Electronic skin gesture calibration method, system and device based on voltage comparison

Abstract

The invention belongs to the technical field of electronic skin, and provides an electronic skin gesture calibration method, system and device based on voltage comparison, and the calibration method comprises the steps: collecting and obtaining a voltage signal generated by a hand motion based on electronic skin; comparing the voltage signal with a set voltage threshold value by using a comparison circuit to obtain a comparison result; based on the comparison result, gesture features generated by the hand action are extracted, and a gesture instruction is obtained through recognition according to the gesture features; and calibrating the electronic skin gesture based on the gesture instruction. According to the method, the gesture characteristics generated by the hand actions can be extracted by obtaining and comparing the voltage signals, the gesture instruction is obtained according to gesture characteristic recognition, and then the electronic skin gesture is calibrated based on the gesture instruction, so that the calibration quality can be improved, and the hand actions can be accurately obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic skin, and in particular to a method, system and device for calibrating electronic skin gestures based on voltage comparison. Background Art

[0002] With the advancement of science and technology, human-computer interaction methods are becoming increasingly diverse. Among them, gesture recognition technology based on electronic skin has attracted widespread attention due to its natural and intuitive characteristics. Electronic skin is an intelligent electronic system that can simulate the perception function of human skin. It senses the changes in physical quantities (such as pressure, temperature, curvature, etc.) caused by hand movements through a sensor array and converts them into electrical signals for transmission and processing. However, due to the complexity and diversity of the electronic skin sensor array, as well as the nonlinearity and uncertainty of hand movements, the accuracy and stability of gesture recognition have become issues that need to be urgently addressed.

[0003] At present, electronic skin gesture recognition technology mainly relies on machine learning algorithms and deep learning technology, which improves recognition accuracy by training a large amount of gesture sample data. However, this method requires a large amount of data support and complex calculation process, and is easily affected by factors such as environmental noise and sensor drift in practical applications, resulting in reduced recognition performance. Therefore, it is of great significance to explore a simple, effective and stable electronic skin gesture module calibration method.

[0004] Therefore, it is necessary to provide a method, system and device for calibrating electronic skin gestures based on voltage comparison. Summary of the invention

[0005] The present invention provides a calibration method, system and device for electronic skin gestures based on voltage comparison. By acquiring and comparing voltage signals, gesture features generated by hand movements can be extracted, and gesture instructions can be obtained based on gesture feature recognition. Based on the gesture instructions, the electronic skin gestures can be calibrated, which can improve the calibration quality and facilitate the accurate acquisition of hand movements.

[0006] The present invention provides a calibration method for electronic skin gestures based on voltage comparison, comprising:

[0007] Based on electronic skin, the voltage signal generated by hand movements is collected and acquired;

[0008] Using a comparison circuit, the voltage signal is compared with a set voltage threshold to obtain a comparison result;

[0009] Based on the comparison results, the gesture features generated by the hand movements are extracted, and the gesture instructions are obtained according to the gesture feature recognition;

[0010] Based on gesture commands, the electronic skin gestures are calibrated.

[0011] Furthermore, based on the electronic skin, the voltage signal generated by the hand movement is collected, including:

[0012] Several different types of sensors are configured on the electronic skin; the sensors include but are not limited to capacitive sensors and resistive sensors; the sensors are used to sense and obtain voltage changes caused by hand movements;

[0013] The sensor is used to collect the voltage signal generated by the hand movement.

[0014] Furthermore, the voltage threshold is set accordingly according to different gesture actions, and the voltage threshold is set to one or more.

[0015] Furthermore, the voltage signal is compared with a set voltage threshold by using a comparison circuit to obtain a comparison result, including:

[0016] Design a comparison circuit, which includes a voltage comparator and a signal processing component;

[0017] A voltage signal is acquired, and a voltage comparator is used to compare the voltage signal with a set voltage threshold to obtain a comparison result.

