公开(公告)号：US07313269B2

公开(公告)日：2007-12-25

申请号：US10734451

申请日：2003-12-12

申请人： Lexing Xie ,  Ajay Divakaran ,  Shih-Fu Chang

发明人： Lexing Xie ,  Ajay Divakaran ,  Shih-Fu Chang

IPC分类号： G06K9/62

CPC分类号： G06F17/30787 ,  G06F17/30802 ,  G06F17/30811 ,  G06F17/30814 ,  G06K9/00711

摘要： A method learns a structure of a video, in an unsupervised setting, to detect events in the video consistent with the structure. Sets of features are selected from the video. Based on the selected features, a hierarchical statistical model is updated, and an information gain of the hierarchical statistical model is evaluated. Redundant features are then filtered, and the hierarchical statistical model is updated, based on the filtered features. A Bayesian information criteria is applied to each model and feature set pair, which can then be rank ordered according to the criteria to detect the events in the video.

摘要翻译： 一种方法在无监督的设置中学习视频的结构，以检测符合结构的视频中的事件。 从视频中选择功能集。 基于所选择的特征，更新层次统计模型，并评估分层统计模型的信息增益。 然后过滤冗余特征，并基于过滤的特征更新分层统计模型。 贝叶斯信息标准适用于每个模型和特征集对，然后可以根据标准对秩进行排序以检测视频中的事件。

公开(公告)号：US20050131869A1

公开(公告)日：2005-06-16

申请号：US10734451

申请日：2003-12-12

申请人： Lexing Xie ,  Ajay Divakaran ,  Shih-Fu Chang

发明人： Lexing Xie ,  Ajay Divakaran ,  Shih-Fu Chang

IPC分类号： G06T7/00 ,  G06F17/30 ,  G06K9/00

CPC分类号： G06F17/30787 ,  G06F17/30802 ,  G06F17/30811 ,  G06F17/30814 ,  G06K9/00711

摘要： A method learns a structure of a video, in an unsupervised setting, to detect events in the video consistent with the structure. Sets of features are selected from the video. Based on the selected features, a hierarchical statistical model is updated, and an information gain of the hierarchical statistical model is evaluated. Redundant features are then filtered, and the hierarchical statistical model is updated, based on the filtered features. A Bayesian information criteria is applied to each model and feature set pair, which can then be rank ordered according to the criteria to detect the events in the video.

摘要翻译： 一种方法在无监督的设置中学习视频的结构，以检测符合该结构的视频中的事件。 从视频中选择功能集。 基于所选择的特征，更新层次统计模型，并评估分层统计模型的信息增益。 然后过滤冗余特征，并基于过滤的特征更新分层统计模型。 贝叶斯信息标准适用于每个模型和特征集对，然后可以根据标准对秩进行排序以检测视频中的事件。

公开(公告)号：US06865226B2

公开(公告)日：2005-03-08

申请号：US10005623

申请日：2001-12-05

申请人： Lexing Xie ,  Shih-Fu Chang ,  Ajay Divakaran ,  Huifang Sun

发明人： Lexing Xie ,  Shih-Fu Chang ,  Ajay Divakaran ,  Huifang Sun

IPC分类号： H04N5/92 ,  G06F17/30 ,  H04N5/91 ,  H04N7/26 ,  H04N7/12

CPC分类号： G06K9/00771 ,  G06F17/30799 ,  G06F17/30811 ,  G06F17/30852 ,  G06K9/00711

摘要： A method analyzes a high-level syntax and structure of a continuous compressed video according to a plurality of states. First, a set of hidden Markov models for each of the states is trained with a training video segmented into known states. Then, a set of domain specific features are extracted from a fixed-length sliding window of the continuous compressed video, and a set of maximum likelihoods is determined for each set of domain specific features using the sets of trained hidden Markov models. Finally, dynamic programming is applied to each set of maximum likelihoods to determine a specific state for each fixed-length sliding window of frames of the compressed video.

