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

US20140348408A1 FLOW DIVERTER DETECTION IN MEDICAL IMAGING 有权
标题翻译：流量分析仪在医学成像中的检测
公开(公告)号：US20140348408A1
公开(公告)日：2014-11-27
申请号：US13899850
申请日：2013-05-22
申请人： Ying Zhu , Thomas Redel
发明人： Ying Zhu , Thomas Redel , Jan Boese
IPC分类号： G06T7/00 , A61B6/03
CPC分类号： G06T7/0012 , A61B6/032 , A61B6/4441 , A61B6/501 , A61B6/507 , A61B6/5211 , A61B8/06 , G06T2207/20081 , G06T2207/30104 , G06T2207/30172
摘要： A flow diverter is automatically detected from medical imaging data. The appearance of the flow diverter as represented in the data as well as the geometry or shape of the flow diverter is used in the detection. Using scoring for appearance relative to the centerline and cross-section of the centerline, the flow diverter is detected for increasing visualization.
摘要翻译：从医学成像数据自动检测流量分流器。在数据中表示的分流器的外观以及分流器的几何形状或形状用于检测。使用相对于中心线的中心线和横截面的外观评分，检测流量分流器以增加可视化。

22. 发明授权

US08345944B2 System and method for coronary digital subtraction angiography 有权
标题翻译：冠状动脉数字减影血管造影的系统和方法
公开(公告)号：US08345944B2
公开(公告)日：2013-01-01
申请号：US12509514
申请日：2009-07-27
申请人： Ying Zhu , Simone Prummer , Terrence Chen , Martin Ostermeier , Dorin Comaniciu
发明人： Ying Zhu , Simone Prummer , Terrence Chen , Martin Ostermeier , Dorin Comaniciu
IPC分类号： G06K9/00
CPC分类号： G06K9/38 , G06K2009/00932 , G06T7/0014 , G06T7/194 , G06T2207/20076 , G06T2207/20081 , G06T2207/30101
摘要： A method and system for extracting coronary vessels fluoroscopic image sequences using coronary digital subtraction angiography (DSA) are disclosed. A set of mask images of a coronary region is received, and a sequence of contrast images for the coronary region is received. For each contrast image, vessel regions are detected in the contrast image using learning-based vessel segment detection and a background region of the contrast image is determined based on the detected vessel regions. Background motion is estimated between one of the mask images and the background region of the contrast image by estimating a motion field between the mask image and the background image and performing covariance-based filtering over the estimated motion field. The mask image is then warped based on the estimated background motion to generate an estimated background layer. The estimated background layer is subtracted from the contrast image to extract a coronary vessel layer for the contrast image.
摘要翻译：公开了使用冠状动脉数字减影血管造影（DSA）提取冠脉血管荧光镜图像序列的方法和系统。接收冠状动脉区域的一组掩模图像，并且接收冠状动脉区域的对比度图像序列。对于每个对比图像，使用基于学习的血管段检测在对比图像中检测血管区域，并且基于检测到的血管区域确定造影剂图像的背景区域。通过估计掩模图像和背景图像之间的运动场并且在估计的运动场上执行协方差滤波来估计背景运动在掩模图像和对比度图像的背景区域中的一个之间。然后基于估计的背景运动来改变掩模图像以产生估计的背景层。从对比图像中减去估计的背景层，以提取对比度图像的冠状血管层。

23. 发明申请

US20120140998A1 Deformable Motion Correction for Stent Visibility Enhancement 有权
标题翻译：用于支架可见度增强的可变形运动校正
公开(公告)号：US20120140998A1
公开(公告)日：2012-06-07
申请号：US13277312
申请日：2011-10-20
申请人： Ying Zhu , Christophe Chefd'hotel
发明人： Ying Zhu , Christophe Chefd'hotel
IPC分类号： G06K9/00
CPC分类号： G06T5/006 , G06T7/194 , G06T2207/10081 , G06T2207/10121 , G06T2207/10132 , G06T2207/30021 , G06T2207/30101 , G06T2207/30204
摘要： A method for enhancing stent visibility includes acquiring a set of image frames including multiple test frames. A set of measurement points uniformly distributed within an image of a stent is defined in the test frames. A local image context is defined around each measurement point. A non-rigid deformation field relating the local image contexts of the test frames to local image contexts of a reference image is calculated. The non-rigid deformation field is optimized by maximizing a similarity function between the local image contexts of the test frames and the local image contexts of the reference image. The optimized non-rigid deformation field is used to deform images of a stent in the multiple test frames and combine the non-rigidly deformed images of the stent from the test frames. An image frame with the combined image of the stents superimposed thereon is displayed.
摘要翻译：一种用于增强支架可见度的方法包括获取包括多个测试框架的一组图像帧。在测试框架中定义了在支架的图像内均匀分布的一组测量点。在每个测量点周围定义一个局部图像上下文。计算将测试帧的局部图像上下文与参考图像的局部图像上下文相关联的非刚性变形场。通过最大化测试帧的局部图像上下文与参考图像的局部图像上下文之间的相似度函数来优化非刚性变形场。优化的非刚性变形场用于在多个测试框架中变形支架的图像，并将来自测试框架的支架的非刚性变形图像组合。显示具有叠加在其上的支架的组合图像的图像帧。

