Method and system for detecting gestures of both hands

Abstract

The embodiment of the invention relates to a method and system for detecting gestures of both hands. A wearable device includes: an accelerometer; the at least three electrodes are used for detecting the electromyographic signals; a communication circuit arrangement; and processor circuitry. A user wears a primary wearable device and a secondary wearable device on both limbs. The wearable device detects a primary movement mode and a secondary movement mode while the user performs a two-hand gesture. The primary device recognizes both-hand gestures from a primary movement mode and a secondary movement mode.

Description

Technical Field

[0001] The present systems, devices, and methods generally relate to wearable devices configured to detect acceleration signals and myoelectric signals of human body parts, and gesture recognition using these wearable devices. Background Art

[0002] Wearable devices may include accelerometers or myoelectric sensors to detect movement of the limbs of the user wearing such a device. The detected movement can be used for gesture recognition. The detected movement data is sent to a different device, typically with greater computing power, such as a personal computer (PC) or a cloud service. Gesture recognition using a single wearable device such as a smart wristband to detect movement is well known. Gesture recognition using a separate device such as a PC is also well known.

[0003] Electromyography (EMG) is a technique that measures the electrical signals that travel through the human nervous system to control muscle movement. Movement is controlled by a complex network of neurons in the brain and spinal cord, collectively known as the motor system. Specifically, the process of moving a finger involves several steps, including:

[0004] Planning: The brain sends signals to the motor cortex, which is responsible for planning and coordinating movement. The motor cortex creates a plan for the movement of the finger based on sensory information from the environment and the individual's intention.

[0005] Execution: Once the plan is created, the motor cortex sends signals to the spinal cord, which contains motor neurons that directly control the muscles of the fingers. These motor neurons release a neurotransmitter called acetylcholine, which causes the muscle fibers to contract and produce movement.

[0006] Feedback: During movement, the brain continuously receives feedback from sensory receptors in the fingers (such as pressure sensors and stretch receptors), which helps to fine-tune the movement and adjust to changes in the environment.

[0007] The process of moving a finger begins with electrical signals originating from the brain, which are transmitted through the wrist using nerves such as the ulnar nerve, radial nerve, and median nerve. Any interruption in this process (such as damage to the motor cortex or spinal cord) can lead to difficulty moving and coordinating the fingers. The electrical signals can be detected by EMG sensors, which include electrodes on the surface of a person's skin or in the form of needles that penetrate the skin and directly couple to the person's neural tissue. The EMG signal is also called an action potential (AP). Summary of the Invention

[0008] Multiple wearable devices can be used to detect gestures that are performed using more than one limb. In some embodiments, two wristbands are used to detect two-handed gestures. Each wristband includes: an accelerometer capable of detecting three-axis acceleration; at least three electrodes for detecting electromyographic (EMG) signals; a communication circuit device; and a processor circuit device. The processor circuit device is coupled to the accelerometer, the electrodes, and the communication circuit device. The processor circuit device receives data from the accelerometer and the electrodes and constructs (prepare) a movement pattern. The movement pattern may include the acceleration of each axis over a time period, and an analog signal representing the action potential (EMG signal) of the finger muscle over the time period. The first wristband is the primary device, and the second wristband is the secondary device. The secondary device sends its movement pattern to the communication circuit device in the primary device via the communication circuit device in the secondary device. The communication circuit device can use wireless communication such as Bluetooth or Wi-Fi, or it can also use body contact transmission. The primary device receives two movement patterns, one from the primary device and one from the secondary device.It should be noted that the system can identify indications of the primary and secondary devices in real time based on which writing tape first detects significant movement.

