公开(公告)号：US07460733B2

公开(公告)日：2008-12-02

申请号：US11215419

申请日：2005-08-30

Applicant: Jing Xiao ,  Bogdan Georgescu ,  Xiang Zhou ,  Dorin Comaniciu

Inventor： Jing Xiao ,  Bogdan Georgescu ,  Xiang Zhou ,  Dorin Comaniciu

IPC: G06K9/32

CPC classification number: G06K9/00127 ,  G06K9/00221 ,  G06K9/00973 ,  G06T7/149

Abstract: A method of registering and modeling a deformable shape in a digitized image is provided, comprising the steps of providing a measurement matrix W of N measurements of P points of a D-dimensional deformable shape, determining a basis number K for the N measurements, wherein K

公开(公告)号：US20080281203A1

公开(公告)日：2008-11-13

申请号：US12054094

申请日：2008-03-24

Applicant: Shaohua Kevin Zhou ,  Feng Guo ,  John Jackson ,  Michael Brendel ,  Dorin Comaniciu

Inventor： Shaohua Kevin Zhou ,  Feng Guo ,  John Jackson ,  Michael Brendel ,  Dorin Comaniciu

IPC: A61B8/00

CPC classification number: A61B8/08 ,  A61B5/1075 ,  A61B5/7267 ,  A61B6/503 ,  A61B8/0883 ,  A61B8/463 ,  A61B8/486 ,  G06K9/00523 ,  G06K9/00536 ,  G06K9/6257 ,  G06T7/60

Abstract: A method for measuring ventricular dimensions from M-mode echocardiograms, includes providing a digitized M-mode echocardiogram image, running a plurality of local classifiers, where each local classifier trained to detect a landmark on either an end-diastole (ED) line or an end-systole (ES) line in the image, recording all possible landmarks detected by the classifiers, where a search range in an N-dimensional parameter space defined by the landmarks for each dimension is reduced to a union of subsets, where each dimension of the parameter space corresponds a landmark, for each combination of possible landmarks, checking if an order of the landmarks is consistent with a known ordering of the landmarks, and if the order is consistent, running a global detector on each consistent combination of landmarks to find a landmark combination with a highest detection probability as a confirmed landmark detection, where the landmarks are used for measuring ventricular dimensions.

Abstract translation: 一种用于从M型超声心动图测量心室尺寸的方法，包括提供数字化的M模式超声心动图图像，运行多个局部分类器，其中训练每个局部分类器以检测舒张末期（ED）线或 记录图像中的终点收缩（ES）线，记录由分类器检测到的所有可能的地标，其中由每个维度的地标定义的N维参数空间中的搜索范围被减少到子集的并集，其中每个维度 参数空间对应于地标，对于可能的地标的每个组合，检查地标的顺序是否与已知的地标的顺序一致，并且如果顺序一致，则在每个一致的地标组合上运行全局检测器以找到 具有最高检测概率的地标组合，作为确认的地标检测，其中地标被用于测量心室维度。

公开(公告)号：US07446798B2

公开(公告)日：2008-11-04

申请号：US10770044

申请日：2004-02-02

Applicant: Dorin Comaniciu ,  Binglong Xie

Inventor： Dorin Comaniciu ,  Binglong Xie

IPC: H04N7/18

CPC classification number: G06K9/3241 ,  G06K2209/23 ,  G06T7/70

Abstract: A method and system of real-time obstacle detection from a moving vehicle is provided. The method and system use a calibrated image capturing device. The method and system use a motion estimation technique to pick points with reliable image motion flows, and performs very fast sparse matching between the image motion flows and true motion flows calculated from the ego-motion of the image capturing device. Any mismatch between the image motion flows and the true motion flows are verified over time to achieve robust obstacle detection.

