供更准确的背景模型。

54. 发明申请

US20080107344A1 SYSTEM AND METHOD PROVIDING SUBPIXEL-EDGE-OFFSET-BASED DETERMINATION OF OPACITY 有权
标题翻译：提供基于边缘边缘偏移的系统和方法的可行性确定
公开(公告)号：US20080107344A1
公开(公告)日：2008-05-08
申请号：US11965821
申请日：2007-12-28
申请人： Andrew Blake , Kentaro Toyama
发明人： Andrew Blake , Kentaro Toyama
IPC分类号： G06K9/40 , G06K9/48
CPC分类号： G06T11/001 , G06T7/12 , G06T7/194
摘要： A system is provided for selecting a foreground region of an image, given a set of pixels defining the boundary of the foreground region of the image. The system includes a component to determine a foreground value (F) and opacity value (α) for each pixel on the set wherein α is determined via a subpixel edge-offset to facilitate a separation the foreground region from background portions of the image. The foreground value (F) and opacity value (α) are then employed to smoothly mix the foreground region of the image with a subsequent image background region.
摘要翻译：给定一组定义图像的前景区域的边界的像素的集合，用于选择图像的前景区域。该系统包括用于确定集合上的每个像素的前景值（F）和不透明度值（α）的组件，其中通过子像素边缘偏移来确定α，以便于将前景区域与图像的背景部分分离。然后使用前景值（F）和不透明度值（alpha）来平滑地将图像的前景区域与随后的图像背景区域进行混合。

55. 发明授权

US07315647B2 System and method providing subpixel-edge-offset-based determination of opacity 有权
公开(公告)号：US07315647B2
公开(公告)日：2008-01-01
申请号：US10967722
申请日：2004-10-18
申请人： Andrew Blake , Kentaro Toyama
发明人： Andrew Blake , Kentaro Toyama
IPC分类号： G06K9/34
CPC分类号： G06T11/001 , G06T7/12 , G06T7/194
摘要： A system is provided for selecting a foreground region of an image, given a set of pixels defining the boundary of the foreground region of the image. The system includes a component to determine a foreground value (F) and opacity value (α) for each pixel on the set wherein α is determined via a subpixel edge-offset to facilitate a separation the foreground region from background portions of the image. The foreground value (F) and opacity value (α) are then employed to smoothly mix the foreground region of the image with a subsequent image background region.

56. 发明申请

US20070214417A1 AUTOMATICALLY AUTHORING VIDEO COMPOSITIONS USING VIDEO CLIPLETS 审中-公开
标题翻译：使用视频剪辑自动创作视频组合
公开(公告)号：US20070214417A1
公开(公告)日：2007-09-13
申请号：US11751614
申请日：2007-05-21
申请人： Kentaro Toyama , Andreas Soupliotis , Sheldon Fisher
发明人： Kentaro Toyama , Andreas Soupliotis , Sheldon Fisher
IPC分类号： G06F3/01
CPC分类号： G11B27/34 , G11B27/031
摘要： A system and a method for automatically authoring video compositions from longer units of digitized video (or a source video) by using short segments of video (or video “cliplets”). The video composition authoring process provides an aesthetically-pleasing layout of data elements to create a video composition. The data elements include multimedia elements, parameter information and description information. Any data elements that are missing but required are automatically selected by the system. The user may then review preliminary video composition results and refine the results if desired. The video composition authoring system includes an element selection and layout module for selecting the data elements in the video composition, and an iterative refinement module that allows the user to change and refine the preliminary results.
摘要翻译：一种用于通过使用短视频（或视频“小”）自动创作来自较长单元的数字化视频（或源视频）的系统和方法。视频构图创作过程提供美观的数据元素布局以创建视频构图。数据元素包括多媒体元素，参数信息和描述信息。系统会自动选择缺少但需要的任何数据元素。然后，如果需要，用户可以查看初步视频合成结果并优化结果。视频构图创作系统包括用于选择视频构图中的数据元素的元素选择和布局模块，以及允许用户改变和改进初步结果的迭代细化模块。

57. 发明申请

US20070171915A1 Cost-aware networking over heterogeneous data channels 失效
标题翻译：异构数据通道的成本感知网络
公开(公告)号：US20070171915A1
公开(公告)日：2007-07-26
申请号：US11342147
申请日：2006-01-26
申请人： Kentaro Toyama , Rohan Murty , Chandramohan Thekkath , Ranveer Chandra
发明人： Kentaro Toyama , Rohan Murty , Chandramohan Thekkath , Ranveer Chandra
IPC分类号： H04L12/56
CPC分类号： H04L47/762 , H04L47/15 , H04L47/70 , H04L47/788 , H04L47/826
摘要： Disclosed herein are scheduling techniques for transmitting time-critical data in a cost-aware manner over a network comprising a plurality of heterogeneous transmission interfaces. The scheduling problem is formulated as a linear programming problem with the deliver-by deadlines of the various data blocks as hard constraints and minimizing cost set as an objective (soft) constraint. The problem is simplified by assuming data blocks with the earliest deadlines should be scheduled first and the most aggressive interfaces should be used first. To formulate the linear programming problem, the time domain is divided into bins and various bin-level schedules are enumerated for switching the transmission of the data over various transmission interfaces. The linear programming techniques are applied to the various bin configurations and the least costly of the resulting transmission schedule is selected for submission to a switching layer.
摘要翻译：这里公开了用于通过包括多个异构传输接口的网络以成本感知方式传送时间关键数据的调度技术。调度问题被形成为作为硬约束的各种数据块的交付期限的线性规划问题，并且将成本设定为目标（软）约束的最小化。通过假设最早的最后期限的数据块应该首先被调度并且应该首先使用最积极的接口来简化问题。为了制定线性规划问题，将时域划分成箱体，并列举各种二进制计划，用于切换各种传输接口上的数据传输。线性编程技术被应用于各种箱体配置，并且选择最终的传输调度成本最低以提交给切换层。

