Posture recognition device

Abstract

The utility model discloses a posture recognition device which comprises a first shell, a first electrode and a second electrode are arranged on the first shell, and the first electrode and the second electrode are used for collecting electromyographic signals of a recognized object; the second shell is matched with the first shell, and the first shell and the second shell are buckled to form a shell of the posture recognition device; the circuit board is arranged between the first shell and the second shell, the circuit board comprises a myoelectricity acquisition channel, a processing chip and a nine-axis attitude sensor, and the processing chip is connected with the myoelectricity acquisition channel and the nine-axis attitude sensor; the first input end of the myoelectricity acquisition channel is provided with a first contact point matched with the first electrode and a second contact point matched with the second electrode, the first contact point is electrically connected with the first electrode, and the second contact point is electrically connected with the second electrode. The posture recognition device is small in size and high in integration level.

Description

Technical Field

[0001] The utility model relates to the technical field of posture recognition, in particular to a posture recognition device. Background Art

[0002] Posture recognition technology refers to the detection and tracking of posture changes of objects or organisms through various sensors and algorithms. Posture usually includes information such as the spatial position, direction and posture of the object. This technology is widely used in motion capture, robot navigation, motion analysis and other fields. Correspondingly, when designing a posture recognition device, it is necessary to consider its miniaturization, lightness and wearability to meet the needs of wearable and mobile application scenarios.

[0003] However, the gesture recognition devices in the related art usually achieve a high signal-to-noise ratio by increasing the electrode size or adding a ground electrode, but this means increasing the device size or occupying more area of ​​the circuit board, resulting in a larger device size and lower integration. Utility Model Content

[0004] The utility model aims to solve at least one of the technical problems existing in the prior art. To this end, the utility model proposes a gesture recognition device, which realizes a gesture recognition device with a small size and a high integration.

[0005] A gesture recognition device according to an embodiment of the utility model includes:

[0006] A first shell, on which a first electrode and a second electrode are disposed, and the first electrode and the second electrode are used to collect myoelectric signals of an identified object;

[0007] a second housing, the second housing being matched with the first housing, and the first housing and the second housing being buckled together to form a housing of the gesture recognition device;

[0008] A circuit board is arranged between the first shell and the second shell, and the circuit board includes an electromyography acquisition channel, a processing chip and a nine-axis posture sensor, and the processing chip is respectively connected to the electromyography acquisition channel and the nine-axis posture sensor; the first input end of the electromyography acquisition channel is provided with a first contact point matching the first electrode and a second contact point matching the second electrode, the first contact point is electrically connected to the first electrode, and the second contact point is electrically connected to the second electrode.

[0009] A gesture recognition device according to an embodiment of the utility model has at least the following beneficial effects:

[0010] The posture recognition device comprises a first shell, a first electrode and a second electrode are arranged on the first shell, and the first electrode and the second electrode are used to collect the electromyographic signal of the recognition object; a second shell, the second shell matches the first shell, and the first shell and the second shell are buckled to form the posture recognition device shell; a circuit board, the circuit board is arranged between the first shell and the second shell, the circuit board comprises an electromyographic acquisition channel, a processing chip and a nine-axis posture sensor, and the processing chip is respectively connected to the electromyographic acquisition channel and the nine-axis posture sensor; the first input end of the electromyographic acquisition channel is provided with a first contact point matched with the first electrode and a second contact point matched with the second electrode, the first contact point is electrically connected to the first electrode, and the second contact point is electrically connected to the second electrode. The utility model shortens the distance from the electrode to the circuit board by arranging the contact point between the circuit board and the motor on the circuit board, and directly connecting with the electrode through the electrode contact point, without increasing the size of the motor, and can reduce the volume of the device while improving the integration of the circuit board.

[0011] According to some embodiments of the present utility model, the electromyography acquisition channel further includes:

[0012] An instrument amplifier circuit, wherein the second input terminal of the instrument amplifier circuit is connected to the first contact point, and the third input terminal is connected to the second contact point, and is used to amplify the electromyographic signals collected by the first electrode and the second electrode;

[0013] A bandpass filter circuit, wherein the fourth input terminal of the bandpass filter circuit is connected to the first output terminal of the instrument amplifier circuit, and is used for filtering and preprocessing the amplified electromyographic signal;

[0014] A driving amplifier circuit, wherein the fifth input terminal of the driving amplifier circuit is connected to the second output terminal of the bandpass filter circuit, and is used to amplify the filtered electromyographic signal and output it to the processing chip.

