-
公开(公告)号：US20230184719A1
公开(公告)日：2023-06-15
申请号：US18164499
申请日：2023-02-03
Applicant: QEEXO, CO.
Inventor： Taihei MUNEMOTO , Leslie J. Schradin, III
IPC: G01N29/036 , G01N29/44 , G01N29/12 , G06F3/043 , G06F3/041
CPC classification number: G01N29/036 , G01N29/4463 , G01N29/12 , G06F3/043 , G06F3/04182 , H04B11/00
Abstract: Disclosed are apparatus and methods for enhancing operation of an ultrasonic sensing device for determining the status of an object near such ultrasonic sensing device. From the ultrasonic sensing device, an emission signal having a current frequency or band in an ultrasonic frequency range is emitted. Ultrasonic signals are received and analyzed to detect an object. After a trigger occurs, a background noise signal emitted, reflected, or diffracted from the object in an environment outside of the ultrasonic sensing device is detected and background noise metrics are estimated based on the background noise signal after halting the emitting of the emission signal. It is then determined whether the current frequency of the emission signal is optimized based on the background noise metrics. A next frequency or band is selected and the emission signal is emitted at the next frequency or band if the current frequency or band is not optimum.
-
公开(公告)号：US20220083823A1
公开(公告)日：2022-03-17
申请号：US17469439
申请日：2021-09-08
Applicant: QEEXO, CO.
Inventor： Karanpreet Singh , Rajen Bhatt
Abstract: Disclosed are apparatus and methods for automatically training a sensor node to detect anomalies in an environment. At the sensor node, an indication is received to initiate training by the sensor node to detect anomalies in the environment based on sensor data generated by a sensor that resides on such sensor node and is operable to detect sensor signals from the environment. After training is initiated, the sensor node automatically trains a model that resides on the sensor to detect anomalies in the environment, and such training is based on the sensor data. After the model is trained, the model to detect anomalies in the environment is executed by the sensor node.
-
公开(公告)号：US20210192714A1
公开(公告)日：2021-06-24
申请号：US17110131
申请日：2020-12-02
Applicant: QEEXO, CO.
Inventor： Rajen Bhatt , Shitong Mao , Raviprakash Kandury , Michelle Tai , Geoffrey Newman
Abstract: Provided are various mechanisms and processes for automatic computer vision-based defect detection using a neural network. A system is configured for receiving historical datasets that include training images corresponding to one or more known defects. Each training image is converted into a corresponding matrix representation for training the neural network to adjust weighted parameters based on the known defects. Once sufficiently trained, a test image of an object that is not part of the historical dataset is obtained. Portions of the test image are extracted as input patches for input into the neural network as respective matrix representations. A probability score indicating the likelihood that the input patch includes a defect is automatically generated for each input patch using the weighted parameters. An overall defect score for the test image is then generated based on the probability scores to indicate the condition of the object.
-
4.发明申请公开(公告)号：US20200209996A1
公开(公告)日：2020-07-02
申请号：US16798139
申请日：2020-02-21
Applicant: QEEXO, CO.
Inventor： Julia Schwarz , Christopher HARRISON
Abstract: A method of classifying touch screen events uses known non-random patterns of touch events over short periods of time to increase the accuracy of analyzing such events. The method takes advantage of the fact that after one touch event, certain actions are more likely to follow than others. Thus if a touch event is classified as a knock, and then within 500 ms a new event in a similar location occurs, but the classification confidence is low (e.g., 60% nail, 40% knuckle), the classifier may add weight to the knuckle classification since this touch sequence is far more likely. Knowledge about the probabilities of follow-on touch events can be used to bias subsequent classification, adding weight to particular events.
-
5.发明授权公开(公告)号：US10606417B2
公开(公告)日：2020-03-31
申请号：US14495041
申请日：2014-09-24
Applicant: QEEXO, CO.
Inventor： Julia Schwarz , Chris Harrison
Abstract: A method of classifying touch screen events uses known non-random patterns of touch events over short periods of time to increase the accuracy of analyzing such events. The method takes advantage of the fact that after one touch event, certain actions are more likely to follow than others. Thus if a touch event is classified as a knock, and then within 500 ms a new event in a similar location occurs, but the classification confidence is low (e.g., 60% nail, 40% knuckle), the classifier may add weight to the knuckle classification since this touch sequence is far more likely. Knowledge about the probabilities of follow-on touch events can be used to bias subsequent classification, adding weight to particular events.
-
Patent Agency Ranking
公开(公告)号：US10095402B2
公开(公告)日：2018-10-09
申请号：US14503894
申请日：2014-10-01
Applicant: QEEXO, CO.
Inventor： Robert Xiao , Julia Schwarz , Christopher Harrison
Abstract: Systems and methods are provided that determine when an initial stroke and a subsequent stroke track may be part of a common user input action. A method may include receiving a signal from which an initial stroke track representing an initial movement of a user controlled indicator against a touch sensitive surface and sensing a subsequent stroke track representing subsequent movement of the user controlled indicator against the touch sensitive surface can be determined. The method further includes determining that the initial stroke track and the subsequent stroke track comprise portions of common user input action when the initial stroke track is followed by the subsequent stroke track within a predetermined period of time and a trajectory of the initial stroke track is consistent with a trajectory of the subsequent stroke track.