[0018] Further, based on the comparison result, the gesture features generated by the hand movement are extracted, and the gesture instructions are obtained according to the gesture feature recognition, including:

[0019] Setting a first corresponding matching relationship library between the comparison result and the gesture feature;

[0020] Based on the set main control chip, according to the first corresponding matching relationship library, a gesture feature matching the comparison result is obtained; the gesture feature includes but is not limited to the amplitude of the voltage signal, the frequency of the voltage signal, the phase of the voltage signal, and the logic level sequence output by the voltage comparator;

[0021] According to a second corresponding matching relationship library between the gesture feature and the set gesture instructions, the gesture instruction corresponding to the gesture feature is matched and obtained.

[0022] Furthermore, the main control chip includes a single chip microcomputer, uses an internal clock source as a clock source, collects signals corresponding to the comparison results through I / O pins, and uses a serial port to transmit data.

[0023] Furthermore, based on the gesture command, the electronic skin gesture is calibrated, including:

[0024] According to different models of electronic skin hands, the voltage threshold is adjusted accordingly;

[0025] According to the different extraction effects of gesture features, the gesture feature extraction algorithm is optimized;

[0026] The gesture feature library is updated regularly, and is used to store data corresponding to gesture features.

[0027] Furthermore, according to the different extraction effects of gesture features, the gesture feature extraction algorithm is optimized, including:

[0028] Obtain the gesture feature extraction result; perform evaluation based on the set evaluation strategy according to the gesture feature extraction result, and obtain the extraction effect of the gesture feature according to the evaluation result; if the extraction effect does not meet the expected effect, optimize the gesture feature extraction algorithm, specifically:

[0029] According to the gesture feature extraction result, using the set gesture feature judgment condition, it is judged whether the gesture feature is a single typical gesture feature or a combined atypical gesture feature; a single typical gesture feature is: only one feature in the amplitude of the voltage signal, the frequency of the voltage signal, the phase of the voltage signal or the logic level sequence output by the voltage comparator, and the gesture feature is a typical data value; the typical data value is obvious and clear data characterizing the gesture feature; a combined atypical gesture feature is: including multiple features in the amplitude of the voltage signal, the frequency of the voltage signal, the phase of the voltage signal or the logic level sequence output by the voltage comparator, and multiple gesture features are atypical data values;

[0030] If it is a single typical gesture feature, then determine the determination value of the single typical gesture feature reflecting the hand movement; if the determination value is less than the set determination value threshold, then generate the first condition;

[0031] If it is a combined atypical gesture feature, the gesture feature prediction model is used to predict the gesture features of the set N extraction cycles to obtain N predicted gesture features; wherein the gesture feature prediction model is constructed based on the XGBoost model; N is a set constant greater than 1;

[0032] Counting the number of single typical gesture features and combined atypical gesture features in the N predicted gesture features, and if the ratio of the number of combined atypical gesture features to the N predicted gesture features is greater than a set ratio threshold, generating a second condition;

[0033] According to the first condition or the second condition, the gesture feature extraction algorithm is optimized according to the set extraction algorithm optimization strategy.

[0034] The calibration system of electronic skin gesture based on voltage comparison includes:

[0035] A voltage signal acquisition module is used to collect and acquire voltage signals generated by hand movements based on the electronic skin;

[0036] The voltage signal comparison module is used to compare the voltage signal with the set voltage threshold using a comparison circuit to obtain a comparison result;

[0037] A gesture command acquisition module is used to extract gesture features generated by hand movements based on the comparison results, and obtain gesture commands according to gesture feature recognition;

[0038] The calibration module is used to calibrate the electronic skin gesture based on the gesture command.

[0039] A device includes a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call the computer program to execute a calibration method for electronic skin gestures based on voltage comparison.