[0015] According to some embodiments of the utility model, the instrument amplifier circuit includes a first amplifier, a second amplifier, a third amplifier and a gain adjustment resistor; wherein the first amplifier includes a first positive electrode, a first negative electrode and a first amplifier output end, the second amplifier includes a second positive electrode, a second negative electrode and a second amplifier output end, the third amplifier includes a third positive electrode, a third negative electrode and a third amplifier output end, the first positive electrode is connected to the first contact point, the second positive electrode is connected to the second contact point, a gain adjustment resistor is arranged between the first negative electrode and the second negative electrode, the gain adjustment resistor includes a first resistor and a first capacitor connected in series, the third positive electrode is connected to the second amplifier output end, the third negative electrode is connected to the third amplifier output end, a second resistor is arranged on the first branch between the first negative electrode and the first amplifier output end, a third resistor is arranged on the second branch between the second negative electrode and the second amplifier output end, and a fourth resistor is arranged on the third branch between the third negative electrode and the third amplifier output end.

[0016] According to some embodiments of the utility model, the bandpass filter circuit includes a fifth resistor, a second capacitor and a third capacitor; the fifth resistor and the second capacitor are connected in series between the fourth input terminal and the second output terminal, the third capacitor is arranged on the second branch between the fifth resistor and the second capacitor and is grounded, a fourth branch is arranged between the second output terminal and the third positive electrode, and a first reference voltage source is arranged on the fourth branch.

[0017] According to some embodiments of the utility model, the driving amplifier circuit includes a second reference voltage source and a fourth amplifier, the fourth amplifier includes a fourth positive electrode, a fourth negative electrode and a fourth amplifier output terminal, the fourth positive electrode is connected to the fifth input terminal, the fourth negative electrode is connected to the second reference voltage source, a sixth resistor is arranged on the fifth branch between the fourth negative electrode and the fourth amplifier output terminal, and the fourth amplifier output terminal is connected to the digital-to-analog conversion input terminal of the processing chip.

[0018] According to some embodiments of the present invention, the processing chip is connected to the terminal device via wireless communication to output the gesture recognition result.

[0019] According to some embodiments of the present utility model, the nine-axis attitude sensor includes a six-axis inertial measurement unit and a three-axis magnetometer, and the nine-axis attitude sensor is connected to the processing chip via an SPI bus.

[0020] According to some embodiments of the present invention, the circuit board also includes an energy storage module for supplying power to the circuit board.

[0021] According to some embodiments of the present invention, a first distance between the first electrode and the first amplifier through a first contact point is equal to a second distance between the second electrode and the second amplifier through a second contact point, the material of the first electrode is the same as the material of the second electrode, and the size of the first electrode is the same as the size of the second electrode.

[0022] According to some embodiments of the present invention, the first contact point, the second contact point, and the first electrode, the second electrode are connected by welding. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the specific implementation of the utility model or the technical solution in the prior art, the following is a brief introduction to the drawings required for the specific implementation or the prior art description. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale.

[0024] Figure 1 A schematic diagram of the structure of a gesture recognition device provided by an embodiment of the utility model;

[0025] Figure 2 A module block diagram of a gesture recognition device provided by an embodiment of the utility model;

[0026] Figure 3 A module block diagram of the myoelectric acquisition channel provided by an embodiment of the utility model;

[0027] Figure 4 A circuit diagram of an instrument amplifier circuit provided in an embodiment of the utility model;

[0028] Figure 5 A circuit diagram of a bandpass filter circuit provided by an embodiment of the utility model;

[0029] Figure 6 A circuit diagram of a drive amplifier circuit provided in an embodiment of the utility model;

[0030] Figure 7 A module block diagram of a nine-axis attitude sensor provided in an embodiment of the utility model. DETAILED DESCRIPTION

[0031] The following embodiments of the technical solution of the utility model are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the utility model, and are therefore only used as examples, and cannot be used to limit the protection scope of the utility model.

