利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

52 条记录 (耗时 0.023 秒)

    Method and apparatus for tracking and recognition with rotation invariant feature descriptors
    2.
    发明授权
    Method and apparatus for tracking and recognition with rotation invariant feature descriptors 有权
    用旋转不变特征描述符跟踪和识别的方法和装置

    公开(公告)号：US08687891B2

    公开(公告)日：2014-04-01

    申请号：US12949455

    申请日：2010-11-18

    申请人： Gabriel Takacs ,  Radek Grzeszczuk ,  Vijay Chandrasekhar ,  Bernd Girod

    发明人： Gabriel Takacs ,  Radek Grzeszczuk ,  Vijay Chandrasekhar ,  Bernd Girod

    IPC分类号： G06K9/46

    CPC分类号： G06K9/4642 ,  G06K9/4671 ,  G06K9/527 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/20164

    摘要： Various methods for tracking and recognition with rotation invariant feature descriptors are provided. One example method includes generating an image pyramid of an image frame, detecting a plurality of interest points within the image pyramid, and extracting feature descriptors for each respective interest point. According to some example embodiments, the feature descriptors are rotation invariant. Further, the example method may also include tracking movement by matching the feature descriptors to feature descriptors of a previous frame and performing recognition of an object within the image frame based on the feature descriptors. Related example methods and example apparatuses are also provided.

    摘要翻译： 提供了用于跟踪和识别旋转不变特征描述符的各种方法。 一种示例性方法包括生成图像帧的图像金字塔，检测图像金字塔内的多个兴趣点，以及针对各个兴趣点提取特征描述符。 根据一些示例实施例，特征描述符是旋转不变量。 此外，示例性方法还可以包括通过将特征描述符与先前帧的特征描述符进行匹配来跟踪移动，并且基于特征描述符执行图像帧内的对象的识别。 还提供了相关的示例性方法和示例设备。

    METHOD AND APPARATUS FOR TRACKING AND RECOGNITION WITH ROTATION INVARIANT FEATURE DESCRIPTORS
    3.
    发明申请
    METHOD AND APPARATUS FOR TRACKING AND RECOGNITION WITH ROTATION INVARIANT FEATURE DESCRIPTORS 有权
    跟踪和识别旋转不确定特征描述符的方法和装置

    公开(公告)号：US20110286627A1

    公开(公告)日：2011-11-24

    申请号：US12949455

    申请日：2010-11-18

    申请人： Gabriel Takacs ,  Radek Grzeszczuk ,  Vijay Chandrasekhar ,  Bernd Girod

    发明人： Gabriel Takacs ,  Radek Grzeszczuk ,  Vijay Chandrasekhar ,  Bernd Girod

    IPC分类号： G06K9/46

    CPC分类号： G06K9/4642 ,  G06K9/4671 ,  G06K9/527 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/20164

    摘要： Various methods for tracking and recognition with rotation invariant feature descriptors are provided. One example method includes generating an image pyramid of an image frame, detecting a plurality of interest points within the image pyramid, and extracting feature descriptors for each respective interest point. According to some example embodiments, the feature descriptors are rotation invariant. Further, the example method may also include tracking movement by matching the feature descriptors to feature descriptors of a previous frame and performing recognition of an object within the image frame based on the feature descriptors. Related example methods and example apparatuses are also provided.

    摘要翻译： 提供了用于跟踪和识别旋转不变特征描述符的各种方法。 一种示例性方法包括生成图像帧的图像金字塔，检测图像金字塔内的多个兴趣点，以及针对各个兴趣点提取特征描述符。 根据一些示例实施例，特征描述符是旋转不变量。 此外，示例性方法还可以包括通过将特征描述符与先前帧的特征描述符进行匹配来跟踪移动，并且基于特征描述符执行图像帧内的对象的识别。 还提供了相关的示例性方法和示例设备。

