专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明申请

WO2005096216A1 FACE DETECTION AND RECOGNITION USING POSE-SPECIFIC DETECTORS AND POSE-SPECIFIC RECOGNIZERS 审中-公开
标题翻译：使用位置特异性检测器和特定识别器的脸部检测和识别
公开(公告)号：WO2005096216A1
公开(公告)日：2005-10-13
申请号：PCT/US2005/010365
申请日：2005-03-29
申请人： SIEMENS CORPORATE RESEARCH, INC. , SIEMENS AKTIENGESELLSCHAFT , BASCLE, Benedicte , COMANICIU, Dorin , BARATOFF, Gregory , KÖHLER, Thorsten
发明人： BASCLE, Benedicte , COMANICIU, Dorin , BARATOFF, Gregory , KÖHLER, Thorsten
IPC分类号： G06K9/00
CPC分类号： G06K9/00228 , G06K9/00288
摘要： Methods for image processing for detecting and recognizing an image object include detecting an image object using pose-specific object detectors (201-203), and performing fusion (32) of the outputs from the pose-specific object detectors. The image object is recognized using pose-specific object recognizers (301-303) that use outputs from the pose-specific object detectors and the fused output of the pose-specific object detectors; and by performing fusion (34) of the outputs of the pose-specific object recognizers to recognize the image object.
摘要翻译：用于检测和识别图像对象的图像处理的方法包括使用姿势特定对象检测器（201-203）检测图像对象，并且执行来自姿势特定对象检测器的输出的融合（32）。使用姿势特定目标识别器（301-303）识别图像对象，所述姿势特定对象识别器使用来自姿势特定对象检测器的输出和姿势特定对象检测器的融合输出; 并且通过执行姿势特定对象识别器的输出的融合（34）来识别图像对象。

22. 发明申请

WO2005052851A3 SYSTEM AND METHOD FOR DETECTING AN OCCUPANT AND HEAD POSE USING STEREO DETECTORS 审中-公开
标题翻译：用于使用立体声探测器来检测占用者和头部位置的系统和方法
公开(公告)号：WO2005052851A3
公开(公告)日：2005-08-04
申请号：PCT/US2004039169
申请日：2004-11-22
申请人： SIEMENS CORP RES INC , SIEMENS AG , COMANICIU DORIN , KOHLER THORSTEN , XIE BINGLONG , ZHU YING
发明人： COMANICIU DORIN , KOHLER THORSTEN , XIE BINGLONG , ZHU YING
IPC分类号： G06K9/00 , G06K9/62 , G06T7/00
CPC分类号： G06K9/00832 , G06K9/00248 , G06K9/00362 , G06T7/74 , G06T2207/10012 , G06T2207/30201 , G06T2207/30248
摘要： A system and method for detecting an occupant and head pose using stereo detectors is disclosed. In the training stage, pairs of images taken simultaneously from a pair of stereo cameras are received and components in each pair of images are identified. Features are associated with each component and a value is associated with each feature. Among them, a subset of features with best discriminative capabilities is selected and forms a strong classifier for a given component in a pair of images. In the detection stage, the strong classifiers are used in the incoming image pairs to detect components. Identified components are used to detect occupants and head pose of the occupants. Stereo detection is combined with stereo matching in a systematic way to improve occupant detection and localization.
摘要翻译：公开了一种使用立体声检测器检测乘员和头部姿势的系统和方法。在训练阶段，接收从一对立体相机同时拍摄的图像对，并识别每对图像中的成分。功能与每个组件相关联，并且值与每个功能相关联。其中，选择具有最佳鉴别能力的特征子集并形成一对图像对中给定组件的强分类器。在检测阶段，在输入图像对中使用强分类器来检测组件。识别的组件用于检测乘员和乘员的头部姿势。立体声检测与系统化立体匹配相结合，以改善乘员检测和定位。

