CN113390387A - User context and activity detection device and method - Google Patents
User context and activity detection device and method Download PDFInfo
- Publication number
- CN113390387A CN113390387A CN202110276091.1A CN202110276091A CN113390387A CN 113390387 A CN113390387 A CN 113390387A CN 202110276091 A CN202110276091 A CN 202110276091A CN 113390387 A CN113390387 A CN 113390387A
- Authority
- CN
- China
- Prior art keywords
- signal
- change
- charge
- pressure
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000001514 detection method Methods 0.000 title abstract description 42
- 230000000694 effects Effects 0.000 title abstract description 13
- 230000008859 change Effects 0.000 claims abstract description 103
- 238000012545 processing Methods 0.000 claims abstract description 39
- 230000001174 ascending effect Effects 0.000 claims description 24
- 230000004044 response Effects 0.000 claims description 21
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 10
- 238000005516 engineering process Methods 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 4
- 239000000872 buffer Substances 0.000 description 4
- 239000003990 capacitor Substances 0.000 description 3
- 230000005684 electric field Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000037081 physical activity Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 239000004020 conductor Substances 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003989 dielectric material Substances 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 210000003414 extremity Anatomy 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000010921 in-depth analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010926 purge Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C5/00—Measuring height; Measuring distances transverse to line of sight; Levelling between separated points; Surveyors' levels
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C5/00—Measuring height; Measuring distances transverse to line of sight; Levelling between separated points; Surveyors' levels
- G01C5/06—Measuring height; Measuring distances transverse to line of sight; Levelling between separated points; Surveyors' levels by using barometric means
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Measuring Fluid Pressure (AREA)
Abstract
Embodiments of the present disclosure relate to user context and activity detection devices and methods. The user context and/or activity detection device envisages a pressure sensor configured to provide a pressure signal; an electrostatic charge change sensor configured to provide a charge change signal indicative of an electrostatic charge change associated with a user; and a processing unit coupled to the pressure sensor and the electrostatic charge variation sensor so as to receive the pressure signal and the charge variation signal and configured to process the pressure signal and the charge variation signal jointly so as to detect a level or height variation.
Description
Technical Field
The present solution relates to a user context and activity detection device and method, in particular for detecting level (or height in general) changes, more particularly floor changes, associated with going upstairs or downstairs in a building.
Background
Mobile electronic devices (such as smartphones, tablet computers, tablet phones, etc.) and wearable electronic devices (such as bracelets, smartwatches, headsets, etc.) are provided with a detection module that integrates multiple sensors (e.g., inertial motion sensors, pressure sensors, temperature sensors, etc.).
The detection module described above, in addition to providing information designed for managing the operation of the electronic device (for example for implementing a corresponding user interface), can also provide useful information for locating the user, for example in order to be able to provide messages, services or alarms associated with a scenario (so-called scenario-based or scenario-aware), and furthermore information associated with the body activity of the user, for example in order to monitor the consumption of calories or the distance covered.
In this respect, for example when the user is inside a building, it is useful to have the possibility to detect a change in level (or in general altitude), in particular a change in floor associated with the user going upstairs or downstairs, in order to propose an appropriate context-based activity, message, service or function; and furthermore to accurately monitor the body activity of the user within the building.
Detection modules for such mobile or wearable electronic devices generally require low power consumption, low latency (low response latency) and high accuracy.
In order to detect the above-mentioned level changes, a detection module based on a pressure sensor or an air pressure sensor is used, wherein the corresponding processing unit is configured to monitor changes in the pressure signal via a suitable algorithm and to identify a level change from the changes in the pressure signal.
For example, US 9,906,845B 2 filed in the name of the applicant envisages the use of a suitably configured state machine for processing the above-mentioned pressure signals.
Besides pressure sensors or barometric pressure sensors, other solutions also envisage the use of motion sensors, in particular acceleration sensors.
Disclosure of Invention
However, the above solutions are not entirely satisfactory, in particular because: in the case of both single technology solutions (based on a single pressure sensor) and dual technology solutions (based on a pressure sensor and a motion sensor), the computational cost is high; possible detection errors (so-called false positives or false negatives) due to noise and interference factors, for example caused by the user's limb movements (in the case of wearable electronic devices, such as bracelets or smartwatches); the delay is high since it is necessary to wait for a sufficient waiting time to prevent the above false detection; and the demand for buffer memory is high for temporarily storing data during the above-mentioned waiting time.
