WO2017036147A1 - 一种基于生物电的控制方法、装置及控制器 - Google Patents
一种基于生物电的控制方法、装置及控制器 Download PDFInfo
- Publication number
- WO2017036147A1 WO2017036147A1 PCT/CN2016/079325 CN2016079325W WO2017036147A1 WO 2017036147 A1 WO2017036147 A1 WO 2017036147A1 CN 2016079325 W CN2016079325 W CN 2016079325W WO 2017036147 A1 WO2017036147 A1 WO 2017036147A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- finger
- surface electromyogram
- pressing operation
- signal
- finger type
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/015—Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/389—Electromyography [EMG]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
Definitions
- the invention relates to the technical field of natural human-computer interaction, in particular to a bioelectric-based control method, device and controller.
- the embodiment of the invention provides a bioelectric-based control method, device and controller, which are used to solve the problem of controlling the wearable device based on the traditional human-computer interaction mode existing in the prior art. Inconvenient and unnatural problems.
- a bioelectric based control method comprising:
- Feature extraction is performed on the collected surface electromyogram signals to obtain feature information
- the finger type recognition template includes a correspondence relationship between each finger type and feature information of a surface electromyogram signal corresponding to each finger type when a finger pressing operation occurs;
- the method before performing feature extraction on the collected surface EMG signals, the method further includes:
- Pre-processing and sampling processing of the acquired surface electromyogram signals including signal amplification and interference suppression.
- the method further includes:
- the correlation function corresponding to the finger type includes a function of a magnitude of a surface electromyogram signal generated when a finger pressing operation occurs for each finger type, and a pressing force;
- the surface electromyogram signal includes a plurality of channel sub-signals
- the amplitude of the surface electromyogram signal is determined by:
- a bioelectric based control device comprising:
- a collecting unit configured to collect a surface electromyogram signal generated when a user performs a finger pressing operation
- a feature extraction unit configured to perform feature extraction on the surface electromyogram signal collected by the acquisition unit, to obtain feature information
- a determining unit configured to determine, according to the pre-created finger type recognition template, the type of the finger used to generate the finger pressing operation corresponding to the feature information obtained by the feature extraction unit;
- the finger type recognition template includes a correspondence relationship between each finger type and feature information of a surface electromyogram signal corresponding to each finger type when a finger pressing operation occurs;
- control unit configured to map the finger type used by the determining unit to generate the finger pressing operation to a corresponding first instruction, and control the controlled device according to the first instruction.
- the device further includes:
- a preparation unit configured to perform pre-processing and sampling processing on the collected surface electromyogram signal before the feature extraction unit performs feature extraction on the surface electromyogram signal collected by the acquisition unit, where the pre-processing includes signal amplification And interference suppression.
- the determining unit is further configured to:
- the correlation function corresponding to the finger type includes a function of a magnitude of a surface electromyogram signal generated when a finger pressing operation occurs for each finger type, and a pressing force;
- the control unit is further configured to: map the finger type determined by the determining unit to the pressing force corresponding to the finger pressing operation, map to a corresponding second instruction, and perform a controlled operation on the controlled device according to the second instruction. control.
- the surface electromyogram signal includes a plurality of channel sub-signals
- the determining unit is specifically configured to determine the amplitude of the surface myoelectric signal in the following manner:
- a bioelectric based controller including a sensor, a processor, and a transceiver, wherein
- the sensor is configured to contact a muscle surface of a user's arm to collect a surface electromyogram signal generated when a user performs a finger pressing operation;
- the processor is configured to invoke a set of program codes, and perform the following operations according to the program code: performing feature extraction on the surface electromyogram signals collected by the sensor, obtaining feature information, and identifying the template according to the pre-created finger type Determining, by the obtained feature information, the type of the finger used to generate the finger pressing operation, and mapping the determined finger type used to generate the finger pressing operation to a corresponding first instruction, the first instruction being used for Control the controlled device;
- the finger type recognition template includes a correspondence relationship between each finger type and feature information of a surface electromyogram signal corresponding to each finger type when a finger pressing operation occurs;
- the transceiver is configured to send the first instruction obtained by the processor to the controlled device.
- the method further includes:
- a memory for storing program code executed by the processor.
- the processor is further configured to:
- the acquired surface electromyogram signals are pre-processed and sampled prior to feature extraction of the acquired surface electromyogram signals, including signal amplification and interference suppression.
- the processor is further configured to:
- the correlation function corresponding to the finger type includes a function of a magnitude of a surface electromyogram signal generated when a finger pressing operation occurs for each finger type, and a pressing force;
- the surface electromyogram signal includes a plurality of channel sub-signals
- the processor is specifically configured to determine the amplitude of the surface electromyogram signal in the following manner:
- the bioelectric-based control device collects the surface electromyogram signal generated when the user performs the finger pressing operation, and extracts the feature of the collected surface electromyogram signal to obtain the feature information according to the pre-created finger type. Identifying a template, determining the type of the finger used to generate the finger pressing operation corresponding to the obtained feature information, mapping the determined finger type used to generate the finger pressing operation to a corresponding first instruction, and according to the first The command controls the controlled device. In this way, by simply pressing on any physical interface, it is possible to control the controlled device such as a wearable device, without requiring a specific input device and an operation interface, and the operation is convenient, and is not affected by environmental factors such as time and space. And the control process is close to the real natural environment, and the controlled device is controlled in a more harmonious and natural human-computer interaction mode.
- FIG. 1 is a structural diagram of a bioelectric based controller according to a first embodiment of the present invention
- FIG. 2 is a flowchart of implementing a bioelectric-based control method according to Embodiment 2 of the present invention
- FIG. 3 is a schematic diagram of a sliding window processing process according to an embodiment of the present invention.
- FIG. 4 is a view showing an example of a relationship between a magnitude of a surface electromyogram signal and a pressing force according to an embodiment of the present invention
- FIG. 5 is a structural diagram of a bioelectric based control device according to a third embodiment of the present invention.
- the embodiment of the invention designs a bioelectric-based control method, device and controller.
- the corresponding muscle group When a user presses a finger, the corresponding muscle group generates a surface electromyogram signal due to tension and deformation, and the surface muscle is generated.
- the electrical signals are collected, processed, and analyzed to identify the type of finger used to perform the finger press operation, map the identified finger type to the corresponding command, and control the controlled device through the command.
- the controlled device may include any electronic device that can receive wired or wireless signals.
- the controlled device is a wearable device, for example, a smart watch, a smart bracelet, smart glasses, smart sports shoes, etc. .
- the first embodiment of the present invention provides a bioelectric-based controller (hereinafter referred to as a controller) 100 for performing the method flow of the second embodiment.
- FIG. 1 is a controller 100 according to an embodiment of the present invention. Schematic diagram of the configuration, as shown in FIG. 1, the controller 100 includes a sensor 110, a processor 130, and a transceiver 140, where
- the sensor 110 is configured to be connected to the muscle surface of the arm of the user, and collect a surface electromyogram signal generated when the user performs a finger pressing operation;
- the processor 130 is configured to invoke a set of program codes, and perform the following operations according to the program code: performing feature extraction on the surface electromyogram signals collected by the sensor 110 to obtain feature information according to the pre-created finger types. Identifying a template, determining the type of the finger used to generate the finger pressing operation corresponding to the obtained feature information, and determining the occurrence of the finger pressing operation The type of finger used is mapped to a corresponding first instruction, and the first instruction is used to control the controlled device;
- the finger type recognition template includes a correspondence relationship between each finger type and feature information of a surface electromyogram signal corresponding to each finger type when a finger pressing operation occurs;
- the transceiver 140 is configured to send the first instruction obtained by the processor 130 to the controlled device.
- the finger pressing operation is an operation of pressing a finger on any physical interface, such as a finger pressing a table, a finger pressing a key in the trouser pocket, a hand holding a water cup, and the like.