摘要翻译： 一种方法根据多种状态分析连续压缩视频的高级语法和结构。 首先，针对每个州的一组隐马尔可夫模型训练有一个分为已知状态的训练视频。 然后，从连续压缩视频的固定长度的滑动窗口中提取一组特定于域的特征，并且使用训练的隐马尔科夫模型集合针对每组特定特征确定一组最大似然。 最后，将动态规划应用于每组最大似然度，以确定压缩视频帧的每个固定长度滑动窗口的特定状态。

公开(公告)号：US06763069B1

公开(公告)日：2004-07-13

申请号：US09610763

申请日：2000-07-06

申请人： Ajay Divakaran ,  Anthony Vetro ,  Huifang Sun ,  Peng Xu ,  Shih-Fu Chang

发明人： Ajay Divakaran ,  Anthony Vetro ,  Huifang Sun ,  Peng Xu ,  Shih-Fu Chang

IPC分类号： H04N712

CPC分类号： G06K9/00711

摘要： A method extracts high-level features from a video including a sequence of frames. Low-level features are extracted from each frame of the video. Each frame of the video is labeled according to the extracted low-level features to generate sequences of labels. Each sequence of labels is associated with one of the extracted low-level feature. The sequences of labels are analyzed using learning machine learning techniques to extract high-level features of the video.

摘要翻译： 一种方法从包括帧序列的视频中提取高级特征。 从视频的每个帧中提取低级功能。 视频的每个帧根据提取的低级特征进行标记，以生成标签序列。 标签的每个序列与提取的低级特征之一相关联。 使用学习机器学习技术来分析标签序列以提取视频的高级特征。

公开(公告)号：US06813313B2

公开(公告)日：2004-11-02

申请号：US09839924

申请日：2001-04-20

申请人： Peng Xu ,  Shih-Fu Chang ,  Ajay Divakaran

发明人： Peng Xu ,  Shih-Fu Chang ,  Ajay Divakaran

IPC分类号： H04N712

CPC分类号： G06K9/00711

摘要： A system and method analyzes a compressed video including a sequence of frames. The amount of a dominant feature in each frame of the compressed video is measured. A label is associated with each frame according the measured amount of the dominant feature. Views in the video are identified according to the labels, and the video is segmented into actions according to the views. The video can then be analyzed according to the action to determine significant events in the video.

摘要翻译： 系统和方法分析包括帧序列的压缩视频。 测量压缩视频的每个帧中的主要特征的量。 根据测量的主要特征量，标签与每个帧相关联。 根据标签识别视频中的视图，并根据视图将视频分割为动作。 然后可以根据动作分析视频以确定视频中的重要事件。

公开(公告)号：US08913783B2

公开(公告)日：2014-12-16

申请号：US12913861

申请日：2010-10-28

申请人： Saad Masood Khan ,  Hui Cheng ,  Dennis Lee Matthies ,  Harpreet Singh Sawhney ,  Sang-Hack Jung ,  Chris Broaddus ,  Bogdan Calin Mihai Matei ,  Ajay Divakaran

发明人： Saad Masood Khan ,  Hui Cheng ,  Dennis Lee Matthies ,  Harpreet Singh Sawhney ,  Sang-Hack Jung ,  Chris Broaddus ,  Bogdan Calin Mihai Matei ,  Ajay Divakaran

IPC分类号： G06K9/00 ,  G06K9/46

CPC分类号： G06K9/00785 ,  B64C39/024 ,  B64C2201/123 ,  B64D47/08 ,  G06K9/00651 ,  G06K9/4671 ,  G06K9/6269 ,  G06K9/6282 ,  G06T7/11 ,  G06T7/20 ,  G06T2207/10012

摘要： A computer implemented method for determining a vehicle type of a vehicle detected in an image is disclosed. An image having a detected vehicle is received. A number of vehicle models having salient feature points is projected on the detected vehicle. A first set of features derived from each of the salient feature locations of the vehicle models is compared to a second set of features derived from corresponding salient feature locations of the detected vehicle to form a set of positive match scores (p-scores) and a set of negative match scores (n-scores). The detected vehicle is classified as one of the vehicle models models based at least in part on the set of p-scores and the set of n-scores.