[0040] Compared with the prior art, the present invention has the following advantages and beneficial effects: by acquiring and comparing voltage signals, the gesture features generated by hand movements can be extracted, and gesture instructions can be obtained based on gesture feature recognition. Based on the gesture instructions, the electronic skin gestures can be calibrated, which can improve the calibration quality and facilitate the accurate acquisition of hand movements.

[0041] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0042] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0044] Figure 1 A schematic diagram of the steps of the calibration method of the electronic skin gesture based on voltage comparison;

[0045] Figure 2 A schematic diagram of the steps of a method for collecting voltage signals generated by hand movements based on sensors;

[0046] Figure 3 Schematic diagram of the electronic skin gesture calibration system structure based on voltage comparison. DETAILED DESCRIPTION

[0047] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0048] The present invention provides a calibration method for electronic skin gestures based on voltage comparison, such as Figure 1 As shown, including:

[0049] Based on electronic skin, the voltage signal generated by hand movements is collected and acquired;

[0050] Using a comparison circuit, the voltage signal is compared with a set voltage threshold to obtain a comparison result;

[0051] Based on the comparison results, the gesture features generated by the hand movements are extracted, and the gesture instructions are obtained according to the gesture feature recognition;

[0052] Based on gesture commands, the electronic skin gestures are calibrated.

[0053] The working principle of the above technical solution is: in order to realize the calibration method of electronic skin gestures based on voltage comparison, the present invention first collects and obtains the voltage signal generated by hand movements based on electronic skin; then uses a comparison circuit to compare the voltage signal with a set voltage threshold to obtain a comparison result; then based on the comparison result, the gesture features generated by the hand movements are extracted, and gesture instructions are obtained according to gesture feature recognition; finally, based on the gesture instructions, the electronic skin gestures are calibrated.

[0054] The beneficial effect of the above technical solution is: by adopting the solution provided in this embodiment, by acquiring and comparing the voltage signal, the gesture features generated by the hand movement can be extracted, and the gesture instructions can be obtained according to the gesture feature recognition, and then based on the gesture instructions, the electronic skin gesture can be calibrated, which can improve the calibration quality and is conducive to accurately acquiring the hand movement.

[0055] In one embodiment, Figure 2 As shown, based on the electronic skin, the voltage signal generated by the hand movement is collected, including:

[0056] Several different types of sensors are configured on the electronic skin; the sensors include but are not limited to capacitive sensors and resistive sensors; the sensors are used to sense and obtain voltage changes caused by hand movements;

[0057] The sensor is used to collect the voltage signal generated by the hand movement.

[0058] The working principle of the above technical solution is: in order to realize the voltage signal generated by hand movement based on sensor collection, the present invention first configures several different types of sensors on the electronic skin; the sensors include but are not limited to capacitive sensors and resistive sensors; the sensors are used to sense the voltage changes caused by hand movements; and then the sensors are used to collect the voltage signals generated by hand movements.

[0059] The beneficial effect of the above technical solution is: by adopting the solution provided in this embodiment, by configuring a number of different types of sensors on the electronic skin, the voltage signal generated by the hand movement can be collected.

[0060] In one embodiment, the voltage threshold is set accordingly according to different gesture actions, and the voltage threshold is set to one or more.

[0061] The working principle of the above technical solution is: by setting one or more voltage thresholds according to different gesture actions, the flexibility of setting the voltage threshold can be guaranteed.

[0062] The beneficial effect of the above technical solution is: by adopting the solution provided by this embodiment, by setting one or more voltage thresholds according to different gesture actions, a basis can be provided for subsequent comparison of voltage signals.

[0063] In one embodiment, a comparison circuit is used to compare the voltage signal with a set voltage threshold to obtain a comparison result, including:

[0064] Design a comparison circuit, which includes a voltage comparator and a signal processing component;

[0065] A voltage signal is acquired, and a voltage comparator is used to compare the voltage signal with a set voltage threshold to obtain a comparison result.