[0032] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by technicians in the field to which the utility model belongs.

[0033] Gesture recognition is a technology that detects and tracks the position, direction, and posture of an object or organism in space through various sensor devices (such as inertial measurement units, etc.) and algorithms. It is widely used in motion capture, robot navigation, motion analysis, virtual reality, and other fields. When designing such gesture recognition devices, their size and weight are very important considerations, especially for wearable devices and mobile applications. The miniaturization and lightweight of the device are particularly critical, which can not only improve the user's wearing comfort, but also make it easier to carry the device.

[0034] Some typical application examples of this attitude acquisition device: 1) Body sensing drone flight control: Use the information obtained by the three-axis gyroscope to realize the movement of the drone, use the muscle force signal to realize the acceleration, deceleration, take-off, landing and other instructions, use the gyroscope + muscle force to realize the rise and descent of the drone, and use the magnetometer to realize the steering of the drone. 2) Sports science research: Use accelerometers and gyroscopes to obtain information such as the acceleration, deceleration, and steering speed of athletes, and use electromyography sensors to obtain information such as the strength of athletes' specific muscles and the degree of muscle fatigue. These application scenarios require that the attitude capture equipment has the characteristics of being small and light, high detection accuracy, and good integration to meet the needs of wearable and mobile.

[0035] However, existing gesture recognition devices have some technical bottlenecks in achieving miniaturization and lightweight. Usually, in order to improve detection accuracy and signal-to-noise ratio, designers will increase the size of electrodes or add ground electrodes, but this approach often makes the device larger, occupies more circuit board area, and leads to a decrease in overall integration.

[0036] In other words, existing gesture recognition devices cannot meet the requirements of miniaturization and lightweight while also meeting the requirements of high detection performance. This contradiction limits their widespread application in wearable, mobile and other application scenarios.

[0037] Based on this, the utility model proposes a posture recognition device, such as Figure 1 and Figure 2 As shown, the utility model discloses a gesture recognition device, including a first shell 1200 and a second shell 1100 .

[0038] The first housing 1200 is provided with a first electrode 1210 and a second electrode 1220 for collecting electromyographic signals of the object to be identified. The second housing 1100 matches the first housing 1200, and the first housing 1200 and the second housing 1100 are buckled together to form the overall housing structure of the gesture recognition device.

[0039] A circuit board 1300 is disposed in the cavity between the first housing 1200 and the second housing 1100 . The circuit board 1300 includes an electromyography acquisition channel 1330 , a processing chip 1340 , and a nine-axis posture sensor 1350 .

[0040] The processing chip 1340 is electrically connected to the electromyographic acquisition channel 1330 and the nine-axis attitude sensor 1350, respectively. The input end of the electromyographic acquisition channel 1330 is provided with a first contact point 1310 matching the first electrode 1210, and a second contact point 1320 matching the second electrode 1220. The first contact point 1310 is electrically connected to the first electrode 1210, and the second contact point 1320 is electrically connected to the second electrode 1220, so as to introduce the electromyographic signals collected by the first electrode 1210 and the second electrode 1220.

[0041] The working principle of the posture recognition device is as follows: when the identification object wears the device, the first electrode 1210 and the second electrode 1220 are close to the skin surface of the identification object, and the electromyographic signal of the identification object can be accurately collected. The collected electromyographic signal is transmitted to the electromyographic acquisition channel 1330 through the first contact point 1310 and the second contact point 1320, and after pre-processing such as signal amplification and filtering in the electromyographic acquisition channel 1330, the processed electromyographic signal is transmitted to the processing chip 1340.

[0042] At the same time, the nine-axis attitude sensor 1350 detects the spatial attitude change of the device and transmits the detection data to the processing chip 1340. The processing chip 1340 integrates and analyzes the electromyographic signal and the attitude data to accurately calculate the attitude information of the identified object, thereby realizing tracking and identifying the attitude of the identified object.

