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

US20110064303A1 Object Recognition Using Textons and Shape Filters 审中-公开
标题翻译：使用纹理和形状过滤器的对象识别
公开(公告)号：US20110064303A1
公开(公告)日：2011-03-17
申请号：US12944130
申请日：2010-11-11
申请人： John Winn , Carsten Rother , Antonio Criminisi , Jamie Shotton
发明人： John Winn , Carsten Rother , Antonio Criminisi , Jamie Shotton
IPC分类号： G06K9/62
CPC分类号： G06K9/3233 , G06K9/4604
摘要： Given an image of structured and/or unstructured objects, semantically meaningful areas are automatically partitioned from the image, each area labeled with a specific object class. Shape filters are used to enable capturing of some or all of the shape, texture, and/or appearance context information. A shape filter comprises one or more regions of arbitrary shape, size, and/or position within a bounding area of an image, paired with a specified texton. A texton comprises information describing the texture of a patch of surface of an object. In a training process a sub-set of possible shape filters is selected and incorporated into a conditional random field model of object classes. The conditional random field model is then used for object detection and recognition.
摘要翻译：给定结构化和/或非结构化对象的图像，语义上有意义的区域将自动从图像分割，每个区域都标有特定的对象类。形状滤波器用于使得能够捕获部分或全部形状，纹理和/或外观上下文信息。形状滤波器包括与指定的文本配对的图像的边界区域内的任意形状，大小和/或位置的一个或多个区域。文本包括描述对象的表面的纹理的信息。在训练过程中，选择可能的形状滤波器的子集，并将其合并到对象类的条件随机场模型中。然后将条件随机场模型用于对象检测和识别。

2. 发明申请

US20080075361A1 Object Recognition Using Textons and Shape Filters 有权
标题翻译：使用纹理和形状过滤器的对象识别
公开(公告)号：US20080075361A1
公开(公告)日：2008-03-27
申请号：US11534019
申请日：2006-09-21
申请人： John Winn , Carsten Rother , Antonio Criminisi , Jamie Shotton
发明人： John Winn , Carsten Rother , Antonio Criminisi , Jamie Shotton
IPC分类号： G06K9/62 , G06K9/34 , G06K9/46 , G06K9/66
CPC分类号： G06K9/3233 , G06K9/4604
摘要： Given an image of structured and/or unstructured objects we automatically partition it into semantically meaningful areas each labeled with a specific object class. We use a novel type of feature which we refer to as a shape filter. Shape filters enable us to capture some or all of shape, texture and appearance context information. A shape filter comprises one or more regions of arbitrary shape, size and position within a bounding area of an image, paired with a specified texton. A texton comprises information describing the texture of a patch of surface of an object. In a training process we select a sub-set of possible shape filters and incorporate those into a conditional random field model of object classes. That model is then used for object detection and recognition.
摘要翻译：给定结构化和/或非结构化对象的图像，我们自动将其划分为语义有意义的区域，每个区域都标有特定的对象类。我们使用一种我们称为形状滤波器的新型特征。形状过滤器使我们能够捕获部分或全部形状，纹理和外观上下文信息。形状滤波器包括在图像的边界区域内的任意形状，大小和位置的一个或多个区域，与指定的文本配对。文本包括描述对象的表面的纹理的信息。在训练过程中，我们选择可能的形状过滤器的子集，并将其合并到对象类的条件随机场模型中。然后将该模型用于对象检测和识别。