-
7.发明申请METHOD AND APPARATUS FOR DIFFERENTIATING TOUCH SCREEN USERS BASED ON TOUCH EVENT ANALYSIS 审中-公开基于触摸事件分析的触控屏幕用户的方法和装置公开(公告)号：US20170024055A1
公开(公告)日：2017-01-26
申请号：US15075648
申请日：2016-03-21
Applicant: QEEXO, CO.
Inventor： JULIA SCHWARZ , CHRIS HARRISON
CPC classification number: G06F3/0416 , G06F3/041 , G06F3/043 , G06F2203/04105
Abstract: Some embodiments of the present invention include a method of differentiating touch screen users based on characterization of features derived from the touch event acoustics and mechanical impact and includes detecting a touch event on a touch sensitive surface, generating a vibro-acoustic waveform signal using at least one sensor detecting such touch event, converting the waveform signal into at least a domain signal, extracting distinguishing features from said domain signal, and classifying said features to associate the features of the domain signal with a particular user.
Abstract translation: 本发明的一些实施例包括基于来自触摸事件声学和机械冲击的特征的特性来区分触摸屏用户的方法，并且包括检测触敏表面上的触摸事件，至少使用至少一个振动声波波形信号 检测这样的触摸事件的一个传感器，将波形信号转换成至少一个域信号，从区域信号中提取区分特征，并对所述特征进行分类以将该域信号的特征与特定用户相关联。
-
8.发明申请INPUT TOOLS HAVING VIBRO-ACOUSTICALLY DISTINCT REGIONS AND COMPUTING DEVICE FOR USE WITH THE SAME 有权具有振动隔离区域的输入工具和与其一起使用的计算装置公开(公告)号：US20150199014A1
公开(公告)日：2015-07-16
申请号：US14668870
申请日：2015-03-25
Applicant: QEEXO, CO.
Inventor： CHRISTOPHER HARRISON
IPC: G06F3/01 , G06F3/0354
CPC classification number: G06F3/0433 , G06F3/016 , G06F3/03545 , G06F3/038 , G06F3/041
Abstract: An input tool includes a body in the form of a stylus with plurality of vibro-acoustically distinct regions. The vibro-acoustically distinct regions produce vibro-acoustic responses when the regions touch the surface of the touch screen. The vibro-acoustic responses are used in a computing device to detect what region of the input tool was used.
Abstract translation: 输入工具包括具有多个振动 - 声学不同区域的触笔形式的主体。 当区域接触触摸屏的表面时，振动 - 声学不同的区域产生振动 - 声响应。 在计算设备中使用振动声响应来检测输入工具的哪个区域被使用。
-
公开(公告)号：US20140327626A1
公开(公告)日：2014-11-06
申请号：US13887711
申请日：2013-05-06
Applicant: QEEXO, CO.
Inventor： Christopher Harrison , Julia Schwarz , Robert Bo Xiao
IPC: G06F3/041
Abstract: An electronic device includes a touch-sensitive surface, for example a touch pad or touch screen. The user interacts with the touch-sensitive surface, producing touch interactions. The resulting actions taken depend at least in part on the touch type. For example, the same touch interactions performed by three different touch types of a finger pad, a finger nail and a knuckle, may result in the execution of different actions.
Abstract translation: 电子设备包括触敏表面，例如触摸板或触摸屏。 用户与触敏表面交互，产生触摸交互。 所得到的动作至少部分取决于触摸类型。 例如，由手指垫，手指指甲和指关节的三种不同触摸类型执行的相同的触摸交互可能导致执行不同的动作。
-
公开(公告)号：US11847775B2
公开(公告)日：2023-12-19
申请号：US18064040
申请日：2022-12-09
Applicant: QEEXO, CO.
Inventor： Rajen Bhatt , Shitong Mao , Raviprakash Kandury , Michelle Tai , Geoffrey Newman
CPC classification number: G06T7/0004 , G06N3/08 , G06T7/11 , G06T7/194 , G06T2207/20076 , G06T2207/20081 , G06T2207/20084 , G06T2207/30164
Abstract: Provided are various mechanisms and processes for automatic computer vision-based defect detection using a neural network. A system is configured for receiving historical datasets that include training images corresponding to one or more known defects. Each training image is converted into a corresponding matrix representation for training the neural network to adjust weighted parameters based on the known defects. Once sufficiently trained, a test image of an object that is not part of the historical dataset is obtained. Portions of the test image are extracted as input patches for input into the neural network as respective matrix representations. A probability score indicating the likelihood that the input patch includes a defect is automatically generated for each input patch using the weighted parameters. An overall defect score for the test image is then generated based on the probability scores to indicate the condition of the object.
-
-
-
-
-
-
-
-
-
Search Results
73
records
(took 0.021 seconds)