[0043] In this embodiment, by highly integrating electrodes, electromyographic signal acquisition circuits, posture detection sensors and processing chips into a miniaturized device, it is possible to efficiently and accurately collect electromyographic and posture data, while ensuring that the device is small in size and easy to wear, suitable for wearable and mobile application scenarios, and has excellent posture recognition performance.

[0044] like Figure 3 As shown, in some embodiments, the electromyography acquisition channel 1330 further includes:

[0045] An instrument amplifier circuit 1331, wherein the second input terminal of the instrument amplifier circuit 1331 is connected to the first contact point 1310, and the third input terminal is connected to the second contact point 1320, and is used to amplify the electromyographic signals collected by the first electrode 1210 and the second electrode 1220;

[0046] A bandpass filter circuit 1332, wherein the fourth input terminal of the bandpass filter circuit is connected to the first output terminal of the instrument amplifier circuit 1331, and is used for filtering and preprocessing the amplified electromyographic signal;

[0047] The driving amplifier circuit 1333 has a fifth input terminal connected to the second output terminal of the bandpass filter circuit 1332 , and is used to amplify the filtered electromyographic signal and output it to the processing chip 1340 .

[0048] Among them, the function of the instrument amplifier circuit 1331 is to preliminarily amplify the tiny electromyographic signals collected by the first electrode 1210 and the second electrode 1220 to improve the signal-to-noise ratio of subsequent processing. The bandpass filter circuit 1332 performs frequency selective filtering on the electromyographic signals amplified by the instrument amplifier circuit 1331, filters out high-frequency and low-frequency noise, and retains the effective electromyographic signal frequency band. The driving amplifier circuit 1333 amplifies the filtered electromyographic signals again so that the signal amplitude reaches the effective input range of the processing chip 1340, and outputs the finally processed electromyographic signals to the processing chip 1340 for subsequent analysis and calculation.

[0049] Through such hierarchical amplification, filtering, and re-amplification structural design, the electromyography acquisition channel 1330 can efficiently pre-process the tiny original electromyography signal, effectively improve the signal-to-noise ratio, and ensure high-quality electromyography data input processing chip 1340, thereby laying the foundation for subsequent electromyography signal analysis and posture recognition calculation. This design embodies excellent circuit design concepts and signal processing methods, and can maximize the performance of the device.

[0050] like Figure 4 As shown, in some embodiments, the instrument amplifier circuit 1331 includes a first amplifier 410, a second amplifier 420, a third amplifier 430 and a gain adjustment resistor 440; wherein, the first amplifier includes a first positive electrode, a first negative electrode and a first amplifier output end, the second amplifier includes a second positive electrode, a second negative electrode and a second amplifier output end, the third amplifier includes a third positive electrode, a third negative electrode and a third amplifier output end, the first positive electrode is connected to the first contact point 1310, the second positive electrode is connected to the second contact point 1320, a gain adjustment resistor 440 is arranged between the first negative electrode and the second negative electrode, the gain adjustment resistor 440 includes a first resistor 441 and a first capacitor 442 connected in series, the third positive electrode is connected to the second amplifier output end, the third negative electrode is connected to the third amplifier output end, a second resistor 450 is arranged on the first branch between the first negative electrode and the first amplifier output end, a third resistor 460 is arranged on the second branch between the second negative electrode and the second amplifier output end, and a fourth resistor 470 is arranged on the third branch between the third negative electrode and the third amplifier output end.

[0051] Among them, the first amplifier 410, the second amplifier 420 and the third amplifier 430 form a topological structure of a three-stage operational amplifier cascade amplification, the positive input terminal of the first amplifier 410 is connected to the first contact point 1310, and receives the electromyographic signal collected by the first electrode 1210, the negative input terminal is connected to the feedback network of the second amplifier 420 through the gain adjustment resistor 440, and the output terminal of the first amplifier forms a feedback loop through the second resistor 450. The positive input terminal of the second amplifier 420 is connected to the second contact point 1320, and the negative input terminal receiving the electromyographic signal collected by the second electrode 1220 is connected to the gain adjustment resistor 440 together with the negative input terminal of the first amplifier 410, and the output terminal of the second amplifier forms a feedback loop through the third resistor 460.

