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：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：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：US09239877B2

公开(公告)日：2016-01-19

申请号：US13169330

申请日：2011-06-27

申请人： Ana Belen Benitez ,  Shih-Fu Chang ,  Qian Huang ,  Seungyup Paek ,  Atul Puri

发明人： Ana Belen Benitez ,  Shih-Fu Chang ,  Qian Huang ,  Seungyup Paek ,  Atul Puri

IPC分类号： G06F17/30

CPC分类号： G06F17/30044 ,  G06F17/3002 ,  G06F17/30038 ,  G06F17/30858 ,  G06F17/30914 ,  G06F17/30958 ,  Y10S707/99945 ,  Y10S707/99948

摘要： The invention provides a system and method for integrating multimedia descriptions in a way that allows humans, software components or devices to easily identify, represent, manage, retrieve, and categorize the multimedia content. In this manner, a user who may be interested in locating a specific piece of multimedia content from a database, Internet, or broadcast media, for example, may search for and find the multimedia content. In this regard, the invention provides a system and method that receives multimedia content and separates the multimedia content into separate components which are assigned to multimedia categories, such as image, video, audio, synthetic and text. Within each of the multimedia categories, the multimedia content is classified and descriptions of the multimedia content are generated. The descriptions are then formatted, integrated, using a multimedia integration description scheme, and the multimedia integration description is generated for the multimedia content. The multimedia description is then stored into a database. As a result, a user may query a search engine which then retrieves the multimedia content from the database whose integration description matches the query criteria specified by the user. The search engine can then provide the user a useful search result based on the multimedia integration description.

公开(公告)号：US08135221B2

公开(公告)日：2012-03-13

申请号：US12574716

申请日：2009-10-07

申请人： Wei Jiang ,  Courtenay Cotton ,  Shih-Fu Chang ,  Daniel P. Ellis ,  Alexander C. Loui

发明人： Wei Jiang ,  Courtenay Cotton ,  Shih-Fu Chang ,  Daniel P. Ellis ,  Alexander C. Loui

IPC分类号： G06K9/62 ,  G06K9/54

CPC分类号： G06K9/00765 ,  G10L25/00

摘要： A method for determining a classification for a video segment, comprising the steps of: breaking the video segment into a plurality of short-term video slices, each including a plurality of video frames and an audio signal; analyzing the video frames for each short-term video slice to form a plurality of region tracks; analyzing each region track to form a visual feature vector and a motion feature vector; analyzing the audio signal for each short-term video slice to determine an audio feature vector; forming a plurality of short-term audio-visual atoms for each short-term video slice by combining the visual feature vector and the motion feature vector for a particular region track with the corresponding audio feature vector; and using a classifier to determine a classification for the video segment responsive to the short-term audio-visual atoms.

摘要翻译： 一种用于确定视频段的分类的方法，包括以下步骤：将视频段分解成多个短视频片段，每个短片段包括多个视频帧和音频信号; 分析每个短期视频片段的视频帧以形成多个区域轨道; 分析每个区域轨迹以形成视觉特征向量和运动特征向量; 分析每个短期视频片段的音频信号以确定音频特征向量; 通过将特定区域轨道的视觉特征向量和运动特征向量与相应的音频特征向量组合，形成每个短期视频片段的多个短期视听原子; 并且使用分类器来确定响应于短期视听原子的视频片段的分类。

公开(公告)号：US20110064136A1

公开(公告)日：2011-03-17

申请号：US12874337

申请日：2010-09-02

申请人： Shih-Fu Chang ,  Horace J. Meng

发明人： Shih-Fu Chang ,  Horace J. Meng

IPC分类号： H04N11/02

CPC分类号： G11B27/28 ,  G11B27/034

摘要： A system and method is provided for editing and parsing compressed digital information. The compressed digital information may include visual information which is edited and parsed in the compressed domain. In a preferred embodiment, the present invention provides a method for detecting moving objects in a compressed digital bitstream which represents a sequence of fields or frames of video information for one or more captured scenes of video.

