Motion pattern classification and gesture recognition

    公开(公告)号:US10209778B2

    公开(公告)日:2019-02-19

    申请号:US14828422

    申请日:2015-08-17

    Applicant: Apple Inc.

    Abstract: Methods, program products, and systems for gesture classification and recognition are disclosed. In general, in one aspect, a system can determine multiple motion patterns for a same user action (e.g., picking up a mobile device from a table) from empirical training data. The system can collect the training data from one or more mobile devices. The training data can include multiple series of motion sensor readings for a specified gesture. Each series of motion sensor readings can correspond to a particular way a user performs the gesture. Using clustering techniques, the system can extract one or more motion patterns from the training data. The system can send the motion patterns to mobile devices as prototypes for gesture recognition.

    Proximity Sensor with Separate Near-Field and Far-Field Measurement Capability

    公开(公告)号:US20170090608A1

    公开(公告)日:2017-03-30

    申请号:US15273540

    申请日:2016-09-22

    Applicant: Apple Inc.

    Abstract: An electronic device that includes a proximity sensor may be provided. The proximity sensor may be a time-of-flight-based proximity sensor that is capable of separately outputting near-field measurements and far-field measurements. The near-field and far-field measurements may be placed in separate bins according to their time-of-flight values. The discrimination between near-field and far-field results may allow the electronic device to filter out false positive events where the presence of smudge or other surface contaminants can otherwise produce skewed readings and also to filter out false negative events where the presence of a user with dark hair or skin can otherwise produce misleading sensor results.

    Reconstruction of original touch image from differential touch image

    公开(公告)号:US09874975B2

    公开(公告)日:2018-01-23

    申请号:US15144706

    申请日:2016-05-02

    Applicant: Apple Inc.

    CPC classification number: G06F3/0418

    Abstract: Reconstruction of an original touch image from a differential touch image is disclosed. Reconstruction can include aligning columns of the differential touch image relative to each other and aligning the image to a baseline DC value. The column and baseline alignment can be based on the differential image data indicative of no touch or hover, because such data can more clearly show the amount of alignment needed to reconstruct the original image. The reconstruction can be performed using the differential image data alone. The reconstruction can also be performed using the differential image data and common mode data indicative of the missing image column average.

    Negative pixel compensation
    4.
    发明授权
    Negative pixel compensation 有权
    负像素补偿

    公开(公告)号:US08754874B2

    公开(公告)日:2014-06-17

    申请号:US14048859

    申请日:2013-10-08

    Applicant: Apple Inc.

    CPC classification number: G06F3/0418 G06F3/0412 G06F3/044 G06F2203/04104

    Abstract: Negative pixel compensation in a touch sensor panel is disclosed. A method can compensate for a negative pixel effect in touch signal outputs due to poor grounding of an object touching the panel. To do so, the method can include determining at least one bound for a negative pixel compensation factor based on touch signal values, estimating the compensation factor within the determined bound based on the touch signal values that are negative, where the negative values indicate the presence of the negative pixel effect, and applying the estimated compensation factor to the touch signal outputs to compensate the touch signal values for the negative pixel effect.

    Abstract translation: 公开了触摸传感器面板中的负像素补偿。 由于接触面板的物体接地不良,一种方法可以补偿触摸信号输出中的负像素效应。 为了这样做,该方法可以包括基于触摸信号值来确定负像素补偿因子的至少一个界限,基于负的触摸信号值估计所确定的界限内的补偿因子,其中负值表示存在 并且将估计的补偿因子应用于触摸信号输出以补偿负像素效应的触摸信号值。

    Presence Sensing
    5.
    发明申请
    Presence Sensing 审中-公开

    公开(公告)号:US20170193282A1

    公开(公告)日:2017-07-06

    申请号:US15445623

    申请日:2017-02-28

    Applicant: Apple Inc.

    Abstract: One embodiment may take the form of a method of operating a computing device to provide presence based functionality. The method may include operating the computing device in a reduced power state and collecting a first set of data from a first sensor. Based on the first set of data, the computing device determines if an object is within a threshold distance of the computing device and, if the object is within the threshold distance, the device activates a secondary sensor to collect a second set of data. Based on the second set of data, the device determines if the object is a person. If the object is a person, the device determines a position of the person relative to the computing device and executes a change of state in the computing device based on the position of the person relative to the computing device. If the object is not a person, the computing device remains in a reduced power state.

    Presence sensing
    6.
    发明授权

    公开(公告)号:US10402624B2

    公开(公告)日:2019-09-03

    申请号:US15445623

    申请日:2017-02-28

    Applicant: Apple Inc.

    Abstract: One embodiment may take the form of a method of operating a computing device to provide presence based functionality. The method may include operating the computing device in a reduced power state and collecting a first set of data from a first sensor. Based on the first set of data, the computing device determines if an object is within a threshold distance of the computing device and, if the object is within the threshold distance, the device activates a secondary sensor to collect a second set of data. Based on the second set of data, the device determines if the object is a person. If the object is a person, the device determines a position of the person relative to the computing device and executes a change of state in the computing device based on the position of the person relative to the computing device. If the object is not a person, the computing device remains in a reduced power state.

    Motion Pattern Classification and Gesture Recognition
    7.
    发明申请
    Motion Pattern Classification and Gesture Recognition 审中-公开
    运动模式分类和手势识别

    公开(公告)号:US20150355721A1

    公开(公告)日:2015-12-10

    申请号:US14828422

    申请日:2015-08-17

    Applicant: Apple Inc.

    CPC classification number: G06F3/017 G06F3/04842 G06F3/04883 G06K9/00355

    Abstract: Methods, program products, and systems for gesture classification and recognition are disclosed. In general, in one aspect, a system can determine multiple motion patterns for a same user action (e.g., picking up a mobile device from a table) from empirical training data. The system can collect the training data from one or more mobile devices. The training data can include multiple series of motion sensor readings for a specified gesture. Each series of motion sensor readings can correspond to a particular way a user performs the gesture. Using clustering techniques, the system can extract one or more motion patterns from the training data. The system can send the motion patterns to mobile devices as prototypes for gesture recognition.

    Abstract translation: 公开了用于手势分类和识别的方法,程序产品和系统。 通常,在一个方面,系统可以根据经验训练数据确定用于相同用户动作(例如,从表中拾取移动设备)的多个运动模式。 系统可以从一个或多个移动设备收集训练数据。 训练数据可以包括用于指定手势的多个运动传感器读数。 每个系列的运动传感器读数可以对应于用户执行手势的特定方式。 使用聚类技术,系统可以从训练数据中提取一个或多个运动模式。 系统可以将运动模式发送到移动设备作为用于手势识别的原型。

Patent Agency Ranking