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. 发明授权

US07620205B2 Method for characterizing shape, appearance and motion of an object that is being tracked 有权
标题翻译：描述被跟踪物体的形状，外观和运动的方法
公开(公告)号：US07620205B2
公开(公告)日：2009-11-17
申请号：US11466477
申请日：2006-08-23
申请人： Shaohua Kevin Zhou , Jie Shao , Dorin Comaniciu , Bogdan Georgescu
发明人： Shaohua Kevin Zhou , Jie Shao , Dorin Comaniciu , Bogdan Georgescu
IPC分类号： G06K9/00 , A61B6/00
CPC分类号： G06K9/621 , G06K9/00335 , G06K9/48 , G06K9/6209 , G06K2009/487 , G06K2209/05 , G06T7/251 , G06T2207/10132 , G06T2207/30048
摘要： A method for generating Pairwise Active Appearance Models (PAAMs) that characterize shape, appearance and motion of an object and using the PAAM to track the motion of an object is disclosed. A plurality of video streams is received. Each video stream includes a series of image frames that depict an object in motion. Each video stream includes an index of identified motion phases that are associated with a motion cycle of the object. For each video stream, a shape of the object is represented by a shape vector. An appearance of an object is represented by an appearance vector. The shape and appearance vectors associated at two consecutive motion phases are concatenated. Paired data for the concatenated shape and appearance vectors is computed. Paired data is computed for each two consecutive motion phases in the motion cycle. A shape subspace is constructed based on the computed paired data. An appearance subspace is constructed based on the computed paired data. A joint subspace is constructed using a combination of the shape subspace and appearance subspace. A PAAM is generated using the joint subspace and the PAAM is stored in a database.
摘要翻译：公开了一种用于产生表征对象的形状，外观和运动以及使用PAAM跟踪对象的运动的成对活动外观模型（PAAM）的方法。接收多个视频流。每个视频流包括描绘运动对象的一系列图像帧。每个视频流包括与对象的运动周期相关联的所识别的运动相位的索引。对于每个视频流，对象的形状由形状向量表示。物体的外观由外观矢量表示。在两个连续的运动阶段相关联的形状和外观矢量被连接起来。计算连续形状和外观向量的配对数据。计算运动周期中每两个连续运动相位的配对数据。基于计算的配对数据构建形状子空间。基于计算出的配对数据构建出现子空间。使用形状子空间和外观子空间的组合构建关节子空间。使用联合子空间生成PAAM，并将PAAM存储在数据库中。

2. 发明授权

US07831074B2 System and method for using a similarity function to perform appearance matching in image pairs 有权
标题翻译：使用相似度函数执行图像对中的外观匹配的系统和方法
公开(公告)号：US07831074B2
公开(公告)日：2010-11-09
申请号：US11539989
申请日：2006-10-10
申请人： Shaohua Kevin Zhou , Jie Shao , Jonathan Dowdall , Adrian Barbu , Bogdan Georgescu , Dorin Comaniciu
发明人： Shaohua Kevin Zhou , Jie Shao , Jonathan Dowdall , Adrian Barbu , Bogdan Georgescu , Dorin Comaniciu
IPC分类号： G06K9/00 , G06K9/62 , H04N5/225
CPC分类号： G06K9/6257 , G06K2209/05 , G06T7/33 , G06T2207/10124 , G06T2207/10132 , G06T2207/30048
摘要： The present invention is directed to a method for populating a database with a set of images of an anatomical structure. The database is used to perform appearance matching in image pairs of the anatomical structure. A set of image pairs of anatomical structures is received, where each image pair is annotated with a plurality of location-sensitive regions that identify a particular aspect of the anatomical structure. Weak learners are iteratively selected and an image patch is identified. A boosting process is used to identify a strong classifier based on responses to the weak learners applied to the identified image patch for each image pair. The responses comprise a feature response and a location response associated with the image patch. Positive and negative image pairs are generated. The positive and negative image pairs are used to learn a similarity function. The learned similarity function and iteratively selected weak learners are stored in the database.
摘要翻译：本发明涉及一种用解剖结构的一组图像填充数据库的方法。该数据库用于在解剖结构的图像对中执行外观匹配。接收一组解剖结构的图像对，其中每个图像对用多个识别解剖结构的特定方面的位置敏感区域注释。迭代选择弱学习者，并识别图像补丁。基于对应用于每个图像对的所识别的图像补丁的弱学习者的响应，使用增强过程来识别强分类器。响应包括与图像块相关联的特征响应和位置响应。产生正负图像对。正负图像对用于学习相似度函数。学习的相似度函数和迭代选择的弱学习者存储在数据库中。

