专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明授权

US08405540B2 Method for detecting small targets in radar images using needle based hypotheses verification 失效
标题翻译：使用基于针的假设验证来检测雷达图像中的小目标的方法
公开(公告)号：US08405540B2
公开(公告)日：2013-03-26
申请号：US12753643
申请日：2010-04-02
申请人： Fatih M. Porikli
发明人： Fatih M. Porikli
IPC分类号： G01S13/66 , G01S13/06 , G01S13/89 , G01S13/00
CPC分类号： G01S7/2923 , G01S13/89
摘要： A method detects a target in a sequence of radar images, wherein each image is partitioned into a grid of cells, and wherein each cell has a corresponding position in an image coordinate system associated with a location in a world coordinate system. For each most recent image in a sliding temporal window of images, intensities of each cell are determined, and the subset of the cells having highest intensities is stored as a set of current needles. A set of hypotheses, obtained by using a state transition model and corresponding maximum limits, is determined for the current set of needles and appended to a set of queues. The hypotheses for the previous sets of needles to the corresponding set of queues are updated, and a maximum likelihood in the set of queues are selected to detect the location of targets.
摘要翻译：一种方法检测雷达图像序列中的目标，其中每个图像被划分为单元格格，并且其中每个单元在与世界坐标系中的位置相关联的图像坐标系中具有相应的位置。对于图像的滑动时间窗口中的每个最新图像，确定每个单元的强度，并且具有最高强度的单元的子集被存储为一组当前针。通过使用状态转换模型和对应的最大限制获得的一组假设是针对当前针组确定的并附加到一组队列。更新针对相应队列的先前针组的假设，并且选择队列集合中的最大似然度来检测目标的位置。

42. 发明授权

US08358823B2 Method for tracking tumors in bi-plane images 有权
标题翻译：双平面图像跟踪肿瘤的方法
公开(公告)号：US08358823B2
公开(公告)日：2013-01-22
申请号：US13075822
申请日：2011-03-30
申请人： Fatih M. Porikli , Mohamed Hussein
发明人： Fatih M. Porikli , Mohamed Hussein
IPC分类号： G06K9/00
CPC分类号： G06K9/6224 , G06T7/11 , G06T7/143 , G06T7/162 , G06T7/174 , G06T7/194 , G06T2207/10136 , G06T2207/20156 , G06T2207/30096
摘要： A tumor is tracked in sequences of bi-plane images by generating a set of segmentation hypotheses using a 3D model of the tumor, a bi-plane geometry, and a previous location of the tumor as determined from the pairs of biplane images. Volume prior probabilities are constructed based on the set of hypotheses. Seed pixels are selected using the volume prior probabilities, and a bi-plane dual image graph is constructed using intensity gradients and the seed pixels to obtaining segmentation masks corresponding to tumor boundaries using the image intensities to determine a current location of the tumor.
摘要翻译：通过使用肿瘤三维模型，双平面几何以及从双平面图像对确定的肿瘤的先前位置产生一组分割假设来跟踪双平面图像序列。体积先验概率是基于一组假设构建的。使用体积先验概率选择种子像素，并且使用强度梯度和种子像素构建双平面双图像图像，以使用图像强度获得对应于肿瘤边界的分割掩模，以确定肿瘤的当前位置。

43. 发明申请

US20120226152A1 Tumor Tracking System and Method for Radiotherapy 审中-公开
标题翻译：肿瘤追踪系统及放射治疗方法
公开(公告)号：US20120226152A1
公开(公告)日：2012-09-06
申请号：US13039906
申请日：2011-03-03
申请人： Fatih M. Porikli
发明人： Fatih M. Porikli
IPC分类号： A61B6/00
CPC分类号： A61N5/1068 , A61B5/1114 , A61B5/1128 , A61B5/113 , A61B5/1135 , A61B5/4836 , A61B6/12 , A61B6/4458 , A61B6/5288 , A61N5/1037 , A61N5/1049 , A61N5/1067 , A61N5/1083 , A61N2005/1058 , A61N2005/1059 , A61N2005/1061 , A61N2005/1062 , A61N2005/1074 , A61N2005/1087
摘要： A system and method for tracking a tumor includes a regression module for selecting, using a motion signal and a regression function, a feature signal from a set of feature signals, each feature signal in the set of feature signals represents a medical image of the body of the patient, wherein the motion signal represents a motion of a surface of a skin of the patient caused by the respiration, and wherein the regression function is trained based on a set of observations of the motion signal synchronized with the set of feature signals; and a registration module for determining the location of the target object using the feature signal and a registration function, wherein the registration function registers each feature signal to a breath-hold location of the target object identified.
摘要翻译：用于跟踪肿瘤的系统和方法包括用于从一组特征信号中选择使用运动信号和回归函数的特征信号的回归模块，所述特征信号组中的每个特征信号表示身体的医学图像其中所述运动信号表示由所述呼吸引起的患者皮肤表面的运动，并且其中所述回归函数基于与所述特征信号组同步的运动信号的一组观察结果进行训练; 以及登记模块，用于使用所述特征信号和登记功能来确定所述目标对象的位置，其中所述登记功能将每个特征信号登记到所识别的所述目标对象的呼吸保持位置。