Abstract translation: 提供了一种来自移动车辆的实时障碍物检测方法和系统。 该方法和系统使用校准的图像捕获装置。 该方法和系统使用运动估计技术来拾取具有可靠图像运动流的点，并且在图像运动流和从图像捕获装置的自身运动计算出的真实运动流之间执行非常快的稀疏匹配。 图像运动流和真实运动流之间的任何不匹配都随时间被验证，以实现鲁棒的障碍物检测。

公开(公告)号：US20080240532A1

公开(公告)日：2008-10-02

申请号：US12056107

申请日：2008-03-26

Applicant: Gustavo Henrique de Barros Carneiro ,  Bogdan Georgescu ,  Sara Good ,  Dorin Comaniciu

Inventor： Gustavo Henrique de Barros Carneiro ,  Bogdan Georgescu ,  Sara Good ,  Dorin Comaniciu

IPC: G06K9/00

CPC classification number: G06K9/46 ,  A61B8/0866 ,  G06K9/3233 ,  G06K9/38 ,  G06K9/4614 ,  G06K9/6282 ,  G06K2009/366 ,  G06K2209/051

Abstract: A method for detecting fetal anatomic features in ultrasound images includes providing an ultrasound image of a fetus, specifying an anatomic feature to be detected in a region S determined by parameter vector θ, providing a sequence of probabilistic boosting tree classifiers, each with a pre-specified height and number of nodes. Each classifier computes a posterior probability P(y|S) where yε{−1,+1}, with P(y=+1|S) representing a probability that region S contains the feature, and P(y=−1|S) representing a probability that region S contains background information. The feature is detected by uniformly sampling a parameter space of parameter vector θ using a first classifier with a sampling interval vector used for training said first classifier, and having each subsequent classifier classify positive samples identified by a preceding classifier using a smaller sampling interval vector used for training said preceding classifier. Each classifier forms a union of its positive samples with those of the preceding classifier.

Abstract translation: 一种用于检测超声图像中的胎儿解剖特征的方法包括提供胎儿的超声图像，指定在由参数矢量θ确定的区域S中要检测的解剖特征，提供一系列概率增强树分类器， 指定的高度和节点数。 每个分类器计算出一个后验概率P（y | S），其中，y（1 + 1），其中P（y = + 1 | S）表示区域S包含特征的概率，P（y = -1 | S）表示区域S包含背景信息的概率。 通过使用具有用于训练所述第一分类器的采样间隔向量的第一分类器对参数向量θ的参数空间进行均匀采样来检测该特征，并且每个后续分类器使用使用较小的采样间隔向量来分类由先前分类器标识的正样本 训练前面的分类器。 每个分类器形成其正样本与上一分类器的并集。

公开(公告)号：US07421101B2

公开(公告)日：2008-09-02

申请号：US10957380

申请日：2004-10-01

Applicant: Bogdan Georgescu ,  Xiang Sean Zhou ,  Dorin Comaniciu ,  Sriram Krishnan

Inventor： Bogdan Georgescu ,  Xiang Sean Zhou ,  Dorin Comaniciu ,  Sriram Krishnan

IPC: G06K9/00

CPC classification number: G06T7/20 ,  G06T7/0016 ,  G06T7/251 ,  G06T2207/10132 ,  G06T2207/30048

Abstract: 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.

Abstract translation: 用于局部可变形运动分析的系统和方法准确地跟踪对象的运动，使得对象的局部运动与对象的全局运动隔离。 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(公告)号：US20080107314A1

公开(公告)日：2008-05-08

申请号：US11860591

申请日：2007-09-25

Applicant: Bogdan Georgescu ,  Peter Durlak ,  Vassilis Athitsos ,  Adrian Barbu ,  Dorin Comaniciu

Inventor： Bogdan Georgescu ,  Peter Durlak ,  Vassilis Athitsos ,  Adrian Barbu ,  Dorin Comaniciu

IPC: G06K9/00 ,  G06K9/40

CPC classification number: G06T5/003 ,  G06T5/20 ,  G06T7/74 ,  G06T2207/10121 ,  G06T2207/20016 ,  G06T2207/30021