Furthermore, in general, the dual technology solution has a high footprint and high energy consumption, given that the pressure sensor and the motion sensor are generally made of two distinct and separate chips (each integrated in a respective package).
There is thus a felt need to overcome the drawbacks of the prior art, in particular floor changes, more particularly for detecting level changes associated with ascending or descending stairs in a building, and to be cheap but reliable and have a low computational load, by providing a user context and activity detection device and method.
In an embodiment, an apparatus comprises: a pressure sensor configured to provide a pressure signal; an electrostatic charge change sensor configured to provide a charge change signal indicative of a change in electrostatic charge; and a circuit device coupled to the pressure sensor and the electrostatic charge variation sensor and configured to detect a level variation based on the pressure signal and the charge variation signal. In an embodiment, the circuitry is configured to: processing a gradient of pressure over time associated with a change in the pressure signal to detect a first indication in a change in level; processing the change in the charge-variation signal over time to detect a second indication in the change in level; and in response to detecting the first indication and the second indication during the threshold time interval, determining an occurrence of a level change. In an embodiment, the level change is associated with a user ascending stair or descending stair, the first indication is detected in response to the pressure gradient exceeding a first pressure threshold in absolute value, the first pressure threshold is indicative of a change in a pressure signal associated with the ascending stair or descending stair, and the second indication is detected in response to detecting a change in a charge change signal associated with the user ascending stair or descending stair. In an embodiment, the circuit arrangement is configured to detect a change in the charge variation signal associated with the user's previous or next stairway by extraction and analysis of features of the charge variation signal. In an embodiment, the analysis of the characteristic of the charge variation signal comprises: detecting a peak value of the amplitude of the charge variation signal exceeding a threshold value; detecting a pattern of the charge variation signal; or a combination thereof. In an embodiment, the circuitry is configured to effect a count of upstairs or downstairs associated with the user based on the pressure signal and the charge change signal. In an embodiment, the circuitry is configured to: setting a baseline value of the pressure signal during a quiescent state; and at the end of the user's upstairs or downstairs: determining a difference between a current value of the pressure signal and a baseline value; determining a change in floor based on a comparison between the difference and a second pressure threshold, the second pressure threshold indicating a change in pressure signal associated with the user on the previous floor or the next floor; and increasing a count of floors raised or lowered by the user based on the determination of the change in floors. In an embodiment, wherein the electrostatic charge change sensor comprises: at least one electrode; an amplifier having an input coupled to at least one electrode; and an analog-to-digital converter coupled to the amplifier output for providing a charge variation signal. In an embodiment, the apparatus comprises an integrated circuit comprising the circuit arrangement, the pressure sensor and the electrostatic charge variation sensor.
In an embodiment, a system comprises: an application processor; sensing circuitry coupled to the application processor, the sensing circuitry comprising: a pressure sensor that generates a pressure signal in operation; a charge sensor operable to generate a charge signal; and control circuitry coupled to the pressure sensor and the charge sensor, wherein the control circuitry detects a change in level based on the pressure signal and the charge signal in operation. In an embodiment, the control circuitry is operable to detect a first indication of a change in level based on the pressure signal; detecting a second indication of a change in level based on the charge signal; and in response to detecting the first indication and the second indication during the threshold time interval, determining an occurrence of a level change. In an embodiment, the control circuitry is in operation: a first indication is detected based on a comparison of the pressure gradient to a first pressure gradient threshold. In an embodiment, the first pressure gradient threshold is indicative of a pressure gradient associated with ascending and descending stairs. In an embodiment, the control circuitry is in operation: a second indication is detected based on features extracted from the charge signal. In an embodiment, the control circuitry is in operation: detecting a second indication based on: a comparison of a peak value of the amplitude of the charge signal to a charge signal threshold; a mode detected in charge; or a combination thereof. In an embodiment, the control circuitry is operable to count the change in stride-level associated with the user based on the occurrence of the determined level change. In an embodiment, the control circuitry is in operation: setting a baseline value of the pressure signal in response to detecting the stationary state; and in response to an indication of the user going upstairs or downstairs: determining a difference between a current value of the pressure signal and a baseline value; determining a change in floor based on a comparison between the difference and a second pressure threshold, the second pressure threshold indicating a change in pressure signal associated with the user on the previous floor or the next floor; and increasing a count of floors raised or lowered by the user based on the determination of the change in floors.
