公开(公告)号：US07590265B2

公开(公告)日：2009-09-15

申请号：US11242204

申请日：2005-10-01

申请人： Richard S. Szeliski ,  Shmuel Avidan ,  Padmanabhan Anandan

发明人： Richard S. Szeliski ,  Shmuel Avidan ,  Padmanabhan Anandan

IPC分类号： G06K9/00

CPC分类号： H04N19/53 ,  G06T7/215

摘要： The present invention is embodied in a system and method for extracting structure from multiple images of a scene by representing the scene as a group of image layers, including reflection and transparency layers. In general, the present invention performs layer extraction from multiple images containing reflections and transparencies. The present invention includes an optimal approach for recovering layer images and their associated motions from an arbitrary number of composite images. The present invention includes image formation equations, the constrained least squares technique used to recover the component images, a novel method to estimate upper and lower bounds on the solution using min- and max-composites, and a motion refinement method.

摘要翻译： 本发明体现在一种用于通过将场景表示为包括反射和透明层的图像层的组来从场景的多个图像提取结构的系统和方法。 通常，本发明从包含反射和透明度的多个图像中执行层提取。 本发明包括从任意数量的合成图像中恢复层图像及其相关运动的最佳方法。 本发明包括图像形成方程，用于恢复分量图像的约束最小二乘法技术，使用最小和最大复合材料估计解的上限和下限的新方法，以及运动细化方法。

公开(公告)号：US20080021899A1

公开(公告)日：2008-01-24

申请号：US11490782

申请日：2006-07-21

申请人： Shmuel Avidan ,  Ariel Elbaz

发明人： Shmuel Avidan ,  Ariel Elbaz

IPC分类号： G06F17/30

CPC分类号： G06K9/6276 ,  G06F2216/03 ,  Y10S707/99934

摘要： A computer implemented method classifies securely a private query sample using exact k-nn classification. A secure dot product protocol is applied to determine securely distances between a private query sample and a plurality of private labeled samples. A secure k-rank protocol is applied to the distances to determine a nearest distance of a kth nearest labeled sample having a particular label. Then, a secure Parzen protocol is applied to the nearest distance to label the private query sample according to the particular label.

摘要翻译： 计算机实现的方法使用精确的k-nn分类安全地分类私人查询样本。 应用安全点产品协议来确定私人查询样本和多个私有标签样本之间的安全距离。 将一个安全的k-rank协议应用于距离，以确定具有特定标签的最近标记样品的最近距离。 然后，将安全的Parzen协议应用于最近的距离，以根据特定标签标记私有查询样本。

公开(公告)号：US20060171594A1

公开(公告)日：2006-08-03

申请号：US11048536

申请日：2005-02-01

申请人： Shmuel Avidan ,  Qiang Zhu

发明人： Shmuel Avidan ,  Qiang Zhu

IPC分类号： G06K9/40 ,  G06K9/62

CPC分类号： G06K9/4609 ,  G06K9/38 ,  G06T7/215

摘要： A computer implemented method models a background in a sequence of frames of a video. For each frame, the method detects static corners using an array of pixels of the frame, and extracts, for each static corner, features from a window of pixels around the static corner. For each static corner, a descriptor is determined from the corresponding features. Each static corner and corresponding descriptor is stored in a memory, and each static corner is classified as a background or foreground according to the descriptor to model a background in the video.

摘要翻译： 计算机实现的方法对视频帧的序列进行建模。 对于每个帧，该方法使用帧的像素数组来检测静态角，并为每个静态角提取来自静态角上的像素窗口的特征。 对于每个静态角，从相应的特征确定描述符。 每个静态角和相应的描述符都存储在一个存储器中，并且根据描述符将每个静态角分类为背景或前景，以对视频中的背景进行建模。

公开(公告)号：US20060165258A1

公开(公告)日：2006-07-27

申请号：US11041338

申请日：2005-01-24

申请人： Shmuel Avidan

发明人： Shmuel Avidan

IPC分类号： G06K9/00

CPC分类号： G06K9/32 ,  G06T7/246

摘要： A method locates an object in a sequence of frames of a video. A feature vector is constructed for every pixel in each frame. The feature vector is used to training the weak classifiers. The weak classifiers separate pixels that are associated with the object from pixels that are associated with the background. The set of weak classifiers are combined into a strong classifier. The strong classifier labels pixels in a frame to generate a confidence map. A ‘peak’ in the confidence is located using a mean-shift operation. The peak indicates a location of the object in the frame. That is, the confidence map distinguishes the object from the background in the video.

公开(公告)号：US20060120524A1

公开(公告)日：2006-06-08

申请号：US11005293

申请日：2004-12-06

申请人： Shmuel Avidan ,  Moshe Butman ,  Ayelet Butman

发明人： Shmuel Avidan ,  Moshe Butman ,  Ayelet Butman

IPC分类号： H04N7/167

CPC分类号： G09C5/00 ,  G06T7/254 ,  G06T2207/30241 ,  H04L2209/46

摘要： A method processes an input image securely. An input image I is acquired in a client. A set of m random images, H1, . . . , Hm, and a coefficient vector, a=[a1, . . . , am], are generated such that the input image I is I=Σi=1mαi Hj. The set of the random images is transferred to a server including a weak classifier. In the server, a set of m convolved random images H′ are determined, such that {HI′=π1(H1*y}i.1m, where * is a convolution operator and π1 is a first random pixel permutation. The set of convolved images is transferred to the client. In the client, a set of m permuted images I′ is determined, such that I′=π2(Σi=1mαi H1′), where π2 is a second random pixel permutation. The set of permuted image is transferred to the server. In the server, a test image {overscore (I)} such that {overscore (I)}=α∫(I′) is determined and a true signal is returned to the client if there exists a pixel q in the test image such that {overscore (I)}(q)>0, otherwise return a false signal is returned to the client to indicate whether or not the input image contains an object.

摘要翻译： 一种方法可以安全地处理输入图像。 在客户端中获取输入图像I。 一组m个随机图像，H 1，...， 。 。 ，H。。。。。。。。。。。。。。。。。。。。。。。。。。。。 。 。 产生一个<！ - SIPO - >子，以使得输入图像I为I =Σ > H 。 随机图像的集合被传送到包括弱分类器的服务器。 在服务器中，确定一组m个卷积的随机图像H'，使得{H 1 = 1/1（H 1 / 其中*是卷积运算符，并且pi <1>是第一随机像素排列，卷积图像集合是 在客户端中，确定一组置换图像I'，使得I'= pi <2>（Σ 1） 其中pi2是第二随机像素排列，该组置换图像被转移到 在服务器中，测试图像{overscore（I，使得{overscore（I =alpha∫（I'））被确定并且如果在测试图像中存在像素q，则将真实信号返回给客户端，使得 {overscore（I（q）> 0，否则返回一个假信号返回到客户端，以指示输入图像是否包含一个对象。