[0066] The working principle of the above technical solution is: in order to use the comparison circuit to compare the voltage signal with the set voltage threshold and obtain the comparison result, the present invention first designs the comparison circuit, and the comparison circuit includes a voltage comparator and a signal processing component; then obtains the voltage signal, and uses the voltage comparator to compare the voltage signal with the set voltage threshold and obtain the comparison result.

[0067] The beneficial effect of the above technical solution is: by adopting the solution provided by this embodiment, by designing a comparison circuit and using a voltage comparator to compare the voltage signal with the set voltage threshold, an accurate comparison result can be obtained.

[0068] In one embodiment, based on the comparison result, the gesture features generated by the hand movement are extracted, and the gesture instruction is obtained according to the gesture feature recognition, including:

[0069] Setting a first corresponding matching relationship library between the comparison result and the gesture feature;

[0070] Based on the set main control chip, according to the first corresponding matching relationship library, the gesture feature matching the comparison result is obtained; the gesture feature includes but is not limited to the amplitude of the voltage signal, the frequency of the voltage signal, the phase of the voltage signal, and the logic level sequence output by the voltage comparator; according to the second corresponding matching relationship library of the gesture feature and the set gesture instruction, the gesture instruction corresponding to the gesture feature is matched; for example, when the obtained voltage signal is greater than the set first voltage threshold, the obtained gesture feature is a low voltage level, and the corresponding hand movement is a straight state; when the obtained voltage signal is less than the set first voltage threshold, the obtained gesture feature is a high voltage level, and the corresponding hand movement is a bent state.

[0071] The working principle of the above technical solution is: in order to extract gesture features generated by hand movements and obtain gesture instructions based on gesture feature recognition, the present invention first sets a first corresponding matching relationship library between comparison results and gesture features; then based on the set main control chip, according to the first corresponding matching relationship library, obtain gesture features that match the comparison results; gesture features include but are not limited to the amplitude of the voltage signal, the frequency of the voltage signal, the phase of the voltage signal, and the logic level sequence output by the voltage comparator; finally, according to the second corresponding matching relationship library between the gesture features and the set gesture instructions, the gesture instructions corresponding to the gesture features are matched.

[0072] The beneficial effect of the above technical solution is: by adopting the solution provided by this embodiment, by setting the first corresponding matching relationship library and the second corresponding matching relationship library, the gesture instruction corresponding to the gesture feature can be obtained according to the comparison result.

[0073] In one embodiment, the main control chip includes a single chip microcomputer, uses an internal clock source as a clock source, collects signals corresponding to the comparison results through I / O pins, and uses a serial port to transmit data.

[0074] The working principle of the above technical solution is: in order to realize the function of the main control chip, the main control chip of the present invention includes a single-chip microcomputer, which uses an internal clock source as a clock source, collects the signal corresponding to the comparison result through the I / O pin, and uses the serial port to realize data transmission.

[0075] The beneficial effect of the above technical solution is: by adopting the solution provided in this embodiment, the function of the main control chip can be realized through the control of the main control chip, which facilitates the transmission of collected data.

[0076] In one embodiment, based on the gesture instruction, the electronic skin gesture is calibrated, including:

[0077] According to different models of electronic skin hands, the voltage threshold is adjusted accordingly;

[0078] According to the different extraction effects of gesture features, the gesture feature extraction algorithm is optimized;

[0079] The gesture feature library is updated regularly, and is used to store data corresponding to gesture features.

[0080] The working principle of the above technical solution is: in order to realize the calibration of electronic skin gestures, the present invention first adjusts the voltage threshold accordingly according to the different models of electronic skin hand shapes; then optimizes the gesture feature extraction algorithm according to the different extraction effects of gesture features; finally, the gesture feature library is regularly updated, and the gesture feature library is used to store the data corresponding to the gesture features.

[0081] The beneficial effect of the above technical solution is: by adopting the solution provided in this embodiment, by adjusting the voltage threshold, optimizing the gesture feature extraction algorithm, and regularly updating the gesture feature library, the quality and effect of electronic skin gesture calibration can be improved.

