System and method for detecting steps using double confirmation

Abstract

Embodiments of the present disclosure relate to systems and methods for detecting steps using dual confirmation. A system for detecting a user's steps includes a processing circuit device and a sensor, the sensor being configured to detect a change in the user's electrostatic charge during the user's step and generate a charge change signal. The accelerometer is configured to detect the acceleration caused by the step and generate an acceleration signal. The processing circuit device is configured to: obtain the charge change signal; obtain the acceleration signal; detect a first characteristic identifying the step in the charge change signal; detect a second characteristic identifying the step in the acceleration signal. If both the first characteristic and the second characteristic are detected, the presence of the step can be confirmed.

Description

Technical Field

[0001] The present invention relates to a system and method for detecting a user's steps. Background Art

[0002] Devices for continuously monitoring a user's body in ambient and free-living conditions are known. A wide range of sensors, for example adapted to detect acceleration, electrical resistance of the skin, temperature of the skin, flow of thermal radiation, and heart rate, are used in various combinations to determine or derive parameters such as calorie burn rate, type and level of activity, and sleep status. The device uses sophisticated algorithms for integrating the various data streams acquired in order to determine an output parameter (e.g., calories burned, type of physical activity, etc.) with the best possible accuracy. Additional sensors for detecting additional parameters feed additional data to the algorithm to improve its accuracy.

[0003] In particular, with regard to the counting of steps, it is known to use a three-axis accelerometer (usually integrated in a portable device) which is suitable for supplying acceleration signals along three orthogonal axes and processing the acceleration signals by a step recognition algorithm in order to identify specific signal changes (or patterns) that can be associated with steps performed by a user. However, the processing of the acceleration signals is calibrated on an "average" or "standard" user and does not take into account specific physical conditions or needs that may arise (even only temporary conditions or needs). For example, due to physical problems, a user can take very short steps or have a step that is different from the gait of an ordinary user used as a reference during the calibration of the step recognition algorithm. Similarly, in the case where the user has problems in the movement of the arm used by the software installed on the wearable device (e.g., a smart watch), this movement will not represent the step. Moreover, other unforeseen conditions may even prevent the correct calculation of the steps.

[0004] The electric field sensor is used as an alternative or in addition to an acceleration sensor for determining the activity of a user, or as an aid to interpreting signals generated by other sensor devices.

[0005] Electric charge is a fundamental part of nature. Electrons from one component can be easily transferred to another component when the components are in direct contact or at a distance. When charge is transferred between two electrically insulating objects, an electrostatic charge is generated, causing the object with an excess of electrons to be negatively charged, while the object with a deficit of electrons is positively charged.

[0006] Electrons move around in objects in various ways, depending on whether the object is conductive or insulating. In conductors, electrons are more or less evenly distributed throughout the material and can be easily moved due to external electric fields. In insulators, charges are primarily present on the surface. However, depending on the properties of the material and other environmental factors, charges can be mobile.

[0007] It is known to detect changes in the electric field generated by a person during his movement, or to use devices of the capacitance type of detection. Technologies using the latter type of detection include, for example, touch screens, systems for detecting the position of the occupants of a motor vehicle, and devices for determining the position, orientation and mass of an object, such as, for example, described in patent document US 5,844,415, which relates to a device for detecting an electric field in order to determine the position, mass distribution and orientation of an object in a defined space by arranging a plurality of electrodes in the defined space. Moreover, the above technical solution can be used to recognize the gestures of the user, the position and orientation of his hands, for example, for interactive use with a processing system other than a mouse or a joystick.

[0008] Patent document US2014 / 232516 proposes using electrostatic charge sensors to obtain physiological parameters or user activities (such as walking, cycling or energy consumption) from field or capacitive sensors.

[0009] However, none of the above-mentioned documents teaches a method of counting steps by using a sensor for detecting a change in electric charge or electrostatic charge.

[0010] The scientific paper "Development of Non-Contact Measurement System of Human Stepping" published by K. Kurita at the SICE Annual Conference 2008 in Japan describes a system and method for counting steps performed by a subject using a non-contact technology. The technology envisages detecting the electrostatic induced current generated as a direct result of the subject's movement in the environment by electrodes set at 1.5m from the subject. However, the experiments described in the document were performed under ideal conditions and are only a demonstration of the applicability of the technology in step counting. The document does not teach a technology that can be applied to real life conditions, in which, in addition to taking steps, the subject performs a variety of other activities, each of which causes a change in the electrostatic charge detected by the sensor. In these conditions, detecting the signal component due solely to the subject's steps is complicated and does not guarantee a high degree of reliability regarding the correctness of the detection and the subsequent counting. Summary of the invention

[0011] According to the present disclosure, a system and method for detecting a user's steps are provided.