In an embodiment, a method comprises: generating a pressure signal using a pressure sensor of the device; generating a charge signal using a charge sensor of the device; and detecting a change in the user level based on the pressure signal and the charge signal. In an embodiment, the method comprises: detecting a first indication of a change in user level based on the pressure signal; detecting a second indication of a change in user level based on the charge signal; and in response to detecting the first indication and the second indication during the threshold time interval, determining an occurrence of a user level change. In an embodiment, a method comprises: a first indication is detected based on a comparison of the pressure gradient to a first pressure gradient threshold. In an embodiment, wherein the first pressure gradient threshold is indicative of a pressure gradient associated with going upstairs or downstairs. In an embodiment, a method comprises: a second indication is detected based on features extracted from the charge signal. In an embodiment, the method comprises detecting the second indication based on: comparing the amplitude peak of the charge signal to a charge signal threshold; a detected pattern in the charge signal; or a combination thereof. In an embodiment, a method comprises: the change in stride-level associated with the user is counted based on the occurrence of the user-level change. In an embodiment, a method comprises: setting a baseline value of the pressure signal in response to detecting the stationary state; and in response to an indication by the user to go up or down stairs: determining a difference between a current value of the pressure signal and a baseline value; determining a change in floor based on a comparison between the difference and a second pressure threshold, the second pressure threshold indicating a change in pressure signal associated with the user on the previous floor or the next floor; and increasing a count of floors raised or lowered by the user based on the determination of the change in floors.
In an embodiment, a non-transitory computer-readable medium having contents to configure an electronic device to perform a method, the method comprising: generating a pressure signal using a pressure sensor of an electronic device; generating a charge signal using a charge sensor of an electronic device; and detecting a user level change based on the pressure signal and the charge signal. In an embodiment, a method comprises: detecting a first indication of a change in user level based on the pressure signal; detecting a second indication of a change in user level based on the charge signal; and in response to detecting the first indication and the second indication during the threshold time interval, determining an occurrence of a user level change. In an embodiment, the method comprises: the change in stride-level associated with the user is counted based on the occurrence of the user-level change. In an embodiment, the content includes instructions executed by sensor signal processing circuitry of the electronic device.
According to the present solution, a detection device and method are provided.
Drawings
For a better understanding of the present disclosure, embodiments thereof are now described, by way of non-limiting example only, and with reference to the accompanying drawings, in which:
fig. 1 is a schematic view of a detection device according to an embodiment of the present solution;
FIG. 2 shows a possible embodiment of an electrostatic charge variation sensor of the detection device of FIG. 1;
fig. 3 shows a flow chart of a method implemented by the detection device of fig. 1 according to an embodiment of the present solution;
fig. 4 and 5 are graphs showing electrostatic charge variation signals detected when a user goes upstairs/downstairs; and
FIG. 6 is a general block diagram of an electronic device that may use the detection apparatus of FIG. 1.
Detailed Description
As will be described in detail below, one aspect of the present solution envisages the joint use of a detection device based on a combination of a pressure sensor (or barometric pressure sensor) and an electrostatic charge variation sensor, for user context and activity detection, in particular for detecting a change in level or altitude associated with going upstairs or downstairs in a building, more particularly a change in floor level.
Charge is an essential component of nature. In the case of direct contact or remote distance, the charge of the electrostatically charged body can be easily transferred to another body. When charge is transferred between two electrically insulating objects, an electrostatic charge is generated, so that objects with too many electrons are negatively charged, while objects with insufficient electrons are positively charged. The displacement of the charge has different properties depending on whether the object is a conductive object or a dielectric. In a conductor, electrons are distributed throughout the material and are free to move under the influence of an external electric field. In a dielectric, there are no freely movable electrons, only electric dipoles, with random orientation in space (so the net charge produced is zero), however, by applying an external electric field, the electric dipoles can be oriented or deformed, thus generating an ordered distribution of charges, thus polarizing. The charge is in any case mobile, depending on the nature of the material and other environmental factors.
