公开(公告)号：US20150084860A1

公开(公告)日：2015-03-26

申请号：US14494274

申请日：2014-09-23

Applicant: Thalmic Labs Inc.

Inventor： Idris S. Aleem ,  Pedram Ataee ,  Matthew Bailey

IPC: G06F3/01

CPC classification number: G06F3/017 ,  G06F3/014 ,  G06F3/015

Abstract: Systems, articles, and methods for performing gesture identification with improved robustness against variations in use parameters and without requiring a user to undergo an extensive training procedure are described. A wearable electromyography (“EMG”) device includes multiple EMG sensors, an on-board processor, and a non-transitory processor-readable storage medium that stores data and/or processor-executable instructions for performing gesture identification. The wearable EMG device detects, determines, and ranks features in the signal data provided by the EMG sensors and generates a digit string based on the ranked features. The permutation of the digit string is indicative of the gesture performed by the user, which is identified by testing the permutation of the digit string against multiple sets of defined permutation conditions. A single reference gesture may be performed by the user to (re-)calibrate the wearable EMG device before and/or during use.

Abstract translation: 描述用于执行手势识别的系统，物品和方法，其具有针对使用参数的变化的改进的鲁棒性，并且不要求用户经历广泛的训练程序。 可穿戴肌电图（“EMG”）装置包括多个EMG传感器，车载处理器和存储用于执行手势识别的数据和/或处理器可执行指令的非暂时处理器可读存储介质。 可穿戴EMG设备检测，确定和排列由EMG传感器提供的信号数据中的特征，并根据排名特征生成数字串。 数字串的排列指示由用户执行的手势，其通过针对多组定义的置换条件测试数字串的排列来识别。 用户可以执行单个参考手势以在使用前和/或使用期间（重新）校准可穿戴EMG装置。

公开(公告)号：US09389694B2

公开(公告)日：2016-07-12

申请号：US14520081

申请日：2014-10-21

Applicant: Thalmic Labs Inc.

Inventor： Pedram Ataee ,  Idris S. Aleem ,  Matthew Bailey

IPC: G06F3/01 ,  A61B5/00 ,  A61B5/0488

CPC classification number: G06F3/017 ,  A61B5/0488 ,  A61B5/681 ,  A61B5/7267 ,  A61B2562/063

Abstract: Systems, articles, and methods perform gesture identification with limited computational resources. A wearable electromyography (“EMG”) device includes multiple EMG sensors, an on-board processor, and a non-transitory processor-readable memory that stores data and/or processor-executable instructions for performing gesture identification. The wearable EMG device detects and determines features of signals when a user performs a physical gesture, and processes the features by performing a decision tree analysis. The decision tree analysis invokes a decision tree stored in the memory, where storing and executing the decision tree may be managed by limited computational resources. The outcome of the decision tree analysis is a probability vector that assigns a respective probability score to each gesture in a gesture library. The accuracy of the gesture identification may be enhanced by performing multiple iterations of the decision tree analysis across multiple time windows of the EMG signal data and combining the resulting probability vectors.

Abstract translation: 系统，文章和方法以有限的计算资源执行手势识别。 可穿戴肌电图（“EMG”）装置包括多个EMG传感器，车载处理器以及存储用于执行手势识别的数据和/或处理器可执行指令的非暂时处理器可读存储器。 可穿戴EMG设备检测并确定用户执行物理手势时的信号特征，并通过执行决策树分析来处理特征。 决策树分析调用存储在存储器中的决策树，其中可以通过有限的计算资源来管理决策树的存储和执行。 决策树分析的结果是向手势库中的每个姿态分配各自的概率分数的概率向量。 可以通过在EMG信号数据的多个时间窗口上执行决策树分析的多次迭代并组合所得到的概率向量来增强手势识别的准确性。

公开(公告)号：US20180120948A1

公开(公告)日：2018-05-03

申请号：US15852196

申请日：2017-12-22

Applicant: THALMIC LABS INC.