[0012] In some embodiments, the present disclosure facilitates or provides systems and methods in which double confirmation is facilitated by a sensor for detecting changes in electrostatic charge and by an accelerometer before confirming that a step was performed.

[0013] Embodiments of the present disclosure remedy or otherwise overcome the shortcomings of the prior art by providing a system for detecting steps (or a step counter system) that is inexpensive, reliable, and involves a low computational load.

[0014] In one or more embodiments, the present disclosure provides a system for detecting a user's steps, the system comprising a processing circuit device, a sensor, and an accelerometer. The sensor is coupled to the processing circuit device, and the sensor is configured to detect a change in the user's electrostatic charge during the user's execution of a step, and to generate a charge change signal. The accelerometer is coupled to the processing circuit device, and is configured to detect acceleration caused by the user's steps, and to generate an acceleration signal. The processing circuit device is configured to: obtain the charge change signal; obtain the acceleration signal; detect a first characteristic identifying the user's steps in the charge change signal; detect a second characteristic identifying the user's steps in the acceleration signal; and confirm that the user is performing a step in response to detecting both the first characteristic and the second characteristic.

[0015] In one or more embodiments, the present disclosure provides a portable electronic device that includes a system for detecting a user's steps.

[0016] In one or more embodiments, the present disclosure provides a method for detecting a user's steps, the method comprising: supplying a charge change signal through a sensor, the sensor being configured to detect a change in the user's electrostatic charge during a step performed by the user; supplying an acceleration signal through an accelerometer, the accelerometer being coupled to a processing circuit device and being configured to: detect acceleration caused by the user's steps; detect a first characteristic identifying the user's steps in the charge change signal; detect a second characteristic identifying the user's steps in the acceleration signal; and confirming that the user has performed a step in response to detecting both the first characteristic and the second characteristic. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] For a better understanding of the present disclosure, embodiments of the present disclosure will now be described by way of non-limiting examples only and with reference to the accompanying drawings, in which:

[0018] Figure 1 is a schematic diagram of a system for detecting steps including an accelerometer and a sensor for detecting charge changes according to an embodiment of the present disclosure;

[0019] Figure 2 An embodiment of a sensor that may be worn by a user for detecting changes in charge is illustrated.

[0020] Figure 3A Picture shows Figure 1 and Figure 2 a signal generated at an output from a sensor for detecting a change in charge;

[0021] Figure 3B The diagram shows the Figure 1 The signal generated at the output of the accelerometer;

[0022] Figure 4 The block diagram illustrates a method according to an embodiment of the present disclosure. Figure 1 A method for implementing a system for detecting steps;

[0023] Figure 5 The block diagram illustrates the Figure 4 An alternative embodiment of the embodiment of Figure 1 A method for implementing a system for detecting steps;

[0024] Figure 6 The block diagram illustrates the Figure 4 and Figure 5 An alternative embodiment of the embodiment of Figure 1 A method for detecting steps implemented by a system; and

[0025] Figure 7 The diagram includes Figure 1 A device for a system for detecting steps. DETAILED DESCRIPTION

[0026] Figure 1 is a schematic diagram of a step detection system 1 according to one aspect of the present disclosure. The step detection system 1 includes a processing circuit device 2 (which may be referred to as a processing unit 2 in this document), an accelerometer 4 coupled to the processing unit 2, and a sensor 6 for detecting electrostatic charge changes coupled to the processing unit 2.

[0027] The accelerometer 4 is configured in a manner known per se to detect at least an acceleration component along a vertical acceleration axis (Z axis, ie a direction parallel to the gravity vector).

[0028] The processing unit 2 receives the acceleration signal S from the accelerometer 4 A , and receives the charge change signal S from the sensor 6 Q , in order to detect the change of electrostatic charge, and according to the acceleration signal S A and the charge change signal S Q Generate the number of steps N for the userS (Not shown).