Abstract: A method for downsampling fluoroscopic images and enhancing guidewire visibility during coronary angioplasty includes providing a first digitized image, filtering the image with one or more steerable filters of different angular orientations, assigning a weight W and orientation O for each pixel based on the filter response for each pixel, wherein each pixel weight is assigned to a function of a maximum filter response magnitude and the pixel orientation is calculated from the angle producing the maximum filter response if the magnitude is greater than zero, wherein guidewire pixels have a higher weight than non-guidewire pixels, and downsampling the orientation and weights to calculate a second image of half the resolution of the first image, wherein the downsampling accounts for the orientation and higher weight assigned to the guidewire pixels.

Abstract translation: 用于在冠状动脉血管成形术期间对荧光透视图像进行下采样并增强导丝线可视性的方法包括提供第一数字化图像，用一个或多个不同角取向的可转向滤光片过滤图像，基于滤波器响应为每个像素分配权重W和取向O 每个像素，其中每个像素权重被分配给最大滤波器响应幅度的函数，并且如果幅度大于零，则从产生最大滤波器响应的角度计算像素取向，其中导丝像素具有比非最大滤波器响应幅度更大的权重， 引导线像素，以及对取向和权重进行下采样以计算第一图像的分辨率的一半的第二图像，其中下采样考虑分配给导丝像素的取向和较高权重。

公开(公告)号：US20080085050A1

公开(公告)日：2008-04-10

申请号：US11856208

申请日：2007-09-17

Applicant: Adrian Barbu ,  Yefeng Zheng ,  Jing Yang ,  Bogdan Georgescu ,  Dorin Comaniciu

Inventor： Adrian Barbu ,  Yefeng Zheng ,  Jing Yang ,  Bogdan Georgescu ,  Dorin Comaniciu

IPC: G06K9/00

CPC classification number: G06K9/6292

Abstract: A system and method for detecting an object in a high dimensional image space is disclosed. A three dimensional image of an object is received. A first classifier is trained in the marginal space of the object center location which generates a predetermined number of candidate object center locations. A second classifier is trained to identify potential object center locations and orientations from the predetermined number of candidate object center locations and maintaining a subset of the candidate object center locations. A third classifier is trained to identify potential locations, orientations and scale of the object center from the subset of the candidate object center locations. A single candidate object pose for the object is identified.

Abstract translation: 公开了一种用于检测高维图像空间中的对象的系统和方法。 接收对象的三维图像。 在对象中心位置的边缘空间中训练第一分类器，其生成预定数量的候选对象中心位置。 训练第二分类器以从预定数量的候选对象中心位置识别潜在对象中心位置和方向，并维护候选对象中心位置的子集。 训练第三分类器以从候选对象中心位置的子集中识别对象中心的潜在位置，方向和尺度。 识别对象的单个候选对象姿势。

公开(公告)号：US20080025588A1

公开(公告)日：2008-01-31

申请号：US11779405

申请日：2007-07-18

Applicant: Wei Zhang ,  Adrian Barbu ,  Simone Prummer ,  Martin Ostermeier ,  Chandan Reddy ,  Dorin Comaniciu

Inventor： Wei Zhang ,  Adrian Barbu ,  Simone Prummer ,  Martin Ostermeier ,  Chandan Reddy ,  Dorin Comaniciu

IPC: G06K9/00

CPC classification number: G06K9/34 ,  G06K2209/05 ,  Y10S128/922

Abstract: A method and system for extracting motion-based layers from fluoroscopic image sequences are disclosed. Portions of multiple objects, such as anatomical structures, are detected in the fluoroscopic images. Motion of the objects is estimated between the images is the sequence of fluoroscopic images. The images in the fluoroscopic image sequence are then divided into layers based on the estimated motion. In a particular implementation, the coronary vessel tree and the diaphragm can be extracted in separate motion layers from coronary angiograph fluoroscopic image sequence.

