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

WO2004081875A3 SYSTEM AND METHOD FOR TRACKING A GLOBAL SHAPE OF AN OBJECT IN MOTION 审中-公开
标题翻译：跟踪运动对象的全球形状的系统和方法
公开(公告)号：WO2004081875A3
公开(公告)日：2005-10-06
申请号：PCT/US2004007068
申请日：2004-03-08
申请人： SIEMENS CORP RES INC , SIEMENS MEDICAL SOLUTIONS , COMANICIU DORIN , KRISHNAN SRIRAM , ZHOU XIANG SEAN , GEORGESCU BOGDAN
发明人： COMANICIU DORIN , KRISHNAN SRIRAM , ZHOU XIANG SEAN , GEORGESCU BOGDAN
IPC分类号： G06K9/00 , G06T5/00 , G06T7/20
CPC分类号： G06K9/6247 , G06K9/3216 , G06K9/629 , G06K2209/051 , G06T7/215 , G06T7/251 , G06T2207/10132 , G06T2207/30048
摘要： A system and method for tracking a global shape of an object in motion is disclosed. One or more control points along an initial contour of the global shape are defined. Each of the one or more control points is tracked as the object is in motion. Uncertainty of a location of a control point in motion is represented using a number of techniques. The uncertainty to constrain the global shape is exploited using a prior shape model. In an alternative embodiment, multiple appearance models are built for each control point and the motion vectors produced by each model are combined in order to track the shape of the object. The movement of the shape of the object can be visually tracked using a display and color vectors.
摘要翻译：公开了一种跟踪运动对象的全局形状的系统和方法。定义沿着全局形状初始轮廓的一个或多个控制点。一个或多个控制点中的每一个在物体运动时被跟踪。使用许多技术来表示控制点在运动中的位置的不确定性。使用先前的形状模型来利用限制全局形状的不确定性。在替代实施例中，为每个控制点构建多个外观模型，并且组合由每个模型产生的运动矢量以跟踪对象的形状。可以使用显示和颜色向量来可视地跟踪对象的形状的移动。

2. 发明申请

WO2005052860A3 SYSTEM AND METHOD FOR DETECTING AND MATCHING ANATOMICAL STRUCTURES USING APPEARANCE AND SHAPE 审中-公开
标题翻译：使用外观和形状检测和匹配解剖结构的系统和方法
公开(公告)号：WO2005052860A3
公开(公告)日：2005-09-22
申请号：PCT/US2004038837
申请日：2004-11-19
申请人： SIEMENS CORP RES INC , SIEMENS MEDICAL SOLUTIONS , ZHOU XIANG SEAN , GEORGESCU BOGDAN , COMANICIU DORIN , RAO R BHARAT , GUPTA ALOK
发明人： ZHOU XIANG SEAN , GEORGESCU BOGDAN , COMANICIU DORIN , RAO R BHARAT , GUPTA ALOK
IPC分类号： G06K9/62 , G06K9/64 , G06T7/00 , G06F19/00
CPC分类号： G06K9/6206 , G06K9/6256 , G06T7/12 , G06T7/149 , G06T7/251 , G06T2207/10132 , G06T2207/30048
摘要： A detection framework that matches anatomical structures using appearance and shape is disclosed. A training set of images are used in which object shapes or structures are annotated in the images. A second training set of images represents negative examples for such shapes and structures, i.e., images containing no such objects or structures. A classification algorithm trained on the training sets is used to detect a structure at its location. The structure is matched to a counterpart in the training set that can provide details about the structure's shape and appearance
摘要翻译：公开了一种使用外观和形状匹配解剖结构的检测框架。使用图像的训练集合，其中对图像中的对象形状或结构进行注释。图像的第二训练集表示这种形状和结构的负面例子，即不包含这样的对象或结构的图像。在训练集上训练的分类算法用于检测其位置处的结构。该结构与训练集中的对应部分相匹配，可以提供关于结构形状和外观的详细信息

3. 发明专利

AU2004294137A1 System and method for detecting and matching anatomical structures using appearance and shape 未知
公开(公告)号：AU2004294137A1
公开(公告)日：2005-06-09
申请号：AU2004294137
申请日：2004-11-19
申请人： SIEMENS CORP RES INC , SIEMENS MEDICAL SOLUTIONS
发明人： GUPTA ALOK , GEORGESCU BOGDAN , RAO R BHARAT , ZHOU XIANG SEAN , COMANICIU DORIN
IPC分类号： G06T7/00 , G06K9/62 , G06K9/64
摘要： A detection framework that matches anatomical structures using appearance and shape is disclosed. A training set of images are used in which object shapes or structures are annotated in the images. A second training set of images represents negative examples for such shapes and structures, i.e., images containing no such objects or structures. A classification algorithm trained on the training sets is used to detect a structure at its location. The structure is matched to a counterpart in the training set that can provide details about the structure's shape and appearance.