[0009] For example, a user wears a wristband on each of their wrists. The right wristband is the primary device, and the left wristband is the secondary device. When the user performs a two-handed gesture by waving their left hand with an open palm and a closed right palm, the left wristband senses or detects acceleration readings associated with the waving motion and action potential readings associated with the open palms, thereby forming a left-hand movement pattern. Similarly, the right wristband senses or detects acceleration readings associated with the waving motion and action potential readings associated with the closed palms, thereby forming a right-hand movement pattern. The left-hand movement pattern is sent or otherwise transmitted to the right wristband. The primary device, the right wristband, receives the left-hand movement pattern, and both the left-hand movement pattern and the right-hand movement pattern are processed on the primary device. The primary device includes a database of stored gestures. The primary device executes a matching algorithm, such as dynamic time warping (DTW), to match the processed movement pattern with the stored gestures, i.e., the pattern with the stored gesture of "waving two hands with an open left palm and a closed right palm." The detected gestures have many applications, for example, to interact with a virtual reality world or control a music player.

[0010] A gesture may include two limb movements, either simultaneously or sequentially. The movement of each limb may be the same or different. For example, a user may wave both of his hands at the same time, or he may wave his right hand after he waves his left hand. A gesture may include only one limb movement. A gesture involving only one limb is different from a gesture that includes the same movement of the same limb but with the addition of another limb movement. A gesture of two combined limb movements may be different from two gestures of the same limb movement but performed separately. For example, a user raising his right arm straight up in front of and above his head with an open palm is different from the user raising both arms straight up in front of and above his head with an open palm. The limb may be a leg, and the wearable device may be an anklet. A necklace may be included to detect gestures that include head movements such as nodding.

[0011] Microelectromechanical system (MEMS) sensors are used because they can measure physical quantities such as acceleration, angular velocity, air pressure, and sound waves through silicon-based micromechanical structures. MEMS sensors can be standalone MEMS packages or integrated into a single silicon package along with other circuit devices as further described herein. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1A is a wearable device according to some embodiments.

[0013] Figure 1B is a wearable device according to some embodiments.

[0014] Figure 1C is a wearable device according to some embodiments.

[0015] Figure 1D is a chip for a wearable device according to some embodiments.

[0016] Figure 2 is a system using two wearable devices according to some embodiments.

[0017] Figures 3A to 3D is an example of a two-hand gesture that may be detected by some embodiments.

[0018] Figure 4 is an example readout of a wearable device according to some embodiments.

[0019] Figure 5 is a flow diagram illustrating the flow of data between two wearable devices according to some embodiments.

[0020] Figure 6 is a flow chart illustrating steps for determining a two-hand gesture in accordance with some embodiments. DETAILED DESCRIPTION

[0021] The present disclosure relates to a system and method for providing a wearable device having two wearable devices such as Figure 1A The invention relates to a wearable device 100A for performing two-hand gesture recognition or two-hand gesture recognition, wherein the two wearable devices are worn by the user on each arm. The wearable device 100A is configured to be worn on the wrist or ankle and includes a band 108 with a latch 107 or other closure device to keep the wearable device in place on the user's body. The wearable device 100A can be integrated into a smartwatch or other device of the user's choice, or can be a stand-alone device dedicated to gesture recognition. In some embodiments, the wearable device 100A can be configured to be worn around the neck as a necklace, or worn on the ankle.

[0022] Wearable device 100A includes a microelectromechanical system (MEMS) 102, which in some embodiments is an accelerometer configured to detect movement in three directions or three axes XYZ. In some embodiments, MEMS 102 may include a gyroscope configured to detect angular movement or rotation along multiple axes. In various embodiments, MEMS 102 is a six-axis motion sensor configured to detect both rotational and linear movement along three axes (e.g., XYZ). MEMS 102 is coupled to processor circuitry 101 to process the detected motion data. MEMS 102 and processor circuitry 101 are within housing 106A of wearable device 100A. The wearable device may include a display on the surface of the arm facing away from the user. MEMS or sensor 102, processing circuitry 101, communication circuitry 103, and analog converter 105 are enclosed in housing 106. These may be separate packages coupled together on a printed circuit board in a housing, or may be formed in a single chip including all of these elements.