44. 发明申请

US20110013804A1 Method for Normalizing Displaceable Features of Objects in Images 有权
标题翻译：规范图像中物体的可移动特征的方法
公开(公告)号：US20110013804A1
公开(公告)日：2011-01-20
申请号：US12504407
申请日：2009-07-16
申请人： Fatih M. Porikli , Mohamed E. Hussein
发明人： Fatih M. Porikli , Mohamed E. Hussein
IPC分类号： G06K9/46 , G06K9/00
CPC分类号： G06K9/42 , G06K9/4671
摘要： A method normalizes a feature of an object in an image. The feature of the object is extracted from a 2D or 3D image. The feature is displaceable within a displacement zone in the object, and wherein the feature has a location within the displacement zone. An associated description of the feature is determined. Then, the feature is displaced to a best location in the displacement zone to produce a normalized feature.
摘要翻译：一种方法使图像中的对象的特征标准化。从2D或3D图像中提取对象的特征。该特征可在物体中的位移区域内移位，并且其中该特征具有位移区域内的位置。确定特征的相关描述。然后，将特征移位到位移区域中的最佳位置以产生归一化特征。

45. 发明授权

US07856120B2 Jointly registering images while tracking moving objects with moving cameras 有权
标题翻译：在移动摄像机跟踪移动物体时共同注册图像
公开(公告)号：US07856120B2
公开(公告)日：2010-12-21
申请号：US11693862
申请日：2007-03-30
申请人： Fatih M. Porikli , Xue Mei
发明人： Fatih M. Porikli , Xue Mei
IPC分类号： G06K9/00
CPC分类号： G06K9/32
摘要： A method tracks a moving object by registering a current image in a sequence of images with a previous image. The sequence of images is acquired of a scene by a moving camera. The registering produces a registration result. The moving object is tracked in the registered image to produce a tracking result. The registered current image is registered with the previous image using tracking result for all the images in the sequence.
摘要翻译：一种方法通过在先前图像的图像序列中注册当前图像来跟踪移动物体。通过移动的相机获取场景的图像序列。注册产生注册结果。在注册的图像中跟踪运动对象以产生跟踪结果。使用跟踪结果将登记的当前图像与先前图像一起登记，使用序列中所有图像的跟踪结果。

46. 发明授权

US07813528B2 Method for detecting objects left-behind in a scene 有权
标题翻译：用于检测场景中遗留物体的方法
公开(公告)号：US07813528B2
公开(公告)日：2010-10-12
申请号：US11697052
申请日：2007-04-05
申请人： Fatih M. Porikli , Yuri A. Ivanov
发明人： Fatih M. Porikli , Yuri A. Ivanov
IPC分类号： G06K9/00
CPC分类号： G06K9/00771
摘要： A method detects an object left-behind in a scene by updating a set of background models using a sequence of images acquired of the scene by a camera. Each background model is updated at a different temporal scales ranging from short term to long term. A foreground mask is determined from each background model after the updating for a particular image of the sequence. A motion image is updated from the set of foreground masks. In the motion, image, each pixel has an associated evidence value. The evidence values are compared with a evidence threshold to detect and signal an object left behind in the scene.
摘要翻译：一种方法通过使用由相机拍摄的场景的图像序列来更新一组背景模型来检测场景中遗留的对象。每个背景模型以不同的时间尺度更新，从短期到长期。在对序列的特定图像进行更新之后，从每个背景模型确定前景蒙版。运动图像从前景蒙版组更新。在运动，图像中，每个像素都具有相关的证据值。将证据值与证据阈值进行比较，以检测并发出场景中留下的物体。

