-
公开(公告)号：US20080063264A1
公开(公告)日：2008-03-13
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
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。
-
2.发明申请公开(公告)号：US20080063285A1
公开(公告)日：2008-03-13
申请号：US11763699
申请日：2007-06-15
申请人： Fatih M. Porikli , Oncel C. Tuzel
发明人： Fatih M. Porikli , Oncel C. Tuzel
IPC分类号： G06K9/46
CPC分类号： G06K9/00369 , G06K9/4642 , G06K9/6257
摘要： A method constructs a classifier from training data and detects moving objects in test data using the trained classifier. High-level features are generated from low-level features extracted from training data. The high level features are positive definite matrices on an analytical manifold. A subset of the high-level features is selected, and an intrinsic mean matrix is determined. Each high-level feature is mapped to a feature vector on a tangent space of the analytical manifold using the intrinsic mean matrix. An untrained classifier is trained with the feature vectors to obtain a trained classifier. Test high-level features are similarly generated from test low-level features. The test high-level features are classified using the trained classifier to detect moving objects in the test data.
摘要翻译： 一种方法从训练数据构建分类器，并使用经过训练的分类器检测测试数据中的移动对象。 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上的正定矩阵。 选择高级特征的子集，并确定固有均值矩阵。 每个高级特征使用内在平均矩阵映射到分析歧管的切线空间上的特征向量。 使用特征向量训练未训练的分类器以获得训练有素的分类器。 测试高级功能类似地从测试低级功能生成。 测试高级功能使用训练有素的分类器进行分类，以检测测试数据中的移动对象。
-
3.发明授权公开(公告)号：US07899253B2
公开(公告)日：2011-03-01
申请号：US11763699
申请日：2007-06-15
申请人： Fatih M. Porikli , Oncel C. Tuzel
发明人： Fatih M. Porikli , Oncel C. Tuzel
IPC分类号： G06K9/46
CPC分类号： G06K9/00369 , G06K9/4642 , G06K9/6257
摘要： A method constructs a classifier from training data and detects moving objects in test data using the trained classifier. High-level features are generated from low-level features extracted from training data. The high level features are positive definite matrices on an analytical manifold. A subset of the high-level features is selected, and an intrinsic mean matrix is determined. Each high-level feature is mapped to a feature vector on a tangent space of the analytical manifold using the intrinsic mean matrix. An untrained classifier is trained with the feature vectors to obtain a trained classifier. Test high-level features are similarly generated from test low-level features. The test high-level features are classified using the trained classifier to detect moving objects in the test data.
摘要翻译： 一种方法从训练数据构建分类器，并使用经过训练的分类器检测测试数据中的移动对象。 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上的正定矩阵。 选择高级特征的子集，并确定固有均值矩阵。 每个高级特征使用内在平均矩阵映射到分析歧管的切线空间上的特征向量。 使用特征向量训练未训练的分类器以获得训练有素的分类器。 测试高级功能类似地从测试低级功能生成。 测试高级功能使用训练有素的分类器进行分类，以检测测试数据中的移动对象。
-
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
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。
-
公开(公告)号：US20090087023A1
公开(公告)日：2009-04-02
申请号：US11862554
申请日：2007-09-27
申请人： Fatih M Porikli , Oncel C. Tuzel
发明人： Fatih M Porikli , Oncel C. Tuzel
IPC分类号： G06K9/00
CPC分类号： G06T7/277 , G06T2207/10016 , G06T2207/30241 , G06T2207/30248
摘要： Invention describes a method and system for detecting and tracking an object in a sequence of images. For each image the invention determines an object descriptor from a tracking region in a current image in a sequence of images, in which the tracking region corresponds to a location of an object in a previous image. A regression function is applied to the descriptor to determine a motion of the object from the previous image to the current image, in which the motion has a matrix Lie group structure. The location of the tracking region is updated using the motion of the object.
摘要翻译： 本发明描述了一种用于在图像序列中检测和跟踪对象的方法和系统。 对于每个图像，本发明根据图像序列中的当前图像中的跟踪区域来确定对象描述符，其中跟踪区域对应于先前图像中的对象的位置。 回归函数被应用于描述符以确定对象从先前图像到当前图像的运动，其中运动具有矩阵李组结构。 使用对象的运动来更新跟踪区域的位置。
-
公开(公告)号：US07961952B2
公开(公告)日：2011-06-14
申请号：US11862554
申请日：2007-09-27
申请人： Fatih M. Porikli , Oncel C. Tuzel
发明人： Fatih M. Porikli , Oncel C. Tuzel
IPC分类号： G06K9/46
CPC分类号： G06T7/277 , G06T2207/10016 , G06T2207/30241 , G06T2207/30248
摘要： Invention describes a method and system for detecting and tracking an object in a sequence of images. For each image the invention determines an object descriptor from a tracking region in a current image in a sequence of images, in which the tracking region corresponds to a location of an object in a previous image. A regression function is applied to the descriptor to determine a motion of the object from the previous image to the current image, in which the motion has a matrix Lie group structure. The location of the tracking region is updated using the motion of the object.