[0023] Wearable device 100A also includes an EMG sensor comprising at least three electrodes 104A. In some embodiments, the EMG sensor includes electrodes 104A on a band 108, and an analog converter 105 is located within housing 106A. Electrodes 104A are configured to detect multiple EMG signals from the user's body (e.g., arm). Electrodes 104A are coupled to analog converter 105, which converts the EMG signals detected by electrodes 104 into analog signals before the processor circuitry 101 receives the analog signals. Analog converter 105 may also be referred to as an analog front end (AFE) 105. When the user activates finger movements, for example, when the user contracts their palm to form a fist or when the user relaxes their palm to open their hand, electrodes 104A capture neural signals from the brain to the wrist. In various embodiments, processor circuitry 101 is configured to identify signal patterns from the analog signals to determine the intent of a specific gesture, which can occur tens of milliseconds in advance of gesture actuation.

[0024] At least three electrodes 104A are configured to contact the user's skin surface, for example, on the top side of the user's wrist. In some embodiments, the electrodes can be incorporated into a band 105 located on the outside of the housing 106 (such as on the inside of the user's wrist) facing the user's skin.

[0025] Wearable device 100A also includes communication circuitry 103 within housing 106. Communication circuitry 103 is coupled to processor circuitry 101. In some embodiments, communication circuitry 103 transmits movement pattern data, which is processed by processor circuitry 101. The movement pattern data includes data derived from a plurality of signals, such as acceleration data detected by MEMS 102 or analog data derived from EMG signals detected by electrodes 104A. In various embodiments, processor circuitry 101 receives movement pattern data from communication circuitry 103, the movement pattern data originating from an external wearable device that is different from wearable device 100A.

[0026] In some embodiments, the communication circuit device 103 includes a radio frequency analog circuit device for a wireless communication protocol (e.g., Wi-Fi or Bluetooth). In various embodiments, the communication circuit device 103 includes a circuit device that enables body contact communication. Body contact communication uses the user's skin as a transmission line for electrical signals. Body contact communication signals are different from EMG signals, and they do not interfere with each other. Because the wearable device 100A is in contact with the wearing user, body contact communication is suitable for applications such as the wearable device 100A. Because the wearable device 100A worn by the user does not need to broadcast radio signals, such as when using Wi-Fi or Bluetooth, body contact communication can improve radio spectrum efficiency. In some embodiments, the communication circuit device 103 can use some electrodes 104A for body contact communication.

[0027] Figure 1B 100B is a wearable device according to some embodiments. On wearable device 100B, three electrodes 104B for detecting EMG signals are directly coupled to housing 106B on the back side. Processor circuitry, communication circuitry, and MEMS are located within housing 106B. In various embodiments, some of electrodes 104A may be incorporated into band 108, while the remaining electrodes 104B may be incorporated into housings 106A and 106B.

[0028] Figure 1C is a wearable device according to some embodiments. Wearable device 100C may include a single package 106C including processor circuitry, communication circuitry, an accelerometer, and electrodes.

[0029] Figure 1D This is a chip for a wearable device according to some embodiments. Chip 106D includes a silicon die 120. MEMS 102, analog front end 105, processor circuitry 101, and communication circuitry 103 may be integrated on a single silicon die 120. Silicon die 120 includes a processor circuitry region 121, a communication circuitry region 122, a MEMS region 123, and an EMG analog front end region 125. Processor circuitry region 121 includes circuitry configured to execute programs. In some embodiments, the processor circuitry is a general-purpose digital computer central processing unit (CPU).

[0030] Communication circuitry area 122 includes circuitry for communication interfaces, such as radio frequency circuitry and an antenna interface for Bluetooth. In some embodiments, communication area 122 includes circuitry configured to interface with body contact communication. Communication circuitry area 122 includes an analog-to-digital converter (ADC) that converts various communication signals into digital data suitable for processing by processor circuitry 101.