[0052] The three-stage structure realizes multi-stage amplification of tiny electromyographic signals, and the amplification gain can be adjusted through the gain adjustment resistor 440. The larger the resistance, the smaller the gain, and vice versa. Due to the decrease in the impedance of the first capacitor 442 at high frequency, the gain of the instrument amplifier increases, forming an effect similar to high-pass filtering, which is used to eliminate non-ideal DC components and motion artifacts in the electromyographic signal acquisition process. The first and second stages amplify the signals from the two electrodes respectively, and the third stage adds the two signals and further amplifies them, thereby obtaining a high-quality electromyographic differential mode signal output.

[0053] like Figure 5 As shown, in some embodiments, the bandpass filter circuit 1332 includes a fifth resistor 510, a second capacitor 520 and a third capacitor 530; the fifth resistor 510 and the second capacitor 520 are connected in series between the fourth input terminal and the second output terminal, the third capacitor 530 is arranged on the second branch between the fifth resistor 510 and the second capacitor 520 and is grounded, a fourth branch is arranged between the second output terminal and the third positive electrode, and a first reference voltage source is arranged on the fourth branch.

[0054] Wherein, the fifth resistor 510 and the second capacitor 520 are connected in series on the feedback loop of the third amplifier 430, forming a filtering link, and the third capacitor 530 is arranged on the second branch between the fifth resistor 510 and the second capacitor 520, and is grounded. In this way, a high-pass filter is formed in the low frequency band, and a low-pass filter is formed in the high frequency band, thereby constituting a band-pass filter. The positive input terminal of the third amplifier 430 is connected to the fourth input terminal, and receives the amplified electromyographic signal from the instrument amplifier circuit 1331. A first reference voltage source VREF is set on the fourth branch of the positive input terminal of the third amplifier 430, and a DC bias voltage is provided for the band-pass filter circuit. The output terminal of the third amplifier 430 is the second output terminal of the band-pass filter circuit 1332, and the electromyographic signal after filtering is output to the driving amplifier circuit 1333.

[0055] In some embodiments, the bandwidth of the bandpass filter is set in the range of 20-500 Hz.

[0056] The design of the bandpass filter circuit is compact and efficient. Through the frequency selectivity of the active filter, the high-frequency noise and low-frequency drift components in the electromyographic signal can be effectively filtered out, the main effective frequency band of the electromyographic signal can be retained, and the signal quality can be further improved.

[0057] like Figure 6 As shown, in some embodiments, the driving amplifier circuit 1333 includes a second reference voltage source, a fourth amplifier 610, the fourth amplifier 610 includes a fourth positive electrode, a fourth negative electrode and a fourth amplifier output terminal, the fourth positive electrode is connected to the fifth input terminal, the fourth negative electrode is connected to the second reference voltage source, a sixth resistor 620 is arranged on the fifth branch between the fourth negative electrode and the fourth amplifier output terminal, and the fourth amplifier output terminal is connected to the digital-to-analog conversion input terminal 1341 of the processing chip 1340.

[0058] The design of the driving amplifier circuit 1333 is simple and practical. Through the amplification of the third amplifier, the electromyographic signal from the bandpass filter circuit is subjected to the final analog amplification, so that its amplitude meets the input range requirements of the analog-to-digital conversion circuit of the processing chip. At the same time, the circuit uses a reference voltage source to provide a DC operating point bias, which can ensure the stability of the electromyographic signal amplitude.

[0059] like Figure 7 As shown, in some embodiments, the nine-axis attitude sensor 1350 includes a six-axis inertial measurement unit and a three-axis magnetometer, and the nine-axis attitude sensor 1350 is connected to the processing chip 1340 via an SPI bus.

[0060] The nine-axis attitude sensor 1350 includes two main functional modules:

[0061] (1) Six-axis inertial measurement unit (6-axis IMU)

[0062] The six-axis inertial measurement unit integrates a three-axis gyroscope and a three-axis accelerometer. It can accurately measure the angular velocity and acceleration changes of the device in three-dimensional space, and is a key data source for determining posture changes.

