利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

87 条记录 (耗时 0.034 秒)

    Networked surveillance and control system
    61.
    发明授权
    Networked surveillance and control system 有权
    网络监控系统

    公开(公告)号：US06646676B1

    公开(公告)日：2003-11-11

    申请号：US09612876

    申请日：2000-07-10

    申请人： Paul DaGraca ,  Anthony Vetro ,  Ajay Divakaran ,  Huifang Sun

    发明人： Paul DaGraca ,  Anthony Vetro ,  Ajay Divakaran ,  Huifang Sun

    IPC分类号： H04N718

    CPC分类号： G06K9/00771 ,  G06F17/30805 ,  G06F17/30811 ,  G06F17/30814 ,  G06F17/30843 ,  H04N7/181 ,  H04N21/23418 ,  H04N21/2389 ,  H04N21/4385 ,  H04N21/8405

    摘要： A surveillance and control system includes a feature extraction unit to dynamically extract low-level features from a compressed digital video signal, a description encoder, coupled to the feature extraction unit, to encode the low-level features as content descriptors. An event detector is coupled to the description encoder to detect security events from the content descriptors, and a control signal processor, coupled to the event detector, to generate control signals in response to detecting the security events.

    摘要翻译： 监视和控制系统包括特征提取单元，其从压缩数字视频信号动态地提取低级特征，耦合到特征提取单元的描述编码器，以将低级特征编码为内容描述符。 事件检测器耦合到描述编码器以检测来自内容描述符的安全事件，以及耦合到事件检测器的控制信号处理器，以响应于检测到安全事件而产生控制信号。

    Adaptable compressed bitstream transcoder
    62.
    发明授权
    Adaptable compressed bitstream transcoder 失效
    适应压缩比特流代码转换器

    公开(公告)号：US06542546B1

    公开(公告)日：2003-04-01

    申请号：US09496706

    申请日：2000-02-02

    申请人： Anthony Vetro ,  Ajay Divakaran ,  Huifang Sun

    发明人： Anthony Vetro ,  Ajay Divakaran ,  Huifang Sun

    IPC分类号： H04N726

    CPC分类号： H04L47/10 ,  H04L29/06 ,  H04L29/06027 ,  H04L65/605 ,  H04L65/80 ,  H04L67/2819 ,  H04L67/2823 ,  H04L69/04 ,  H04L69/329 ,  H04N19/124 ,  H04N19/147 ,  H04N19/149 ,  H04N19/152 ,  H04N19/172 ,  H04N19/19 ,  H04N19/40 ,  H04N19/61 ,  H04N21/84

    摘要： A multi-media delivery system for delivering a compressed bitstream through a network to a user device includes a transcoder and a manager. The transcoder is configured to operate on the bit stream using in any one of a plurality of conversion modes. The manager is configured to selecting a particular one of the plurality of conversion modes dependent on semantic content of the bitstream and network characteristics. The system also includes a content classifier to determine the content characteristics, and a model predicator to determine the network characteristics, and user device characteristics. An integrator of the manager generates an optimal rate-quality function to be used for selecting the particular conversion model for a given available bit rate of the network.

    摘要翻译： 用于通过网络将压缩比特流传送到用户设备的多媒体传送系统包括代码转换器和管理器。 代码转换器被配置为使用多种转换模式中的任何一种对比特流进行操作。 管理器被配置为根据比特流的语义内容和网络特性来选择多个转换模式中的特定一个。 该系统还包括内容分类器，用于确定内容特征，以及一个模型预测器来确定网络特性，以及用户设备特性。 管理者的积分器产生最佳速率质量函数，用于为网络的给定可用比特率选择特定的转换模型。

    Three-layer scaleable decoder and method of decoding
    63.
    发明授权
    Three-layer scaleable decoder and method of decoding 失效
    三层可扩展解码器和解码方法