[0031] MEMS region 123 includes a MEMS structure configured to detect motion and an ADC configured to sense motion through the MEMS structure and convert the sensed motion into digital data suitable for processing by processor circuitry 101 .

[0032] The analog front-end region 125 may be referred to as a vertical analog front-end (vAFE). The vAFE includes analog circuitry for task-specific analog sensing functions that is fully synchronized with the other sensing channels (e.g., MEMS 102) provided by chip 106D. This disclosure provides some examples of chips with vAFE features in portable and wearable devices. These electrodes and vAFE features can be used to integrate vital sign monitoring.

[0033] Chip 106D is designed to provide accuracy and reliability in detecting activities such as motion while minimizing power consumption and size, and to solve the problem of data fusion of analog sensing data with motion channels. The design of this vertical analog front end can vary depending on the specific application requirements (such as the desired range, sensitivity and bandwidth of the target analog sensing signal). For stand-alone analog front-end devices that are primarily fully configurable and programmable but with expensive die area, the vAFE is designed to fit into the chip. The vAFE can be used to perform specific tasks where the sensor itself does not require external circuitry. In some embodiments, analog sensing, accelerometer and gyroscope data are acquired fully synchronously, enabling low power (200uA when using all resources) feature extraction with high accuracy on a standard system architecture with an external microcontroller and a separate analog front end.

[0034] In various embodiments, chip 106D provides the vAFE with ESD protection pads, filters, and amplifiers, while the analog-to-digital converter, voltage reference, and power management are shared with the traditional architecture. Designing vAFEs for specific tasks is accomplished by sharing the standard architecture and resources of chip 106D, aiming to minimize die 120 area, resulting in significant design challenges. The concept of a vAFE plug-in library is also introduced, along with the concept of a collection of vAFEs for a single task and all circuitry implemented within the MEMS sensor architecture.

[0035] Figure 2is a system using two wearable devices according to some embodiments.

[0036] The two-hand gesture recognition system utilizes vAFEs and motion sensors placed on both wrists to collect hand acceleration and EMG signals. EMG signals travel from the brain across the wrist to the hand, driving finger and hand movements. Electrodes are used to collect EMG signals. Acceleration and EMG patterns are used to classify gestures using an algorithm based on dynamic time warping.

[0037] A user 200 wears a right smart wristband 201 on his right arm and a left smart wristband 202 on his left arm. The right wristband 201 and the left wristband 202 are connected via a body contact communication link 203. According to some embodiments, each of the right and left wristbands is a wearable device 100A.

[0038] Wristbands 201 and 202 detect gestures performed by user 200. For example, user 200 rests his left arm with his palm 210 closed, and then performs a gesture by raising and waving his left hand and then opening his left palm 220 for a period of time. The MEMS 102 of left wristband 202 detects acceleration data along three axes corresponding to the raising and waving motion during this period of time, and the electrodes 104 of left wristband 202 detect EMG signals associated with the relaxation of the palm. The MEMS 102 of right wristband 201 detects acceleration data along three axes corresponding to the idle position 230 during this period of time, and its electrodes 104 detect EMG signals associated with the contraction of palm 230. The EMG signals are combined to generate an analog signal by the analog front end 105. The acceleration data for this period of time is recorded. The analog signal and acceleration data are combined by the processor circuitry 101 to form a movement pattern. The left wristband 202 transmits its movement data to the right wristband 201 via the communication link 203. The right wristband 201 receives movement data from the communication link 203. The right wristband 201 and its processor circuitry 101 detect the gesture of "raising and waving the left hand with an open palm while resting the right hand with a closed palm" based on its movement pattern and the movement pattern sent by the left wristband 202. In some embodiments, the right wristband 202 detects the gesture by executing a matching algorithm (e.g., dynamic time warping (DTW)) using the processor circuitry of the right wristband 202.