58. 发明申请

US20070153017A1 Semantics-guided non-photorealistic rendering of images 审中-公开
标题翻译：语义引导的非真实感的图像渲染
公开(公告)号：US20070153017A1
公开(公告)日：2007-07-05
申请号：US11325250
申请日：2006-01-03
申请人： Kentaro Toyama , Neeharika Adabala
发明人： Kentaro Toyama , Neeharika Adabala
IPC分类号： G09G5/00
CPC分类号： G06T15/02
摘要： A facility for semantics-guided non-photorealistic rendering is described. In various embodiments, the facility receives a set of objects that are to be rendered in a non-photorealistic manner. For each received object, the facility determines whether the object has an associated indication of a feature type and, when the object has an associated indication of a feature type, employs a transformation function corresponding to the indicated feature type to render the object in a non-photorealistic style provided by the transformation function.
摘要翻译：描述了一种用于语义指导的非真实感渲染的设施。在各种实施例中，设施接收将以非真实感的方式呈现的一组对象。对于每个接收到的对象，设备确定对象是否具有相关联的特征类型的指示，并且当对象具有特征类型的相关联的指示时，采用与所指示的特征类型相对应的变换函数来将对象呈现为非特征类型，由转换功能提供的逼真风格。

59. 发明授权

US07136525B1 System and method for background maintenance of an image sequence 有权
标题翻译：用于图像序列的后台维护的系统和方法
公开(公告)号：US07136525B1
公开(公告)日：2006-11-14
申请号：US09400346
申请日：1999-09-20
申请人： Kentaro Toyama , John C. Krumm , Barry L. Brumitt , Brian R. Meyers
发明人： Kentaro Toyama , John C. Krumm , Barry L. Brumitt , Brian R. Meyers
IPC分类号： G06K9/34 , G06K9/46 , G06K9/66
CPC分类号： G06K9/38 , G06T7/11 , G06T7/174 , G06T7/194 , G06T2207/10016 , G06T2207/20016 , G06T2207/20081
摘要： The present invention is embodied in a system and method for maintaining a background model of an image sequence by processing on multiple spatial scales. These multiple spatial scales include a pixel scale, a regional scale and a frame scale. The image sequence undergoes pixel processing that determines a current background model and provides an initial pixel assignment as either a background or a foreground pixel. Region processing further refines the initial pixel assignments by considering relationships between pixels and possibly reassigning pixels. Frame processing further refines the current background model by determining whether a substantial change has occurred in the actual background and, if so, providing a more accurate background model.
摘要翻译：本发明体现在通过在多个空间尺度上进行处理来保持图像序列的背景模型的系统和方法。这些多个空间尺度包括像素尺度，区域尺度和帧尺度。图像序列经历像素处理，其确定当前背景模型，并将初始像素分配提供为背景或前景像素。区域处理通过考虑像素之间的关系和可能重新分配的像素进一步优化初始像素分配。帧处理通过确定在实际背景中是否发生实质性变化而进一步优化当前背景模型，如果是，则提供更准确的背景模型。

60. 发明申请

US20060193494A1 MACHINE VISION SYSTEM AND METHOD FOR ESTIMATING AND TRACKING FACIAL POSE 有权
公开(公告)号：US20060193494A1
公开(公告)日：2006-08-31
申请号：US11382012
申请日：2006-05-05
申请人： Kentaro Toyama
发明人： Kentaro Toyama
IPC分类号： G06K9/00
CPC分类号： G06K9/00228 , G06K9/32 , G06K2009/3291 , G06T7/277 , G06T7/74
摘要： System and method for estimating and tracking an orientation of a user's face by combining head tracking and face detection techniques. The orientation of the face, or facial pose, can be expressed in terms of pitch, roll and yaw of the user's head. Facial pose information can be used, for example, to ascertain in which direction the user is looking. In general, the facial pose estimation method obtains a position of the head and a position of the face and compares the two to obtain the facial pose. In particular, a camera is used to obtain an image containing a user's head. Any movement of the user's head is tracked and the head position is determined. A face then is detected on the head and the face position is determined. The head and face positions then are compared.

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