- a finger pressing a table a finger pressing a key in the trouser pocket
- a hand holding a water cup a hand holding a water cup
- the controller 100 in the first embodiment of the present invention is placed in a wearable device by means of a chip or the like, and the manufacturing material of the wearable device is not limited, and is placed around the arm of the user and closely attached to the muscle surface of the user's arm.
- the sensor 110 is placed on the inner side of the wearable device to contact the muscle surface of the arm to collect the surface electromyogram signal.
- the wearable device can be a wrist strap. Since the surface electromyography signal is a weak biosignal, the wristband is in close contact with the muscle surface of the user's arm, so that the sensor 110 in the controller 100 can effectively collect the surface electromyogram generated by the user when a finger press occurs. signal.
- the controller 100 further includes a memory 120 for storing program code executed by the processor 130.
- the processor 130 is further configured to:
- the acquired surface electromyogram signals are subjected to pre-processing and sampling processing, the pre-processing signal amplification and interference suppression.
- the processor 130 is further configured to:
- the correlation function corresponding to the finger type includes finger pressing for each finger type The relationship between the amplitude of the surface EMG signal generated during operation and the pressing force;
- the surface electromyogram signal includes multiple channel sub-signals
- the processor 130 is specifically configured to determine the amplitude of the surface myoelectric signal in the following manner:
- a controller closely attached to the muscle surface of the arm of the user when the user performs a finger pressing operation, a surface electromyogram signal can be collected, and the surface electromyogram signal is processed and analyzed, and mapped. Go to the instruction to control the controlled device.
- the controlled device such as a wearable device, without requiring a specific input device and an operation interface, and the operation is convenient, and is not affected by environmental factors such as time and space.
- the control process is close to the real natural environment, and the controlled device is controlled in a more harmonious and natural human-computer interaction mode.
- the second embodiment of the present invention provides a bioelectric-based control method
- FIG. 2 is a flow chart of the bioelectric-based control method according to the second embodiment of the present invention.
- the embodiment of the second embodiment of the present invention is a bioelectric based controller as described in the first embodiment above. As shown in FIG. 2, the method includes:
- Step 200 Collect a surface electromyogram signal generated when a user performs a finger pressing operation.
- the controlled device when the controlled device is in a state to be controlled, it can receive control device to control it, wherein the controlled state means that the controlled device can receive an instruction to implement an application, for example, when the controlled device is in the power-on state.
- An instruction can be received to implement an application or an operation that can be executed in standby mode; for example, when the controlled device starts an application, it can receive an instruction to implement an application or an operation that can be executed for one of the above applications.
- the controlled device When the controlled device is in a state to be controlled, the user performs a finger pressing operation, and a surface electromyographic signal is generated due to contraction of the arm muscle of the user, and a control device (such as a wrist) placed around the user's arm and closely fitting with the user's arm portion
- the belt will collect the generated surface EMG signals. Since an action is generally performed by multiple muscles, the controller expects to collect multiple surface EMG signals simultaneously.
- the controller collects multi-channel surface EMG through sensors placed at different muscle positions. signal.
- the finger pressing operation that occurs by the user is an operation of pressing a finger on any interface.
- pressing the key in the trouser pocket, the table top, the wall, other parts of the body, holding the cup, etc. can be any medium that can produce a useful surface EMG signal to the user's arm muscles.
- Step 210 Perform feature extraction on the collected surface electromyogram signals to obtain feature information.
- pre-processing and sampling processing are performed before feature extraction of the collected surface electromyogram signals.
- the pre-processing includes signal amplification and interference suppression.
- the surface electromyogram signal collected by the controller is the original surface electromyogram signal. Since the surface electromyogram signal is relatively weak, in the process of collecting, interference is inevitably introduced, which often makes a useful surface electromyogram signal. Submerged in noise. Therefore, the original surface EMG signal needs to be pre-processed.
- the embodiment of the present invention does not limit the pre-processing process, and mainly performs operations such as amplifying and suppressing the original surface EMG signal, and the interference suppression includes some filtering. Operation, such as power frequency filtering, high-pass filtering, and the like.
- sampling processing is performed on the surface electromyogram signal after the pretreatment.
- the sampling process may be a sliding window process.
- FIG. 3 is a schematic diagram of a sliding window processing process according to an embodiment of the present invention.
- the time t1 is taken as the sliding window width, and the time period t2 is the sampling interval for sampling the pre-processed surface electromyogram signal.
- the pre-processed surface myoelectric signal is divided into a plurality of time windows to form a window sequence.
- Feature extraction is the basis for the analysis of surface EMG signals.
- the surface EMG signals of each time window of each channel after pre-processing are extracted to obtain feature information.
- the embodiment of the present invention is described by taking a time domain analysis method as an example.
- the extracted feature information is: an absolute average value of the surface electromyogram signal (indicated by MAV) of each time window of each channel after preprocessing and the first three coefficients of the fourth-order autoregressive (AR) model A1, a2, a3.
- MAV surface electromyogram signal
- AR autoregressive
- the absolute average MAV is defined as:
- N represents the number of sampling points of the surface electromyogram signal of each time window of each channel after preprocessing
- X i represents the amplitude of the surface electromyogram signal of the i th sampling point.
- the AR model can be expressed as follows:
- X k represents the kth sampling point of the surface electromyogram signal of each time window of each channel after preprocessing
- X k-1 represents the k-1th sampling point
- N 4
- a i is the AR coefficient
- Step 220 Determine, according to the finger type recognition template created in advance, the type of the finger used to generate the finger pressing operation corresponding to the obtained feature information.
- the finger type recognition template includes a correspondence relationship between each finger type and feature information of a surface electromyogram signal corresponding to a finger pressing operation of each finger type.
- the finger type identification template is created in advance for the controlled device, and the specific process is:
- the user can determine the pressing force according to his own pressing habit, and perform button simulation on the physical interface with the same or similar pressing force. In practical applications, the user also performs a pressing operation with the pressing force of the same or similar pressing force.
- the obtained feature information is the absolute average value of the surface myoelectric signals of the respective time windows of the respective channels after preprocessing and the first three coefficients a1, a2, and a3 of the fourth-order AR model.
- a correspondence relationship between feature information of the surface electromyogram corresponding to each finger type and each finger type is used as the finger type recognition template.
- the feature information obtained in step 210 is dimension-reduced by linear discriminant analysis or other methods, and then according to the above-mentioned pre-created finger type recognition template, the support vector machine or other classifier is used to classify the dimension-reduced feature information to identify The type of finger used for the finger press operation.
- Step 230 Map the determined finger type used to generate the finger pressing operation to a corresponding first instruction, and control the controlled device according to the first instruction.
- the first instruction is transmitted to an external controlled device by wire or wirelessly, and the wireless manner includes but is not limited to one of Wireless Fidelity (WiFi), Bluetooth, ZigBee (Zigbee Protocol) or Any combination of several.
- WiFi Wireless Fidelity
- Bluetooth ZigBee
- ZigBee Protocol Zigbee Protocol
- the controller before the controller is used to control the controlled device, in addition to creating the finger type identification template for the controlled device in advance, it is also required to establish a mapping relationship between each finger type and the corresponding instruction to control the controlled device by using the instruction. .
- the controlled device is a smart watch
- the instruction mapped to the right index finger is to open the WeChat application
- the command mapped to the right middle finger is to turn on the camera.
- the controller collects the surface electromyogram signal generated by the muscle surface of the right arm of the user, and recognizes the finger used for the pressing operation by processing and analyzing the surface electromyogram signal.
- the right index finger it maps to the instruction to open the WeChat application, and controls the smart watch to open the WeChat application.
- the above method only describes the surface electromyogram signal generated by the pressing operation of collecting one finger, Mapping to the process of controlling the controlled device in the instruction.