摘要翻译： 提供了一种用于编辑和解析压缩数字信息的系统和方法。 压缩的数字信息可以包括在压缩域中编辑和解析的视觉信息。 在优选实施例中，本发明提供了一种用于检测压缩数字比特流中的运动对象的方法，该压缩数字比特流表示视频的一个或多个拍摄场景的视频信息的字段或帧序列。

公开(公告)号：US07254285B1

公开(公告)日：2007-08-07

申请号：US09831215

申请日：1999-11-05

申请人： Seungup Paek ,  Ana Benitez ,  Shih-Fu Chang ,  Chung-Sheng Li ,  John R. Smith ,  Lawrence D. Bergman ,  Atul Puri ,  Qian Huang

发明人： Seungup Paek ,  Ana Benitez ,  Shih-Fu Chang ,  Chung-Sheng Li ,  John R. Smith ,  Lawrence D. Bergman ,  Atul Puri ,  Qian Huang

IPC分类号： G06K9/60

CPC分类号： G06K9/4685

摘要： Systems and methods for describing image content establish image description records which include an object set (24), an object hierarchy (26) and entity relation graphs (28). For image content, image objects can include global objects (O0 8) and local objects (O1 2 and O2 6). The image objects are further defined by a number of features of different classes (36, 38 and 40), which in turn are further defined by a number of feature descriptors. The relationships between and among the objects in the object set are defined by the object hierarchy (26) and entity relation graphs (28). The image description records provide a standard vehicle for describing the content and context of image information for subsequent access and processing by computer applications such as search engines, filters, and archive systems.

摘要翻译： 用于描述图像内容的系统和方法建立包括对象集（24），对象层次（26）和实体关系图（28）的图像描述记录。 对于图像内容，图像对象可以包括全局对象（O 0 8）和本地对象（O 1 2和O 2 6）。 图像对象由不同类别（36,38和40）的许多特征进一步限定，这些特征又由许多特征描述符进一步限定。 对象集合中的对象之间和之间的关系由对象层次结构（26）和实体关系图（28）定义。 图像描述记录提供用于描述图像信息的内容和上下文的标准车辆，用于随后由计算机应用（例如搜索引擎，过滤器和归档系统）的访问和处理。

公开(公告)号：US06879703B2

公开(公告)日：2005-04-12

申请号：US10220776

申请日：2002-01-10

申请人： Ching-Yung Lin ,  Shih-Fu Chang

发明人： Ching-Yung Lin ,  Shih-Fu Chang

IPC分类号： G06T1/00 ,  H04N1/32 ,  G06K9/10

CPC分类号： G06T1/0057 ,  G06T1/0042 ,  G06T1/005 ,  G06T2201/0052 ,  G06T2201/0061 ,  H04N1/32165 ,  H04N1/32187 ,  H04N1/32277 ,  H04N1/3232 ,  H04N2201/3236 ,  H04N2201/327

摘要： Digital watermarks are embedded in image data (102)in order to enable authentication of the image data and/or replacement of rejected portions of the image data. Authentication codes are derived by comparing selected discrete cosine transform (DCT) (104) coefficients within DCT data (106) derived from the original, spatial-domain image data. The authentication codes thus generated are embedded in DCT coefficients (612) other than the ones which were used to derive the authentication codes. The resulting, watermarked data can be sent or made available to one or more recipients who can compress or otherwise use the watermarked data. Image data derived from the watermarked data—e.g, compressed versions of the watermarked data—can be authenticated by: extracting the embedded authentication codes, comparing DCT coefficients derived from the coefficients from which the original authentication codes were generated; and determining whether the compared DCT coefficients are consistent with the extracted authentication codes.

摘要翻译： 数字水印被嵌入在图像数据（102）中，以便能够对图像数据进行认证和/或替换图像数据的被拒绝的部分。 通过比较从原始的空间域图像数据导出的DCT数据（106）内的选定的离散余弦变换（DCT）（104）系数，导出认证码。 这样生成的认证码被嵌入除了用于导出认证码的那些之外的DCT系数（612）中。 所得到的水印数据可以被发送或使其可用于可压缩或以其他方式使用水印数据的一个或多个接收者。 从水印数据导出的图像数据（例如，水印数据的压缩版本）可以通过以下方式来认证：提取嵌入的认证码，比较从产生原始认证码的系数导出的DCT系数; 以及确定所述比较的DCT系数是否与所提取的认证码一致。