    公开(公告)号：US06519288B1

    公开(公告)日：2003-02-11

    申请号：US09035969

    申请日：1998-03-06

    申请人： Anthony Vetro ,  Huifang Sun ,  Tommy Poon

    发明人： Anthony Vetro ,  Huifang Sun ,  Tommy Poon

    IPC分类号： H04N0718

    CPC分类号： H04N19/59

    摘要： The apparatus for decoding a digital signal includes a composite picture forming unit for forming a composite picture from a first digital video signal and a second digital video signal. The first digital video signal includes inter-coded picture data. A down-converter receives a third digital video signal, and outputs the third digital video signal to the composite picture forming unit as the first digital signal in a first mode. However, the down-converter down-converts the third digital video signal into a fourth digital video signal in a second mode, and outputs the fourth digital video signal to the composite picture forming unit in the second mode. A memory stores the anchor pictures output from the composite picture forming unit, and a motion compensator generates the second digital signal based on the stored anchor pictures.

    摘要翻译： 用于对数字信号进行解码的装置包括用于从第一数字视频信号和第二数字视频信号形成合成图像的合成图像形成单元。 第一数字视频信号包括帧间编码图像数据。 下变频器接收第三数字视频信号，并以第一模式将第三数字视频信号作为第一数字信号输出到合成图像形成单元。 然而，下变频器在第二模式中将第三数字视频信号下变频为第四数字视频信号，并在第二模式中将第四数字视频信号输出到复合图像形成单元。 存储器存储从复合图像形成单元输出的锚图像，并且运动补偿器基于存储的锚图像生成第二数字信号。

    Motion compensated digital video signal processing
    66.
    发明授权
    Motion compensated digital video signal processing 失效
    运动补偿数字视频信号处理

    公开(公告)号：US06192080B1

    公开(公告)日：2001-02-20

    申请号：US09206032

    申请日：1998-12-04

    申请人： Huifang Sun ,  Anthony Vetro ,  Yen-Kuang Chen ,  Sun-Yuan Kung

    发明人： Huifang Sun ,  Anthony Vetro ,  Yen-Kuang Chen ,  Sun-Yuan Kung

    IPC分类号： H04N712

    CPC分类号： H04N19/577

    摘要： A method determines true motion vectors associated with a sequence of images. The images include fields made up of blocks of pixels. The method selects candidate feature blocks from the blocks of pixels. The candidate feature blocks have intensity variances above a threshold indicative of texture features. Candidate feature blocks in similarly numbered adjacent field intervals are compared to determine sets of displaced frame differences parameters for each candidate feature block. The true motion vectors for each candidate feature block are determined from a minimum weighted score derived from the difference parameters.

    摘要翻译： 一种方法确定与图像序列相关联的真实运动矢量。 图像包括由像素块组成的场。 该方法从像素块中选择候选特征块。 候选特征块具有高于指示纹理特征的阈值的强度方差。 将相似编号的相邻场间隔中的候选特征块进行比较，以确定每个候选特征块的位移帧差参数的集合。 每个候选特征块的真实运动矢量是从差分参数导出的最小加权得分确定的。

    Methods of feature extraction of video sequences
    67.
    发明授权
    Methods of feature extraction of video sequences 失效
    视频序列特征提取方法

    公开(公告)号：US06618507B1

    公开(公告)日：2003-09-09

    申请号：US09236838

    申请日：1999-01-25

    申请人： Ajay Divakaran ,  Huifang Sun ,  Hiroshi Ito

    发明人： Ajay Divakaran ,  Huifang Sun ,  Hiroshi Ito

    IPC分类号： G06K946

    CPC分类号： G06K9/00744 ,  G06F17/30811

    摘要： This invention relates to methods of feature extraction from MPEG-2 and MPEG-4 compressed video sequences. The spatio-temporal compression complexity of video sequences is evaluated for feature extraction by inspecting the compressed bitstream and the complexity is used as a descriptor of the spatio-temporal characteristics of the video sequence. The spatio-temporal compression complexity measure is used as a matching criterion and can also be used for absolute indexing. Feature extraction can be accomplished in conjunction with scene change detection techniques and the combination has reasonable accuracy and the advantage of high simplicity since it is based on entropy decoding of signals in compressed form and does not require computationally expensive inverse Discrete Cosine Transformation (DCT).