- any finger type identification template when at least two finger types are pressed against the physical interface may be created, and any at least two finger types described above may be established.
- the surface electromyogram signal generated by the pressing operation of any of the at least two fingers is mapped to the command to control the controlled device.
- the controlled device is controlled by the finger type mapping to the command.
- the finger type and the pressing force are also mapped to the command control device.
- the correlation function corresponding to the finger type includes a relationship between a magnitude of a surface electromyogram signal generated when a finger pressing operation occurs for each finger type, and a pressing force.
- the surface electromyogram signal includes a plurality of channel sub-signals
- the amplitude of the surface electromyogram signal is determined by:
- the average is used as the amplitude of the surface myoelectric signal.
- the controller Before using the controller to control the controlled device, it is also required to create a correlation function corresponding to the finger type for the controlled device in advance, and establish a mapping relationship between each finger type, pressing force, and corresponding instruction to pass the instruction. Control the controlled device.
- the above is the creation process of the correlation function corresponding to the finger type.
- the magnitude of the surface electromyogram signal and the pressing force are a power function relationship.
- FIG. 4 it is an image of the relationship between the amplitude of the surface myoelectric signal generated by a user's right middle finger during the pressing operation and the pressing force in the actual application of the embodiment of the present invention.
- the finger type determined in step 230 is combined with the pressing force corresponding to the finger pressing operation, and mapped to a corresponding second instruction, and the controlled device is controlled according to the second instruction.
- the controlled device is smart glasses
- the right thumb is defined as the left shift of the cursor
- the right hand little finger is defined as the right shift of the cursor
- the pressing force is defined as the displacement amount of the cursor movement.
- the controller collects the surface electromyogram signal generated by the muscle surface of the right arm of the user, and through the processing and analysis of the surface electromyogram signal, recognizes that the finger used for the pressing operation is the right hand little finger, and if the pressing force is obtained, the right hand little finger is And the pressing force maps to the right shift of the cursor by a certain amount of displacement.
- the controller closely attached to the muscle surface of the arm of the user, when the user performs a finger pressing operation, the surface electromyogram signal can be collected, and the surface electromyogram signal is processed and analyzed, and mapped. Go to the instruction to control the controlled device.
- the controlled device such as a wearable device, without requiring a specific input device and an operation interface, and the operation is convenient, and is not affected by environmental factors such as time and space.
- the control process is close to the real natural environment, and the controlled device is controlled in a more harmonious and natural human-computer interaction manner.
- the third embodiment of the present invention provides a bioelectric-based control device (hereinafter referred to as a control device) 510.
- a control device 510 includes an acquisition unit 520, a feature extraction unit 530, a determination unit 540, and a control unit 550.
- the collecting unit 520 is configured to collect a surface electromyogram signal generated when a user performs a finger pressing operation
- the finger pressing operation is an operation of pressing a finger on any interface.
- the feature extraction unit 530 is configured to perform feature extraction on the surface electromyogram signal collected by the acquisition unit 520 to obtain feature information.
- a determining unit 540 configured to determine, according to the finger type identification template created in advance, the type of the finger used to generate the finger pressing operation corresponding to the feature information obtained by the feature extracting unit 530;