[0029] Preferably, the accelerometer 4 is a three-axis accelerometer, i.e. suitable for detecting accelerations along three mutually orthogonal directions X, Y, Z. For example, the accelerometer 4 is an integrated sensor of semiconductor material of a type known per se provided in MEMS technology, and therefore will not be described in detail. In use, according to one embodiment, the accelerometer 4 detects the component of the vertical acceleration generated when taking a step along the sensing axis Z, and generates a corresponding acceleration signal S A ( Figure 3B ). In any case, it is apparent that, in general, the present disclosure may also use acceleration information on other sensing axes (X-axis and / or Y-axis) of the accelerometer.

[0030] The processing unit 2 is, for example, a microcontroller or an MLC (Machine Learning Core) residing in an integrated ASIC (Application Specific Integrated Circuit) in a MEMS.

[0031] The step detection system 1 is formed, for example, in an integrated form on the same printed circuit board, or in an integrated form in a MEMS device that houses the circuit. In fact, it is possible to envisage a device in which, in addition to the three axes X, Y, Z of the accelerometer 4, several sensors ("combinations") may be present, as well as dedicated channels for other detections (e.g., detection by gyroscopes, temperature sensors, etc.), including sensors for detecting electrostatic charge variations and subsequent ones.

[0032] In one embodiment ( Figure 5 ), the step detection system 1 forms part of a device 1 which is wearable by a user, for example on his wrist, so as to be fixed relative to the user's body, and which is in electrical contact with an area of ​​the user's body (e.g. the wrist). The device 1 is therefore affected by both the vertical acceleration caused by the foot striking the ground during a step (and optionally along other axes, as mentioned previously) and the electrostatic charge changes caused by the user's movements (in particular, by the steps taken).

[0033] Figure 2 An embodiment of a sensor 6 for detecting changes in electrostatic charge is illustrated by way of non-limiting example. The sensor 6 for detecting changes in electrostatic charge comprises a pair of input electrodes 8a, 8b which can be coupled to a portion 10 of a user's body. Specifically, Figure 2 The sensor 6 for detecting a change in electrostatic charge is configured to be placed in direct contact with a body part of a user.

[0034] The pair of input electrodes 8a, 8b represent the differential inputs of the instrumentation amplifier 12 and, in use, receive an input voltage Vd.

[0035] The instrumentation amplifier 12 is basically composed of two operational amplifiers OP1 and OP2. A bias stage (buffer) OP3 is used to bias the common mode voltage V CM The instrumentation amplifier 12 is biased at this location.

[0036] The inverting terminals of the operational amplifiers OP1 and OP2 are connected together through a resistor R2. Since the two inputs of each operational amplifier OP1, OP2 should be at the same potential, the input voltage Vd will also be applied to the end of R2, and the current equal to I2=Vd / R2 is made through the resistor R2. This current I2 does not come from the input terminals of the operational amplifiers OP1, OP2, and therefore flows through the two series resistors between the outputs of the operational amplifiers OP1, OP2 (from R1 to the resistor R2). Therefore, by flowing through the three series resistors R1-R2-R1, the current I2 produces an output voltage Vd' given by Vd'=I2(2R1+R2)=Vd(1+2R1 / R2). Therefore, Figure 2 The overall gain of the circuit will be Ad = (+2R1 / R2). The differential gain depends on the value of resistor R2 and can therefore be modified by acting on resistor R2.

[0037] Therefore, a differential output Vd′ proportional to the potential Vd between the input electrodes 8a, 8b is supplied at the input to the analog-to-digital converter 14, which supplies the charge change signal S at the output. Q , to describe the charge change signal S Q Sent to processing circuit 2. Charge change signal S Q For example a high resolution (16 or 24 bit) digital stream. The analog to digital converter 14 is optional as long as the processing unit 2 can be configured to work directly on analog signals or can itself comprise an analog to digital converter suitable for converting the signal Vd'.

[0038] By way of example, Figure 3A The charge change signal S is shown in FIG. Q .according to Figure 3A , charge change signal S Q There are a plurality of peaks p1-p7 which follow each other over time (indicated by the axis t of the abscissa). Each peak p1-p7 is generated as a result of a step detected by a sensor 6 for detecting electrostatic charge variations in the electrostatic charge variation of the user (input signal Vd). Figure 3A In the example, the values ​​on the ordinate axis are dimensionless.

[0039] As better illustrated below, the peaks p1-p7 are identified as the charge change signal S Q exceeds the threshold value ThQ The amount.