47. 发明授权

US07809165B2 Method for generating distance maps using scan lines 失效
标题翻译：使用扫描线生成距离图的方法
公开(公告)号：US07809165B2
公开(公告)日：2010-10-05
申请号：US11626974
申请日：2007-01-25
申请人： Fatih M. Porikli
发明人： Fatih M. Porikli
IPC分类号： G06K9/00
CPC分类号： G06K9/4638 , G06K9/50
摘要： A method generates a distance map from an image including a set of pixels arranged in a Euclidian n-space. The set of pixels includes a subset of background pixels and a subset of foreground pixels. The distance map stores a distance value for every corresponding background pixel to a nearest foreground pixel. A set of scan lines having different directions are defined. The scanning of the set of pixels along each scan lines is performed by moving from a current pixel to a next pixel. The scanning of each scan line includes: making the next pixel the current pixel; initializing a counter to zero when the current pixel is one of the foreground pixels and the next pixel is one of the background pixels; incrementing the counter by one when the next pixel is one of the background pixels; and assigning the counter as the distance corresponding to the current pixel if the current pixel is one of the background pixels, and repeating beginning with the making step.
摘要翻译：一种方法从包括在欧几里得n空间中排列的一组像素的图像产生距离图。像素集合包括背景像素的子集和前景像素的子集。距离图将每个对应的背景像素的距离值存储到最近的前景像素。定义了一组具有不同方向的扫描线。通过从当前像素移动到下一个像素来执行沿着每条扫描线的像素组的扫描。每个扫描线的扫描包括：使下一个像素成为当前像素; 当当前像素是前景像素之一并且下一像素是背景像素之一时，将计数器初始化为零; 当下一个像素是背景像素之一时，将计数器递增1; 以及如果所述当前像素是所述背景像素之一，则将所述计数器分配为与所述当前像素对应的距离，并且从所述制作步骤开始重复。

48. 发明申请

US20100250473A1 Active Learning Method for Multi-Class Classifiers 有权
标题翻译：多类分类器的主动学习方法
公开(公告)号：US20100250473A1
公开(公告)日：2010-09-30
申请号：US12413492
申请日：2009-03-27
申请人： Fatih M. Porikli , Ajay Joshi
发明人： Fatih M. Porikli , Ajay Joshi
IPC分类号： G06F15/18 , G06N3/02
CPC分类号： G06N99/005
摘要： A method trains a multi-class classifier by iteratively performing the following steps until a termination condition is reached. The probabilities of class membership for unlabeled data obtained from an active pool of unlabeled data are estimated. A difference between a largest probability and a second largest probability is determined. The unlabeled data with the lowest difference is selected, labeled and then added to a training data set for training the classifier.
摘要翻译：一种方法通过迭代地执行以下步骤来训练多类分类器，直到达到终止条件。估计从未标记数据的活动池获得的未标记数据的类成员资格概率。确定最大概率和第二大概率之间的差异。选择具有最低差异的未标记数据，标记，然后添加到用于训练分类器的训练数据集中。

49. 发明授权

US07724961B2 Method for classifying data using an analytic manifold 有权
标题翻译：使用分析歧管对数据进行分类的方法
公开(公告)号：US07724961B2
公开(公告)日：2010-05-25
申请号：US11517645
申请日：2006-09-08
申请人： Fatih M. Porikli , Oncel C. Tuzel
发明人： Fatih M. Porikli , Oncel C. Tuzel
IPC分类号： G06K9/62 , G06E1/00
CPC分类号： G06K9/6256 , G06K9/00369 , G06K9/4642
摘要： A computer implemented method constructs a classifier for classifying test data. High-level features are generated from low-level features extracted from training data. The high level features are positive definite matrices in a form of an analytical manifold. A subset of the high-level features is selected. An intrinsic mean matrix is determined from the subset of the selected high-level features. Each high-level feature is mapped to a feature vector onto a tangent space of the analytical manifold using the intrinsic mean matrix. Then, an untrained classifier model can be trained with the feature vectors to obtain a trained classifier. Subsequently, the trained classifier can classify unknown test data.
摘要翻译：计算机实现的方法构建用于分类测试数据的分类器。高级功能是从训练数据中提取的低级功能产生的。高级特征是分析歧管形式的正定矩阵。选择高级功能的子集。从所选择的高级特征的子集确定固有均值矩阵。使用内在平均矩阵将每个高级特征映射到分析歧管的切线空间上的特征向量。然后，可以使用特征向量来训练未经训练的分类器模型以获得训练有素的分类器。随后，经过训练的分类器可以对未知的测试数据进行分类。

50. 发明申请

US20090317015A1 Method for Filtering of Images with Bilateral Filters and Power Images 有权
标题翻译：用双向滤波器和功率图像滤波图像的方法
公开(公告)号：US20090317015A1
公开(公告)日：2009-12-24
申请号：US12143565
申请日：2008-06-20
申请人： Fatih M. Porikli
发明人： Fatih M. Porikli
IPC分类号： G06K9/40
CPC分类号： G06T5/20 , G06T2207/20028
摘要： The current invention describes a method for filtering an input image with a bilateral filter. The bilateral filter includes a spatial filter and a range filter. The method constructs a set of power images from an input image including pixels, each pixel having intensity. Then, the method applies, to each power image, the spatial filter to determine a response for the spatial filter and the corresponding power image and combines the responses and the set of power images to produce a response for the bilateral filter.
摘要翻译：本发明描述了一种用双边滤波器对输入图像进行滤波的方法。双边滤波器包括空间滤波器和范围滤波器。该方法从包括像素的输入图像构建一组功率图像，每个像素具有强度。然后，该方法对每个功率图像应用空间滤波器以确定空间滤波器和对应的功率图像的响应，并组合响应和功率图像集合以产生双边滤波器的响应。

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