[0082] In one embodiment, the gesture feature extraction algorithm is optimized according to the different extraction effects of the gesture features, including:

[0083] Obtain the gesture feature extraction result; perform evaluation based on the set evaluation strategy according to the gesture feature extraction result, and obtain the extraction effect of the gesture feature according to the evaluation result; if the extraction effect does not meet the expected effect, optimize the gesture feature extraction algorithm, specifically:

[0084] According to the gesture feature extraction result, using the set gesture feature judgment condition, it is judged whether the gesture feature is a single typical gesture feature or a combined atypical gesture feature; a single typical gesture feature is: only one feature in the amplitude of the voltage signal, the frequency of the voltage signal, the phase of the voltage signal or the logic level sequence output by the voltage comparator, and the gesture feature is a typical data value; the typical data value is obvious and clear data characterizing the gesture feature; a combined atypical gesture feature is: including multiple features in the amplitude of the voltage signal, the frequency of the voltage signal, the phase of the voltage signal or the logic level sequence output by the voltage comparator, and multiple gesture features are atypical data values;

[0085] If it is a single typical gesture feature, then determine the determination value of the single typical gesture feature reflecting the hand movement; if the determination value is less than the set determination value threshold, then generate the first condition;

[0086] If it is a combined atypical gesture feature, the gesture feature prediction model is used to predict the gesture features of the set N extraction cycles to obtain N predicted gesture features; wherein the gesture feature prediction model is constructed based on the XGBoost model; N is a set constant greater than 1;

[0087] Counting the number of single typical gesture features and combined atypical gesture features in the N predicted gesture features, and if the ratio of the number of combined atypical gesture features to the N predicted gesture features is greater than a set ratio threshold, generating a second condition;

[0088] According to the first condition or the second condition, the gesture feature extraction algorithm is optimized according to the set extraction algorithm optimization strategy.

[0089] The working principle of the above technical solution is as follows: in order to optimize the gesture feature extraction algorithm, the present invention first obtains the gesture feature extraction result; then, based on the gesture feature extraction result, an evaluation is performed based on the set evaluation strategy, and based on the evaluation result, the gesture feature extraction effect is obtained; if the extraction effect does not meet the expected effect, the gesture feature extraction algorithm is optimized, specifically, based on the gesture feature extraction result, using the set gesture feature judgment condition to judge whether the gesture feature is a single typical gesture feature or a combined atypical gesture feature; a single typical gesture feature is: only one feature in the amplitude of the voltage signal, the frequency of the voltage signal, the phase of the voltage signal, or the logic level sequence output by the voltage comparator, and the gesture feature is a typical data value; the typical data value is obvious and clear data that characterizes the gesture feature; the combined atypical gesture feature is: including multiple features in the amplitude of the voltage signal, the frequency of the voltage signal, the phase of the voltage signal, or the logic level sequence output by the voltage comparator, and multiple gesture features are atypical data values; If it is a single typical gesture feature, then determine the determination value of the single typical gesture feature that reflects the hand movement; if the determination value is less than the set determination value threshold, then generate the first condition; if it is a combined atypical gesture feature, then use the gesture feature prediction model to predict the gesture features of the set last N extraction cycles to obtain N predicted gesture features; wherein, the gesture feature prediction model is constructed based on the XGBoost model; XGboost is a highly complex algorithm that has sufficient ability to learn various irregular features of data. By constructing a gesture feature prediction model through the XGBoost model, the quality of model prediction can be guaranteed; N is a set constant greater than 1; count the number of single typical gesture features and combined atypical gesture features in the N predicted gesture features, and if the proportion of the number of combined atypical gesture features to the N predicted gesture features is greater than the set proportion threshold, then generate the second condition; according to the first condition or the second condition, optimize the gesture feature extraction algorithm according to the set extraction algorithm optimization strategy.