[0039] Figures 3A to 3D is an example of a two-hand gesture that may be detected by some embodiments.

[0040] Figure 3AThis is the "backward" gesture. Both left hand 31A and right hand 32A have their palms clenched into fists. Left hand 31A moves to the left and away from right hand 32A. Right hand 32A moves to the right and away from left hand 31A. In various embodiments, this gesture can be used to interact with a virtual reality environment, an electronic device such as a music player, or a computer system. The "backward" gesture can cause a music player or video player to rewind the content currently being played. In some embodiments, the "backward" gesture can cause an image to be zoomed in on in image viewing software.

[0041] Figure 3B This is a "high five" gesture. Left hand 31B and right hand 32B are both open and facing each other. Left hand 31B and right hand 32B move toward each other and strike each other at a center point, thereby producing a high five noise. In various embodiments, this gesture can be used to interact with a virtual reality environment, an electronic device such as a smart light, or a computer system. In some embodiments, the "high five" gesture can cause a smart light to turn on or off, or cause a music player or video player to start or stop playing content.

[0042] Figure 3C It is a "slide" gesture. Both left hand 31B and right hand 32B are open. Left hand 31C is facing upward, and right hand 32C is facing downward. Right hand 32C is placed on top of left hand 31C. Left hand 31C remains still, and right hand 32C slides toward the front. In various embodiments, this gesture can be used to interact with a virtual reality environment, an electronic device such as a music player, or a computer system. The "slide" gesture can cause a music player or video player to play the next item from a playlist. In some embodiments, the "slide" gesture can cause an address book application on a smartphone to display the next page of contacts. In a card game application, the "slide" gesture can cause a player character to deal virtual playing cards.

[0043] Figure 3D This is a "pull" gesture. Left hand 31D is clenched into a fist, palm facing down, and right hand 32D is open, palm facing left. Left hand 31B moves to the left, away from right hand 32D, while right hand 32D remains stationary. In various embodiments, this gesture can be used to interact with a virtual reality environment, an electronic device such as a music player, or a computer system. In some embodiments, the "pull" gesture can cause a document viewer application to zoom in from a page being displayed. In a video game, the "pull" gesture can cause a player character to draw a weapon.

[0044] Figure 3A 、 Figure 3B 、 Figure 3C 、 Figure 3DThe gestures shown in can be stored in a gesture database according to some embodiments. The gestures shown are performed over a time period. The time period can vary, and in some embodiments, different lengths of time when each gesture is performed can have different meanings and different references in the gesture database. For example, a "pull" gesture performed in one second ("quick pull") is different from a "pull" gesture performed in three seconds ("slow pull"). Gestures can include movement in multiple directions.

[0045] Figure 4 4 is an example readout of wearable devices 43, 44 according to some embodiments. A user wearing two wearable devices (one on each wrist) performs a "roll" gesture 40. In this "roll" gesture 40, both the left hand 41 and the right hand 42 are open. The left hand 41 moves horizontally to the left for a period of time (e.g., one second), while the right hand 42 remains stationary.

[0046] A left wristband 43 is worn on the left hand 41. Graph 411 shows readings from the MEMS accelerometer in the left wristband 43. Lines 413, 414, and 415 show the acceleration of the left wristband 43 along the x, y, and z axes, respectively, during this time period. Lines 413, 414, and 415 indicate horizontal movement to the left during this time period. Graph 412 shows EMG readings from the electrodes of the left wristband 43. Line 416 is the envelope of the electrode signal during this time period. Graph 412 is simplified to show only envelope 416. The EMG signal varies within the boundaries of envelope 416. Line 417 is the analog signal processed by the EMG analog front end of the left wristband 43. Each line 413, 414, 415, and 416 is a time series. The data from lines 413, 414, 415, and 417 form a leftward movement pattern.