3. 发明申请

US20070098239A1 METHOD FOR CHARACTERIZING SHAPE, APPEARANCE AND MOTION OF AN OBJECT THAT IS BEING TRACKED 有权
标题翻译：用于表征正在跟踪的对象的形状，外观和运动的方法
公开(公告)号：US20070098239A1
公开(公告)日：2007-05-03
申请号：US11466477
申请日：2006-08-23
申请人： Shaohua Zhou , Jie Shao , Dorin Comaniciu , Bogdan Georgescu
发明人： Shaohua Zhou , Jie Shao , Dorin Comaniciu , Bogdan Georgescu
IPC分类号： G06K9/00
CPC分类号： G06K9/621 , G06K9/00335 , G06K9/48 , G06K9/6209 , G06K2009/487 , G06K2209/05 , G06T7/251 , G06T2207/10132 , G06T2207/30048
摘要： A method for generating Pairwise Active Appearance Models (PAAMs) that characterize shape, appearance and motion of an object and using the PAAM to track the motion of an object is disclosed. A plurality of video streams is received. Each video stream includes a series of image frames that depict an object in motion. Each video stream includes an index of identified motion phases that are associated with a motion cycle of the object. For each video stream, a shape of the object is represented by a shape vector. An appearance of an object is represented by an appearance vector. The shape and appearance vectors associated at two consecutive motion phases are concatenated. Paired data for the concatenated shape and appearance vectors is computed. Paired data is computed for each two consecutive motion phases in the motion cycle. A shape subspace is constructed based on the computed paired data. An appearance subspace is constructed based on the computed paired data. A joint subspace is constructed using a combination of the shape subspace and appearance subspace. A PAAM is generated using the joint subspace and the PAAM is stored in a database.
摘要翻译：公开了一种用于产生表征对象的形状，外观和运动以及使用PAAM跟踪对象的运动的成对活动外观模型（PAAM）的方法。接收多个视频流。每个视频流包括描绘运动对象的一系列图像帧。每个视频流包括与对象的运动周期相关联的所识别的运动相位的索引。对于每个视频流，对象的形状由形状向量表示。物体的外观由外观矢量表示。在两个连续的运动阶段相关联的形状和外观矢量被连接起来。计算连续形状和外观向量的配对数据。计算运动周期中每两个连续运动相位的配对数据。基于计算的配对数据构建形状子空间。基于计算出的配对数据构建出现子空间。使用形状子空间和外观子空间的组合构建关节子空间。使用联合子空间生成PAAM，并将PAAM存储在数据库中。

4. 发明申请

US20070237370A1 System and Method For Using A Similarity Function To Perform Appearance Matching In Image Pairs 有权
标题翻译：在图像对中使用相似性函数进行外观匹配的系统和方法
公开(公告)号：US20070237370A1
公开(公告)日：2007-10-11
申请号：US11539989
申请日：2006-10-10
申请人： Shaohua Zhou , Jie Shao , Jonathan Dowdall , Adrian Barbu , Bogdan Georgescu , Dorin Comaniciu
发明人： Shaohua Zhou , Jie Shao , Jonathan Dowdall , Adrian Barbu , Bogdan Georgescu , Dorin Comaniciu
IPC分类号： G06K9/00
CPC分类号： G06K9/6257 , G06K2209/05 , G06T7/33 , G06T2207/10124 , G06T2207/10132 , G06T2207/30048
摘要： The present invention is directed to a method for populating a database with a set of images of an anatomical structure. The database is used to perform appearance matching in image pairs of the anatomical structure. A set of image pairs of anatomical structures is received, where each image pair is annotated with a plurality of location-sensitive regions that identify a particular aspect of the anatomical structure. Weak learners are iteratively selected and an image patch is identified. A boosting process is used to identify a strong classifier based on responses to the weak learners applied to the identified image patch for each image pair. The responses comprise a feature response and a location response associated with the image patch. Positive and negative image pairs are generated. The positive and negative image pairs are used to learn a similarity function. The learned similarity function and iteratively selected weak learners are stored in the database.
摘要翻译：本发明涉及一种用解剖结构的一组图像填充数据库的方法。该数据库用于在解剖结构的图像对中执行外观匹配。接收一组解剖结构的图像对，其中每个图像对用多个识别解剖结构的特定方面的位置敏感区域注释。迭代选择弱学习者，并识别图像补丁。基于对应用于每个图像对的所识别的图像补丁的弱学习者的响应，使用增强过程来识别强分类器。响应包括与图像块相关联的特征响应和位置响应。产生正负图像对。正负图像对用于学习相似度函数。学习的相似度函数和迭代选择的弱学习者存储在数据库中。