- the finger type recognition template includes a correspondence relationship between each finger type and feature information of a surface electromyogram signal corresponding to each finger type when a finger pressing operation occurs;
- the control unit 550 is configured to map the finger type used by the determining unit 540 to generate the finger pressing operation to a corresponding first instruction, and control the controlled device according to the first instruction.
- the device further includes:
- the preparation unit 560 is configured to perform pre-processing and sampling processing on the collected surface myoelectric signals before the feature extraction unit 530 performs feature extraction on the collected surface electromyogram signals.
- the determining unit 540 is further configured to:
- the correlation function corresponding to the finger type includes a function of a magnitude of a surface electromyogram signal generated when a finger pressing operation occurs for each finger type, and a pressing force;
- the control unit 550 is further configured to map the finger type determined by the determining unit 540 to the corresponding second command according to the pressing force corresponding to the finger pressing operation, and according to the The second instruction controls the controlled device.
- the surface electromyogram signal includes multiple channel sub-signals
- the determining unit 540 is specifically configured to determine the amplitude of the surface myoelectric signal in the following manner:
- a surface electromyogram signal can be collected, and the surface electromyogram signal is processed and analyzed, and mapped. Go to the instruction to control the controlled device.
- the controlled device such as a wearable device, without requiring a specific input device and an operation interface, and the operation is convenient, and is not affected by environmental factors such as time and space.
- the control process is close to the real natural environment, and the controlled device is controlled in a more harmonious and natural human-computer interaction manner.
- embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
- computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
- the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
- the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
- These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
- the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Neurosurgery (AREA)
- Neurology (AREA)
- Dermatology (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
一种基于生物电的控制方法、装置及控制器，用以提高人机交互的自然性。该方法为：采集当用户发生手指按压操作时产生的表面肌电信号（200），针对采集到的表面肌电信号进行特征提取，获得特征信息（210），根据预先创建的手指种类识别模板，确定获得的特征信息对应的发生所述手指按压操作所使用的手指种类（220），将确定的发生所述手指按压操作所使用的手指种类映射到相应的第一指令，并按照所述第一指令对被控设备进行控制（230）。可实现以更和谐、自然的人机交互方式实现对被控设备的控制。
Description
本申请要求在2015年8月28日提交中国专利局、申请号为201510543246.8、发明名称为“一种基于生物电的控制方法、装置及控制器”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
本发明涉及自然人机交互技术领域，特别涉及一种基于生物电的控制方法、装置及控制器。
伴随着互联网技术的发展，人机交互方式也在不断的进步，现在广泛使用的人机交互方式大多数是基于键盘和触屏的。但是，随着可穿戴设备的不断普及，传统的基于键盘和触屏的人机交互方式受到了挑战。基于键盘和触屏的人机交互方式必须要依赖于特定的输入设备和操作界面，而可穿戴设备一般比较小巧，且大多数都没有操作界面，因此，利用传统的人机交互方式对可穿戴设备进行控制显得十分不自然，且操作不方便。
目前，更和谐、自然的人机交互方式正引起学界和工业界等各界的广泛关注，它更能利用人的意图进行交互，更具有意图感知能力，更强调交互方式的自然性，人机关系的和谐性。实物人机交互界面主张“回归真实世界”，将真实世界和数字世界有机的结合在一起。
综上所述，现有技术中，基于传统的人机交互方式对可穿戴设备进行控制时，操作不方便，不自然，且远离真实的自然环境，不能实现以更自然友好的交互方式对可穿戴设备进行控制。
发明内容
本发明实施例提供一种基于生物电的控制方法、装置及控制器，用以解决现有技术中存在的基于传统的人机交互方式对可穿戴设备进行控制时，操
作不方便且不自然的问题。
本发明实施例提供的具体技术方案如下：
第一方面，提供一种基于生物电的控制方法，包括：
采集当用户发生手指按压操作时产生的表面肌电信号；
针对采集到的表面肌电信号进行特征提取，获得特征信息；
根据预先创建的手指种类识别模板，确定获得的特征信息对应的发生所述手指按压操作所使用的手指种类；
其中，所述手指种类识别模板包含每一个手指种类、以及每一个手指种类发生手指按压操作时对应的表面肌电信号的特征信息的对应关系；
将确定的发生所述手指按压操作所使用的手指种类映射到相应的第一指令，并按照所述第一指令对被控设备进行控制。
结合第一方面，在第一方面的第一种可能的实现方式中，针对采集到的表面肌电信号进行特征提取之前，还包括：
对采集到的表面肌电信号进行预处理和采样处理，所述预处理包括信号放大以及干扰抑制。
结合第一方面或第一方面的第一种可能的实现方式，在第一方面的第二种可能的实现方式中，在确定发生所述手指按压操作所使用的手指种类之后，还包括：
基于采集到的表面肌电信号的幅值、以及预先创建的手指种类对应的相关函数，确定所述手指按压操作对应的按压力度；
其中，所述手指种类对应的相关函数包含每一个手指种类发生手指按压操作时产生的表面肌电信号的幅值、以及按压力度之间的函数关系；
将确定的所述手指种类结合所述手指按压操作对应的按压力度，映射到相应的第二指令，并按照所述第二指令对被控设备进行控制。
结合第一方面的第二种可能的实现方式，在第一方面的第三种可能的实现方式中，所述表面肌电信号包括多个通道子信号；
所述表面肌电信号的幅值，由下述方式确定：
将采集到的表面肌电信号包括的各个通道子信号的信号幅值进行累加平均计算，获得所述表面肌电信号的平均信号幅值，将所述平均信号幅值作为所述表面肌电信号的幅值。
第二方面，提供一种基于生物电的控制装置，包括：
采集单元，用于采集当用户发生手指按压操作时产生的表面肌电信号；
特征提取单元，用于针对所述采集单元采集到的表面肌电信号进行特征提取，获得特征信息；
确定单元，用于根据预先创建的手指种类识别模板，确定所述特征提取单元获得的特征信息对应的发生所述手指按压操作所使用的手指种类；
其中，所述手指种类识别模板包含每一个手指种类、以及每一个手指种类发生手指按压操作时对应的表面肌电信号的特征信息的对应关系；
控制单元，用于将所述确定单元确定的发生所述手指按压操作所使用的手指种类映射到相应的第一指令，并按照所述第一指令对被控设备进行控制。
结合第二方面，在第二方面的第一种可能的实现方式中，所述装置还包括：
准备单元，用于在所述特征提取单元针对所述采集单元采集到的表面肌电信号进行特征提取之前，对采集到的表面肌电信号进行预处理和采样处理，所述预处理包括信号放大以及干扰抑制。
结合第二方面或第二方面的第一种可能的实现方式，在第二方面的第二种可能的实现方式中，所述确定单元还用于：