[0063] (2) Three-axis magnetometer

[0064] By detecting the components of the Earth's magnetic field in three dimensions, the three-axis magnetometer can obtain the relative orientation of the device and the reference direction of the Earth's magnetic field, providing important magnetic data reference for determining absolute spatial posture.

[0065] The nine-axis attitude sensor 1350 is connected to the processing chip 1340 via a serial peripheral interface (SPI) bus to achieve data communication and control. Among them, SPI interface 1 can be used to communicate with the six-axis IMU, and SPI interface 2 can be used to communicate with the three-axis magnetometer. The processing chip 1340 can access these two SPI interfaces in time-sharing to read the corresponding attitude data.

[0066] The nine-axis attitude sensor 1350 is used in conjunction with the processing chip 1340 to measure six-axis inertial motion data and three-axis magnetic data with high precision and in all directions, providing data support for subsequent fusion analysis through calculation algorithms to obtain the three-dimensional attitude of the device, and is the core hardware foundation for achieving excellent attitude recognition performance.

[0067] In some embodiments, the processing chip 1340 may be an nRF52 series single-chip microcomputer, which may be integrated with a Bluetooth module for connecting to a terminal device via wireless communication to output a gesture recognition result.

[0068] In some embodiments, an energy storage module may be integrated on the circuit board 1300 to provide a stable power supply for each electronic component on the entire circuit board. The energy storage module may include energy storage elements such as rechargeable batteries or super capacitors, and may be equipped with a corresponding power management circuit to ensure that appropriate operating voltage and current are provided for processing chips, sensors, amplifier circuits, etc.

[0069] In some embodiments, the device can work continuously for about 8 hours when equipped with a 100mAh battery. The length, width and height of the device are 30, 21 and 11 mm respectively, and the device weighs 9 grams.

[0070] In some embodiments, the first contact point 1310 and the second contact point 1320 may be electrically connected to the first electrode 1210 and the second electrode 1220 respectively by welding.

[0071] Welding connection is a common way to assemble electrical components. It can provide reliable, low-impedance electrical connections to meet the needs of EMG signal transmission. At the same time, welding also ensures the mechanical strength of the connection and increases the service life of the device.

[0072] In some embodiments, the distance between the first electrode 1210 and the first amplifier 410 through the first contact point 1310 is equal to the distance between the second electrode 1220 and the second amplifier 420 through the second contact point 1320. This symmetrical wiring design can make the two electromyographic signals be affected by substantially the same capacitance effect during transmission, thereby ensuring the consistency and balance of the two signals to the greatest extent, which is beneficial to the subsequent differential mode amplification of the electromyographic signals and improving the common mode rejection performance.

[0073] Among them, the first electrode 1210 and the second electrode 1220 need to use the same material and size, so that the two electrodes are consistent in structure and process, so that they have the same sensing characteristics for electromyographic signals, further enhancing the matching degree of the two electromyographic signals.

[0074] In some embodiments, the first contact point 1310 and the second contact point 1320 are respectively arranged on two opposite surfaces of the circuit board 1300 with other circuit modules on the circuit board 1300. This discrete placement can effectively prevent other analog and digital circuits from interfering with tiny electromyographic signals, ensure that the transmission path of the electromyographic signals remains clean, the signal-to-noise ratio is guaranteed, and can increase the available area for the surface where the functional circuit is located, thereby improving the integration of the circuit board.

[0075] By using the solution of this utility model patent, various functional modules can be highly integrated into a miniaturized device, which can not only efficiently and accurately collect electromyographic and posture data, but also ensure that the device is small in size and easy to wear, suitable for wearable and mobile application scenarios, and has excellent posture recognition performance.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the utility model, rather than to limit it. Although the utility model has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the utility model, and they should all be included in the scope of the claims and specification of the utility model.