In an embodiment of the present solution, the electrostatic charge variation sensor of the detection device is configured to detect, by means of capacitive detection, electric field variations occurring during movement of the user, so that the charge is transferred from the body of the user to the ground when the user performs a stride, in particular when ascending or descending stairs.
Fig. 1 is a schematic view of a detection device 1 according to an embodiment of the present solution, comprising:
the pressure sensor 2, for example an integrated sensor made of semiconductor material in MEMS technology of a type known per se (not described in detail herein), and designed to provide a pressure signal SPIndicating a pressure or a pressure change according to the pressure (or air pressure) acting on the detection device 1;
the electrostatic charge variation sensor 4, an embodiment of which will be described in detail below, is designed to provide a charge variation signal SQCharge variation signal SQIndicating a change in electrostatic charge associated with a user; and
a processing unit 6 coupled to the pressure sensor 2 and the electrostatic charge variation sensor 4 for receiving the pressure signal SPAnd a charge variation signal SQAnd is configured to jointly process the above-mentioned pressure signals SPAnd a charge variation signal SQTo detect a level change, more specifically a change in floor associated with a user ascending or descending stairs.
The processing unit 6 comprises, for example, a microcontroller or an MLC (machine learning core) processor, which resides in an ASIC (application specific integrated circuit) coupled to the pressure sensor 2 and the electrostatic charge variation sensor 4 for processing the corresponding pressure signal SPAnd a charge variation signal SQ(ii) a The pressure sensor 2, the electrostatic charge variation sensor 4 and the processing unit 6 described above may be provided within the same package provided with suitable elements for electrical connection with the external environment (for example, for connection to host electronics, such as mobile or wearable equipment).
Fig. 2 shows an embodiment of the electrostatic charge variation sensor 4, provided by way of non-limiting example, the electrostatic charge variation sensor 4 comprising at least one input electrode 8, designed to be arranged in direct contact or in proximity with a portion of the user's body.
For example, in case the detection device 1 is integrated in a wearable device (such as a smart watch), the input electrodes 8 may be arranged outside the corresponding housing so as to be in direct contact with the wrist of the user. However, it is emphasized that direct contact with the conductive material of the electrodes is generally not required. For example, it is also conceivable to perform the separation by means of a dielectric material having a thickness in the order of millimeters.
The input electrode 8 forms part of a differential input 9 of an instrumentation amplifier 12, the instrumentation amplifier 12 being coupled to a corresponding first input terminal 9 a.
Between the first input terminal 9a and the second input terminal 9b of the differential input 9, a capacitor C is inputIAnd an input resistor RIAre connected in parallel with each other.
During operation, at the input capacitor CIInput voltage V at both endsdDue to variations through the charging and discharging process of the user's body, in particular due to contact with the ground, more particularly due to the user going up or down stairs. In the transient (its duration is defined by the capacitor C)IAnd a resistor RIR defined in parallel betweenI·CIConstant given), the input voltage VdReturning to its steady state value.
The instrumentation amplifier 12 is basically constituted by two operational amplifiers OP1 and OP2 having non-inverting input terminals connected to the first input terminal 9a and the second input terminal 9b, respectively, and via a gain resistor RG2Inverted terminals connected together.
The bias stage (buffer) OP3 passes through a resistor R coupled to the second input terminal 9b1 Biasing instrumentation amplifier 12 to common mode voltage VCM。
Output terminals of the operational amplifiers OP1 and OP2 are via respective gain resistors RG1Connected to respective inverting input terminals; an output voltage V exists between the output terminalsd’。
The gain of instrumentation amplifier 12 is equal to (1+2 · R1/R2); therefore, the above-mentioned output voltage Vd' is equal to: vd (1+ 2. R1/R2).
The components that select instrumentation amplifier 12 may be selected such that the same instrumentation amplifier 12 has low noise and high impedance (e.g., 10 Hz) in its operating bandwidth (e.g., included between 0Hz and 500 Hz)9Amount of omegaStages).