    摘要翻译： 本发明涉及从MPEG-2和MPEG-4压缩视频序列中提取特征的方法。 通过检查压缩比特流来评估视频序列的时空压缩复杂度，并将复杂度用作视频序列的时空特征的描述符。 时空压缩复杂度测量用作匹配标准，也可用于绝对索引。 特征提取可以结合场景变化检测技术来实现，并且组合具有合理的精度和高简单性的优点，因为它是基于压缩形式的信号的熵解码，并且不需要计算上昂贵的反离散余弦变换（DCT）。

    Descriptor for spatial distribution of motion activity in compressed video
    68.
    发明授权
    Descriptor for spatial distribution of motion activity in compressed video 有权
    压缩视频中运动活动空间分布的描述符

    公开(公告)号：US06600784B1

    公开(公告)日：2003-07-29

    申请号：US09496707

    申请日：2000-02-02

    申请人： Ajay Divakaran ,  Kadir A. Peker ,  Huifang Sun

    发明人： Ajay Divakaran ,  Kadir A. Peker ,  Huifang Sun

    IPC分类号： H04N712

    CPC分类号： G06F17/30781 ,  G06K9/00335 ,  G06K9/00711 ,  G06T7/215 ,  G06T2207/10016 ,  G06T2207/20021

    摘要： A method describes motion activity in a video sequence. A motion activity matrix is determined for the video sequence. A threshold for the motion activity matrix is determined. Connected regions of motion vectors at least equal to the threshold are identified and measured for size. A histogram of the distribution of the sizes of the connected areas is constructed for the entire video sequence. The histogram is normalized to characterize the spatial distribution of the video sequence in a motion activity descriptor.

    摘要翻译： 一种方法描述视频序列中的运动活动。 为视频序列确定运动活动矩阵。 确定运动活动矩阵的阈值。 至少等于阈值的运动矢量的连接区域被识别并测量尺寸。 为整个视频序列构建连接区域的大小分布的直方图。 将直方图归一化以表征运动活动描述符中的视频序列的空间分布。

    System for processing data in variable segments and with variable data resolution
    69.
    发明授权
    System for processing data in variable segments and with variable data resolution 失效
    用于处理可变段和可变数据分辨率数据的系统

    公开(公告)号：US5828788A

    公开(公告)日：1998-10-27

    申请号：US572844

    申请日：1995-12-14

    申请人： Tihao Chiang ,  Huifang Sun ,  Joel Walter Zdepski

    发明人： Tihao Chiang ,  Huifang Sun ,  Joel Walter Zdepski

    IPC分类号： G06T9/00 ,  H03M7/30 ,  H04N7/26 ,  G06K9/46 ,  H04N7/12

    CPC分类号： H04N19/37 ,  H04N19/30

    摘要： A dynamically configurable video signal processing system partitions and encodes data using a variable number of data segments and variable data resolution. The system partitions data into a variable number of data segments by predicting, as a function of the data rate, first and second distortion factors for the data partitioned into first and second numbers of data segments. The first and second distortion factors are mutually compared and the data is partitioned into the number of data segments which exhibits the lower distortion factor value. First and second distortion factors for the data encoded with first and second data resolutions are also predicted. The first and second distortion factors are similarly compared and the data is encoded with the resolution exhibiting the lower distortion factor value.

    摘要翻译： 动态可配置的视频信号处理系统使用可变数量的数据段和可变数据分辨率对数据进行分区和编码。 该系统通过根据数据速率预测分割为第一和第二数量数据段的数据的第一和第二失真因子来将数据分割成可变数量的数据段。 相互比较第一和第二失真因子，并将数据划分成具有较低失真因子值的数据段的数量。 还预测了用第一和第二数据分辨率编码的数据的第一和第二失真因子。 类似地比较第一和第二失真因子，并且数据以表现出较低失真因子值的分辨率进行编码。

    Structural analysis of videos with hidden markov models and dynamic programming
    70.
    发明授权
    Structural analysis of videos with hidden markov models and dynamic programming 失效
    具有隐马尔可夫模型和动态规划的视频的结构分析

    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。