[0090] The beneficial effect of the above technical solution is: by adopting the solution provided in this embodiment, by first evaluating the gesture feature extraction results based on the set evaluation strategy, and then optimizing the gesture feature extraction algorithm when the extraction effect does not meet the expected effect, the pertinence and effectiveness of the extraction algorithm optimization can be improved.

[0091] The calibration system of electronic skin gesture based on voltage comparison, such as Figure 3 As shown, including:

[0092] A voltage signal acquisition module is used to collect and acquire voltage signals generated by hand movements based on the electronic skin;

[0093] The voltage signal comparison module is used to compare the voltage signal with the set voltage threshold using a comparison circuit to obtain a comparison result;

[0094] A gesture command acquisition module is used to extract gesture features generated by hand movements based on the comparison results, and obtain gesture commands according to gesture feature recognition;

[0095] The calibration module is used to calibrate the electronic skin gesture based on the gesture command.

[0096] The working principle of the above technical scheme is: in order to realize the calibration system of electronic skin gestures based on voltage comparison, the present invention proposes a voltage signal acquisition module, which is used to collect and obtain the voltage signal generated by hand movements based on electronic skin; proposes a voltage signal comparison module, which is used to compare the voltage signal with the set voltage threshold by using a comparison circuit to obtain a comparison result; proposes a gesture instruction acquisition module, which is used to extract the gesture features generated by the hand movements based on the comparison results, and obtain gesture instructions according to gesture feature recognition; proposes a calibration module, which is used to calibrate the electronic skin gestures based on the gesture instructions.

[0097] The beneficial effect of the above technical solution is: by adopting the solution provided in this embodiment, by acquiring and comparing the voltage signal, the gesture features generated by the hand movement can be extracted, and the gesture instructions can be obtained according to the gesture feature recognition, and then based on the gesture instructions, the electronic skin gesture can be calibrated, which can improve the calibration quality and is conducive to accurately acquiring the hand movement.

[0098] A device includes a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call the computer program to execute a calibration method for electronic skin gestures based on voltage comparison.

[0099] The working principle of the above technical solution is: a computer program can be stored in a memory, and the computer program can be called by a processor to execute a calibration method of an electronic skin gesture based on voltage comparison.

[0100] The beneficial effect of the above technical solution is: by adopting the solution provided in this embodiment, the calibration method of the electronic skin gesture based on voltage comparison can be implemented through the memory and the processor.

[0101] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A calibration method for electronic skin gestures based on voltage comparison, characterized in that: include: Based on electronic skin, the voltage signal generated by hand movements is collected and acquired; Using a comparison circuit, the voltage signal is compared with a set voltage threshold to obtain a comparison result; Based on the comparison results, the gesture features generated by the hand movements are extracted, and the gesture instructions are obtained according to the gesture feature recognition; Based on gesture commands, the electronic skin gestures are calibrated.

2. The method for calibrating electronic skin gestures based on voltage comparison according to claim 1, characterized in that: Based on electronic skin, the voltage signals generated by hand movements are collected, including: Several different types of sensors are configured on the electronic skin; the sensors include but are not limited to capacitive sensors and resistive sensors; the sensors are used to sense and obtain voltage changes caused by hand movements; The sensor is used to collect the voltage signal generated by the hand movement.

3. The method for calibrating electronic skin gestures based on voltage comparison according to claim 1, characterized in that: The voltage threshold is set accordingly according to different gesture actions, and the voltage threshold is set to one or more.

4. The method for calibrating electronic skin gestures based on voltage comparison according to claim 1, characterized in that: The voltage signal is compared with the set voltage threshold by using a comparison circuit to obtain a comparison result, including: Design a comparison circuit, which includes a voltage comparator and a signal processing component; A voltage signal is acquired, and a voltage comparator is used to compare the voltage signal with a set voltage threshold to obtain a comparison result.