5. 发明申请

US20090240431A1 Panoramic Images Within Driving Directions 有权
标题翻译：行车路线内的全景图像
公开(公告)号：US20090240431A1
公开(公告)日：2009-09-24
申请号：US12410033
申请日：2009-03-24
申请人： Stephen Chau , Stephane Lafon , Jie Shao , Andrew Timothy Szybalski , Luc Vincent
发明人： Stephen Chau , Stephane Lafon , Jie Shao , Andrew Timothy Szybalski , Luc Vincent
IPC分类号： G01C21/34 , G09G5/00 , G06T15/00
CPC分类号： G01C21/3647
摘要： Embodiments of the present invention enable displaying a plurality of driving direction steps that form a driving directions path between a start address and a destination address; receiving input selecting a driving direction step of said plurality of driving direction steps; and displaying a panoramic image of a geographic area where a driving action associated with said selected driving direction step would be performed by a driver. In other embodiments, the panoramic image is replaced and/or complemented with one or more of 3D models, full-motion video, full-motion video of 360 degrees images, and live feeds from video cameras to provide enhanced driving directions.
摘要翻译：本发明的实施例能够显示形成起始地址和目的地地址之间的行驶方向路径的多个行驶方向步骤; 接收选择所述多个驱动方向步骤的驱动方向步骤的输入; 以及显示与所述选择的驾驶方向步骤相关联的驾驶动作将由驾驶员执行的地理区域的全景图像。在其他实施例中，全景图像被3D模型，全动态视频，360度图像的全动态视频以及来自摄像机的实况馈送中的一个或多个替代和/或补充，以提供增强的行进方向。

6. 发明申请

US20150154745A1 3D Object Positioning in Street View 有权
标题翻译：街景视图中的3D对象定位
公开(公告)号：US20150154745A1
公开(公告)日：2015-06-04
申请号：US13414351
申请日：2012-03-07
申请人： Stéphane LAFON , Jie Shao
发明人： Stéphane LAFON , Jie Shao
IPC分类号： G06T15/00 , G06T7/00 , G06K9/00
CPC分类号： G01C21/00 , G06F17/30241 , G06F17/30873 , G06T17/05 , G06T19/00 , G06T2219/004
摘要： Systems, methods, and computer storage mediums are provided for correcting the placement of an object on an image. An example method includes providing the image and depth data that describes the depth of the three-dimensional scene captured by the image. The depth data describes at least a distance between a camera that captured the three-dimensional scene and one or more structures in the scene and a geolocation of the camera when the three-dimensional scene was captured. When the object is moved from a first location on the image to a second location on the image, a set of coordinates that describes the second location relative to the image is received. The set of coordinates are then translated into geolocated coordinates that describe a geolocation that corresponds to the second location. The set of coordinate is translated, at least in part, using the depth data associated with the image.
摘要翻译：系统，方法和计算机存储介质被提供用于校正物体在图像上的放置。示例性方法包括提供描述由图像捕获的三维场景的深度的图像和深度数据。深度数据描述了捕获三维场景的摄像机与场景中的一个或多个结构之间的距离和拍摄三维场景时相机的地理位置之间的距离。当物体从图像上的第一位置移动到图像上的第二位置时，接收一组描述相对于图像的第二位置的坐标。然后将该坐标系转换为描述与第二个位置对应的地理位置的地理位置坐标。至少部分地使用与图像相关联的深度数据来转换坐标集合。

7. 发明授权

US07376246B2 Subspace projection based non-rigid object tracking with particle filters 失效
标题翻译：基于子空间投影的非刚性物体跟踪与粒子滤波器
公开(公告)号：US07376246B2
公开(公告)日：2008-05-20
申请号：US11167684
申请日：2005-06-27
申请人： Jie Shao , Fatih M. Porikli
发明人： Jie Shao , Fatih M. Porikli
IPC分类号： G06K9/00
CPC分类号： G06K9/6207 , G06K9/3216 , G06T7/277 , G06T2207/30241
摘要： A method tracks non-rigid objects in a video acquired of a cluttered scene by a camera. The method uses a particle filter. The tracking includes the following steps: motion transition estimation, contour deformation detection, and contour regulation. The method uses a dynamic affine transform model and employs the particle filter to estimate the parameters of the model. The method generates a probabilistic map of deformation for tracking the contour of the object followed by a projection step to constrain or regulate the contour in a contour subspace.
摘要翻译：一种方法跟踪摄像机拍摄的杂乱场景中的非刚性物体。该方法使用粒子滤波器。跟踪包括以下步骤：运动转换估计，轮廓变形检测和轮廓调节。该方法使用动态仿射变换模型，并使用粒子滤波器来估计模型的参数。该方法生成用于跟踪对象轮廓的变形的概率图，随后是在轮廓子空间中约束或调节轮廓的投影步骤。