[0047] A right wristband 44 is worn on the right hand 42. Graph 421 shows readings from the accelerometer in the right wristband 44. Lines 423, 424, and 425 show the acceleration of the right wristband 44 on the x, y, and z axes, respectively, during this time period. Graph 421 indicates the stable position during this time period. Graph 422 shows EMG readings from the electrodes of the right wristband 44. Line 426 is the envelope of the electrode signal over the time period. Graph 422 is simplified to show only envelope 426. The EMG signal varies within the boundaries of envelope 426. Line 427 is the analog signal processed by the EMG analog front end of the right wristband 44. Each line 423, 424, 425, and 427 is a time series. The data from lines 423, 424, 425, and 427 form a right movement pattern.

[0048] In some embodiments, the movement pattern can be stored in a manner that can be processed by the processor circuit device (e.g., in binary form). The movement pattern can include additional data, such as rotational movement and position. In various embodiments, the movement pattern can include multiple analog signals corresponding to multiple EMG signals detected by the electrodes and further processed by the analog front end.

[0049] Figure 5 is a flow chart illustrating the flow of data on a wearable device in a system including two wearable devices, according to some embodiments. At 501, the wearable device detects acceleration signals on the x, y, and z axes as a user performs a gesture. At 502, the acceleration signal 501 is validated to prevent false positives, such as when the user is on a moving bus and acceleration is detected. At 503, the wearable device detects multiple EMG signals. At 504, the analog front end converts the EMG signals into analog signals representing the contraction or relaxation of the hand. The acceleration signals and the analog signals form a movement pattern. The movement pattern includes data representing the acceleration on each axis and the analog signals during that period.

[0050] In one embodiment, the primary device is identified as the device of the two wearable devices that first detects a significant movement pattern. Both devices have the same role in triggering data acquisition for the other device. If a significant motion has been first identified and verified on the first of the devices, this is the primary device. The primary device sends a trigger command to the other secondary device requesting the start of data acquisition throughout the time frame, regardless of whether the signal in the secondary device is above or below the threshold of interest at that moment. This "peer to peer" approach allows for the collection and storage of signals that are out of phase, thereby maintaining their relative time shift, regardless of the device that initiates the process. Figure 5 In this "peer-to-peer" approach, steps 505 and 510 would be omitted, such that at 506, once significant movement is detected, the wearable device, which becomes the primary device, would request and receive data from the secondary device.

[0051] It is contemplated that in all instances, the system may identify one of the wearable devices as the primary device, such that step 505 is included in the system to determine whether the significant movement pattern first detected is in the wearable device that is the primary device at 505. At 510, if the significant movement is in the secondary device in the fixed system, the secondary device sends its movement pattern to the primary device. At 506, if the significant movement is first detected in the primary device, the primary device requests to receive the movement pattern from the secondary device.

[0052] When the primary device detects a gesture involving movement of both limbs and the secondary device also detects an acceleration signal or EMG signal, the primary device can spontaneously receive the movement pattern at that moment or within a short period of time. If the gesture involves movement only on the limb with the primary device, the primary device will request the movement pattern from the secondary device by sending a command to the secondary device. The primary device now has two movement patterns: one from the secondary device and one from its accelerometer and EMG electrodes. At 507, the primary device combines the two movement patterns. At 508, the primary device performs gesture recognition on the combined data.

[0053] Figure 6 6 is a flow chart illustrating steps for determining a two-hand posture according to some embodiments. A primary device generates a movement pattern 601 and receives a movement pattern 602 from a secondary device. The primary device determines whether the two movement patterns are unusual 603. An unusual movement pattern is a movement pattern that indicates movement of a limb. An unusual movement pattern is a movement pattern that indicates noise from a sensor (e.g., MEMS), which indicates movement but does not indicate limb movement. One of the two movement patterns may be unusual because the arm on which the wearable device is worn has not moved, for example, in a posture where one hand is held still.