Abstract translation: 公开了一种从透视图像序列中提取基于运动的层的方法和系统。 在透视图像中检测到多个对象的部分，例如解剖结构。 在图像之间估计物体的运动是荧光图像的序列。 然后，基于估计的运动将透视图像序列中的图像分成多个层。 在特定的实施方案中，冠状动脉血管和隔膜可以与冠状动脉血管造影术透视图像序列分开提取。

公开(公告)号：US20070270692A1

公开(公告)日：2007-11-22

申请号：US11675678

申请日：2007-02-16

Applicant: Adrian Barbu ,  Vassilis Athitsos ,  Bogdan Georgescu ,  Stefan Boehm ,  Peter Durlak ,  Dorin Comaniciu

Inventor： Adrian Barbu ,  Vassilis Athitsos ,  Bogdan Georgescu ,  Stefan Boehm ,  Peter Durlak ,  Dorin Comaniciu

IPC: A61B6/00

CPC classification number: A61B6/12 ,  G06K9/48 ,  G06K2209/057

Abstract: A system and method for populating a database with a set of image sequences of an object is disclosed. The database is used to detect localization of a guidewire in the object. A set of images of anatomical structures is received in which each image is annotated to show a guidewire, catheter, wire tip and stent. For each given image a Probabilistic Boosting Tree (PBT) is used to detect short line segments of constant length in the image. Two segment curves are constructed from the short line segments. A discriminative joint shape and appearance model is used to classify each two segment curve. A shape of an n-segment curve is constructed by concatenating all the two segment curves. A guidewire curve model is identified that includes a start point, end point and the n-segment curve. The guidewire curve model is stored in the database.

Abstract translation: 公开了一种使用一组对象的图像序列填充数据库的系统和方法。 数据库用于检测对象中导丝的定位。 接收一组解剖结构的图像，其中每个图像被注释以示出导丝，导管，线尖和支架。 对于每个给定的图像，使用概率增强树（PBT）来检测图像中恒定长度的短线段。 从短线段构建两段曲线。 使用歧视关节形状和外观模型对每个两段曲线进行分类。 通过连接所有两个段曲线构建n段曲线的形状。 识别出导线曲线模型，其包括起始点，终点和n段曲线。 导丝曲线模型存储在数据库中。

公开(公告)号：US07260259B2

公开(公告)日：2007-08-21

申请号：US10338335

申请日：2003-01-08

Applicant: Dorin Comaniciu ,  Visvanathan Ramesh

Inventor： Dorin Comaniciu ,  Visvanathan Ramesh

IPC: G06K9/34

CPC classification number: G06K9/6226 ,  G06K9/342 ,  G06T7/11 ,  G06T7/143 ,  G06T2207/10016 ,  G06T2207/20164

Abstract: A system and method for image segmentation using statistical clustering with saddle point detection includes representation means for representing the image data in a joint space of dimension d=r+2 that includes two special coordinates, where r=1 for gray-scale images, r=3 for color images, and r>3 for multi-spectral images; partitioning means for partitioning the data set comprising a plurality of image data points into a plurality of statistically meaningful clusters by decomposing the data set by a mean shift based data decomposition; and characterization means for characterizing the statistical significance of at least one of a plurality of clusters of data points by selecting a cluster and computing the value of a statistical measure for the saddle point lying on the border of the selected cluster and having the highest density.

Abstract translation: 使用具有鞍点检测的统计聚类的图像分割的系统和方法包括用于在包括两个特殊坐标的维度d = r + 2的关节空间中表示图像数据的表示装置，其中对于灰度图像，r = 1 = 3为彩色图像，r> 3为多光谱图像; 分割装置，用于通过基于平均移位的数据分解来分解所述数据集，将包括多个图像数据点的数据集划分成多个统计意义上的集群; 以及表征装置，用于通过选择一个群集并计算位于所选择的群集边界并且具有最高密度的鞍点的统计度量的值来表征多个数据点集群中的至少一个的统计显着性。