8. 发明申请

US20060291696A1 Subspace projection based non-rigid object tracking with particle filters 失效
标题翻译：基于子空间投影的非刚性物体跟踪与粒子滤波器
公开(公告)号：US20060291696A1
公开(公告)日：2006-12-28
申请号：US11167684
申请日：2005-06-27
申请人： Jie Shao , Fatih Porikli
发明人： Jie Shao , Fatih Porikli
IPC分类号： G06K9/00
CPC分类号： G06K9/6207 , G06K9/3216 , G06T7/277 , G06T2207/30241
摘要： A method tracks non-rigid objects in a video acquired of a cluttered scene by a camera. The method uses a particle filter. The tracking includes the following steps: motion transition estimation, contour deformation detection, and contour regulation. The method uses a dynamic affine transform model and employs the particle filter to estimate the parameters of the model. The method generates a probabilistic map of deformation for tracking the contour of the object followed by a projection step to constrain or regulate the contour in a contour subspace.
摘要翻译：一种方法跟踪摄像机拍摄的杂乱场景中的非刚性物体。该方法使用粒子滤波器。跟踪包括以下步骤：运动转换估计，轮廓变形检测和轮廓调节。该方法使用动态仿射变换模型，并使用粒子滤波器来估计模型的参数。该方法生成用于跟踪对象轮廓的变形的概率图，随后是在轮廓子空间中约束或调节轮廓的投影步骤。

9. 发明授权

US07359555B2 Detecting roads in aerial images using feature-based classifiers 失效
标题翻译：使用基于特征的分类器检测航空图像中的道路
公开(公告)号：US07359555B2
公开(公告)日：2008-04-15
申请号：US10961926
申请日：2004-10-08
申请人： Fatih M. Porikli , Jie Shao
发明人： Fatih M. Porikli , Jie Shao
IPC分类号： G06K9/46 , G06K9/40 , G06K9/00
CPC分类号： G06K9/0063 , G03B15/006 , G06K9/6292
摘要： A method detects roads in an aerial image of ground topology by determining low-level features, such as intensities and gradients, for each pixel in the aerial image, determining middle-level features, such as an orientation for each pixel from the low-level features, and determining high-level features from the middle-level features. Each high-level feature is assigned a probability, and the probabilities of the high-level features for each pixel are normalized and aggregated to a single probability that the pixel is associated with a road.
摘要翻译：一种方法通过确定空中图像中每个像素的低级特征（如强度和梯度）来检测地面拓扑的空中图像中的道路，确定中间层特征，例如来自低层的每个像素的取向功能，并确定中级功能的高级功能。每个高级特征被分配概率，并且将每个像素的高级特征的概率归一化并聚合成像素与道路相关联的单一概率。

10. 发明申请

US20060078205A1 Detecting roads in aerial images using feature-based classifiers 失效
标题翻译：使用基于特征的分类器检测航空图像中的道路
公开(公告)号：US20060078205A1
公开(公告)日：2006-04-13
申请号：US10961926
申请日：2004-10-08
申请人： Fatih Porikli , Jie Shao
发明人： Fatih Porikli , Jie Shao
IPC分类号： G06K9/46
CPC分类号： G06K9/0063 , G03B15/006 , G06K9/6292
摘要： A method detects roads in an aerial image of ground topology by determining low-level features, such as intensities and gradients, for each pixel in the aerial image, determining middle-level features, such as an orientation for each pixel from the low-level features, and determining high-level features from the middle-level features. Each high-level feature is assigned a probability, and the probabilities of the high-level features for each pixel are normalized and aggregated to a single probability that the pixel is associated with a road.
摘要翻译：一种方法通过确定空中图像中每个像素的低级特征（如强度和梯度）来检测地面拓扑的空中图像中的道路，确定中间层特征，例如来自低层的每个像素的取向功能，并确定中级功能的高级功能。每个高级特征被分配概率，并且将每个像素的高级特征的概率归一化并聚合成像素与道路相关联的单一概率。

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