[0054] If there is an unusual movement pattern 603, the primary device generates a filler movement pattern to replace the invalid movement pattern 604. There cannot be two unusual movement patterns because a gesture cannot be performed when both limbs are not moving. The filler movement pattern includes a clean acceleration signal to represent a non-moving hand. In some embodiments, the filler movement pattern is generated by the processor circuitry. In various embodiments, the filler movement pattern is stored in a non-transitory data storage device on the primary device, and the processor circuitry accesses the non-transitory data storage device to retrieve the filler movement pattern. The primary device replaces the unusual movement pattern with the filler movement pattern for gesture recognition 605. The filler movement pattern is used in place of the unusual movement pattern for further processing by the primary device.

[0055] The primary device matches 606 the combined data of the two movement patterns with possible gestures in a gesture database 607. The gesture database 607 is stored on the primary device's non-volatile memory. In some embodiments, the primary device uses dynamic time warping (DTW) to match the combined movement pattern with gestures from the gesture database 607. DTW is an algorithm that measures the similarity between two time series. Movement patterns are time series because they record acceleration data over a period of time. DTW measures the similarity between movement patterns and gestures in the gesture database 607 and matches the gesture with the highest similarity. DTW requires processing of large amounts of data that cannot be performed by the human brain in any reasonable manner or in the time required for any embodiment to actually operate.

[0056] The matched gestures are output for further use. In some embodiments, the matched gestures are used to control a wearable device. For example, to start or stop a timer on a fitness smartwatch, or to shuffle the next song on a music streaming service. In various embodiments, the matched gestures are used to interact with external devices. For example, to control a smart TV or dim a smart light bulb. These gestures can be used to interact with a virtual reality environment or an augmented reality environment. For example, moving a user's arm can cause a virtual character to move its arm. Contracting a user's hand can cause a character to pick up a virtual item in a virtual reality environment.

[0057] The various embodiments described above can be combined to provide other embodiments. Aspects of the embodiments can be modified, if necessary, to employ concepts from various patents, applications, and publications to provide other embodiments.

[0058] These and other changes can be made to the embodiments in light of the above detailed description. In general, in the following claims, the terms used should not be construed to limit the claims to the specific embodiments disclosed in the specification and claims, but should be construed to include all possible embodiments and the full scope of equivalents to which such claims are entitled. Therefore, the claims are not limited by this disclosure.

Claims

1. A method for detecting hand posture, comprising: Receiving, by a first wearable device, a first movement pattern, wherein receiving, by the first wearable device, the first movement pattern comprises: receiving a first plurality of acceleration data within a time period from a first accelerometer on the first wearable device; and receiving a first plurality of EMG signals within the time period from a first electromyography (EMG) sensor on the first wearable device; Receiving, by the second wearable device, a second movement pattern, wherein receiving, by the second wearable device, the second movement pattern comprises: receiving a second plurality of acceleration data within the time period from a second accelerometer on the second wearable device; and receiving a second plurality of EMG signals within the time period from a second EMG sensor on the second wearable device; transferring the second movement pattern from the second wearable device to the first wearable device; and The first wearable device detects a posture, where the first wearable device detects the posture including: A gesture from the gesture database is matched to the first movement pattern and the second movement pattern. 2 . The method of claim 1 , wherein transmitting the second movement pattern from the second wearable device to the first wearable device uses body contact transmission.

3. The method according to claim 1, further comprising: generating a first analog signal from the first plurality of EMG signals, and A second analog signal is generated from the second plurality of EMG signals. 4 . The method of claim 3 , wherein the first EMG sensor comprises at least three electrodes, and the second EMG sensor comprises at least three electrodes.

5. The method according to claim 4, further comprising: processing the first analog signal to determine contraction or relaxation of the first hand, and The second analog signal is processed to determine contraction or relaxation of the second hand.

6. The method of claim 1 , wherein receiving the movement pattern further comprises: The plurality of acceleration data from the accelerometer is validated.