Claims

1. A gesture recognition device, characterized in that: include: A first shell, on which a first electrode and a second electrode are disposed, and the first electrode and the second electrode are used to collect myoelectric signals of an identified object; a second housing, the second housing being matched with the first housing, and the first housing and the second housing being buckled together to form a housing of the gesture recognition device; A circuit board is arranged between the first shell and the second shell, and the circuit board includes an electromyography acquisition channel, a processing chip and a nine-axis posture sensor, and the processing chip is respectively connected to the electromyography acquisition channel and the nine-axis posture sensor; the first input end of the electromyography acquisition channel is provided with a first contact point matching the first electrode and a second contact point matching the second electrode, the first contact point is electrically connected to the first electrode, and the second contact point is electrically connected to the second electrode.

2. The gesture recognition device according to claim 1, characterized in that: The electromyography acquisition channel also includes: An instrument amplifier circuit, wherein the second input terminal of the instrument amplifier circuit is connected to the first contact point, and the third input terminal is connected to the second contact point, and is used to amplify the electromyographic signals collected by the first electrode and the second electrode; A bandpass filter circuit, wherein the fourth input terminal of the bandpass filter circuit is connected to the first output terminal of the instrument amplifier circuit, and is used for filtering and preprocessing the amplified electromyographic signal; A driving amplifier circuit, wherein the fifth input terminal of the driving amplifier circuit is connected to the second output terminal of the bandpass filter circuit, and is used to amplify the filtered electromyographic signal and output it to the processing chip.

3. The gesture recognition device according to claim 2, characterized in that: The instrument amplifier circuit includes a first amplifier, a second amplifier, a third amplifier and a gain adjustment resistor; wherein the first amplifier includes a first positive electrode, a first negative electrode and a first amplifier output end, the second amplifier includes a second positive electrode, a second negative electrode and a second amplifier output end, the third amplifier includes a third positive electrode, a third negative electrode and a third amplifier output end, the first positive electrode is connected to the first contact point, the second positive electrode is connected to the second contact point, a gain adjustment resistor is arranged between the first negative electrode and the second negative electrode, the gain adjustment resistor includes a first resistor and a first capacitor connected in series, the third positive electrode is connected to the second amplifier output end, the third negative electrode is connected to the third amplifier output end, a second resistor is arranged on the first branch between the first negative electrode and the first amplifier output end, a third resistor is arranged on the second branch between the second negative electrode and the second amplifier output end, and a fourth resistor is arranged on the third branch between the third negative electrode and the third amplifier output end.

4. The gesture recognition device according to claim 3, characterized in that: The bandpass filter circuit includes a fifth resistor, a second capacitor and a third capacitor; the fifth resistor and the second capacitor are connected in series between the fourth input terminal and the second output terminal, the third capacitor is arranged on the second branch between the fifth resistor and the second capacitor and is grounded, a fourth branch is arranged between the second output terminal and the third positive electrode, and a first reference voltage source is arranged on the fourth branch.

5. The gesture recognition device according to claim 2, characterized in that: The driving amplifier circuit includes a second reference voltage source and a fourth amplifier. The fourth amplifier includes a fourth positive electrode, a fourth negative electrode and a fourth amplifier output terminal. The fourth positive electrode is connected to the fifth input terminal, the fourth negative electrode is connected to the second reference voltage source, a sixth resistor is arranged on the fifth branch between the fourth negative electrode and the fourth amplifier output terminal, and the fourth amplifier output terminal is connected to the digital-to-analog conversion input terminal of the processing chip.

6. The gesture recognition device according to claim 1, characterized in that: The nine-axis attitude sensor includes a six-axis inertial measurement unit and a three-axis magnetometer, and the nine-axis attitude sensor is connected to the processing chip via an SPI bus.

7. The gesture recognition device according to claim 1, characterized in that: The processing chip is connected to the terminal device via wireless communication to output the gesture recognition result.

8. The gesture recognition device according to claim 1, characterized in that: The circuit board also includes an energy storage module for supplying power to the circuit board.

9. The gesture recognition device according to claim 3, characterized in that: The first distance between the first electrode and the first amplifier through the first contact point is equal to the second distance between the second electrode and the second amplifier through the second contact point. The material of the first electrode is the same as that of the second electrode. The size of the first electrode is the same as that of the second electrode.

10. The gesture recognition device according to claim 1, characterized in that: The first contact point, the second contact point, the first electrode, and the second electrode are connected by welding.

Images