23. 发明申请

WO2005034039A3 SYSTEM AND METHOD FOR LOCAL DEFORMABLE MOTION ANALYSIS 审中-公开
标题翻译：用于局部可变形运动分析的系统和方法
公开(公告)号：WO2005034039A3
公开(公告)日：2005-07-21
申请号：PCT/US2004032724
申请日：2004-10-04
申请人： SIEMENS CORP RES INC , GEORGESCU BOGDAN , ZHOU XIANG SEAN , COMANICIU DORIN , KRISHNAN SRIRAM
发明人： GEORGESCU BOGDAN , ZHOU XIANG SEAN , COMANICIU DORIN , KRISHNAN SRIRAM
IPC分类号： G06K9/00 , G06T7/20
CPC分类号： G06T7/20 , G06T7/0016 , G06T7/251 , G06T2207/10132 , G06T2207/30048
摘要： [0061] A system and method for local deformable motion analysis and for accurately tracking motion of an object isolating local motion of an object from global motion of an object is disclosed. 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. A system and method for accurately measuring the local deformable motion of an object as the relative motion between two control point sets is disclosed. The point sets are defined as the inner contour and the outer contour of an object. The motion of the control point sets is estimated and the relative motion is used to characterize the local deformation and local motion of the object
摘要翻译：公开了一种用于局部可变形运动分析和准确跟踪物体的运动的系统和方法，该物体隔离物体的局部运动与物体的全局运动。该对象在图像序列中被查看并且图像区域被采样以识别对象图像区域和背景图像区域。估计所识别的背景图像区域中的至少一个的运动以识别受全局运动影响的那些背景图像区域。来自多个背景图像区域的运动被组合以测量该图像帧中的全局运动。对物体图像区域中的测量的全局运动进行补偿以测量物体的局部运动，并跟踪物体的局部运动。公开了一种用于精确测量物体的局部可变形运动的系统和方法，作为两个控制点集之间的相对运动。点集被定义为对象的内部轮廓和外部轮廓。估计控制点集的运动，并使用相对运动来表征物体的局部变形和局部运动

24. 发明申请

WO2005036463A2 MULTISCALE DETECTION OF LOCAL IMAGE STRUCTURES 审中-公开
标题翻译：局部图像结构的多尺度检测
公开(公告)号：WO2005036463A2
公开(公告)日：2005-04-21
申请号：PCT/US2004/032334
申请日：2004-10-01
申请人： SIEMENS CORPORATE RESEARCH, INC. , DALAL, Navneet , COMANICIU, Dorin
发明人： DALAL, Navneet , COMANICIU, Dorin
IPC分类号： G06T7/00
CPC分类号： G06K9/6226 , G06T7/207
摘要： A method (200) and apparatus (101) for the detection of local image structures represented as clusters in a joint-spatial range domain where the method comprises receiving an input image, having one or more clusters in a joint-spatial range domain, and each of the one or more clusters having a corresponding mode (205). Receiving a set of analysis matrices and selecting through each one of the analysis matrices (206). Using the selected analysis matrix to partition the input image into the one or more clusters and their corresponding modes, and computing a mean, µ, and a local covariance matrix S for each of the corresponding modes of each of the one or more clusters (210). Selecting at least one of the one or more clusters, where each selected cluster has a stable mean and stable covariance matrix across the set of analysis matrices, whereby each of the selected clusters is indicative of a local image structure (220)
摘要翻译：一种用于检测表示为联合空间范围域中的聚类的局部图像结构的方法（200）和装置（101），其中所述方法包括接收具有联合空间范围域中的一个或多个聚类的输入图像，以及一个或多个聚类中的每一个具有相应的模式（205）。接收一组分析矩阵并通过每个分析矩阵（206）进行选择。使用所选择的分析矩阵将输入图像划分成一个或多个聚类及其对应模式，并且针对一个或多个聚类（210）中的每一个的每个对应模式计算平均值μ和局部协方差矩阵）。选择所述一个或多个聚类中的至少一个，其中每个所选择的聚类在所述分析矩阵集合之间具有稳定的平均和稳定的协方差矩阵，由此所选择的聚类中的每一个指示局部图像结构（220）

25. 发明申请

WO2005034039A2 SYSTEM AND METHOD FOR LOCAL DEFORMABLE MOTION ANALYSIS 审中-公开
标题翻译：用于局部可变运动分析的系统和方法
公开(公告)号：WO2005034039A2
公开(公告)日：2005-04-14
申请号：PCT/US2004/032724
申请日：2004-10-04
申请人： SIEMENS CORPORATE RESEARCH, INC. , GEORGESCU, Bogdan , ZHOU, Xiang Sean , COMANICIU, Dorin , KRISHNAN, Sriram
发明人： GEORGESCU, Bogdan , ZHOU, Xiang Sean , COMANICIU, Dorin , KRISHNAN, Sriram
IPC分类号： G06T7/20
CPC分类号： G06T7/20 , G06T7/0016 , G06T7/251 , G06T2207/10132 , G06T2207/30048
摘要： [0061] A system and method for local deformable motion analysis and for accurately tracking motion of an object isolating local motion of an object from global motion of an object is disclosed. 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. A system and method for accurately measuring the local deformable motion of an object as the relative motion between two control point sets is disclosed. The point sets are defined as the inner contour and the outer contour of an object. The motion of the control point sets is estimated and the relative motion is used to characterize the local deformation and local motion of the object
摘要翻译：公开了一种用于局部可变形运动分析和用于精确跟踪物体的局部运动与对象的全局运动隔离的物体的运动的系统和方法。以图像序列查看对象，并对图像区域进行采样以识别对象图像区域和背景图像区域。估计所识别的背景图像区域中的至少一个的运动以识别受全局运动影响的那些背景图像区域。来自多个背景图像区域的运动被组合以测量该图像帧中的全局运动。在对象图像区域中测量的全局运动被补偿以测量对象的局部运动，并跟踪对象的局部运动。公开了一种用于精确测量物体的局部可变形运动作为两个控制点组之间的相对运动的系统和方法。点集被定义为对象的内轮廓和外轮廓。估计控制点集的运动，并使用相对运动来表征对象的局部变形和局部运动