7. The method according to claim 6, further comprising: determining whether at least one of the first movement mode and the second movement mode is valid; as well as If one of the first movement mode or the second movement mode is invalid, then: generating a fill movement pattern to replace the one invalid movement pattern; and The one invalid movement pattern is replaced with the fill movement pattern.

8. The method of claim 1, wherein the matching algorithm is dynamic time warping.

9. A system comprising: A first wearable device configured to be worn on a first limb by a user, wherein the first wearable device comprises: a first accelerometer configured to detect acceleration in at least three axes; at least three first electrodes configured to detect electromyographic (EMG) signals; first processor circuit means, a first memory, and first communication circuitry; and a second wearable device, wherein the second wearable device is configured to be worn by the user on a second limb, and the second wearable device is configured to: detecting movement of a second limb of the second limb, and A second limb movement pattern is transmitted to the first wearable device, the first wearable device being configured to detect a gesture using the first processor circuitry in response to the second limb movement.

10. The system of claim 9, wherein the first communication circuitry comprises body contact communication.

11. The system of claim 9, wherein the first limb is a first arm of the user and the second limb is a second arm of the user, and the first wearable device is configured to generate a first analog signal from EMG signals detected by the at least three first electrodes over a period of time using a first analog-to-digital converter.

12. The system of claim 11, wherein the second limb movement pattern comprises: a plurality of acceleration data within the time period, and A second analog signal is generated from EMG signals detected by at least three second electrodes during the time period, the first analog signal representing a first contraction or relaxation of the user's first hand; and the second analog signal representing a second contraction or relaxation of the user's second hand.

13. The system of claim 12, wherein the first wearable device is further configured to: verifying a first plurality of acceleration data, the first plurality of acceleration data being detected by an accelerometer of the first wearable device; verifying a second plurality of acceleration data, the second plurality of acceleration data being included in the second limb movement pattern; and If one of the first plurality of acceleration data or the second plurality of acceleration data is invalid, then: generating fill acceleration data; and The invalid acceleration data is replaced by the filling acceleration data.

14. The system of claim 13 , wherein the first wearable device is configured to detect a gesture by: executing, on the first processor circuitry, a matching algorithm on a gesture database on the first memory; and A gesture from the gesture database is matched with the first and second pluralities of acceleration data.

15. The system of claim 14, wherein the matching algorithm is dynamic time warping.

16. The system of claim 15, wherein the first wearable device is configured to detect a gesture by further performing: The matched gesture is verified using the first analog signal and the second analog signal.

17. The system of claim 16, wherein the first processor circuitry, the first communication circuitry, the first accelerometer, and the first analog-to-digital converter are fabricated on a single silicon die.

18. A system comprising: The first wearable device; A second wearable device, wherein the second wearable device includes: accelerometer; at least three electrodes configured to detect myoelectric signals; processing circuitry, and The communication circuit device of the second wearable device is configured to: constructing a first movement pattern based on a plurality of acceleration data from the accelerometer within a time period and a plurality of EMG signals from the at least three electrodes within the time period; receiving a second movement pattern from the first wearable device; and A gesture from a gesture database is matched to the first movement pattern and the second movement pattern.

19. The system of claim 18, wherein the communication circuitry comprises body contact communication.

20. The system of claim 18, wherein the second wearable device is further configured to: verifying the first movement pattern; verifying the second movement pattern; and If one of the first movement mode or the second movement mode is invalid, then: generating a fill movement pattern; and The one invalid movement pattern is replaced with the fill movement pattern.

21. The system of claim 20, wherein the first movement mode further comprises: An analog signal is generated from the at least three electrodes, the analog signal representing contraction or relaxation of a user's hand.

22. The system according to claim 21, comprising: An analog-to-digital converter is provided for generating an analog signal, wherein the processor circuitry, the communication circuitry, the accelerometer, and the analog-to-digital converter are fabricated on a single silicon die.

Images