[0040] exist Figure 3B By way of example, the signal S at the output from the accelerometer 4 A are represented as a function of time t with respect to the detection axis only (e.g. the Z axis) and filtered from any possible non-significant frequency components. It should be noted that a step performed by the user is detected as an increasing acceleration in one direction (positive values ​​towards the axis of the ordinate representing the magnitude of acceleration, relative to a plateau value of 1G due only to gravity) and by a corresponding acceleration in the opposite direction (negative values ​​towards the axis of the ordinate, relative to a plateau value of 1). Figure 3B In , the dashed line between the intersection points c1 and c2 of the threshold 1G defines the steps. Figure 3B As shown, the acceleration signal S A The graph of has a given acceleration profile, which is repeated at each step (between c1 and c2). In detail, the acceleration profile includes: a positive part, in which there is a positive acceleration peak (i.e., pointing upward) due to the impact of the foot resting on the ground; and a negative part, in which there is a rebound (i.e., pointing downward) with an absolute value of a negative acceleration peak lower than the positive acceleration peak.

[0041] Furthermore, the following reference Figure 4 Step 110, the detection of which is described more fully.

[0042] Figure 4 The operations performed by the processing unit 2 are illustrated by means of a flow chart.

[0043] Referring to steps 100 and 101, the processing unit receives a charge change signal S from the sensor 6 and the accelerometer 4 for detecting electrostatic charge changes, respectively. Q and acceleration signal S A Steps 100 and 101 may be performed in parallel (simultaneously) or indiscriminately at consecutive moments in time.

[0044] Then, at steps 104 and 105, the processing unit 2 receives the signal S Q and S A The corresponding buffering operation is performed on the signal S (storing the data in a local memory) and filtering is performed (e.g., by a Kalman filter). Specifically, the filtering has the function of repurifying the signal S from noise or interference components at insignificant frequencies (e.g., 50 Hz or 60 Hz of the mains power supply), for example, by using a low-pass filter. Q and S A The filter used is configured according to the signal to be processed. For example, step 104 includes:Q Filtering; Step 105 (optional) includes: filtering the signal S through a low-pass filter (more specifically, the cut-off frequency is 100 Hz) A In practice, to determine the execution of a step, a slowly varying signal is preferred, for example a signal of only a few tens of hertz. Signals at higher frequencies are of little significance or may cause problems in processing.

[0045] Then, at step 108, the charge change signal S that identifies the steps taken by the user is extracted. Q The amount.

[0046] To this end, the threshold Th Q ( Figure 3A ) is used to identify the charge change signal S Q Component, charge change signal S Q Specifically, the charge change signal S Q Exceeding the threshold Th Q Associated with steps executed by the user.

[0047] In one embodiment, the threshold Th Q There are fixed and preset thresholds.

[0048] In another embodiment, the threshold Th Q is of adaptive type, i.e., it varies according to the charge change signal S Q By using the techniques known in the art, an adaptive type threshold Th can be performed. Q For example, a sliding window or overlapping windows can be used. Other techniques for calculating adaptive thresholds in real time can be used.

[0049] In an embodiment provided as an example, the threshold value Th Q Selected as signal S Q The average value (in the window under consideration) plus the signal S Q Multiple of the standard deviation (in the window considered): Th Q =mean(S Q )+n stddev(S Q ), where n is selected in the range between 2 and 6, for example, 4 (wherein the term "mean" is used to refer to the operation of calculating the arithmetic mean, and "stddev" refers to the operation of calculating the standard deviation).

[0050] The time window is for example chosen from suitable values. Said values ​​depend on the type of application; the Applicant has found that values ​​compatible with processing on a microcontroller (ie taking into account buffers, used memory and computing resources) range from 2s to 10s.

[0051] In step 108, the signal S of the accelerometer 4 A is not obtained by the processing unit, or in the signal S A When the signal S is obtained A is not processed to detect the execution of a step or to detect walking. In other words, during step 108, only the charge change signal S Q The pace is identified based on the

[0052] If the charge change signal S Q If at least one step is detected in the step S, step 110 is executed (arrow 108a at the output from block 108); vice versa (arrow 108b at the output from block 108), signal S is repeated. Q and S A The acquisition, storage, conversion to digital domain and the charge change signal S Q Processing is performed to detect the step of the step. Therefore, the charge change signal S Q Exceeding the threshold Th Q , generates the acceleration signal S A The corresponding trigger signal for processing.