基于所述采集单元采集到的表面肌电信号的幅值、以及预先创建的手指种类对应的相关函数，确定所述手指按压操作对应的按压力度；
其中，所述手指种类对应的相关函数包含每一个手指种类发生手指按压操作时产生的表面肌电信号的幅值、以及按压力度之间的函数关系；
所述控制单元还用于，将所述确定单元确定的所述手指种类结合所述手指按压操作对应的按压力度，映射到相应的第二指令，并按照所述第二指令对被控设备进行控制。
结合第二方面的第二种可能的实现方式，在第二方面的第三种可能的实现方式中，所述表面肌电信号包括多个通道子信号；
所述确定单元具体用于按下述方式确定所述表面肌电信号的幅值：
将采集到的表面肌电信号包括的各个通道子信号的信号幅值进行累加平均计算，获得所述表面肌电信号的平均信号幅值，将所述平均信号幅值作为所述表面肌电信号的幅值。
第三方面，提供一种基于生物电的控制器，包括传感器、处理器和收发器，其中，
所述传感器，用于与用户的臂部肌肉表面相接触，以采集当用户发生手指按压操作时产生的表面肌电信号；
所述处理器，用于调用一组程序代码，并按照所述程序代码执行以下操作：针对所述传感器采集到的表面肌电信号进行特征提取，获得特征信息，根据预先创建的手指种类识别模板，确定获得的特征信息对应的发生所述手指按压操作所使用的手指种类，以及将确定的发生所述手指按压操作所使用的手指种类映射到相应的第一指令，所述第一指令用于对被控设备进行控制；
其中，所述手指种类识别模板包含每一个手指种类、以及每一个手指种类发生手指按压操作时对应的表面肌电信号的特征信息的对应关系；
所述收发器，用于发送所述处理器获得的所述第一指令给被控设备。
结合第三方面，在第三方面的第一种可能的实现方式中，还包括：
存储器，用于存储所述处理器执行的程序代码。
结合第三方面或第三方面的第一种可能的实现方式，在第三方面的第二种可能的实现方式中，所述处理器还用于：
在针对采集到的的表面肌电信号进行特征提取之前，对采集到的表面肌电信号进行预处理和采样处理，所述预处理包括信号放大以及干扰抑制。
结合第三方面和第三方面的第一种至第二种可能的实现方式中的任意一种，在第三方面的第三种可能的实现方式中，所述处理器还用于：
基于采集到的表面肌电信号的幅值、以及预先创建的手指种类对应的相
关函数，确定所述手指按压操作对应的按压力度；
其中，所述手指种类对应的相关函数包含每一个手指种类发生手指按压操作时产生的表面肌电信号的幅值、以及按压力度之间的函数关系；
将确定的所述手指种类结合所述手指按压操作对应的按压力度，映射到相应的第二指令，所述第二指令用于对被控设备进行控制。
结合第三方面的第三种可能的实现方式，在第三方面的第四种可能的实现方式中，所述表面肌电信号包括多个通道子信号；
所述处理器具体用于按下述方式确定所述表面肌电信号的幅值：
将采集到的表面肌电信号包括的各个通道子信号的信号幅值进行累加平均计算，获得所述表面肌电信号的平均信号幅值，将所述平均信号幅值作为所述表面肌电信号的幅值。
本发明实施例中，基于生物电的控制装置采集当用户发生手指按压操作时产生的表面肌电信号，并对采集到的表面肌电信号进行特征提取，获得特征信息，根据预先创建的手指种类识别模板，确定获得的特征信息对应的发生所述手指按压操作所使用的手指种类，将确定的发生所述手指按压操作所使用的手指种类映射到相应的第一指令，并按照所述第一指令对被控设备进行控制。这样，通过简单地对任意实物界面的按压操作，即可实现对可穿戴设备等被控设备进行控制，不需要特定的输入设备和操作界面，操作方便，不受时间空间地点等环境因素的影响，且控制过程接近真实的自然环境，实现了以更和谐、更自然的人机交互方式来对被控设备进行控制。
图1为本发明实施例一中基于生物电的控制器结构图；
图2为本发明实施例二中基于生物电的控制方法实现流程图；
图3为本发明实施例中滑动窗处理过程的示意图；
图4为本发明实施例表面肌电信号的幅值与按压力度之间的关系示例图；
图5为本发明实施例三中基于生物电的控制装置结构图。
为了使本发明的目的、技术方案和优点更加清楚，下面将结合附图对本发明作进一步地详细描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。
本发明实施例设计了一种基于生物电的控制方法、装置及控制器，利用当用户发生手指按压操作时，相应的肌肉群由于紧张和形变会产生表面肌电信号，通过对产生的表面肌电信号进行采集、处理以及分析，识别出发生手指按压操作所使用的手指类型，将识别出来的手指类型映射到相应的指令，通过指令对被控设备进行控制。
本发明实施例涉及的被控设备可包括任意可接收有线或无线信号的电子设备，较佳地，被控设备为可穿戴设备，例如，智能手表、智能手环、智能眼镜、智能运动鞋等。
本发明以下将结合具体实施例对本发明实施例提供的基于生物电的控制方法、装置及控制器，进行详细说明。
实施例一
本发明实施例一提供一种基于生物电的控制器(以下简称控制器)100，该控制器100用于执行后续实施例二涉及的方法流程，图1为本发明实施例提供的控制器100的构成示意图，如图1所示，该控制器100包括传感器110、处理器130和收发器140，其中，
所述传感器110，用于与用户的臂部肌肉表面相连，采集当用户发生手指按压操作时产生的表面肌电信号；
所述处理器130，用于调用一组程序代码，并按照所述程序代码执行以下操作：针对所述传感器110采集到的表面肌电信号进行特征提取，获得特征信息，根据预先创建的手指种类识别模板，确定获得的特征信息对应的发生所述手指按压操作所使用的手指种类，以及将确定的发生所述手指按压操作
所使用的手指种类映射到相应的第一指令，所述第一指令用于对被控设备进行控制；
其中，所述手指种类识别模板包含每一个手指种类、以及每一个手指种类发生手指按压操作时对应的表面肌电信号的特征信息的对应关系；
所述收发器140，用于将所述处理器130获得的所述第一指令向被控设备发送。
较佳地，所述手指按压操作为手指按压任意实物界面的操作，比如手指按压桌子，手指按压裤兜内的钥匙，手握水杯等。这使得本发明实施例提供的人机交互方式更接近自然。
本发明实施例一中的控制器100通过芯片等方式置于一种可穿戴设备中，该可穿戴设备的制作材料不限，置于用户的臂部周围，且与用户臂部肌肉表面紧密贴合，传感器110需置于该可穿戴设备的内侧，以与臂部肌肉表面接触，采集表面肌电信号。例如，该可穿戴设备可以为一种腕带。由于表面肌电信号是一种微弱的生物信号，腕带与用户的臂部肌肉表面紧密贴合，可以使控制器100中的传感器110有效地采集到用户在发生手指按压时产生的表面肌电信号。
结合上述实施例一，在第一种可能的实现方式中，控制器100还包括存储器120，用于存储处理器130执行的程序代码。
结合上述实施例一或者第一种可能的实现方式，在第二种可能的实现方式中，所述处理器130还用于：
在针对采集到的表面肌电信号进行特征提取之前，对采集到的表面肌电信号进行预处理和采样处理，所述预处理信号放大以及干扰抑制。
结合上述实施例一、第一种至第二种可能的实现方式中的任意一种，在第三种可能的实现方式中，所述处理器130还用于：
基于采集到的表面肌电信号的幅值、以及预先创建的手指种类对应的相关函数，确定所述手指按压操作对应的按压力度；
其中，所述手指种类对应的相关函数包含每一个手指种类发生手指按压
操作时产生的表面肌电信号的幅值、以及按压力度之间的函数关系；
将确定的所述手指种类结合所述手指按压操作对应的按压力度，映射到相应的第二指令，所述第二指令用于对被控设备进行控制。
结合上述实施例一的第三种可能的实现方式，在第四种可能的实现方式中，所述表面肌电信号包括多个通道子信号；
所述处理器130具体用于按下述方式确定所述表面肌电信号的幅值：
将采集到的表面肌电信号包括的各个通道子信号的信号幅值进行累加平均计算，获得所述表面肌电信号的平均信号幅值，将所述平均信号幅值作为所述表面肌电信号的幅值。
本发明实施例一中，通过与用户的臂部肌肉表面紧密贴合的控制器，当用户发生手指按压操作时，可以采集到表面肌电信号，对表面肌电信号进行处理与分析，并映射到指令，以对被控设备进行控制。这样，通过简单地对任意实物界面的按压操作，即可实现对可穿戴设备等被控设备进行控制，不需要特定的输入设备和操作界面，操作方便，不受时间空间地点等环境因素的影响，且控制过程接近真实的自然环境，实现了以更和谐、更自然的人机交互方式来对被控设备进行控制。
实施例二、
基于上述实施例一提供的基于生物电的控制器，本发明实施例二提供一种基于生物电的控制方法，图2为本发明实施例二提供的基于生物电的控制方法实现流程图，本发明实施例二的执行主体为如上述实施例一所述的基于生物电的控制器，如图2所示，该方法包括：
步骤200：采集当用户发生手指按压操作时产生的表面肌电信号。
实际应用中，被控设备处于待控状态时，能够接收控制装置对其进行控制，其中，待控状态是指被控设备可以接收指令来实现某一应用，例如，被控设备处于开机状态时，可以接收指令来实现在待机时能够执行的应用或者操作；又例如，被控设备开启某一应用程序时，可以接收指令来实现针对上述某一应用程序能够执行的应用或者操作。
在被控设备处于待控状态时，用户发生手指按压操作，由于用户臂部肌肉发生收缩会产生表面肌电信号，置于用户臂部周围且与用户臂部紧密贴合的控制装置(例如腕带)会采集产生的表面肌电信号。由于一个动作一般是由多个肌肉共同作用完成的，控制器期望同时采集多路表面肌电信号，当发生手指按压操作时，控制器通过置于不同肌肉位置的传感器采集到多通道表面肌电信号。
其中，用户发生的手指按压操作为手指按压任意界面的操作。比如，按压裤兜中的钥匙，桌面，墙壁，身体的其他部位，手握水杯，等等，只要能使用户的臂部肌肉产生有用的表面肌电信号的任意介质皆可。
步骤210：针对采集到的表面肌电信号进行特征提取，获得特征信息。
较佳地，在对采集到的表面肌电信号进行特征提取之前，进行预处理和采样处理。所述预处理包括信号放大以及干扰抑制。
在步骤200中，控制器采集到的表面肌电信号为原始表面肌电信号，由于表面肌电信号比较微弱，在采集的过程中，不可避免的会引入干扰，常会使有用的表面肌电信号淹没在噪声中。因此，需要对采集到的原始表面肌电信号进行预处理，本发明实施例对预处理的过程不进行限制，主要是对原始表面肌电信号进行放大、干扰抑制等操作，干扰抑制包括一些滤波操作，例如工频滤波、高通滤波等。
接着，在针对预处理后的表面肌电信号进行采样处理。所述采样处理可以是滑动窗处理。
如图3所示为本发明实施例中滑动窗处理过程的示意图。
以时间t1作为滑动窗宽度，以时间段t2为针对预处理后的表面肌电信号进行采样的采样间隔，这样，预处理后的表面肌电信号被分割成多个时间窗口，形成窗口序列。
特征提取是对表面肌电信号进行分析的基础，针对预处理后的各个通道的各个时间窗口的表面肌电信号进行特征提取，获得特征信息。特征提取的方法有很多种，本发明实施例以时域分析方法为例进行说明。