4. 发明专利

CA2546440C SYSTEM AND METHOD FOR DETECTING AND MATCHING ANATOMICAL STRUCTURES USING APPEARANCE AND SHAPE 未知
公开(公告)号：CA2546440C
公开(公告)日：2012-05-15
申请号：CA2546440
申请日：2004-11-19
申请人： SIEMENS CORP RES INC , SIEMENS MEDICAL SOLUTIONS
发明人： ZHOU XIANG SEAN , GEORGESCU BOGDAN , COMANICIU DORIN , RAO R BHARAT , GUPTA ALOK
IPC分类号： G06T7/00 , G06K9/62 , G06K9/64
摘要： A detection framework that matches anatomical structures using appearance and shape is disclosed. A training set of images are used in which object shapes or structures are annotated in the images. A second training set of images represents negative examples for such shapes and structures, i.e., images containing no such objects or structures. A classification algorithm trained on the training sets is used to detect a structure at its location. The structure is matched to a counterpart in the training set that can provide details about the structure's shape and appearance

5. 发明专利

DE112004001861T5 未知
公开(公告)号：DE112004001861T5
公开(公告)日：2006-09-07
申请号：DE112004001861
申请日：2004-10-04
申请人： SIEMENS CORP RES INC , SIEMENS MEDICAL SOLUTIONS
发明人： GEORGESCU BOGDAN , ZHOU XIANG SEAN , COMANICIU DORIN , KRISHNAN SRIRAM
IPC分类号： G06T7/20 , G06K9/00
摘要： A system and method for local deformable motion analysis accurately tracks the motion of an object such that local motion of an object is isolated from global motion of an object. The object is viewed in an image sequence and image regions are sampled to identify object image regions and background image regions. The motion of at least one of the identified background image regions is estimated to identify those background image regions affected by global motion. Motion from multiple background image regions are combined to measure the global motion in that image frame. The measured global motion in the object image regions are compensated to measure local motion of the object and the local motion of the object is tracked.

6. 发明专利

DE112004000393T5 未知
公开(公告)号：DE112004000393T5
公开(公告)日：2006-03-02
申请号：DE112004000393
申请日：2004-03-08
申请人： SIEMENS CORP RES INC , SIEMENS MEDICAL SOLUTIONS
发明人： COMANICIU DORIN , KRISHNAN SRIRAM , ZHOU XIANG SEAN , GEORGESCU BOGDAN
IPC分类号： G06K9/00 , G06T5/00 , G06T7/20
摘要： A system and method for tracking a global shape of an object in motion is disclosed. One or more control points along an initial contour of the global shape are defined. Each of the one or more control points is tracked as the object is in motion. Uncertainty of a location of a control point in motion is represented using a number of techniques. The uncertainty to constrain the global shape is exploited using a prior shape model. In an alternative embodiment, multiple appearance models are built for each control point and the motion vectors produced by each model are combined in order to track the shape of the object. The movement of the shape of the object can be visually tracked using a display and color vectors.

7. 发明专利

CA2546440A1 SYSTEM AND METHOD FOR DETECTING AND MATCHING ANATOMICAL STRUCTURES USING APPEARANCE AND SHAPE 未知
公开(公告)号：CA2546440A1
公开(公告)日：2005-06-09
申请号：CA2546440
申请日：2004-11-19
申请人： SIEMENS CORP RES INC , SIEMENS MEDICAL SOLUTIONS
发明人： COMANICIU DORIN , RAO R BHARAT , ZHOU XIANG SEAN , GUPTA ALOK , GEORGESCU BOGDAN
IPC分类号： G06T7/00 , G06F19/00 , G06K9/62 , G06K9/64
摘要： A detection framework that matches anatomical structures using appearance and shape is disclosed. A training set of images are used in which object shapes or structures are annotated in the images. A second training set of images represents negative examples for such shapes and structures, i.e., images containing no such objects or structures. A classification algorithm trained on the training sets is used to detect a structure at its location. The structure is matched to a counterpart in the training set that can provide details about the structure's shape and appearance.

8. 发明专利

JP2009072593A Automated detection method of plane from three-dimensional echocardiographic data 审中-公开
标题翻译：自动检测方法从三维地球化学数据
公开(公告)号：JP2009072593A
公开(公告)日：2009-04-09
申请号：JP2008240045
申请日：2008-09-18
申请人： Siemens Medical Solutions Usa Inc , シーメンスメディカルソリューションズユーエスエーインコーポレイテッドSiemens Medical Solutions USA,Inc.
发明人： LU XIAOGUANG , GEORGESCU BOGDAN , ZHENG YEFENG , JOANNE OTSUKI , DORIN COMANICIU
IPC分类号： A61B8/08 , G06F19/00
CPC分类号： A61B8/00 , A61B8/06 , A61B8/065 , A61B8/08 , A61B8/0883 , A61B8/0891 , A61B8/13 , A61B8/14 , A61B8/463 , A61B8/483 , A61B8/488 , A61B8/523 , G06F19/321 , G06K9/468 , G06K9/6256 , G16H50/20
摘要： PROBLEM TO BE SOLVED: To provide a method for automatically detecting planes from three-dimensional echocardiographic data. SOLUTION: A plane position for a standard view is detected from three-dimensional echocardiographic data (step 36). The position of the plane within the volume is defined by translation, orientation (rotation), and/or scale. Possible positions are detected (step 36) and other possible positions are ruled out. The classification of the possible positions occurs sequentially by translation (step 26), then orientation (step 28), and then scale (step 30). The sequential process may limit calculations required to identify the plane position for a desired view. COPYRIGHT: (C)2009,JPO&INPIT
摘要翻译：要解决的问题：提供一种用于从三维超声心动图数据自动检测平面的方法。解决方案：从三维超声心动图数据检测标准视图的平面位置（步骤36）。平面在体积内的位置由平移，定向（旋转）和/或刻度来定义。检测到可能的位置（步骤36），排除其它可能的位置。可能的位置的分类通过平移（步骤26），然后取向（步骤28），然后按比例（步骤30）顺序地进行。顺序过程可能会限制为所需视图识别平面位置所需的计算。版权所有（C）2009，JPO＆INPIT