    METHOD AND APPARATUS FOR REPRESENTING AND IDENTIFYING FEATURE DESCRIPTIONS UTILIZING A COMPRESSED HISTOGRAM OF GRADIENTS
    4.
    发明申请
    METHOD AND APPARATUS FOR REPRESENTING AND IDENTIFYING FEATURE DESCRIPTIONS UTILIZING A COMPRESSED HISTOGRAM OF GRADIENTS 有权
    用于表示和识别特征描述的方法和装置，使用压缩的梯形图

    公开(公告)号：US20100226575A1

    公开(公告)日：2010-09-09

    申请号：US12617514

    申请日：2009-11-12

    申请人： Radek Grzeszczuk ,  Vijay Chandrasekhar ,  Gabriel Takacs ,  Bernd Girod

    发明人： Radek Grzeszczuk ,  Vijay Chandrasekhar ,  Gabriel Takacs ,  Bernd Girod

    IPC分类号： G06K9/46

    CPC分类号： G06F17/30256 ,  G06K9/4642 ,  G06T9/20 ,  G06T9/40 ,  H04N19/14 ,  H04N19/96

    摘要： A method, apparatus and computer program product may be provided for generating a plurality of compressed feature descriptors that can be represented by a relatively small number of bits, thereby facilitating transmission and storage of the feature descriptors. A method, apparatus and computer program product may also be provided for permitting a compressed representation of a feature descriptor to be compared with a plurality of compressed representations of feature descriptors of respective predefined features. By permitting the comparison to be performed utilizing compressed representations of feature descriptors, a respective feature descriptor may be identified without having to first decompress the feature descriptor, thereby potentially increasing the efficiency with which feature descriptors may be identified.

    摘要翻译： 可以提供一种方法，装置和计算机程序产品，用于生成可以由相对较少数量的比特表示的多个压缩特征描述符，从而便于特征描述符的传输和存储。 还可以提供一种方法，装置和计算机程序产品，用于允许特征描述符的压缩表示与各个预定义特征的特征描述符的多个压缩表示进行比较。 通过允许使用特征描述符的压缩表示来执行比较，可以识别相应的特征描述符，而不必首先解压缩特征描述符，从而潜在地提高可以识别特征描述符的效率。

    System and method for echo suppression in web browser-based communication
    6.
    发明授权
    System and method for echo suppression in web browser-based communication 有权
    基于Web浏览器的通信中回波抑制的系统和方法

    公开(公告)号：US08553520B2

    公开(公告)日：2013-10-08

    申请号：US13034714

    申请日：2011-02-25

    申请人： Badri N. Rajasekar ,  Chuo-Ling Chang ,  Gaurav Gupta ,  Bernd Girod ,  Yang Cao

    发明人： Badri N. Rajasekar ,  Chuo-Ling Chang ,  Gaurav Gupta ,  Bernd Girod ,  Yang Cao

    IPC分类号： H04J3/10

    CPC分类号： H04M9/082

    摘要： A system and method for performing echo suppression on a server in browser-based online audio conferences without downloading or installing software on a participant's computing device is disclosed. Streams of audio communication data from the participants in an audio conference are received at the server. An echo suppression application determines the first party that speaks by analyzing the streams to locate speech data, and assigns that party as the “owner” of the audio channel. The speech data is sent to the other participants in the conference. The application then determines whether newly received audio from the owner of the channel is new speech; if so, then the party remains the owner of the channel, and the new speech data is also sent to the other parties in the conference. The channel is surrendered if no new speech is received from the owner in a defined period, and the next party that speaks becomes the new owner of the channel. The other audio data from the participants is replaced by silence.