摘要翻译： 本发明描述了一种用于在图像序列中检测和跟踪对象的方法和系统。 对于每个图像，本发明根据图像序列中的当前图像中的跟踪区域来确定对象描述符，其中跟踪区域对应于先前图像中的对象的位置。 回归函数被应用于描述符以确定对象从先前图像到当前图像的运动，其中运动具有矩阵李组结构。 使用对象的运动来更新跟踪区域的位置。
-
7.发明授权公开(公告)号：US08155447B2
公开(公告)日：2012-04-10
申请号：US12730279
申请日：2010-03-24
CPC分类号： G06K9/4661 , G06T7/64 , G06T2207/10016
摘要： Embodiments of the invention disclose a system and a method for determining points of parabolic curvature on a surface of a specular object from a set of images of the object is acquired by a camera under a relative motion between a camera-object pair and the environment. The method determines directions of image gradients at each pixel of each image in the set of images, wherein pixels from different images corresponding to an identical point on the surface of the object form corresponding pixels. The corresponding pixels having substantially constant the direction of the image gradients are selected as pixels representing points of the parabolic curvature.
摘要翻译： 本发明的实施例公开了一种用于从相机对象和环境之间的相对运动的相机获取用于从对象的一组图像确定镜面物体的表面上的抛物线曲率点的系统和方法。 该方法确定图像集合中每个图像的每个像素处的图像梯度的方向，其中对应于对象表面上的相同点的不同图像的像素形成相应的像素。 选择基本上恒定图像梯度方向的对应像素作为代表抛物面曲率点的像素。
-
公开(公告)号：US20110235916A1
公开(公告)日：2011-09-29
申请号：US12730279
申请日：2010-03-24
IPC分类号： G06K9/46
CPC分类号： G06K9/4661 , G06T7/64 , G06T2207/10016
摘要： Embodiments of the invention disclose a system and a method for determining points of parabolic curvature on a surface of a specular object from a set of images of the object is acquired by a camera under a relative motion between a camera-object pair and the environment. The method determines directions of image gradients at each pixel of each image in the set of images, wherein pixels from different images corresponding to an identical point on the surface of the object form corresponding pixels. The corresponding pixels having substantially constant the direction of the image gradients are selected as pixels representing points of the parabolic curvature.
摘要翻译： 本发明的实施例公开了一种用于从相机对象和环境之间的相对运动的相机获取用于从对象的一组图像确定镜面物体的表面上的抛物线曲率点的系统和方法。 该方法确定图像集合中每个图像的每个像素处的图像梯度的方向，其中对应于对象表面上的相同点的不同图像的像素形成相应的像素。 选择基本上恒定图像梯度方向的对应像素作为代表抛物面曲率点的像素。
-
9.发明授权公开(公告)号：US08229242B2
公开(公告)日：2012-07-24
申请号：US12731333
申请日：2010-03-25
CPC分类号： G06T7/514 , G06T2207/10016
摘要： A point correspondence procedure is applied to a set of images of a specular object to produce sparse reflection correspondences. The set of images is subject to rotation while acquired by a camera. That is, either the camera, the environment or the object rotates. Either a linear system AΘ=0 is solved or a related second order cone program (SOCP) is solved, where Θ is a vector of local surface parameters. Gradients of the surface are obtained from the local quadric surface parameters, and the gradients are integrated to obtain normals, wherein the normals define a shape of the surface.
摘要翻译： 点对应程序应用于镜面对象的一组图像以产生稀疏反射对应。 相机拍摄时，该组图像会转动。 也就是说，相机，环境或对象旋转。 求解线性系统AΘ= 0或相关的二阶锥体程序（SOCP），其中Θ是局部表面参数的向量。 表面的梯度从局部二次曲面参数获得，并且梯度被积分以获得法线，其中法线定义了表面的形状。
-
10.发明申请公开(公告)号：US20110235933A1
公开(公告)日：2011-09-29
申请号：US12731333
申请日：2010-03-25
IPC分类号： G06K9/40
CPC分类号： G06T7/514 , G06T2207/10016
摘要： A point correspondence procedure is applied to a set of images of a specular object to produce sparse reflection correspondences. The set of images is subject to rotation while acquired by a camera. That is, either the camera, the environment or the object rotates. Either a linear system AΘ=0 is solved or a related second order cone program (SOCP) is solved, where Θ is a vector of local surface parameters. Gradients of the surface are obtained from the local quadric surface parameters, and the gradients are integrated to obtain normals, wherein the normals define a shape of the surface.
摘要翻译： 点对应程序应用于镜面对象的一组图像以产生稀疏反射对应。 相机拍摄时，该组图像会转动。 也就是说，相机，环境或对象旋转。 求解线性系统AΘ= 0或相关的二阶锥体程序（SOCP），其中Θ是局部表面参数的向量。 表面的梯度从局部二次曲面参数获得，并且梯度被积分以获得法线，其中法线定义了表面的形状。
-
-
-
-
-
-
-
-
-
搜索结果
10 条记录 (耗时 0.016 秒)