26. 发明申请

WO2009042074A1 AUTOMATED VIEW CLASSIFICATION WITH ECHOCARDIOGRAPHIC DATA FOR GATE LOCALIZATION OR OTHER PURPOSES 审中-公开
标题翻译：用于门控定位或其他目的的自动化视图分类
公开(公告)号：WO2009042074A1
公开(公告)日：2009-04-02
申请号：PCT/US2008/010902
申请日：2008-09-18
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , COMANICIU, Dorin , PARK, Jin Hyeong , ZHOU, Shaohua Kevin , SIMOPOULOS, Constantine , OTSUKI, Joanne
发明人： PARK, Jin Hyeong , ZHOU, Shaohua Kevin , SIMOPOULOS, Constantine , OTSUKI, Joanne
IPC分类号： G06K9/62 , G06T7/00
CPC分类号： G06K9/6257 , G06K9/6292 , G06K2209/05
摘要： A view represented by echocardiographic data is classified (64). A probabilistic boosting network (30) is used to classify the view. The probabilistic boosting network (30) may include multiple levels where each level has a multi-class local structure classifier (32) and a plurality of local-structure detectors (34) corresponding to the respective multiple classes. In each level, the local structure is classified (50) as a particular view and then the local structure is detected (54) to determine (56) whether the currently selected local structure corresponds to the class.
摘要翻译：由超声心动图数据表示的视图被分类（64）。概率增强网络（30）用于对视图进行分类。概率提升网络（30）可以包括多个级别，其中每个级别具有对应于相应的多个类别的多类局部结构分类器（32）和多个局部结构检测器（34）。在每个级别中，将本地结构分类为（50）作为特定视图，然后检测到本地结构（54）以确定（56）当前选择的本地结构是否对应于该类。

27. 发明申请

WO2004102467A3 COMPONENT FUSION FOR FACE DETECTION 审中-公开
标题翻译：用于面部检测的组件熔断器
公开(公告)号：WO2004102467A3
公开(公告)日：2008-01-03
申请号：PCT/EP2004050796
申请日：2004-05-13
申请人： SIEMENS CORP RES INC , COMANICIU DORIN , RAMESH VISVANATHAN , SIMON MARKUS , XIE BINGLONG
发明人： COMANICIU DORIN , RAMESH VISVANATHAN , SIMON MARKUS , XIE BINGLONG
IPC分类号： G06K9/00
CPC分类号： G06K9/00281
摘要： A system (100) and method for object detection are provided where the system includes a component detection unit (170) for detecting components in an image, a component fusion unit (180) in signal communication with the component detection unit for fusing the components into an object, and a CPU (102) in signal communication with the detection and fusion units for comparing the fused components with a statistical model; and the method includes receiving observation data for a plurality of training images, forming at least one statistical model from the plurality of training images, receiving an input image having a plurality of pixels, detecting a plurality of components in the input image, determining a fusion of the detected components, comparing the fusion with the statistical model, and detecting an object in accordance with the comparison.
摘要翻译：提供了一种用于物体检测的系统（100）和方法，其中系统包括用于检测图像中的分量的分量检测单元（170），与分量检测单元进行信号通信的分量融合单元（180）与所述检测和融合单元进行信号通信的CPU（102），用于将所述融合分量与统计模型进行比较; 并且该方法包括接收多个训练图像的观测数据，从多个训练图像中形成至少一个统计模型，接收具有多个像素的输入图像，检测输入图像中的多个分量，确定融合的检测组件，将融合与统计模型进行比较，并根据比较来检测对象。