The output voltage Vd' is provided at an input of an analog-to-digital converter (ADC)14, the ADC 14 providing at an output thereof the above-mentioned charge variation signal S for the processing unit 6Q. Charge variation signal SQFor example a high resolution digital signal (having 16 or 24 bits).
According to various embodiments, if the analog-to-digital converter 14 has suitable characteristics (e.g. differential input, high input impedance, high resolution, dynamic range optimized for the quantity to be measured, low noise), the instrumentation amplifier 12 may be omitted, in which case the input voltage VdIs provided directly to the input of the analog-to-digital converter 14.
In a manner not shown, the charge variation signal SQMay be provided to a first input of the multiplexer block, and may furthermore receive the above-mentioned pressure signal S on at least one further inputP(and possibly an additional detection signal on a further input, such as a temperature signal). In this case, the output of the multiplexer block is coupled to the input of the processing unit 6 in order to provide the above-mentioned charge variations S sequentially in timeQAnd pressure SPThe signals (and possibly further detection signals) for joint processing by the processing unit 6.
Fig. 3 shows by means of a flow chart a possible embodiment of the present solution by varying the signal S by the processing unit 6 for the chargeQAnd a pressure signal SPThe operation of the joint process is performed.
In an embodiment, the processing unit 6 is configured to execute two different processing branches in parallel (in a substantially simultaneous manner), one for processing the charge variation signal SQAnd the other for processing the pressure signal SP(in the embodiment described, both signals are of the digital type) and, based on the results of the above-mentioned processing branches, detect in a joint manner a level change, more particularly a floor change, associated with the user ascending or descending stairs.
In detail, the first processing branch designated by 20 envisages that, at an initial step (for example, when the user enters a building or similar closed environment), at block 21, a variable "level" representing the count of floors or levels upstairs or downstairs by the user and a variable "stride" representing the count of strides taken by the user during upstairs or downstairs activities are initialized to zero.
In particular, "level 0" denotes the initial starting layer; "horizontal-1" means the layer of the user directly below the starting level; "level + 1" means that the user is located in a layer directly above the starting level; and so on.
In addition, in block 22, the pressure signal S determined at the start level ("level 0") is setPA baseline level of (d); also, in block 23, the value of the state variable "state" is set to "on the floor" (which may also assume the values "going upstairs" and "going upstairs end" depending on the user's activity, as shown below).
In block 24, the value of the pressure gradient G, which is represented by the pressure signal S, is then calculated continuously in time within the circulation loopPIn particular the difference between the current value (in particular the sample) and the previous value of (a).
The above-mentioned pressure gradient G is compared in absolute value with a first pressure threshold Th, which may be a determined value of a preset value, as indicated by block 25P1Making a comparison, the first pressure threshold ThP1Indicating a change in the pressure signal associated with the upper or lower stairs (the first pressure threshold ThP1May be predetermined or determined in an initial characterization phase).
If the pressure gradient G is lower in absolute value than a first pressure threshold ThP1The process returns to block 24 to calculate a new value for the pressure gradient (taking into account the pressure signal S)PThe next value of (d).
Conversely, if the pressure gradient G is equal to or higher than the first pressure threshold Th in absolute valueP1The first processing branch provides a first indication of the fact that the user is ascending or descending stairs, in particular has ascended or descended.
In parallel, a second processing branch, designated by 30, is envisaged, such asThe charge variation signal S is processed in a corresponding loop, shown in block 31, continuously in timeQ(possibly subject to appropriate filtering action initially).
In the embodiment shown, by way of example, the above-mentioned block 31 is performed after the previously described block 24.
In particular, at block 32, the charge variation signal S is first appliedQA preliminary check is made to identify significant changes from a reference (or baseline) value.
In a possible embodiment, the above-mentioned preliminary check may be via the charge variation signal SQAnd a charge threshold ThQIs performed. Threshold value Th of electric chargeQMay be fixed and may be preset or, alternatively, may be adaptive, e.g. dependent on the charge variation signal SQMay vary. Adaptive type of charge threshold ThQThe calculation of (c) can be performed by utilizing techniques known in the art; for example, sliding or overlapping windows, or other techniques for real-time adaptive threshold computation, may be used.
