中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

80 records (took 0.021 seconds)

    Efficient gesture processing
    3.
    发明授权
    Efficient gesture processing 有权
    高效的手势处理

    公开(公告)号：US09535506B2

    公开(公告)日：2017-01-03

    申请号：US14205210

    申请日：2014-03-11

    Applicant: Giuseppe Raffa ,  Lama Nachman ,  Jinwon Lee

    Inventor： Giuseppe Raffa ,  Lama Nachman ,  Jinwon Lee

    IPC: G06F1/16 ,  G06F3/01 ,  G06F3/0346

    CPC classification number: G06F3/017 ,  G01C19/00 ,  G01P15/18 ,  G06F1/1694 ,  G06F3/0346 ,  H04M2250/12

    Abstract: Embodiments of the invention describe a system to efficiently execute gesture recognition algorithms. Embodiments of the invention describe a power efficient staged gesture recognition pipeline including multimodal interaction detection, context based optimized recognition, and context based optimized training and continuous learning. Embodiments of the invention further describe a system to accommodate many types of algorithms depending on the type of gesture that is needed in any particular situation. Examples of recognition algorithms include but are not limited to, HMM for complex dynamic gestures (e.g. write a number in the air), Decision Trees (DT) for static poses, peak detection for coarse shake/whack gestures or inertial methods (INS) for pitch/roll detection.

    Abstract translation: 本发明的实施例描述了一种有效执行手势识别算法的系统。 本发明的实施例描述了一种功率效率分级手势识别流水线，其包括多模式交互检测，基于上下文的优化识别和基于上下文的优化训练和连续学习。 本发明的实施例进一步描述了根据在任何特定情况下需要的手势类型来适应许多类型的算法的系统。 识别算法的示例包括但不限于用于复杂动态手势的HMM（例如在空中编写一个数字），用于静态姿势的决策树（DT），用于粗略摇动/打击手势的峰值检测或惯性方法（INS），用于 俯仰/滚动检测。

    SENSOR ASSOCIATED DATA OF MULTIPLE DEVICES BASED COMPUTING
    4.
    发明申请
    SENSOR ASSOCIATED DATA OF MULTIPLE DEVICES BASED COMPUTING 有权
    基于多个设备的传感器相关数据计算

    公开(公告)号：US20140280137A1

    公开(公告)日：2014-09-18

    申请号：US13797981

    申请日：2013-03-12

    Applicant: Glen J. Anderson ,  Richard P. Crawford ,  Audrey C. Younkin ,  Giuseppe Raffa

    Inventor： Glen J. Anderson ,  Richard P. Crawford ,  Audrey C. Younkin ,  Giuseppe Raffa

    IPC: G06F17/30

    CPC classification number: G06F17/30309 ,  G06F17/3071 ,  G06F17/30864

    Abstract: Computer-readable storage media, apparatus and method associated with storing a copy of local data in a historical data store, among other embodiments, are disclosed herein. In embodiments, one or more computer-readable storage media may contain instructions which when executed by a computing device may provide access of local data to one or more applications on the computing device for contemporaneous processing by the one or more applications. The local data may be associated, at least in part, with one or more sensors of the computing device. In some embodiments, a copy of the local data may be transmitted to a remote historical data store where it may be categorized and correlated with data from computing devices associated with one or more other users for further processing.

    Abstract translation: 本文公开了与历史数据存储中的本地数据的副本相关联的计算机可读存储介质，装置和方法。 在实施例中，一个或多个计算机可读存储介质可以包含当由计算设备执行时可以向计算设备上的一个或多个应用提供本地数据的访问以用于一个或多个应用的​​同时处理的指令。 至少部分地，本地数据可以与计算设备的一个或多个传感器相关联。 在一些实施例中，本地数据的副本可以被发送到远程历史数据存储，其中它可以被分类并与来自与一个或多个其他用户相关联的计算设备的数据相关联以用于进一步处理。

    TECHNIQUES FOR POSE ESTIMATION AND FALSE POSITIVE FILTERING FOR GESTURE RECOGNITION
    6.
    发明申请
    TECHNIQUES FOR POSE ESTIMATION AND FALSE POSITIVE FILTERING FOR GESTURE RECOGNITION 审中-公开
    用于姿势识别和假阳性滤波的技术识别

    公开(公告)号：US20140002338A1

    公开(公告)日：2014-01-02

    申请号：US13536262

    申请日：2012-06-28

    Applicant: GIUSEPPE RAFFA ,  SANGITA SHARMA ,  JUNAITH AHEMED SHAHABDEEN

    Inventor： GIUSEPPE RAFFA ,  SANGITA SHARMA ,  JUNAITH AHEMED SHAHABDEEN

    IPC: G09G5/00

    CPC classification number: G06F3/0346 ,  G06F1/1694 ,  G06F3/017

    Abstract: Techniques for pose estimation and false positive filtering for gesture recognition are described. For example, a method may comprise receiving data from one or more sensors indicating motion of an electronic device, determining if the motion comprises a gesture motion using one or more statistical gesture recognition algorithms, determining a start pose and an end pose for the gesture motion, determining if the start pose and end pose of the gesture motion correspond to a start pose and end pose of a gesture model corresponding to the gesture motion, and triggering a gesture event if the start pose and end pose of the gesture motion match the start pose and end pose of the gesture model. Other embodiments are described and claimed.