28. 发明申请

WO2005024651A3 A SYSTEM AND METHOD FOR SEQUENTIAL KERNEL DENSITY APPROXIMATION THROUGH MODE PROPAGATION 审中-公开
标题翻译：通过模式传播的用于顺序密度密度近似的系统和方法
公开(公告)号：WO2005024651A3
公开(公告)日：2006-09-08
申请号：PCT/US2004029316
申请日：2004-09-09
申请人： SIEMENS CORP RES INC , HAN BOHYUNG , COMANICIU DORIN , ZHU YING , ZHOU XIANG SEAN
发明人： HAN BOHYUNG , COMANICIU DORIN , ZHU YING , ZHOU XIANG SEAN
IPC分类号： G06F17/18 , G06T5/00 , G06T7/40
CPC分类号： G06K9/6226 , G06F17/18 , G06T7/44
摘要： A system and method for sequential kernel density approximation uses mode propagation to determine mode locations by the mean-shift method and reduce the generated modes. Hessians are calculated corresponding to the mode locations to determine the covariance. Density is approximated to update the density function depending on whether the Hessian is a negative indefinite.
摘要翻译：用于顺序核密度近似的系统和方法使用模式传播来通过平均移位方法确定模式位置并减少生成的模式。对应于模式位置计算Hessians以确定协方差。近似密度来更新密度函数，取决于黑森西是否是负不确定的。

29. 发明申请

WO2005096226A3 SYSTEMS AND METHODS PROVIDING AUTOMATED DECISION SUPPORT FOR MEDICAL IMAGING 审中-公开
标题翻译：提供医疗成像自动化决策支持的系统和方法
公开(公告)号：WO2005096226A3
公开(公告)日：2006-04-27
申请号：PCT/US2005009646
申请日：2005-03-23
申请人： SIEMENS MEDICAL SOLUTIONS , SIEMENS CORP RES INC , KRISHNAN SRIRAM , COMANICIU DORIN , XIANG SEAN ZHOU , CANNON MICHAEL G , DUTTON ALLEN
发明人： KRISHNAN SRIRAM , COMANICIU DORIN , XIANG SEAN ZHOU , CANNON MICHAEL G , DUTTON ALLEN
IPC分类号： G06T7/00
CPC分类号： G06T7/0012
摘要： Systems and methods are provided for processing a medical image to automatically identify the anatomy and view (or pose) from the medical image and automatically assess the diagnostic quality of the medical image. In one aspect a method for automated decision support for medical imaging includes obtaining image data, extracting feature data from the image data, and automatically performing anatomy identification, view identification and/or determining a diagnostic quality of the image data, using the extracted feature data.
摘要翻译：提供了系统和方法来处理医学图像以自动识别解剖结构并从医学图像中观察（或姿势）并自动评估医学图像的诊断质量。一方面，用于医学成像的自动决策支持的方法包括从所述图像数据获取图像数据，提取特征数据，以及使用所提取的特征数据自动执行解剖识别，查看识别和/或确定图像数据的诊断质量。

30. 发明申请

WO2006029227A2 SYSTEM AND METHOD FOR ANATOMICAL STRUCTURE PARSING AND DETECTION 审中-公开
标题翻译：用于解剖结构分析和检测的系统和方法
公开(公告)号：WO2006029227A2
公开(公告)日：2006-03-16
申请号：PCT/US2005/031912
申请日：2005-09-06
申请人： SIEMENS CORPORATE RESEARCH, INC. , SIEMENS MEDICAL SOLUTIONS USA, INC. , TU, Zhuowen , ZHOU, Xiang Sean , COMANICIU, Dorin , SCHULTZ, Christian P.
发明人： TU, Zhuowen , ZHOU, Xiang Sean , COMANICIU, Dorin , SCHULTZ, Christian P.
IPC分类号： G06T5/00
CPC分类号： G06K9/6256 , G06T7/11 , G06T7/143 , G06T2207/10072 , G06T2207/30004
摘要： A method for segmenting a digitized image includes providing a digitized image comprising a plurality of intensities defined on a lattice of pixels, initializing (22) a Bayesian prior probability and likelihood function for segmenting said image, decomposing (23) said image into a union of a plurality of subspaces wherein each subspace is a product of k-partitions, and distributing a plurality Bayesian posterior probability functions over said subspaces, updating (25) said Bayesian posterior probability functions via a data-driven Markov-chain, and selecting (27) a subset of said Bayesian posterior probability functions that approximate a true Bayesian posterior probability function.
摘要翻译：一种用于分割数字化图像的方法包括提供包括在像素点阵上定义的多个强度的数字化图像，初始化（22）用于分割所述图像的贝叶斯先验概率和似然函数，分解（ 23）所述图像为多个子空间的并集，其中每个子空间是k分区的乘积，并且在所述子空间上分布多个贝叶斯后验概率函数，通过数据驱动的马尔可夫模型更新（25）所述贝叶斯后验概率函数并选择（27）所述贝叶斯后验概率函数的接近真实贝叶斯后验概率函数的子集。

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