9. 发明专利

JP2008080132A System and method for detecting object in high-dimensional image space 审中-公开
标题翻译：用于检测高维图像空间中物体的系统和方法
公开(公告)号：JP2008080132A
公开(公告)日：2008-04-10
申请号：JP2007254196
申请日：2007-09-28
申请人： Siemens Medical Solutions Usa Inc , シーメンスメディカルソリューションズユーエスエーインコーポレイテッドSiemens Medical Solutions USA,Inc.
发明人： BARBU ADRIAN , ZHENG YEFENG , YANG JIN , GEORGESCU BOGDAN , COMANICIU DORIN
IPC分类号： A61B6/03 , G06T1/00
CPC分类号： G06K9/6292
摘要： PROBLEM TO BE SOLVED: To provide a method for a high speed detection of an object in a high-dimensional space by which the searching space can remarkably be reduced while still maintaining an accurate result.
SOLUTION: This system and this method for detecting the object in the high dimensional image space are disclosed. The three-dimensional image of the object is received. The training of a first classifier is performed in an edge space at the object central positions which form the central positions of a predetermined number of candidate objects. The training of a second classifier is performed in order to recognize the possible object central positions and the orientations from the central positions of the predetermined number of candidate objects. The training of a third classifier is performed in order to recognize the possible positions, the orientations and the scales of the object centers from a subsidiary setting for the central positions of the candidate objects. A single candidate object pose for the object is recognized.
COPYRIGHT: (C)2008,JPO&INPIT
摘要翻译：要解决的问题：提供一种用于高维度空间中的对象的高速检测的方法，通过该方法可以显着地减少搜索空间，同时仍然保持精确的结果。公开了该系统和用于检测高维图像空间中的对象的该方法。接收对象的三维图像。在形成预定数量候选对象的中心位置的对象中心位置的边缘空间中执行第一分类器的训练。执行第二分类器的训练以便从预定数量的候选对象的中心位置识别可能的对象中心位置和取向。执行第三分类器的训练，以便从候选对象的中心位置的辅助设置识别对象中心的可能位置，方向和尺度。识别对象的单个候选对象姿势。版权所有（C）2008，JPO＆INPIT

10. 发明专利

JP2009226226A Apparatus and method for local deformable motion analysis 审中-公开
标题翻译：用于局部变形运动分析的装置和方法
公开(公告)号：JP2009226226A
公开(公告)日：2009-10-08
申请号：JP2009141398
申请日：2009-06-12
申请人： Siemens Medical Solutions Usa Inc , シーメンスメディカルソリューションズユーエスエーインコーポレイテッドSiemens Medical Solutions USA,Inc.
发明人： GEORGESCU BOGDAN , ZHOU XIANG SEAN , DORIN COMANICIU , KRISHNAN SRIRAM
IPC分类号： A61B8/08 , G06K9/00 , G06T7/20
CPC分类号： G06T7/20 , G06T7/0016 , G06T7/251 , G06T2207/10132 , G06T2207/30048
摘要： PROBLEM TO BE SOLVED: To solve the problems that although it has been postulated that the shape of the normal heart remains in the same status during systole, the heart itself has local rotation or strain, and the shape of the normal heart remarkably differs during systole in many examples, and consequently to appropriately compensate the whole motion for the purpose of raising the accuracy of medical diagnosis. SOLUTION: A target object is observed as an image sequence. In this case, an image domains are sampled in order to distinguish a background image domain from a target object domain image. In order to distinguish the background image domain on which the whole motion acts, the motion of at least one of the distinguished background image domains is presumed. In order to measure the whole motion in an image frame, movements from the two or more background image domains are combined. COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：为了解决尽管假设心脏收缩期间正常心脏的形状保持在相同状态的问题，心脏本身具有局部旋转或应变，并且正常心脏的形状显着地在许多例子中收缩期不同，因此为了提高医学诊断的准确性，适当补偿整个运动。
解决方案：将目标对象作为图像序列进行观察。在这种情况下，对图像域进行采样以区分背景图像域与目标对象域图像。为了区分整个运动所在的背景图像域，假设至少一个区分背景图像域的运动。为了测量图像帧中的整个运动，组合来自两个或更多个背景图像域的运动。版权所有（C）2010，JPO＆INPIT

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