较佳地，提取的特征信息为：预处理后的各个通道的各个时间窗口的表面肌电信号的绝对平均值(用MAV表示)和4阶自回归(AutoRegressive，AR)模型的前3个系数a1、a2、a3。
其中，绝对平均值MAV定义为：
N代表预处理后的各个通道的各个时间窗口的表面肌电信号的采样点的个数，Xi代表第i个采样点的表面肌电信号的幅值。
AR模型可表示如下：
Xk表示预处理后的各个通道的各个时间窗口的表面肌电信号第k个采样点，Xk-1表示第k-1个采样点，N＝4，ai为AR系数，i＝1、2……N，ek为残差白噪声。
步骤220：根据预先创建的手指种类识别模板，确定获得的特征信息对应的发生所述手指按压操作所使用的手指种类。
其中，所述手指种类识别模板包含每一个手指种类、以及每一个手指种类发生手指按压操作时对应的表面肌电信号的特征信息的对应关系。
具体地，在使用控制器对被控设备控制之前，预先针对被控设备创建手指种类识别模板，具体过程为：
1)采集用户以任意一个手指在实物界面上进行按键模拟时产生的表面肌电信号。
其中，用户可根据自己的按压习惯确定按压力度，以相同或相近的按压力度在实物界面上进行按键模拟。在实际应用中，用户也以上述按压力度相同或相近的按压力度进行按压操作。
2)针对采集到的表面肌电信号进行信号放大、工频滤波、高通滤波等预
处理。
3)针对预处理后的表面肌电信号进行采样，将每个通道的表面肌电信号分成了多个时间窗口，并对各通道各时间窗口的表面肌电信号进行特征提取，获得特征信息。
获得的特征信息为：预处理后的各个通道的各个时间窗口的表面肌电信号的绝对平均值和4阶AR模型的前3个系数a1、a2、a3。
将每一个手指种类、以及每一个手指种类发生手指按压操作时对应的表面肌电信号的特征信息的对应关系作为手指种类识别模板。
以上是手指种类识别模板的创建过程。
将步骤210中获得的特征信息通过线性判别分析或其他方法进行降维，然后根据上述预先创建的手指种类识别模板，应用支持向量机或其他分类器将降维后的特征信息进行分类，从而识别出发生手指按压操作所使用的手指种类。
步骤230：将确定的发生所述手指按压操作所使用的手指种类映射到相应的第一指令，并按照所述第一指令对被控设备进行控制。
其中，将第一指令通过有线或无线的方式传输给外部的被控设备，无线方式包括但不限于无线保真(Wireless Fidelity，WiFi)、蓝牙、ZigBee(紫蜂协议)中的其中一种或任意几种的结合。
具体地，在使用控制器对被控设备控制之前，除了预先针对被控设备创建手指种类识别模板，还需建立每一个手指种类与相应的指令的映射关系，以通过指令对被控设备进行控制。
例如，被控设备为智能手表，右手食指映射到的指令为打开微信应用，右手中指映射到的指令是打开摄像头。在智能手表待机状态时，用户发生手指按压操作时，控制器采集用户右部臂部肌肉表面产生的表面肌电信号，并通过对表面肌电信号的处理分析，识别出按压操作所使用的手指为右手食指，则映射到打开微信应用的指令，控制智能手表打开微信应用。
此外，上述方法仅叙述了采集一个手指的按压操作所产生表面肌电信号，
映射到指令对被控设备进行控制的过程，实际应用中，根据需求，可以在使用之前，创建任意至少两个手指种类按压实物界面时的手指种类识别模板，并建立上述任意至少两个手指种类与相应的指令的映射关系，通过采集上述任意至少两个手指的按压操作所产生的表面肌电信号，映射到指令对被控设备进行控制。
上述实施例叙述了通过手指种类映射到指令控制被控设备，本发明实施例中，还可将手指种类结合按压力度映射到指令控制被控设备。
具体过程为：
S1、在上述步骤220中确定发生所述手指按压操作所使用的手指种类之后，基于预处理后的表面肌电信号的幅值、以及预先创建的手指种类对应的相关函数，确定所述手指按压操作对应的按压力度；
其中，所述手指种类对应的相关函数包含每一个手指种类发生手指按压操作时产生的表面肌电信号的幅值、以及按压力度之间的函数关系。
所述表面肌电信号包括多个通道子信号；
所述表面肌电信号的幅值，由下述方式确定：
将采集到的(较佳地为预处理后的)表面肌电信号包括的各个通道子信号的信号幅值进行累加平均计算，获得所述表面肌电信号的平均信号幅值，将所述平均信号幅值作为所述表面肌电信号的幅值。
具体地，在使用控制器对被控设备控制之前，还需要预先针对被控设备创建手指种类对应的相关函数，以及建立每一个手指种类、按压力度，与相应的指令的映射关系，以通过指令对被控设备进行控制。
创建手指种类对应的相关函数的具体过程为：
1)采集用户以任意一个手指且按压力度从小到大在实物界面上进行按键模拟时产生的表面肌电信号。
2)针对采集到的表面肌电信号进行信号放大、工频滤波、高通滤波等预处理。
3)将预处理后的各个通道的表面肌电信号的幅值进行累加平均，并对累
加平均处理后的表面肌电信号进行拟合分析，得到上述任意一个手指种类发生手指按压操作时产生的表面肌电信号的幅值、以及按压力度之间的函数关系。
以上是手指种类对应的相关函数的创建过程。
现有的分析表明，肌肉的紧张程度与产生的表面肌电信号的幅值之间存在良好的线性关系，肌肉的紧张程度与手指按压操作的按压力度正相关，因此，按压力度与表面肌电信号的幅值之间也必然存在良好的线性关系。
本发明实施例中，通过对大量数据的拟合分析发现，表面肌电信号的幅值与按压力度之间为幂函数关系。如图4所示，为本发明实施例实际应用中某一用户右手中指在按压操作时产生的表面肌电信号的幅值与按压力度之间的关系图像。
S2、将步骤230中确定的所述手指种类结合所述手指按压操作对应的按压力度，映射到相应的第二指令，并按照所述第二指令对被控设备进行控制。
例如，被控设备为智能眼镜，右手拇指定义为光标的左移，右手小指定义为光标的右移，按压力度定义为光标移动的位移量，在智能眼镜处于待控状态时，用户发生手指按压操作，控制器采集用户右部臂部肌肉表面产生的表面肌电信号，并通过对表面肌电信号的处理分析，识别出按压操作使用的手指为右手小指，且得到按压力度，则将右手小指以及按压力度映射到光标右移一定的位移量。
本发明实施例二中，通过与用户的臂部肌肉表面紧密贴合的控制器，当用户发生手指按压操作时，可以采集到表面肌电信号，对表面肌电信号进行处理与分析，并映射到指令，以对被控设备进行控制。这样，通过简单地对任意实物界面的按压操作，即可实现对可穿戴设备等被控设备进行控制，不需要特定的输入设备和操作界面，操作方便，不受时间空间地点等环境因素的影响，且控制过程接近真实的自然环境，实现以更和谐、更自然的人机交互方式对被控设备进行控制。通过手指种类结合按压力度共同映射到指令，可以使输出的指令为连续状态。
实施例三、
基于上述实施例一和上述实施例二，本发明实施例三提供一种基于生物电的控制装置(以下简称控制装置)510，图5为本发明实施例三提供的控制装置510的构成示意图，如图5所示，该控制装置510包括采集单元520、特征提取单元530、确定单元540，以及控制单元550。
采集单元520，用于采集当用户发生手指按压操作时产生的表面肌电信号；
其中，所述手指按压操作为手指按压任意界面的操作。
特征提取单元530，用于针对所述采集单元520采集到的表面肌电信号进行特征提取，获得特征信息；
确定单元540，用于根据预先创建的手指种类识别模板，确定所述特征提取单元530获得的特征信息对应的发生所述手指按压操作所使用的手指种类；
其中，所述手指种类识别模板包含每一个手指种类、以及每一个手指种类发生手指按压操作时对应的表面肌电信号的特征信息的对应关系；
控制单元550，用于将所述确定单元540确定的发生所述手指按压操作所使用的手指种类映射到相应的第一指令，并按照所述第一指令对被控设备进行控制。
结合上述实施例三，在第一种可能的实现方式中，所述装置还包括：
准备单元560，用于在所述特征提取单元530针对采集到的表面肌电信号进行特征提取之前，对采集到的表面肌电信号进行预处理和采样处理。
结合上述实施例三以及第一种可能的实现方式，在第二种可能的实现方式中，所述确定单元540还用于：
基于所述采集单元520采集到的表面肌电信号的幅值、以及预先创建的手指种类对应的相关函数，确定所述手指按压操作对应的按压力度；
其中，所述手指种类对应的相关函数包含每一个手指种类发生手指按压操作时产生的表面肌电信号的幅值、以及按压力度之间的函数关系；
所述控制单元550还用于，将所述确定单元540确定的所述手指种类结合所述手指按压操作对应的按压力度，映射到相应的第二指令，并按照所述
第二指令对被控设备进行控制。
结合第三种可能的实现方式，在第四种可能的实现方式中，所述表面肌电信号包括多个通道子信号；
所述确定单元540具体用于按下述方式确定所述表面肌电信号的幅值：
将采集到的表面肌电信号包括的各个通道子信号的信号幅值进行累加平均计算，获得所述表面肌电信号的平均信号幅值，将所述平均信号幅值作为所述表面肌电信号的幅值。
本发明实施例三中，通过与用户的臂部肌肉表面紧密贴合的控制装置，当用户发生手指按压操作时，可以采集到表面肌电信号，对表面肌电信号进行处理与分析，并映射到指令，以对被控设备进行控制。这样，通过简单地对任意实物界面的按压操作，即可实现对可穿戴设备等被控设备进行控制，不需要特定的输入设备和操作界面，操作方便，不受时间空间地点等环境因素的影响，且控制过程接近真实的自然环境，实现以更和谐、更自然的人机交互方式对被控设备进行控制。
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本发明的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例作出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本发明范围的所有变更和修改。
显然，本领域的技术人员可以对本发明实施例进行各种改动和变型而不脱离本发明实施例的精神和范围。这样，倘若本发明实施例的这些修改和变型属于本发明权利要求及其等同技术的范围之内，则本发明也意图包含这些改动和变型在内。
Claims (13)
- 一种基于生物电的控制方法，其特征在于，包括：采集当用户发生手指按压操作时产生的表面肌电信号；针对采集到的表面肌电信号进行特征提取，获得特征信息；根据预先创建的手指种类识别模板，确定获得的特征信息对应的发生所述手指按压操作所使用的手指种类；其中，所述手指种类识别模板包含每一个手指种类、以及每一个手指种类发生手指按压操作时对应的表面肌电信号的特征信息的对应关系；将确定的发生所述手指按压操作所使用的手指种类映射到相应的第一指令，并按照所述第一指令对被控设备进行控制。
- 如权利要求1所述的方法，其特征在于，针对采集到的表面肌电信号进行特征提取之前，还包括：对采集到的表面肌电信号进行预处理和采样处理，所述预处理包括信号放大以及干扰抑制。