[0053] Referring to step 110, in the signal S Q Based on the acceleration signal S A Processing is performed to confirm the presence of the step identified in step 108. Only if the charge change signal S Q The analysis of the acceleration signal S is performed only when the analysis of has produced a positive result (ie, when it has identified the presence of at least one step). A Vice versa, in the charge change signal S Q Below the threshold Th Q In this case, step 110 is not performed.

[0054] According to one aspect of the present invention, since the charge change signal S Q The charge change signal S may be generated and / or received by the processing unit 2 with respect to the signal of the accelerometer with a certain delay (for example, with a delay of tens of milliseconds or hundreds of milliseconds), so the processing unit 2 obtains the charge change signal S Q Exceeding the threshold Th Q The acceleration signal S from the previous moment A As described above, since the acceleration signal S is converted into A This is possible because the charge change signal S is detected. Q Exceeding the threshold ThQ Tens of milliseconds (10ms to 100ms) or hundreds of milliseconds (100ms to 800ms) before the moment of acceleration signal S A to be processed.

[0055] According to the prior art, for example, as described in EP1770368 or EP1770369, the acceleration signal S A Processing is performed to identify steps.

[0056] refer to Figure 3B , line Th A corresponds to a constant acceleration of 1 G (ie, corresponding to the gravity of the user under static conditions), and the line Th A Serves as a comparison threshold for detecting steps taken by the user. A The measurement of the accelerometer 4 indicated exceeds the threshold value Th A (or, in a different but equivalent embodiment, falls below a threshold value Th A For example, when the accelerometer 4 measures the signal S A The positive or upward slope of A Thus, in this example, the identified step corresponds to the step detected by the signal S A Towards a value higher than 1G, crossing the threshold Th A .

[0057] As previously described (with a constant comparison threshold Th A As an alternative to the above, an adaptive type of comparison threshold (e.g., a moving average threshold) can also be used, as described in patent application US2013 / 0085711 or in patent EP1770368. For example, the moving average threshold adjusts the comparison threshold based on the average value of the detected acceleration.

[0058] Furthermore, as an alternative to the aforementioned embodiment, it is also possible to perform a frequency analysis (eg by means of a Fast Fourier Transformation, FFT) and to apply a threshold in order to detect signals S exceeding said threshold. A frequency components of the signal. These components therefore identify the execution of a step. An example is described in patent application US2013 / 0085700. A frequency analysis can be performed on the data of the accelerometer in order to optionally determine the dominant frequency that can be used to select a band of a bandpass filter for filtering the signal. For example, if the dominant frequency is found to be 2 Hz, a filter with a frequency band of 1.5 Hz to 2.5 Hz can be selected to filter the signal. Filtering can unify the data for better analysis and detection of steps.

[0059] Then, in Figure 4 In step 112, if the check made in step 110 also yields a positive result, the step event is confirmed and the counter (N S +1) is incremented accordingly.

[0060] Figure 5 Another embodiment of the present disclosure regarding the steps performed by the processing unit 2 is illustrated. Figure 5 Pictured Figure 4 However, Figure 5 and Figure 4 Common blocks and operations are identified by the same reference numerals and will not be described further.

[0061] Specifically, Figure 4 and Figure 5 The embodiment of the present invention has blocks 100, 101, 104 and 105 and Figure 4 and Figure 5 .

[0062] However, according to Figure 5 In this embodiment, the acceleration signal S A is always acquired by the processing unit 2 and processed by the processing unit 2 (block 201) so as to obtain the data according to the prior art (e.g., according to the previous reference blocks 110 and Figure 3B Already identified method) Identify the steps.

[0063] When the process confirms that the user has taken a step, then (output 201a) control passes to block 202 where the charge change signal S Q is obtained and processed. Figure 3A The content described above, the charge change signal S Q processing.

[0064] Only when the charge change signal S Q Only when the processing of the step is confirmed that the step has been executed, control is passed to the block 112, wherein the detection of the step is confirmed and the step is counted. Otherwise (output 201b), the step is not confirmed / counted, and the signal S is acquired again. A and S Q , so that the steps of frames 100 to 105 are repeated.

[0065] In another embodiment, Figure 6 Middle icon ( Figure 6 and Figure 4 The common blocks are illustrated by the same reference numerals and will not be described again), the steps of blocks 108 and 110 are performed simultaneously, and then the corresponding results (corresponding signals S Q and S AThe identification of the steps in the signal S is sent to the processing unit 2. Then (step 301), the processing unit 2 checks to identify whether at corresponding moments (or intervals), the signal S Q and S A Both identify the user's execution steps.