24. 发明授权

US07769228B2 Method for combining boosted classifiers for efficient multi-class object detection 有权
标题翻译：用于组合升级分类器以实现高效多类对象检测的方法
公开(公告)号：US07769228B2
公开(公告)日：2010-08-03
申请号：US11111640
申请日：2005-04-21
申请人： Claus Bahlmann , Ying Zhu , Dorin Comaniciu , Thorsten Köhler , Martin Pellkofer
发明人： Claus Bahlmann , Ying Zhu , Dorin Comaniciu , Thorsten Köhler , Martin Pellkofer
IPC分类号： G06K9/62
CPC分类号： G06K9/6256 , G06K9/6228
摘要： A method for training a system for detecting multi-class objects in an image or a video sequence is described. A common ensemble of weak classifiers for a set of object classes is identified. For each object class, a separate weighting scheme is adapted for the ensemble of weak classifiers. A method for detecting objects of multiple classes in an image or a video sequence is also disclosed. Each class is assigned a detector that is implemented by a weighted combination of weak classifiers such that all of the detectors are based on a common ensemble of weak classifiers. Then weights are individually set for each class.
摘要翻译：描述了一种用于训练用于检测图像或视频序列中的多类对象的系统的方法。识别一组对象类的弱分类器的常见集合。对于每个对象类，单独的加权方案适用于弱分类器的集合。还公开了一种用于检测图像或视频序列中的多个类别的对象的方法。每个类被分配一个由弱分类器的加权组合实现的检测器，使得所有检测器都基于弱分类器的共同集合。然后，每个课程都可以单独设置权重。

25. 发明申请

US20100034446A1 System and Method for Coronary Digital Subtraction Angiography 有权
标题翻译：冠状动脉数字减影血管造影术的系统与方法
公开(公告)号：US20100034446A1
公开(公告)日：2010-02-11
申请号：US12509514
申请日：2009-07-27
申请人： Ying Zhu , Simone Prummer , Terrence Chen , Martin Ostermeier , Dorin Comaniciu
发明人： Ying Zhu , Simone Prummer , Terrence Chen , Martin Ostermeier , Dorin Comaniciu
IPC分类号： G06K9/00
CPC分类号： G06K9/38 , G06K2009/00932 , G06T7/0014 , G06T7/194 , G06T2207/20076 , G06T2207/20081 , G06T2207/30101
摘要： A method and system for extracting coronary vessels fluoroscopic image sequences using coronary digital subtraction angiography (DSA) are disclosed. A set of mask images of a coronary region is received, and a sequence of contrast images for the coronary region is received. For each contrast image, vessel regions are detected in the contrast image using learning-based vessel segment detection and a background region of the contrast image is determined based on the detected vessel regions. Background motion is estimated between one of the mask images and the background region of the contrast image by estimating a motion field between the mask image and the background image and performing covariance-based filtering over the estimated motion field. The mask image is then warped based on the estimated background motion to generate an estimated background layer. The estimated background layer is subtracted from the contrast image to extract a coronary vessel layer for the contrast image.
摘要翻译：公开了使用冠状动脉数字减影血管造影（DSA）提取冠脉血管荧光镜图像序列的方法和系统。接收冠状动脉区域的一组掩模图像，并且接收冠状动脉区域的对比度图像序列。对于每个对比图像，使用基于学习的血管段检测在对比图像中检测血管区域，并且基于检测到的血管区域确定造影剂图像的背景区域。通过估计掩模图像和背景图像之间的运动场并且在估计的运动场上执行协方差滤波来估计背景运动在掩模图像和对比度图像的背景区域中的一个之间。然后基于估计的背景运动来改变掩模图像以产生估计的背景层。从对比图像中减去估计的背景层，以提取对比度图像的冠状血管层。

26. 发明授权

US07508979B2 System and method for detecting an occupant and head pose using stereo detectors 有权
标题翻译：使用立体声检测器检测乘员和头部姿势的系统和方法
公开(公告)号：US07508979B2
公开(公告)日：2009-03-24
申请号：US10991684
申请日：2004-11-18
申请人： Dorin Comaniciu , Thorsten Köhler , Binglong Xie , Ying Zhu
发明人： Dorin Comaniciu , Thorsten Köhler , Binglong Xie , Ying Zhu
IPC分类号： G06K9/00
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获取的图像对，并且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，选择具有最佳辨别能力的特征的子集，并为一对图像中的给定分量形成强分类器。在检测阶段，强分类器用于输入图像对以检测组件。识别的组件用于检测乘员的乘客和头部姿势。立体声检测与系统的立体匹配相结合，提高乘员检测和定位。