- 如权利要求1或2所述的方法，其特征在于，在确定发生所述手指按压操作所使用的手指种类之后，还包括：基于采集到的表面肌电信号的幅值、以及预先创建的手指种类对应的相关函数，确定所述手指按压操作对应的按压力度；其中，所述手指种类对应的相关函数包含每一个手指种类发生手指按压操作时产生的表面肌电信号的幅值、以及按压力度之间的函数关系；将确定的所述手指种类结合所述手指按压操作对应的按压力度，映射到相应的第二指令，并按照所述第二指令对被控设备进行控制。
- 如权利要求3所述的方法，其特征在于，所述表面肌电信号包括多个通道子信号；所述表面肌电信号的幅值，由下述方式确定：将采集到的表面肌电信号包括的各个通道子信号的信号幅值进行累加平 均计算，获得所述表面肌电信号的平均信号幅值，将所述平均信号幅值作为所述表面肌电信号的幅值。
- 一种基于生物电的控制装置，其特征在于，包括：采集单元，用于采集当用户发生手指按压操作时产生的表面肌电信号；特征提取单元，用于针对所述采集单元采集到的表面肌电信号进行特征提取，获得特征信息；确定单元，用于根据预先创建的手指种类识别模板，确定所述特征提取单元获得的特征信息对应的发生所述手指按压操作所使用的手指种类；其中，所述手指种类识别模板包含每一个手指种类、以及每一个手指种类发生手指按压操作时对应的表面肌电信号的特征信息的对应关系；控制单元，用于将所述确定单元确定的发生所述手指按压操作所使用的手指种类映射到相应的第一指令，并按照所述第一指令对被控设备进行控制。
- 如权利要求5所述的装置，其特征在于，所述装置还包括：准备单元，用于在所述特征提取单元针对所述采集单元采集到的表面肌电信号进行特征提取之前，对采集到的表面肌电信号进行预处理和采样处理，所述预处理包括信号放大以及干扰抑制。
- 如权利要求5或6所述的装置，其特征在于，所述确定单元还用于：基于所述采集单元采集到的表面肌电信号的幅值、以及预先创建的手指种类对应的相关函数，确定所述手指按压操作对应的按压力度；其中，所述手指种类对应的相关函数包含每一个手指种类发生手指按压操作时产生的表面肌电信号的幅值、以及按压力度之间的函数关系；所述控制单元还用于，将所述确定单元确定的所述手指种类结合所述手指按压操作对应的按压力度，映射到相应的第二指令，并按照所述第二指令对被控设备进行控制。
- 如权利要求7所述的装置，其特征在于，所述表面肌电信号包括多个通道子信号；所述确定单元具体用于按下述方式确定所述表面肌电信号的幅值：将采集到的表面肌电信号包括的各个通道子信号的信号幅值进行累加平均计算，获得所述表面肌电信号的平均信号幅值，将所述平均信号幅值作为所述表面肌电信号的幅值。
- 一种基于生物电的控制器，其特征在于，包括传感器、处理器和收发器，其中，所述传感器，用于与用户的臂部肌肉表面相接触，以采集当用户发生手指按压操作时产生的表面肌电信号；所述处理器，用于调用一组程序代码，并按照所述程序代码执行操作：针对所述传感器采集到的表面肌电信号进行特征提取，获得特征信息，根据预先创建的手指种类识别模板，确定获得的特征信息对应的发生所述手指按压操作所使用的手指种类，以及将确定的发生所述手指按压操作所使用的手指种类映射到相应的第一指令，所述第一指令用于对被控设备进行控制；其中，所述手指种类识别模板包含每一个手指种类、以及每一个手指种类发生手指按压操作时对应的表面肌电信号的特征信息的对应关系；所述收发器，用于发送所述处理器获得的所述第一指令给被控设备。
- 如权利要求9所述的基于生物电的控制器，其特征在于，还包括：存储器，用于存储所述处理器执行的程序代码。
- 如权利要求9或10所述的基于生物电的控制器，其特征在于，所述处理器还用于：在针对采集到的表面肌电信号进行特征提取之前，对采集到的表面肌电信号进行预处理和采样处理，所述预处理包括信号放大以及干扰抑制。
- 如权利要求9、10或11所述的基于生物电的控制器，其特征在于，所述处理器还用于：基于采集到的表面肌电信号的幅值、以及预先创建的手指种类对应的相关函数，确定所述手指按压操作对应的按压力度；其中，所述手指种类对应的相关函数包含每一个手指种类发生手指按压操作时产生的表面肌电信号的幅值、以及按压力度之间的函数关系；将确定的所述手指种类结合所述手指按压操作对应的按压力度，映射到相应的第二指令，所述第二指令用于对被控设备进行控制。
- 如权利要求12所述的基于生物电的控制器，其特征在于，所述表面肌电信号包括多个通道子信号；所述处理器具体用于按下述方式确定所述表面肌电信号的幅值：将采集到的表面肌电信号包括的各个通道子信号的信号幅值进行累加平均计算，获得所述表面肌电信号的平均信号幅值，将所述平均信号幅值作为所述表面肌电信号的幅值。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US15/908,179 US10901507B2 (en) | 2015-08-28 | 2018-02-28 | Bioelectricity-based control method and apparatus, and bioelectricity-based controller |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510543246.8 | 2015-08-28 | ||
| CN201510543246.8A CN106484082B (zh) | 2015-08-28 | 2015-08-28 | 一种基于生物电的控制方法、装置及控制器 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US15/908,179 Continuation US10901507B2 (en) | 2015-08-28 | 2018-02-28 | Bioelectricity-based control method and apparatus, and bioelectricity-based controller |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2017036147A1 true WO2017036147A1 (zh) | 2017-03-09 |
Family
ID=58186438
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2016/079325 WO2017036147A1 (zh) | 2015-08-28 | 2016-04-14 | 一种基于生物电的控制方法、装置及控制器 |
Country Status (3)
| Country | Link |
|---|---|
| US (1) | US10901507B2 (zh) |
| CN (1) | CN106484082B (zh) |
| WO (1) | WO2017036147A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110850979A (zh) * | 2019-11-07 | 2020-02-28 | 中国航天员科研训练中心 | 基于航天医监医保信号的手势识别人机交互方法 |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107608524B (zh) * | 2017-10-13 | 2020-04-14 | 中国科学院软件研究所 | 一种基于肌电的多目标控制指令生成装置 |
| US10955955B2 (en) * | 2019-03-29 | 2021-03-23 | Cirrus Logic, Inc. | Controller for use in a device comprising force sensors |
| CN111657931B (zh) * | 2020-06-30 | 2023-06-06 | 康泰医学系统（秦皇岛）股份有限公司 | 一种心电电极复用为按键的方法、装置及存储介质 |
| CN113625882B (zh) * | 2021-10-12 | 2022-06-14 | 四川大学 | 一种基于稀疏多通道相关性特征的肌电手势识别方法 |
| CN114201052A (zh) * | 2022-02-16 | 2022-03-18 | 浙江强脑科技有限公司 | 一种仿生手的动作力度控制方法、装置及存储介质 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101482773A (zh) * | 2009-01-16 | 2009-07-15 | 中国科学技术大学 | 一种多通道无线表面肌电信号采集装置及系统 |
| US20120249417A1 (en) * | 2011-03-29 | 2012-10-04 | Korea University Research And Business Foundation | Input apparatus |
| CN104461365A (zh) * | 2014-12-11 | 2015-03-25 | 三星电子（中国）研发中心 | 终端的触控方法和装置 |
| CN104571517A (zh) * | 2014-12-31 | 2015-04-29 | 杨皓 | 一种人体动作对电子设备进行输入及控制的方法 |
| CN104714645A (zh) * | 2015-03-24 | 2015-06-17 | 华为技术有限公司 | 人机交互方法和人机交互设备 |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8447704B2 (en) * | 2008-06-26 | 2013-05-21 | Microsoft Corporation | Recognizing gestures from forearm EMG signals |
| US8581856B2 (en) * | 2009-05-27 | 2013-11-12 | Microsoft Corporation | Touch sensitive display apparatus using sensor input |
| US20100315266A1 (en) | 2009-06-15 | 2010-12-16 | Microsoft Corporation | Predictive interfaces with usability constraints |