3. 发明授权

US07840059B2 Object recognition using textons and shape filters 有权
标题翻译：使用纹理和形状过滤器的对象识别
公开(公告)号：US07840059B2
公开(公告)日：2010-11-23
申请号：US11534019
申请日：2006-09-21
申请人： John Winn , Carsten Rother , Antonio Criminisi , Jamie Shotton
发明人： John Winn , Carsten Rother , Antonio Criminisi , Jamie Shotton
IPC分类号： G06K9/62
CPC分类号： G06K9/3233 , G06K9/4604
摘要： Given an image of structured and/or unstructured objects we automatically partition it into semantically meaningful areas each labeled with a specific object class. We use a novel type of feature which we refer to as a shape filter. Shape filters enable us to capture some or all of shape, texture and appearance context information. A shape filter comprises one or more regions of arbitrary shape, size and position within a bounding area of an image, paired with a specified texton. A texton comprises information describing the texture of a patch of surface of an object. In a training process we select a sub-set of possible shape filters and incorporate those into a conditional random field model of object classes. That model is then used for object detection and recognition.
摘要翻译：给定结构化和/或非结构化对象的图像，我们自动将其划分为语义有意义的区域，每个区域都标有特定的对象类。我们使用一种我们称为形状滤波器的新型特征。形状过滤器使我们能够捕获部分或全部形状，纹理和外观上下文信息。形状滤波器包括在图像的边界区域内的任意形状，大小和位置的一个或多个区域，与指定的文本配对。文本包括描述对象的表面的纹理的信息。在训练过程中，我们选择可能的形状过滤器的子集，并将其合并到对象类的条件随机场模型中。然后将该模型用于对象检测和识别。

4. 发明授权

US08660303B2 Detection of body and props 有权
标题翻译：检测身体和道具
公开(公告)号：US08660303B2
公开(公告)日：2014-02-25
申请号：US12972837
申请日：2010-12-20
申请人： Shahram Izadi , Jamie Shotton , John Winn , Antonio Criminisi , Otmar Hilliges , Mat Cook , David Molyneaux
发明人： Shahram Izadi , Jamie Shotton , John Winn , Antonio Criminisi , Otmar Hilliges , Mat Cook , David Molyneaux
IPC分类号： G06K9/00 , G06K9/62 , G06K9/36
CPC分类号： G06K9/00369
摘要： A system and method for detecting and tracking targets including body parts and props is described. In one aspect, the disclosed technology acquires one or more depth images, generates one or more classification maps associated with one or more body parts and one or more props, tracks the one or more body parts using a skeletal tracking system, tracks the one or more props using a prop tracking system, and reports metrics regarding the one or more body parts and the one or more props. In some embodiments, feedback may occur between the skeletal tracking system and the prop tracking system.
摘要翻译：描述了用于检测和跟踪包括身体部位和道具的目标的系统和方法。在一个方面，所公开的技术获取一个或多个深度图像，生成与一个或多个身体部位和一个或多个道具相关联的一个或多个分类图，使用骨骼跟踪系统跟踪一个或多个身体部位，使用道具跟踪系统的更多道具，并且报告关于一个或多个身体部位和一个或多个道具的指标。在一些实施例中，可以在骨骼跟踪系统和支架跟踪系统之间进行反馈。

5. 发明申请

US20110085705A1 DETECTION OF BODY AND PROPS 有权
标题翻译：身体和检查的检测
公开(公告)号：US20110085705A1
公开(公告)日：2011-04-14
申请号：US12972837
申请日：2010-12-20
申请人： Shahram Izadi , Jamie Shotton , John Winn , Antonio Criminisi , Otmar Hilliges , Mat Cook , David Molyneaux
发明人： Shahram Izadi , Jamie Shotton , John Winn , Antonio Criminisi , Otmar Hilliges , Mat Cook , David Molyneaux
IPC分类号： G06K9/00
CPC分类号： G06K9/00369
摘要： A system and method for detecting and tracking targets including body parts and props is described. In one aspect, the disclosed technology acquires one or more depth images, generates one or more classification maps associated with one or more body parts and one or more props, tracks the one or more body parts using a skeletal tracking system, tracks the one or more props using a prop tracking system, and reports metrics regarding the one or more body parts and the one or more props. In some embodiments, feedback may occur between the skeletal tracking system and the prop tracking system.
摘要翻译：描述了用于检测和跟踪包括身体部位和道具的目标的系统和方法。一方面，所公开的技术获取一个或多个深度图像，生成与一个或多个身体部位和一个或多个道具相关联的一个或多个分类图，使用骨骼跟踪系统跟踪该一个或多个身体部位，使用道具跟踪系统的更多道具，并且报告关于一个或多个身体部位和一个或多个道具的指标。在一些实施例中，可以在骨骼跟踪系统和支架跟踪系统之间进行反馈。