[0066] Only in signal S Q and S A In the case where both identify steps (data from the outputs of boxes 108 and 110), control is passed (output 301a) to box 112, where the detected corresponding steps are confirmed and counted. Otherwise (output 301b), the steps 100 to 110 and 301 already described are repeated.

[0067] Figure 7 is a schematic diagram of a portable device 30 (eg, a pedometer, a smart watch, a smart phone, etc.), the portable device 30 comprising Figure 1 The system 1 further comprises a graphical user interface 32 connected to the processing unit 2. The graphical user interface 32 is connected to the output of the system 1 (specifically, the output from the Figure 4 The output of step 108) displays information, such as, in particular, the number of steps performed by the user; moreover, the user can use the graphical user interface 32 to enter data into the processing unit 2 or issue commands to the processing unit 2.

[0068] Finally, it is obvious that modifications and variations can be made to what has been discussed above without departing from the scope of the present disclosure.

[0069] For example, when detecting Figure 3A After the peaks p1-p7 in the signal S of FIG. 1 are detected, it is possible to perform the identification of such peaks (or more precisely, the signal S in the time interval including the peaks). Q ). For example, machine learning and / or artificial intelligence techniques may be used to automatically identify a signal S associated with a step performed by a user. Q of the user in order to distinguish different types of steps, such as: forward steps, backward steps, upward steps, downward steps, or footsteps on the ground without the user moving.

[0070] As an alternative, machine learning and / or artificial intelligence techniques may be used to automatically identify the signal S associated with the steps performed by the user. Q The specific mode, as the use of threshold TH Q An alternative solution to identify the signal S Q There are steps and / or step types in.

[0071] Likewise, an automatic pattern recognition algorithm associated with the steps taken by the user can be used to identify the acceleration signal S A The presence of steps and / or the type of steps in.

[0072] Furthermore, it should be noted that a charge change sensor of the type that cannot be worn by the user but is configured to detect at a distance the electrostatic changes generated after a step performed by the user can be used. In this case, only the accelerometer 4 is carried by the user for detecting the steps he has performed. This type of system is a distributed system and can be used, for example, for gaming or augmented reality applications in which the user performs his own movements in a delimited environment (e.g. a room).

[0073] From the foregoing description, the advantages achieved by the present disclosure are apparent.

[0074] In particular, the present disclosure significantly reduces false positives when counting steps of system users, so much so that the present disclosure contemplates double confirmation of confirmation of steps performed.

[0075] In addition, due to Figure 4 In the embodiment, the charge change signal S is first analyzed. Q The result of this analysis determines the accelerometer signal S A Subsequent processing (which would otherwise not be performed) can be performed, so a lot of computing resources and consumption levels can be saved, so that the accelerometer signal is processed only when necessary.

[0076] Likewise, reference Figure 5 , since firstly by analyzing the acceleration signal S A To identify the step, the mark determines the charge change signal S Q Subsequent processing (otherwise the charge change signal S Q Processing), so a lot of computing resources and consumption levels can be saved, so that the signal of the sensor 6 is processed only when necessary and the data provided by the accelerometer 4 is confirmed.

[0077] Therefore, in Figure 4 and Figure 5 In both embodiments, the reliability of the step detection / counting system is improved and the energy efficiency is optimized at the same time.

[0078] The various embodiments described above can be combined to provide other embodiments. These and other changes can be made to the embodiments according to the above specific implementation. In general, in the following claims, the terms used should not be interpreted as limiting the claims to the specific embodiments disclosed in the specification and claims, but should be interpreted as including all possible embodiments and equivalents of the full scope of rights enjoyed by these claims. Therefore, the claims are not limited by the disclosure.

Claims

1. A system for detecting a user's steps, comprising: processing circuit devices; a sensor coupled to the processing circuitry, the sensor being configured to detect a change in electrostatic charge of the user during a step performed by the user and to generate a charge change signal, and the sensor being configured to be worn by the user to be in direct electrical contact with a body part of the user; as well as an accelerometer coupled to the processing circuitry and configured to detect acceleration due to the step of the user and to generate an acceleration signal, Wherein the processing circuit device is configured to: acquiring the charge change signal; Acquiring the acceleration signal; detecting in the charge change signal a first characteristic identifying the step of the user; detecting in the acceleration signal a second characteristic identifying the step of the user; as well as Responsive to detecting both the first characteristic and the second characteristic, performing the step by the user is confirmed. 2 . The system of claim 1 , wherein the processing circuitry is configured to detect the first characteristic before detecting the second characteristic, and the processing circuitry is configured to detect the second characteristic only if the first characteristic has been detected. 3 . The system of claim 1 , wherein the processing circuitry is configured to detect the second characteristic before detecting the first characteristic, and the processing circuitry is configured to detect the first characteristic only if the second characteristic has been detected.