| US20110099507A1 (en) | 2009-10-28 | 2011-04-28 | Google Inc. | Displaying a collection of interactive elements that trigger actions directed to an item |
| US8868039B2 (en) | 2011-10-12 | 2014-10-21 | Digimarc Corporation | Context-related arrangements |
| EP2807594B1 (en) | 2012-01-26 | 2021-08-25 | BlackBerry Limited | Methods and devices for distributing content to an electronic device |
| CN103309584A (zh) * | 2012-03-12 | 2013-09-18 | 联想(北京)有限公司 | 一种控制显示屏显示内容的方法、系统及一种电子设备 |
| US20140180595A1 (en) | 2012-12-26 | 2014-06-26 | Fitbit, Inc. | Device state dependent user interface management |
| CN203224838U (zh) | 2013-02-06 | 2013-10-02 | 鲍炜 | 手握式键盘 |
| CN103823551B (zh) | 2013-03-17 | 2017-07-21 | 浙江大学 | 一种实现多维度感知虚拟交互的系统和方法 |
| CN103246836A (zh) * | 2013-04-03 | 2013-08-14 | 李健 | 触摸屏手指滑动身份识别解锁方法 |
| CN103442129A (zh) * | 2013-08-09 | 2013-12-11 | 宇龙计算机通信科技(深圳)有限公司 | 智能手表与移动终端的交互方法及系统 |
| US9226330B2 (en) * | 2013-09-10 | 2015-12-29 | Playtabase, LLC | Wireless motion activated user device with bi-modality communication |
| CN104536558B (zh) * | 2014-10-29 | 2019-01-25 | 三星电子（中国）研发中心 | 一种智能指环和控制智能设备的方法 |
-
2015
- 2015-08-28 CN CN201510543246.8A patent/CN106484082B/zh active Active
-
2016
- 2016-04-14 WO PCT/CN2016/079325 patent/WO2017036147A1/zh active Application Filing
-
2018
- 2018-02-28 US US15/908,179 patent/US10901507B2/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101482773A (zh) * | 2009-01-16 | 2009-07-15 | 中国科学技术大学 | 一种多通道无线表面肌电信号采集装置及系统 |
| US20120249417A1 (en) * | 2011-03-29 | 2012-10-04 | Korea University Research And Business Foundation | Input apparatus |
| CN104461365A (zh) * | 2014-12-11 | 2015-03-25 | 三星电子（中国）研发中心 | 终端的触控方法和装置 |
| CN104571517A (zh) * | 2014-12-31 | 2015-04-29 | 杨皓 | 一种人体动作对电子设备进行输入及控制的方法 |
| CN104714645A (zh) * | 2015-03-24 | 2015-06-17 | 华为技术有限公司 | 人机交互方法和人机交互设备 |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110850979A (zh) * | 2019-11-07 | 2020-02-28 | 中国航天员科研训练中心 | 基于航天医监医保信号的手势识别人机交互方法 |
| CN110850979B (zh) * | 2019-11-07 | 2023-05-09 | 中国航天员科研训练中心 | 基于航天医监医保信号的手势识别人机交互方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| US10901507B2 (en) | 2021-01-26 |
| CN106484082A (zh) | 2017-03-08 |
| CN106484082B (zh) | 2021-08-13 |
| US20180188809A1 (en) | 2018-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017036147A1 (zh) | 一种基于生物电的控制方法、装置及控制器 | |
| CA3033852C (en) | Electronic device and method of controlling the same | |
| US20160313801A1 (en) | Method and apparatus for a gesture controlled interface for wearable devices | |
| Yang et al. | A proportional pattern recognition control scheme for wearable a-mode ultrasound sensing | |
| US11102591B2 (en) | Ear-worn electronic device incorporating motor brain-computer interface | |
| CN110069199B (zh) | 一种基于智能手表的皮肤式手指手势识别方法 | |
| CN117032398A (zh) | 用于可穿戴设备的姿势控制接口的方法和装置 | |
| US10521018B2 (en) | Human body-based interaction method and interaction apparatus | |
| Becker et al. | Touchsense: classifying finger touches and measuring their force with an electromyography armband | |
| WO2013075466A1 (zh) | 一种基于图像传感模块的字符输入方法、装置及终端 | |
| CN104571837B (zh) | 一种实现人机交互的方法及系统 | |
| Naik et al. | Classification of finger extension and flexion of EMG and Cyberglove data with modified ICA weight matrix | |
| Cognolato et al. | Improving robotic hand prosthesis control with eye tracking and computer vision: A multimodal approach based on the visuomotor behavior of grasping | |
| Aggelides et al. | A gesture recognition approach to classifying allergic rhinitis gestures using wrist-worn devices: a multidisciplinary case study | |
| Lee et al. | Echowrist: Continuous hand pose tracking and hand-object interaction recognition using low-power active acoustic sensing on a wristband | |
| Eddy et al. | Understanding the influence of confounding factors in myoelectric control for discrete gesture recognition | |
| CN115857696A (zh) | 一种设备交互方法、可穿戴设备和存储介质 | |
| Peters | An assessment of single-channel emg sensing for gestural input | |
| CN108391049A (zh) | 拍摄控制方法及相关设备 | |
| Carrino et al. | Gesture segmentation and recognition with an EMG-based intimate approach-an accuracy and usability study | |
| Ishii et al. | Improvement of EMG pattern recognition by eliminating posture-dependent components | |
| CN110309740A (zh) | 手势识别方法、可穿戴设备及手势控制系统 | |
| Wang et al. | Subtle finger motion recognition based on the cots smartwatch | |
| CN109901700A (zh) | 一种新的手势识别方法 | |
| CN108268088A (zh) | 基于表面心肌信号的可穿戴交互系统 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16840576 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 16840576 Country of ref document: EP Kind code of ref document: A1 |