摘要翻译： 公开了一种用于确定在图像中检测到的车辆的车辆类型的计算机实现的方法。 接收具有检测到的车辆的图像。 在检测到的车辆上投影出具有显着特征点的多个车辆模型。 将来自车辆模型的每个突出特征位置的第一组特征与从所检测到的车辆的相应突出特征位置导出的第二组特征进行比较，以形成一组正的匹配得分（p分数）和 一组负面比赛得分（n分）。 检测到的车辆至少部分地基于p分数集合和n分数集合被分类为车辆模型模型之一。

公开(公告)号：US08345930B2

公开(公告)日：2013-01-01

申请号：US12758208

申请日：2010-04-12

申请人： Amir Tamrakar ,  Harpreet Singh Sawhney ,  Qian Yu ,  Ajay Divakaran

发明人： Amir Tamrakar ,  Harpreet Singh Sawhney ,  Qian Yu ,  Ajay Divakaran

IPC分类号： G06K9/00

CPC分类号： G06T7/0002 ,  G06T7/44 ,  G06T7/593 ,  G06T7/62 ,  G06T7/77 ,  G06T2207/20016 ,  G06T2207/30128

摘要： A computer-implemented method for estimating a volume of at least one food item on a food plate is disclosed. A first and second plurality of images are received from different positions above a food plate, wherein angular spacing between the positions of the first plurality of images is greater than angular spacing between the positions of the second plurality of images. A first set of poses of each of the first plurality of images is estimated. A second set of poses of each of the second plurality of images is estimated based on at least the first set of poses. A pair of images taken from each of the first and second plurality of images is rectified based on at least the first and second set of poses. A 3D point cloud is reconstructed based on at least the rectified pair of images. At least one surface of the at least one food item above the food plate is estimated based on at least the reconstructed 3D point cloud. The volume of the at least one food item is estimated based on the at least one surface.

摘要翻译： 公开了一种用于估计食品板上的至少一种食品的体积的计算机实现的方法。 从食品牌上方的不同位置接收第一和第二多个图像，其中第一多个图像的位置之间的角度间隔大于第二多个图像的位置之间的角度间隔。 估计第一多个图像中的每一个的第一组姿势。 基于至少第一组姿势来估计第二组多个图像中的每一个的第二组姿势。 从第一和第二多个图像中的每一个拍摄的一对图像至少基于第一和第二组姿势进行整改。 至少基于整流图像对来重构3D点云。 基于至少重构的3D点云来估计食物板上方的至少一个食物的至少一个表面。 基于至少一个表面来估计至少一个食物的体积。

公开(公告)号：US08330819B2

公开(公告)日：2012-12-11

申请号：US12758507

申请日：2010-04-12

申请人： Sang-Hack Jung ,  Ajay Divakaran ,  Harpreet Singh Sawhney

发明人： Sang-Hack Jung ,  Ajay Divakaran ,  Harpreet Singh Sawhney

IPC分类号： H04N7/18

CPC分类号： G06K9/00771 ,  G06K9/6206 ,  G06K9/6211

摘要： A computer-implemented method for for matching objects is disclosed. At least two images where one of the at least two images has a first target object and a second of the at least two images has a second target object are received. At least one first patch from the first target object and at least one second patch from the second target object are extracted. A distance-based part encoding between each of the at least one first patch and the at least one second patch based upon a corresponding codebook of image parts including at least one of part type and pose is constructed. A viewpoint of one of the at least one first patch is warped to a viewpoint of the at least one second patch. A parts level similarity measure based on the view-invariant distance measure for each of the at least one first patch and the at least one second patch is applied to determine whether the first target object and the second target object are the same or different objects.