6. 发明授权

US07809183B2 Gaze manipulation 有权
标题翻译：凝视操纵
公开(公告)号：US07809183B2
公开(公告)日：2010-10-05
申请号：US10681007
申请日：2003-10-08
申请人： Antonio Criminisi , Andrew Blake , Philip H. S. Torr , Jamie Shotton
发明人： Antonio Criminisi , Andrew Blake , Philip H. S. Torr , Jamie Shotton
IPC分类号： G06K9/00
CPC分类号： H04N7/144 , G06T7/30 , G06T7/593 , G06T7/97
摘要： A multi-layer graph for dense stereo dynamic programming can improve synthesis of cyclopean virtual images by distinguishing between stereo disparities caused by occlusion and disparities caused by non-fronto-parallel surfaces. This distinction can be leveraged to reduce image artifacts, such as “halos”. Distinguishing at least between these two types of disparities allows improved matching of left and right pixel data, which increases the amount of correct pixel information used in constructing the cyclopean virtual image and minimizes occlusion artifacts.
摘要翻译：用于密集立体动态规划的多层图可以通过区分由闭塞引起的立体差异和由非前平行表面引起的差异来改善环形虚拟图像的合成。可以利用这种区别来减少图像伪影，如“光晕”。至少区分这两种类型的差异，可以改善左和右像素数据的匹配，这增加了在构建环形虚拟图像中使用的正确的像素信息的量并且最小化遮挡伪像。

7. 发明申请

US20050078865A1 Gaze manipulation 有权
标题翻译：凝视操纵
公开(公告)号：US20050078865A1
公开(公告)日：2005-04-14
申请号：US10681007
申请日：2003-10-08
申请人： Antonio Criminisi , Andrew Blake , Philip Torr , Jamie Shotton
发明人： Antonio Criminisi , Andrew Blake , Philip Torr , Jamie Shotton
IPC分类号： G06T7/00 , H04N7/14 , G06K9/00
CPC分类号： H04N7/144 , G06T7/30 , G06T7/593 , G06T7/97
摘要： A multi-layer graph for dense stereo dynamic programming can improve synthesis of cyclopean virtual images by distinguishing between stereo disparities caused by occlusion and disparities caused by non-fronto-parallel surfaces. This distinction can be leveraged to reduce image artifacts, such as “halos”. Distinguishing at least between these two types of disparities allows improved matching of left and right pixel data, which increases the amount of correct pixel information used in constructing the cyclopean virtual image and minimizes occlusion artifacts.
摘要翻译：用于密集立体动态规划的多层图可以通过区分由闭塞引起的立体差异和由非前平行表面引起的差异来改善环形虚拟图像的合成。可以利用这种区别来减少图像伪影，如“光晕”。至少区分这两种类型的差异，可以改善左和右像素数据的匹配，这增加了在构建环形虚拟图像中使用的正确的像素信息的量并且最小化遮挡伪像。

8. 发明授权

US07570803B2 Virtual camera translation 有权
标题翻译：虚拟相机翻译
公开(公告)号：US07570803B2
公开(公告)日：2009-08-04
申请号：US10763453
申请日：2004-01-23
申请人： Antonio Criminisi , Andrew Blake , Philip H. S. Torr , Jamie Shotton
发明人： Antonio Criminisi , Andrew Blake , Philip H. S. Torr , Jamie Shotton
IPC分类号： G06K9/00
CPC分类号： H04N7/144 , G06T7/30 , G06T7/593 , G06T7/97 , H04N7/147
摘要： A multi-layer graph for dense stereo dynamic programming can improve synthesis of cyclopean virtual images by distinguishing between stereo disparities causes by occlusion and disparities caused by non-fronto-parallel surfaces. In addition, cyclopean virtual image processing may be combined with simulation of three-dimensional translation of a virtual camera to assist in aligning the user's gaze with the virtual camera. Such translation may include without limitation one or more of the following: horizontal (e.g., left and right) translation of the virtual camera, vertical translation (e.g., up and down) of the virtual camera, and axial translation (e.g., toward the subject and away from the subject) of the virtual camera.
摘要翻译：用于密集立体动态规划的多层图可以通过区分由闭塞引起的立体差异和由非前平行表面引起的差异来改善环形虚拟图像的合成。此外，环形虚拟图像处理可以与虚拟相机的三维平移的仿真结合起来，以帮助将用户的注视与虚拟相机对准。这样的翻译可以包括但不限于以下的一个或多个：虚拟相机的水平（例如，左和右）平移，虚拟相机的垂直平移（例如，上下）以及轴向平移（例如朝向主体并远离主题）的虚拟相机。