In a possible embodiment, the charge threshold ThQCan be selected as the charge variation signal SQAverage value (in the considered time window) plus the same charge variation signal SQThe multiples of the standard deviation (in the considered window) are as follows:
ThQ＝mean(SQ)+n·stddev(SQ)，
where "n" is selected in the range between 2 and 6, for example 4 (where "mean" denotes the operation of arithmetic mean and "stddev" denotes the operation of standard deviation). The time window may be chosen to be of an appropriate value. The value depends on the type of application; the applicant has found that values compatible with processing on the microcontroller (taking into account buffers, used memory and computational resources), for example, the time window may be in the range of 2 to 10 seconds.
If the signal S changes for the chargeQDoes not cause an indication of a significant change, the process returns to block 31 to change the same chargeChange signal SQA new processing cycle is performed.
On the contrary, if the aforementioned charge variation signal SQIs identified, a charge variation signal S is appliedQA further and more in-depth analysis is performed in order to verify the presence of features indicating the steps taken by the user, in particular whether the same user is already an upper or a lower stair.
The above further analysis may envisage that in a simpler (and less cumbersome from a computational point of view) embodiment, the identification is at the charge variation signal S, due to the transfer of the electrostatic charge to groundQWith respect to a reference value (positive and/or negative).
As will also be pointed out below, the applicant has in fact verified that the charge variation signal S is identified each time a step, in particular in the case of a user ascending or descending stairs, due to the above-mentioned transfer of charge from the user' S body to the groundQThe probability of a peak in (c).
In a different embodiment, as illustrated in fig. 3 above, this is more tedious from a computational point of view, but ensures improved accuracy in detecting these strides, possibly by extracting the charge variation signal SQAnd a double step of analyzing the extracted features (block 34) to perform the charge variation signal S (block 33)QThe above further analysis.
The above significant features characterize the charge-variation signal SQE.g. corresponding envelopes, and may be obtained by processing the same charge variation signal SQTo identify and detect. Advantageously, performing the above-described feature extraction and analysis operations, suitably trained machine-learning artificial intelligence algorithms (models) can be used, for example by means of neural networks, SVMs, bayesian networks, etc.
According to a further analysis, in block 35 it is checked whether there is a feature in the charge variation signal SQ that indicates a step taken by the user (in particular, a step corresponding to a staircase).
If no such feature is present, the process assumes the same charge variation signal SQIn this example, back to block 24 described above.
Otherwise, the second indication provides the fact that the user is ascending or descending stairs (in particular the same user has been ascending or descending stairs).
In particular, in block 40, the process envisages verifying the simultaneous presence of the aforesaid first and second indications substantially at the same moment, at the same time interval or within a threshold time period, so as to verify (in the case of a positive result of verifying the aforesaid simultaneous presence) the detection of the fact that the user has ascended the stairs or descended the stairs. In other words, in block 40, the AND operation is performed (time) between the first indication and the second indication.
It is to be noted that in any case a certain delay (for example of the order of tens of milliseconds) between the two detections of the first indication and of the second indication is acceptable, since it is a normal delay (operations performed by means of processes different from each other) of the generation, acquisition and processing of the two signals.
In the event that the simultaneous presence of the first indication and the second indication is validly verified, control passes from block 40 to block 41, where the state variable "state" is set to the value "is ascending stairs".
In addition, at block 42, the variable "stride" is incremented (stride + 1).
In a possible embodiment, two different counters may be used to count going upstairs or downstairs. The distinction between ascending and descending stairs may be based solely on the pressure gradient G, depending on whether it is positive or negative. Alternatively, advantageously, a pressure gradient G and a charge variation signal S may be performedQJoint evaluation of further features of (1). As will be highlighted below, in fact, the signal S can be varied by varying the chargeQThere are different features in the pattern to distinguish between ascending and descending stairs.
As highlighted in block 44, the pressure signal S is thenPAnd a charge variation signal SQUntil the pressure signal S is processedPThe check performed indicates its stationarity.
At one endIn one embodiment, the stationarity check includes, for example, verifying the pressure signal SPWhether there is a significant change (relative to a given threshold) within a given time interval.