    Abstract translation: 描述用于姿态估计和假阳性滤波的手势识别技术。 例如，方法可以包括从指示电子设备的运动的一个或多个传感器接收数据，使用一个或多个统计手势识别算法确定运动是否包括手势运动，确定手势运动的起始姿势和结束姿势 确定手势运动的开始姿态和结束姿势是否对应于与手势运动相对应的手势模型的开始姿态和结束姿势，并且如果手势运动的开始姿态和结束姿势与开始相匹配，则触发手势事件 手势模型的姿态和结束姿势。 描述和要求保护其他实施例。

    MOBILE DEVICE OPERATION USING GRIP INTENSITY
    7.
    发明申请
    MOBILE DEVICE OPERATION USING GRIP INTENSITY 有权
    移动设备使用GRIP强度的操作

    公开(公告)号：US20130335319A1

    公开(公告)日：2013-12-19

    申请号：US13997160

    申请日：2011-12-30

    Applicant: Sai Prasad Balasundaram ,  David Graumann ,  Giuseppe Raffa ,  Sangita Sharma

    Inventor： Sai Prasad Balasundaram ,  David Graumann ,  Giuseppe Raffa ,  Sangita Sharma

    IPC: G06F3/01

    CPC classification number: G06F3/011 ,  G06F3/03547 ,  G06F3/0485 ,  G06F3/0488 ,  G06F2203/0339 ,  H04M1/72522 ,  H04M2250/22

    Abstract: Mobile device operation using grip intensity. An embodiment of a mobile device includes a touch sensor to detect contact or proximity by a user of the mobile device; a memory to store indicators of grip intensity in relation to the touch sensor; and a processor to evaluate contact to the touch sensor. The processor is to compare a contact with the touch sensor to the indicators of grip shape and firmness to determine grip intensity, and the mobile device is to receive an input for a function of the mobile device based at least in part on determined grip intensity for the mobile device.

    Abstract translation: 移动设备操作使用握力。 移动设备的实施例包括触摸传感器，用于检测移动设备的用户的接触或接近; 用于存储相对于触摸传感器的握持强度指示的存储器; 以及用于评估与触摸传感器的接触的处理器。 处理器是将触摸传感器与触摸传感器的指示器与抓地力形状和坚固度的指标进行比较以确定抓地力，并且移动装置至少部分地基于所确定的抓地力来接收用于移动装置的功能的输入 移动设备。

    EFFICIENT GESTURE PROCESSING
    10.
    发明申请
    EFFICIENT GESTURE PROCESSING 审中-公开
    高效的加工

    公开(公告)号：US20120016641A1

    公开(公告)日：2012-01-19

    申请号：US12835079

    申请日：2010-07-13

    Applicant: Giuseppe Raffa ,  Lama Nachman ,  Jinwon Lee

    Inventor： Giuseppe Raffa ,  Lama Nachman ,  Jinwon Lee

    IPC: G06F17/10 ,  G06F15/00 ,  G01P15/00

    CPC classification number: G06F3/017 ,  G01C19/00 ,  G01P15/18 ,  G06F1/1694 ,  G06F3/0346 ,  H04M2250/12

    Abstract: Embodiments of the invention describe a system to efficiently execute gesture recognition algorithms. Embodiments of the invention describe a power efficient staged gesture recognition pipeline including multimodal interaction detection, context based optimized recognition, and context based optimized training and continuous learning. Embodiments of the invention further describe a system to accommodate many types of algorithms depending on the type of gesture that is needed in any particular situation. Examples of recognition algorithms include but are not limited to, HMM for complex dynamic gestures (e.g. write a number in the air), Decision Trees (DT) for static poses, peak detection for coarse shake/whack gestures or inertial methods (INS) for pitch/roll detection.

    Abstract translation: 本发明的实施例描述了一种有效执行手势识别算法的系统。 本发明的实施例描述了一种功率效率分级手势识别流水线，其包括多模式交互检测，基于上下文的优化识别和基于上下文的优化训练和连续学习。 本发明的实施例进一步描述了根据在任何特定情况下需要的手势类型来适应许多类型的算法的系统。 识别算法的示例包括但不限于用于复杂动态手势的HMM（例如在空中编写一个数字），用于静态姿势的决策树（DT），用于粗略摇动/打击手势的峰值检测或惯性方法（INS），用于 俯仰/滚动检测。

Patent Agency Ranking