5. The method for calibrating electronic skin gestures based on voltage comparison according to claim 1, characterized in that: Based on the comparison results, the gesture features generated by the hand movements are extracted, and gesture instructions are obtained according to gesture feature recognition, including: Setting a first corresponding matching relationship library between the comparison result and the gesture feature; Based on the set main control chip, according to the first corresponding matching relationship library, a gesture feature matching the comparison result is obtained; the gesture feature includes but is not limited to the amplitude of the voltage signal, the frequency of the voltage signal, the phase of the voltage signal, and the logic level sequence output by the voltage comparator; According to a second corresponding matching relationship library between the gesture feature and the set gesture instructions, the gesture instruction corresponding to the gesture feature is matched and obtained.

6. The method for calibrating electronic skin gestures based on voltage comparison according to claim 5, characterized in that: The main control chip includes a single chip microcomputer, which uses an internal clock source as a clock source, collects signals corresponding to comparison results through I / O pins, and uses a serial port to transmit data.

7. The method for calibrating electronic skin gestures based on voltage comparison according to claim 5, characterized in that: Based on the gesture instructions, the electronic skin gesture is calibrated, including: According to different models of electronic skin hands, the voltage threshold is adjusted accordingly; According to the different extraction effects of gesture features, the gesture feature extraction algorithm is optimized; The gesture feature library is updated regularly, and is used to store data corresponding to gesture features.

8. The method for calibrating electronic skin gestures based on voltage comparison according to claim 7, characterized in that: According to the different extraction effects of gesture features, the gesture feature extraction algorithm is optimized, including: Obtain the gesture feature extraction result; perform evaluation based on the gesture feature extraction result based on the set evaluation strategy, and obtain the gesture feature extraction effect based on the evaluation result; if the extraction effect does not meet the expected effect, optimize the gesture feature extraction algorithm, specifically: According to the gesture feature extraction result, using the set gesture feature judgment condition, it is judged whether the gesture feature is a single typical gesture feature or a combined atypical gesture feature; a single typical gesture feature is: only one feature in the amplitude of the voltage signal, the frequency of the voltage signal, the phase of the voltage signal or the logic level sequence output by the voltage comparator, and the gesture feature is a typical data value; the typical data value is obvious and clear data characterizing the gesture feature; a combined atypical gesture feature is: including multiple features in the amplitude of the voltage signal, the frequency of the voltage signal, the phase of the voltage signal or the logic level sequence output by the voltage comparator, and multiple gesture features are atypical data values; If it is a single typical gesture feature, then determine the determination value of the single typical gesture feature reflecting the hand movement; if the determination value is less than the set determination value threshold, then generate the first condition; If it is a combined atypical gesture feature, the gesture feature prediction model is used to predict the gesture features of the set N extraction cycles to obtain N predicted gesture features; wherein the gesture feature prediction model is constructed based on the XGBoost model; N is a set constant greater than 1; Counting the number of single typical gesture features and combined atypical gesture features in the N predicted gesture features, and if the ratio of the number of combined atypical gesture features to the N predicted gesture features is greater than a set ratio threshold, generating a second condition; According to the first condition or the second condition, the gesture feature extraction algorithm is optimized according to the set extraction algorithm optimization strategy.

9. The electronic skin gesture calibration system based on voltage comparison is characterized in that: include: A voltage signal acquisition module is used to collect and acquire voltage signals generated by hand movements based on the electronic skin; The voltage signal comparison module is used to compare the voltage signal with the set voltage threshold using a comparison circuit to obtain a comparison result; A gesture command acquisition module is used to extract gesture features generated by hand movements based on the comparison results, and obtain gesture commands according to gesture feature recognition; The calibration module is used to calibrate the electronic skin gesture based on the gesture command.

10. A device, characterized in that: The device comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call the computer program to execute the electronic skin gesture calibration method based on voltage comparison as described in any one of claims 1 to 8.

Images