In verifying the pressure signal SPAfter quiescence, a further check is made to verify whether the user is actually going up floor or down floor (instead of, for example, returning his steps to the starting level).
For this purpose, block 46, the pressure signal S is calculatedPIs compared with the same pressure signal SPThe difference in pressure between the (previously set) baseline levels, and a check is made to verify whether the difference in absolute value is greater than a second pressure threshold Th of a determined valueP2Second pressure threshold Th of a determined valueP2May be a preset threshold value, the second pressure threshold value ThP2Indicating a change in pressure signal associated with the first floor upwards or downwards (second pressure threshold Th)P2The value of (d) can be determined in advance or in an initial characterization step).
If said pressure difference is lower in absolute value than a second pressure threshold ThP2The process returns to the above-mentioned block 24, a new cycle of the pressure gradient G is carried out, and the charge variation signal S is carried out in parallelQAnd (4) carrying out new circulation treatment.
On the contrary, if the above-mentioned pressure difference is greater than or equal to the second pressure threshold value Th in absolute valueP2Then the state variable "state" is set to the value "end of stairs", block 47; in addition, the variable "level" is incremented (or decremented, according to the sign of the pressure differential) by the level ± 1, block 48.
Processing then returns to block 22, where the pressure signal SPIs set as the pressure signal SPAfter which processing continues in a loop as previously described.
Fig. 4 shows a pattern of charge variation signals SQ during the user's upstairs, as schematically shown, occurring within a time interval identified by Δ T. In particular, it is clear that for each step up the building, a peak (indicated by a dot) appears, and changes in charge occurChange signal SQThe characteristic pattern (indicated by the rectangular box) in (a) can thus be identified via processing of the signal by the processing unit 6.
Again indicated in fig. 4 is the charge threshold ThQE.g. with respect to the charge variation signal SQIs calculated in an adaptive manner, in particular with respect to the same charge variation signal SQAverage value of (whose pattern is traced with a dashed line). Therefore, in this case, the peak refers to the above-described charge threshold ThQ。
Furthermore, it is apparent that outside the above-mentioned time interval Δ T, for example in the case of a normal walking of the user, the charge variation signal SQ has quite different characteristics, in particular below the charge threshold ThQOf the amplitude of (c).
Fig. 5 again shows a pattern of the charge variation signal SQ, this time both during an activity of the user going down stairs (time interval identified by "down") and during an activity of the user going up stairs (time interval identified by "up").
It is apparent how the characteristic pattern of the signal at each step up the stairs is different in sensing from the characteristic pattern of the signal at each step down the stairs, so that the stairs up and down and the corresponding different counts can be identified as discussed previously. In particular, as shown in the block section (provided by way of example for a single stride), during descent of the stairs, a natural movement or braking is performed by the user, contrary to gravity, which determines the charge variation signal S that is not present when the user ascends the stairsQThe characteristic pattern of (1).
Fig. 6 is a schematic view of an electronic device 50 comprising a detection apparatus 1 as previously described; for example, the electronic device 50 is a mobile electronic device (such as a smartphone, tablet computer, tablet phone, etc.) or a wearable device (such as a bracelet, smart watch, headset, etc.).
The electronic device 50 comprises a main controller 52 (microcontroller, microprocessor or similar digital processing unit), which main controller 52 is coupled to the processing unit 6 of the detection apparatus 1 in order to receive information about floor changes or level changes, more particularly information associated with a user going up or down stairs.
In the previously described embodiment, the main controller 52 receives the detected values for the level, stride and state variables, for example from the processing unit 6 of the detection device 1, in order to provide context-based messages, services or alarms, in a manner known per se (not described in detail herein), and in addition to retrieve information associated with the body activity of the user, for example in order to monitor the consumption of calories or the covered distance.
The advantages achieved by the present solution emerge clearly from the above description.
In any case, it is again emphasized that in the detection device 1, the monitoring of the change in charge can enhance the information associated only with the pressure detection.
In particular, the detection device 1 is able to optimize performance (in particular, reduce the number of false detections, false positives and false negatives), have an optimized energy consumption and a reduced space occupation (in particular, integrate the two detection techniques, pressure detection and charge variation detection, in a single package).