Inventor： Idris S. Aleem ,  Pedram Ataee

IPC: G06F3/01 ,  G06K9/62 ,  G06F1/16 ,  G06K9/00

CPC classification number: G06F3/017 ,  G06F1/163 ,  G06F3/015 ,  G06K9/00335 ,  G06K9/6202

Abstract: Systems, devices, and methods adapt established concepts from natural language processing for use in gesture identification algorithms. A gesture identification system includes sensors, a processor, and a non-transitory processor-readable memory that stores data and/or instructions for performing gesture identification. A gesture identification system may include a wearable gesture identification device. The gesture identification process involves segmenting signals from the sensors into data windows, assigning a respective “window class” to each data window, and identifying a user-performed gesture based on the corresponding sequence of window classes. Each window class exclusively characterizes at least one data window property and is analogous to a “letter” of an alphabet. Under this model, each gesture is analogous to a “word” made up of a particular combination of window classes.

公开(公告)号：US20150169074A1

公开(公告)日：2015-06-18

申请号：US14567826

申请日：2014-12-11

Applicant: Thalmic Labs Inc.

Inventor： Pedram Ataee ,  Idris S. Aleem ,  Matthew Bailey

IPC: G06F3/01 ,  G06T7/20

CPC classification number: G06F3/017 ,  G06F3/014 ,  G06F3/015 ,  G06F3/016 ,  G06F3/0346

Abstract: Systems, articles, and methods perform gesture identification with limited computational resources. A wearable electromyography (“EMG”) device includes multiple EMG sensors, an on-board processor, and a non-transitory processor-readable memory storing data and/or instructions for performing gesture identification. The wearable EMG device detects signals when a user performs a physical gesture and characterizes a signal vector {right arrow over (s)} based on features of the detected signals. A library of gesture template vectors G is stored in the memory of the wearable EMG device and a respective property of each respective angle θi formed between the signal vector {right arrow over (s)} and respective ones of the gesture template vectors {right arrow over (g)}i is analyzed to match the direction of the signal vector {right arrow over (s)} to the direction of a particular gesture template vector {right arrow over (g)}*. The accuracy of the gesture identification may be enhanced by performing multiple iterations across multiple time-synchronized portions of the EMG signal data.

Abstract translation: 系统，文章和方法以有限的计算资源执行手势识别。 可穿戴肌电图（“EMG”）装置包括多个EMG传感器，车载处理器和存储用于执行手势识别的数据和/或指令的非暂时处理器可读存储器。 可穿戴EMG装置根据检测到的信号的特征，检测用户执行物理手势时的信号，并对信号矢量{向右箭头}进行表征。 手势模板矢量G的库被存储在可穿戴EMG装置的存储器中，并且每个相应的角度和角度的相应属性i形成在信号向量{右箭头（s）}和相应的手势模板向量{ （g）}中的右箭头被分析以将信号向量{向右箭头（s）}的方向与特定姿态模板向量{右箭头（g）} *的方向相匹配。 可以通过在EMG信号数据的多个时间同步部分上执行多个迭代来增强手势识别的准确度。

公开(公告)号：US09483123B2

公开(公告)日：2016-11-01

申请号：US14494274

申请日：2014-09-23

Applicant: Thalmic Labs Inc.

Inventor： Idris S. Aleem ,  Pedram Ataee ,  Matthew Bailey

IPC: G06F3/01

CPC classification number: G06F3/017 ,  G06F3/014 ,  G06F3/015

Abstract: Systems, articles, and methods for performing gesture identification with improved robustness against variations in use parameters and without requiring a user to undergo an extensive training procedure are described. A wearable electromyography (“EMG”) device includes multiple EMG sensors, an on-board processor, and a non-transitory processor-readable storage medium that stores data and/or processor-executable instructions for performing gesture identification. The wearable EMG device detects, determines, and ranks features in the signal data provided by the EMG sensors and generates a digit string based on the ranked features. The permutation of the digit string is indicative of the gesture performed by the user, which is identified by testing the permutation of the digit string against multiple sets of defined permutation conditions. A single reference gesture may be performed by the user to (re-)calibrate the wearable EMG device before and/or during use.

Abstract translation: 描述用于执行手势识别的系统，物品和方法，其具有针对使用参数的变化的改进的鲁棒性，并且不要求用户经历广泛的训练程序。 可穿戴肌电图（“EMG”）装置包括多个EMG传感器，车载处理器和存储用于执行手势识别的数据和/或处理器可执行指令的非暂时处理器可读存储介质。 可穿戴EMG设备检测，确定和排列由EMG传感器提供的信号数据中的特征，并根据排名特征生成数字串。 数字串的排列指示由用户执行的手势，其通过针对多组定义的置换条件测试数字串的排列来识别。 用户可以执行单个参考手势以在使用前和/或使用期间（重新）校准可穿戴EMG装置。

公开(公告)号：US20150277575A1

公开(公告)日：2015-10-01

申请号：US14669878

申请日：2015-03-26

Applicant: Thalmic Labs Inc.