4. The system according to claim 1, further comprising: The acceleration signal or the charge change signal is processed by a machine learning or artificial intelligence algorithm to identify a step type, wherein the step type includes at least one of the following: a step forward, a step backward, a step upward, a step downward, or footsteps on the ground without displacement of the user.

5. A system according to claim 1, wherein detecting the first characteristic includes at least one of the following: detecting a peak of the charge change signal exceeding a fixed threshold; detecting a peak of the charge change signal exceeding an adaptive threshold; or detecting a specific pattern of the charge change signal through a machine learning or artificial intelligence algorithm.

6. The system of claim 5, wherein detecting a peak of the charge variation signal exceeding an adaptive threshold comprises: calculating an average value assumed by the charge change signal in a time interval; calculating a standard deviation coefficient of the charge variation signal in the time interval; and The mean is added to a multiple of the standard deviation factor.

7. The system of claim 1, wherein detecting the second characteristic comprises at least one of: detecting a peak of the acceleration signal exceeding a fixed threshold; detecting a peak of the acceleration signal exceeding an adaptive threshold; or performing a frequency analysis of the acceleration signal.

8. The system of claim 1, wherein the sensor comprises an instrumentation amplifier and an analog-to-digital converter coupled at an output of the instrumentation amplifier.

9. The system of claim 1, configured to be worn by the user.

10. The system of claim 1, wherein confirming that the step is performed by the user comprises: A counter of the number of steps performed by the user is incremented.

11. A portable electronic device comprising the system for detecting the steps of a user according to claim 1.

12. The portable electronic device of claim 11, comprising at least one of the following: a pedometer, a smart watch, or a smart phone.

13. A method for detecting a user's steps, comprising: supplying a charge change signal via a sensor configured to detect a change in electrostatic charge of the user during a step performed by the user, wherein the sensor is configured to be worn by the user to be in direct electrical contact with a body part of the user; supplying an acceleration signal via an accelerometer, the accelerometer being coupled to processing circuitry and the accelerometer being configured to detect acceleration due to the step of the user; detecting in the charge change signal a first characteristic identifying the step of the user; detecting in the acceleration signal a second characteristic identifying the step of the user; as well as Responsive to detecting both the first characteristic and the second characteristic, performing the step by the user is confirmed.

14. The method of claim 13, wherein detecting the first characteristic is performed before detecting the second characteristic, and detecting the second characteristic is performed only if the first characteristic has been detected.

15. The method of claim 13, wherein detecting the second characteristic is performed before detecting the first characteristic, and detecting the first characteristic is performed only if the second characteristic has been detected.

16. The method according to claim 13, further comprising: The acceleration signal or the charge change signal is processed by a machine learning or artificial intelligence algorithm to identify a step type, wherein the step type includes at least one of the following: a step forward, a step backward, a step upward, a step downward, or footsteps on the ground without displacement of the user.

17. The method of claim 13, wherein detecting the first characteristic comprises at least one of: detecting a peak value of the charge change signal exceeding a fixed threshold; detecting a peak value of the charge change signal exceeding an adaptive threshold; or detecting a specific pattern of the charge change signal through a machine learning or artificial intelligence algorithm.

18. The method of claim 17, wherein detecting a peak of the charge variation signal exceeding an adaptive threshold comprises: calculating an average value assumed by the charge change signal in a time interval; calculating a standard deviation coefficient of the charge variation signal in the time interval; and The mean is added to a multiple of the standard deviation factor.

19. The method of claim 13, wherein detecting the second characteristic comprises at least one of: detecting a peak of the acceleration signal exceeding a fixed threshold; detecting a peak of the acceleration signal exceeding an adaptive threshold; or performing a frequency analysis of the acceleration signal.

20. The method of claim 13, wherein confirming that the step is performed by the user comprises: A counter of the number of steps performed by the user is incremented.

Images