摘要翻译： 公开了一种用于匹配对象的计算机实现的方法。 接收至少两个图像，其中至少两个图像中的一个具有第一目标对象，并且至少两个图像中的第二图像具有第二目标对象。 提取来自第一目标对象的至少一个第一补丁和来自第二目标对象的至少一个第二补丁。 构建基于包括部件类型和姿态中的至少一个的图像部件的对应码本的至少一个第一贴片和至少一个第二贴片中的每一个之间的基于距离的部件编码。 所述至少一个第一贴片中的一个的视点弯曲到所述至少一个第二贴片的观点。 应用基于对于至少一个第一贴片和至少一个第二贴片中的每一个的视图不变距离度量的零件级相似性度量来确定第一目标对象和第二目标对象是相同还是不同的对象。

公开(公告)号：US20100271905A1

公开(公告)日：2010-10-28

申请号：US12766219

申请日：2010-04-23

申请人： Saad Khan ,  Ajay Divakaran ,  Harpreet Singh Sawhney

发明人： Saad Khan ,  Ajay Divakaran ,  Harpreet Singh Sawhney

IPC分类号： G01S3/80

CPC分类号： G10L25/48

摘要： A computer implemented method for automatically detecting and classifying acoustic signatures across a set of recording conditions is disclosed. A first acoustic signature is received. The first acoustic signature is projected into a space of a minimal set of exemplars of acoustic signature types derived from a larger set of exemplars using a wrapper method. At least one vector distance is calculated between the projected acoustic signature and each exemplar of the minimal set of exemplars. An exemplar is selected from the minimal set of exemplars having the smallest vector distance to the projected acoustic signature as a class corresponding to and classifying the first acoustic signature. The first acoustic signature and the plurality of acoustic signatures may correspond to one of gunshots, musical instruments, songs, and speech. The minimal set of exemplars may correspond to a hierarchy of acoustic signature types.

摘要翻译： 公开了一种用于在一组记录条件下自动检测和分类声学签名的计算机实现的方法。 接收到第一个声学签名。 第一声​​学签名被投影到使用包装方法从更大的样本集合导出的声学签名类型的最小样本集合的空间中。 在投影的声学特征与最小样本集的每个样本之间计算至少一个矢量距离。 从具有与投影的声学签名的最小向量距离的最小样本集合中选择一个示例作为对应于和分类第一声学签名的类别。 第一声​​学签名和多个声学签名可以对应于枪声，乐器，歌曲和语音之一。 最小的一组样本可以对应于声学签名类型的层级。

公开(公告)号：US07409407B2

公开(公告)日：2008-08-05

申请号：US10840824

申请日：2004-05-07

申请人： Regunathan Radhakrishnan ,  Ajay Divakaran

发明人： Regunathan Radhakrishnan ,  Ajay Divakaran

IPC分类号： G06F17/30 ,  G06F17/00

CPC分类号： G06F17/30787 ,  G06F17/30802 ,  G06F17/30808 ,  G06F17/30811 ,  G06F17/30843 ,  G06K9/00711 ,  Y10S707/99943 ,  Y10S707/99945

摘要： A method detects events in multimedia. Features are extracted from the multimedia. The features are sampled using a sliding window to obtain samples. A context model is constructed for each sample. An affinity matrix is determined from the models and a commutative distance metric between each pair of context models. A second generation eigenvector is determined for the affinity matrix, and the samples are then clustered into events according to the second generation eigenvector.

摘要翻译： 一种方法来检测多媒体中的事件。 功能从多媒体提取。 使用滑动窗口对特征进行采样以获得样品。 为每个样本构建上下文模型。 从模型和每对上下文模型之间的交换距离度量确定亲和度矩阵。 针对亲和度矩阵确定第二代特征向量，然后根据第二代特征向量将样本聚类成事件。