27. 发明申请

US20080273752A1 SYSTEM AND METHOD FOR VEHICLE DETECTION AND TRACKING 有权
标题翻译：用于车辆检测和跟踪的系统和方法
公开(公告)号：US20080273752A1
公开(公告)日：2008-11-06
申请号：US12014397
申请日：2008-01-15
申请人： Ying Zhu , Gregory Baratoff , Thorsten Kohler
发明人： Ying Zhu , Gregory Baratoff , Thorsten Kohler
IPC分类号： G06K9/00
CPC分类号： B60W40/02 , G06T7/246 , G06T2207/20016 , G06T2207/20076 , G06T2207/20081 , G06T2207/30252 , G08G1/16 , G08G1/166 , G08G1/167
摘要： A method for vehicle detection and tracking includes acquiring video data including a plurality of frames, comparing a first frame of the acquired video data against a set of one or more vehicle detectors to form vehicle hypotheses, pruning and verifying the vehicle hypotheses using a set of course-to-fine constraints to detect a vehicle, and tracking the detected vehicle within one or more subsequent frames of the acquired video data by fusing shape template matching with one or more vehicle detectors.
摘要翻译：一种用于车辆检测和跟踪的方法包括获取包括多个帧的视频数据，将所获取的视频数据的第一帧与一组一个或多个车辆检测器进行比较，以形成车辆假设，使用一组通过融合与一个或多个车辆检测器的形状模板匹配来跟踪所获取的视频数据的一个或多个后续帧中的检测到的车辆。

28. 发明授权

US07436980B2 Graphical object models for detection and tracking 有权
标题翻译：用于检测和跟踪的图形对象模型
公开(公告)号：US07436980B2
公开(公告)日：2008-10-14
申请号：US11135210
申请日：2005-05-23
申请人： Leonid Sigal , Ying Zhu , Dorin Comaniciu
发明人： Leonid Sigal , Ying Zhu , Dorin Comaniciu
IPC分类号： G06K9/00
CPC分类号： G06K9/00805 , G06K9/32 , G06T7/277
摘要： A computer implemented method for object detection includes providing a spatio-temporal model for an object to be detected, providing a video including a plurality of images including the object, and measuring the object as a collection of components in each image. The method further includes determining a probability that the object is in each image, and detecting the object in any image upon comparing the probabilities for each image to a threshold for detecting the object.
摘要翻译：一种用于对象检测的计算机实现方法包括：提供用于待检测对象的时空模型，提供包括包括对象在内的多个图像的视频，以及将对象作为每个图像中的组件的集合进行测量。该方法还包括确定对象在每个图像中的概率，并且在将每个图像的概率与用于检测对象的阈值进行比较时，检测任何图像中的对象。

29. 发明申请

US20080069400A1 Context adaptive approach in vehicle detection under various visibility conditions 有权
标题翻译：在各种可见度条件下车辆检测中的上下文自适应方法
公开(公告)号：US20080069400A1
公开(公告)日：2008-03-20
申请号：US11825619
申请日：2007-07-05
申请人： Ying Zhu , Gregory Baratoff , David Acunzo
发明人： Ying Zhu , Gregory Baratoff , David Acunzo
IPC分类号： G06K9/00
CPC分类号： G06K9/3241 , G06K9/00805 , G06K9/00825 , G06K2209/23
摘要： Adaptive vision-based vehicle detection methods, taking into account the lighting context of the images are disclosed. The methods categorize the scenes according to their lighting conditions and switch between specialized classifiers for different scene contexts. Four categories of lighting conditions have been identified using a clustering algorithm in the space of image histograms: Daylight, Low Light, Night, and Saturation. Trained classifiers are used for both Daylight and Low Light categories, and a tail-light detector is used for the Night category. Improved detection performance by using the provided context-adaptive methods is demonstrated. A night time detector is also disclosed.
摘要翻译：公开了考虑到图像的照明背景的基于视觉的自适应车辆检测方法。这些方法根据场景的照明条件对场景进行分类，并在不同场景环境的特殊分类器之间进行切换。在图像直方图的空间中，使用聚类算法识别了四类照明条件：日光，低光，夜和饱和度。训练分类器用于日光和低光类别，尾灯检测器用于夜间类别。通过使用提供的上下文自适应方法来提高检测性能。还公开了一种夜间检测器。

30. 发明申请

US20070183651A1 System and method for detecting an occupant and head pose using stereo detectors 有权
标题翻译：使用立体声检测器检测乘员和头部姿势的系统和方法
公开(公告)号：US20070183651A1
公开(公告)日：2007-08-09
申请号：US10991684
申请日：2004-11-18
申请人： Dorin Comaniciu , Thorsten Kohler , Binglong Xie , Ying Zhu
发明人： Dorin Comaniciu , Thorsten Kohler , Binglong Xie , Ying Zhu
IPC分类号： G06K9/00 , G06K9/62 , G06K9/46
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获取的图像对，并且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，选择具有最佳辨别能力的特征的子集，并为一对图像中的给定分量形成强分类器。在检测阶段，强分类器用于输入图像对以检测组件。识别的组件用于检测乘员的乘客和头部姿势。立体声检测与系统的立体匹配相结合，提高乘员检测和定位。

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