    摘要翻译： 公开了一种用于在基于浏览器的在线音频会议中在服务器上执行回声抑制而不在参与者的计算设备上下载或安装软件的系统和方法。 来自音频会议的参与者的音频通信数据流在服务器处被接收。 回声抑制应用程序通过分析流来定位语音数据来确定说话的第一方，并将该方分配为音频频道的“所有者”。 语音数据被发送给会议的其他与会者。 然后，应用程序确定来自频道的所有者的新接收的音频是否是新的语音; 如果是，则该方仍然是频道的所有者，并且新的语音数据也被发送给会议的其他方。 如果在规定的时间内没有收到业主的新发言，则该频道被交出，而说话的下一方成为频道的新拥有者。 来自与会者的其他音频数据被沉默所取代。

    Video-assisted audio signal processing system and method
    7.
    再颁专利
    Video-assisted audio signal processing system and method 有权
    视频辅助音频信号处理系统及方法

    公开(公告)号：USRE40054E1

    公开(公告)日：2008-02-12

    申请号：US10994220

    申请日：2004-11-19

    申请人： Bernd Girod

    发明人： Bernd Girod

    IPC分类号： H04N3/00

    CPC分类号： H04N7/147 ,  G10L2021/02082 ,  H04N7/142

    摘要： A circuit arrangement for controlling audio signal transmissions for a communications system that includes a microphone and a video camera. The arrangement comprises a video processor configured and arranged to receive a video signal from the video camera, detect movement of an object in the video signal, and provide a motion-indicating signal indicating movement relative to the object. An audio processor is coupled to the video processor and is configured and arranged to modify the audio signal to be transmitted responsive to the motion-indicating signal. In another embodiment, a video signal processor is configured and arranged to receive a video signal from the video camera, detect mouth movement of a person and provide a mouth-movement signal indicative of movement of the person's mouth. An echo-cancellation circuit is coupled to the video signal processor and configured and arranged to filter from an audio signal provided by the microphone sound energy output by the speaker responsive to the mouth-movement signal.

    摘要翻译： 一种用于控制包括麦克风和摄像机的通信系统的音频信号传输的电路装置。 该装置包括视频处理器，其被配置和布置成从视频摄像机接收视频信号，检测视频信号中的对象的移动，并提供指示相对于对象移动的运动指示信号。 音频处理器耦合到视频处理器，并且被配置和布置为响应于运动指示信号来修改要发送的音频信号。 在另一个实施例中，视频信号处理器被配置和布置成从摄像机接收视频信号，检测人的嘴部移动并提供指示人的嘴的运动的口部运动信号。 回声消除电路耦合到视频信号处理器，并且被配置和布置为响应于口部移动信号，由由扬声器输出的麦克风声音能量提供的音频信号进行滤波。

    Wireless user-interface arrangement and method
    8.
    发明授权
    Wireless user-interface arrangement and method 失效
    无线用户界面布置和方法

    公开(公告)号：US06677987B1

    公开(公告)日：2004-01-13

    申请号：US08984602

    申请日：1997-12-03

    申请人： Bernd Girod

    发明人： Bernd Girod

    IPC分类号： H04N5225

    CPC分类号： G06F3/0386

    摘要： A wireless user-interface method and arrangement having a light source and a circuit arrangement that detects the presence and position of the light source. A light source emits modulated light having a first modulation frequency that is captured by a camera circuit arrangement. A circuit arrangement uses relative pixel luminances and differences in pixel luminances between frames to detect the presence of modulated light from the light source. The position of the light source is tracked from frame to frame and the position information is output for use by application software or circuitry to direct movement of a pointer in a computer display, for example. Modulated light having a second modulation frequency from the light source is detected by the circuit arrangement and interpreted as selection of a control function, which is provided as output to application software or circuitry. The application uses the position of the light source along with control signals to identify an operation to perform.

    摘要翻译： 一种具有检测光源的存在和位置的光源和电路装置的无线用户接口方法和装置。 光源发射具有由相机电路装置捕获的第一调制频率的调制光。 电路装置使用相对像素亮度和帧之间的像素亮度的差异来检测来自光源的调制光的存在。 光源的位置从帧到帧被跟踪，并且输出位置信息以供应用软件或电路用于将指针的移动引导到例如计算机显示器中。 具有来自光源的第二调制频率的调制光由电路装置检测，并被解释为作为对应用软件或电路的输出提供的控制功能的选择。 应用程序使用光源的位置以及控制信号来识别要执行的操作。