9. 发明申请

US20050078866A1 Virtual camera translation 有权
标题翻译：虚拟相机翻译
公开(公告)号：US20050078866A1
公开(公告)日：2005-04-14
申请号：US10763453
申请日：2004-01-23
申请人： Antonio Criminisi , Andrew Blake , Philip Torr , Jamie Shotton
发明人： Antonio Criminisi , Andrew Blake , Philip Torr , Jamie Shotton
IPC分类号： G06T7/00 , H04N7/14 , G06K9/00
CPC分类号： H04N7/144 , G06T7/30 , G06T7/593 , G06T7/97 , H04N7/147
摘要： A multi-layer graph for dense stereo dynamic progranmmiing can improve synthesis of cyclopean virtual images by distinguishing between stereo disparities causes by occlusion and disparities caused by non-fronto-parallel surfaces. In addition, cyclopean virtual image processing may be combined with simulation of three-dimensional translation of a virtual camera to assist in aligning the user's gaze with the virtual camera. Such translation may include without limitation one or more of the following: horizontal (e.g., left and right) translation of the virtual camera, vertical translation (e.g., up and down) of the virtual camera, and axial translation (e.g., toward the subject and away from the subject) of the virtual camera.
摘要翻译：用于密集立体声动态前进的多层图可以通过区分由闭塞引起的立体差异和由非前平行表面引起的差异来改善环形虚拟图像的合成。此外，环形虚拟图像处理可以与虚拟相机的三维平移的仿真结合起来，以帮助将用户的注视与虚拟相机对准。这样的翻译可以包括但不限于以下的一个或多个：虚拟相机的水平（例如，左和右）平移，虚拟相机的垂直平移（例如，上下）以及轴向平移（例如朝向主体并远离主题）的虚拟相机。

10. 发明申请

US20110274352A1 Image Segmentation Using Star-Convexity Constraints 有权
标题翻译：使用星形凸度约束的图像分割
公开(公告)号：US20110274352A1
公开(公告)日：2011-11-10
申请号：US12776082
申请日：2010-05-07
申请人： Andrew Blake , Varun Gulshan , Carsten Rother , Antonio Criminisi
发明人： Andrew Blake , Varun Gulshan , Carsten Rother , Antonio Criminisi
IPC分类号： G06K9/34
CPC分类号： G06T7/11 , G06T7/194 , G06T2207/20101 , G06T2207/20168
摘要： Image segmentation using star-convexity constraints is described. In an example, user input specifies positions of one or more star centers in a foreground to be segmented from a background of an image. In embodiments, an energy function is used to express the problem of segmenting the image and that energy function incorporates a star-convexity constraint which limits the number of possible solutions. For example, the star-convexity constraint may be that, for any point p inside the foreground, all points on a shortest path (which may be geodesic or Euclidean) between the nearest star center and p also lie inside the foreground. In some examples continuous star centers such as lines are used. In embodiments a user may iteratively edit the star centers by adding brush strokes to the image in order to progressively change the star-convexity constraints and obtain an accurate segmentation.
摘要翻译：描述了使用星形凸度约束的图像分割。在一个示例中，用户输入指定要从图像的背景分割的前景中的一个或多个星形中心的位置。在实施例中，能量函数用于表示分割图像的问题，并且能量函数包含限制可能解决方案数量的星形 - 凸度约束。例如，星凸约束可以是，对于前景中的任何点p，最近的星中心和p之间的最短路径上的所有点（可以是测地线或欧几里德）也位于前景内。在一些示例中，使用诸如线的连续星形中心。在实施例中，用户可以通过向图像中添加画笔笔触来迭代地编辑星形中心，以逐渐改变星形凸度约束并获得准确的分割。

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