Inventor： Pedram Ataee ,  Stephen Lake

IPC: G06F3/01 ,  G09G5/00

CPC classification number: G09G5/006 ,  G06F1/163 ,  G06F1/1694 ,  G06F3/015 ,  G06F3/016

Abstract: Systems, devices, and methods that implement state machine models in wearable electronic devices are described. A wearable electronic device stores processor-executable gesture identification instructions that, when executed by an on-board processor, enable the wearable electronic device to identify one or more gesture(s) performed by a user. The wearable electronic device also stores processor-executable state determination instructions that, when executed by the processor, cause the wearable electronic device to enter into and transition between various operational states depending on signals detected by on-board sensors. The state machine models described herein enable the wearable electronic devices to identify and automatically recover from operational errors, malfunctions, or crashes with minimal intervention from the user.

Abstract translation: 描述了在可穿戴电子设备中实现状态机模型的系统，设备和方法。 可穿戴电子设备存储处理器可执行的手势识别指令，当由机载处理器执行时，该可执行手势识别指令使可穿戴电子设备能够识别用户执行的一个或多个手势。 可穿戴式电子设备还存储处理器可执行状态确定指令，其在由处理器执行时，根据车载传感器检测到的信号，使可穿戴电子设备进入各种操作状态之间并转换。 本文描述的状态机模型使得可穿戴式电子设备能够以最小的用户干预来识别并自动从操作错误，故障或崩溃中恢复。

公开(公告)号：US09880632B2

公开(公告)日：2018-01-30

申请号：US14737081

申请日：2015-06-11

Applicant: Thalmic Labs Inc.

Inventor： Pedram Ataee ,  Idris S. Aleem

IPC: G06F3/01 ,  G06F1/16 ,  G06K9/00

CPC classification number: G06F3/017 ,  G06F1/163 ,  G06F3/015 ,  G06K9/00335 ,  G06K9/6202

Abstract: Systems, devices, and methods adapt established concepts from natural language processing for use in gesture identification algorithms. A gesture identification system includes sensors, a processor, and a non-transitory processor-readable memory that stores data and/or instructions for performing gesture identification. A gesture identification system may include a wearable gesture identification device. The gesture identification process involves segmenting signals from the sensors into data windows, assigning a respective “window class” to each data window, and identifying a user-performed gesture based on the corresponding sequence of window classes. Each window class exclusively characterizes at least one data window property and is analogous to a “letter” of an alphabet. Under this model, each gesture is analogous to a “word” made up of a particular combination of window classes.

公开(公告)号：US09367139B2

公开(公告)日：2016-06-14

申请号：US14567826

申请日：2014-12-11

Applicant: Thalmic Labs Inc.

Inventor： Pedram Ataee ,  Idris S. Aleem ,  Matthew Bailey

IPC: G06F3/01 ,  G06F3/0346

CPC classification number: G06F3/017 ,  G06F3/014 ,  G06F3/015 ,  G06F3/016 ,  G06F3/0346

Abstract: Systems, articles, and methods perform gesture identification with limited computational resources. A wearable electromyography (“EMG”) device includes multiple EMG sensors, an on-board processor, and a non-transitory processor-readable memory storing data and/or instructions for performing gesture identification. The wearable EMG device detects signals when a user performs a physical gesture and characterizes a signal vector {right arrow over (s)} based on features of the detected signals. A library of gesture template vectors G is stored in the memory of the wearable EMG device and a respective property of each respective angle θi formed between the signal vector {right arrow over (s)} and respective ones of the gesture template vectors {right arrow over (g)}i is analyzed to match the direction of the signal vector {right arrow over (s)} to the direction of a particular gesture template vector {right arrow over (g)}*. The accuracy of the gesture identification may be enhanced by performing multiple iterations across multiple time-synchronized portions of the EMG signal data.

Abstract translation: 系统，文章和方法以有限的计算资源执行手势识别。 可穿戴肌电图（“EMG”）装置包括多个EMG传感器，车载处理器和存储用于执行手势识别的数据和/或指令的非暂时处理器可读存储器。 可穿戴EMG装置根据检测到的信号的特征，检测用户执行物理手势时的信号，并对信号矢量{向右箭头}进行表征。 手势模板矢量G的库被存储在可穿戴EMG装置的存储器中，并且每个相应的角度和角度的相应属性i形成在信号向量{右箭头和s之间}和手势模板向量{ （g）}中的右箭头被分析以将信号向量{向右箭头（s）}的方向与特定姿态模板向量{右箭头（g）} *的方向相匹配。 可以通过在EMG信号数据的多个时间同步部分上执行多个迭代来增强手势识别的准确度。

公开(公告)号：US20150370333A1

公开(公告)日：2015-12-24

申请号：US14737081

申请日：2015-06-11

Applicant: Thalmic Labs Inc.

Inventor： Pedram Ataee ,  Idris S. Aleem

IPC: G06F3/01

CPC classification number: G06F3/017 ,  G06F1/163 ,  G06F3/015 ,  G06K9/00335 ,  G06K9/6202

Abstract: Systems, devices, and methods adapt established concepts from natural language processing for use in gesture identification algorithms. A gesture identification system includes sensors, a processor, and a non-transitory processor-readable memory that stores data and/or instructions for performing gesture identification. A gesture identification system may include a wearable gesture identification device. The gesture identification process involves segmenting signals from the sensors into data windows, assigning a respective “window class” to each data window, and identifying a user-performed gesture based on the corresponding sequence of window classes. Each window class exclusively characterizes at least one data window property and is analogous to a “letter” of an alphabet. Under this model, each gesture is analogous to a “word” made up of a particular combination of window classes.

Abstract translation: 系统，设备和方法适应于自然语言处理中已建立的概念，用于手势识别算法。 手势识别系统包括传感器，处理器和存储用于执行手势识别的数据和/或指令的非暂时处理器可读存储器。 手势识别系统可以包括可穿戴姿势识别装置。 手势识别过程涉及将来自传感器的信号分割成数据窗口，将相应的“窗口类别”分配给每个数据窗口，以及基于相应的窗口类别序列来识别用户执行的手势。 每个窗口类仅仅表示至少一个数据窗口属性，并且类似于字母表的“字母”。 在这个模型下，每个手势类似于由窗口类的特定组合组成的“单词”。

公开(公告)号：US20150109202A1

公开(公告)日：2015-04-23

申请号：US14520081

申请日：2014-10-21

Applicant: Thalmic Labs Inc.

Inventor： Pedram Ataee ,  Idris S. Aleem ,  Matthew Bailey

IPC: G06F3/01

CPC classification number: G06F3/017 ,  A61B5/0488 ,  A61B5/681 ,  A61B5/7267 ,  A61B2562/063

Abstract: Systems, articles, and methods perform gesture identification with limited computational resources. A wearable electromyography (“EMG”) device includes multiple EMG sensors, an on-board processor, and a non-transitory processor-readable memory that stores data and/or processor-executable instructions for performing gesture identification. The wearable EMG device detects and determines features of signals when a user performs a physical gesture, and processes the features by performing a decision tree analysis. The decision tree analysis invokes a decision tree stored in the memory, where storing and executing the decision tree may be managed by limited computational resources. The outcome of the decision tree analysis is a probability vector that assigns a respective probability score to each gesture in a gesture library. The accuracy of the gesture identification may be enhanced by performing multiple iterations of the decision tree analysis across multiple time windows of the EMG signal data and combining the resulting probability vectors.

Abstract translation: 系统，文章和方法以有限的计算资源执行手势识别。 可穿戴肌电图（“EMG”）装置包括多个EMG传感器，车载处理器以及存储用于执行手势识别的数据和/或处理器可执行指令的非暂时处理器可读存储器。 可穿戴EMG设备检测并确定用户执行物理手势时的信号特征，并通过执行决策树分析来处理特征。 决策树分析调用存储在存储器中的决策树，其中可以通过有限的计算资源来管理决策树的存储和执行。 决策树分析的结果是向手势库中的每个姿态分配各自的概率分数的概率向量。 可以通过在EMG信号数据的多个时间窗口上执行决策树分析的多次迭代并组合所得到的概率向量来增强手势识别的准确性。