As mentioned before, there is also a change from charge signal SQAn advantageous possibility to obtain information about going upstairs or downstairs, which information can be used in conjunction with information about the pressure gradient G to improve the accuracy of the detection.
In this respect, it is noted that known step count solutions based on acceleration sensors, on the contrary, do not allow to distinguish between steps when ascending stairs and when descending stairs.
Furthermore, the present solution has reduced latency and reduced memory usage (e.g., does not require the use of large size buffer memory).
Finally, modifications and variations may be made to the present solution without thereby departing from the scope identified by the appended claims.
In particular, in a manner not shown, it is possible to envisage applying the pressure S before the treatment operation describedPAnd change of charge SQThe signal is subjected to an appropriate filtering operation (e.g., using a low-pass filter or a high-pass filter). FilteringMay have a purge pressure signal SPAnd a charge variation signal SQIs made immune to noise or non-significant frequency (e.g., the frequency of the charge variation signal SQ is about 50Hz or 60Hz) interference components. The charge variation signal SQ can likewise be subjected to a frequency analysis (for example by means of a fast fourier transform-FFT) in order to identify its characteristics, in order to identify whether the user is ascending or descending stairs, and to perform a corresponding step counting.
In a way not shown, the detection device 1 can integrate other sensors (for example, gyroscopes, temperature sensors, etc.) and envisage other processing channels dedicated to other detections.
Furthermore, the processing unit 6 of the detection device 1 may be configured to be based on the pressure signal SPAnd corresponding pressure gradients to detect level changes associated with the use of the elevator by the user, for example as described in detail in the above-mentioned document US 9,906,845B 2.
Some embodiments may take the form of or include a computer program product. For example, according to an embodiment, a computer-readable medium is provided, comprising a computer program adapted to perform one or more of the above-described methods or functions. The medium may be a physical storage medium such as a read-only memory (ROM) chip, or a magnetic disk such as a digital versatile disk (DVD-ROM), a compact disk (CD-ROM), a hard disk, a memory, a network, or a portable media item, for reading by a suitable drive or via a suitable connection, including encoded in one or more bar codes or other associated code stored on one or more such computer-readable media and readable by a suitable reader device.
Further, in some embodiments, some or all of the methods and/or functions may be implemented or provided in other ways, such as at least partially in firmware and/or hardware, including but not limited to one or more Application Specific Integrated Circuits (ASICs), digital signal processors, discrete circuit devices, logic gates, standard integrated circuits, controllers (e.g., by executing appropriate instructions and including microcontrollers and/or embedded controllers), Field Programmable Gate Arrays (FPGAs), Complex Programmable Logic Devices (CPLDs), and the like, as well as devices employing RFID technology, and various combinations thereof.
The various embodiments described above can be combined to provide further embodiments. Aspects of the embodiments can be modified, if necessary, to employ concepts of the various patents, applications and publications to provide yet further embodiments.
These and other changes can be made to the embodiments in light of the above-detailed description. In general, in the following claims, the terms used should not be construed to limit the claims to the specific embodiments disclosed in the specification and the claims, but should be construed to include all possible embodiments along with the full scope of equivalents to which such claims are entitled. Accordingly, the claims are not limited by the disclosure.
Claims (29)
1. An apparatus, comprising:
a pressure sensor configured to provide a pressure signal;
an electrostatic charge change sensor configured to provide a charge change signal indicative of a change in electrostatic charge; and
circuitry coupled to the pressure sensor and the electrostatic charge change sensor and configured to detect a level change based on the pressure signal and the charge change signal.
2. The apparatus of claim 1, wherein the circuitry is configured to:
processing a pressure gradient over time associated with a change in the pressure signal to detect a first indication of a change in level;
processing the change in the charge-variation signal over time to detect a second indication of a change in level; and
in response to detecting the first indication and the second indication during a threshold time interval, determining an occurrence of a level change.
3. The apparatus of claim 2, wherein the change in level is associated with a user ascending stair or descending stair, the first indication is detected in response to the pressure gradient exceeding, in absolute value, a first pressure threshold indicative of the change in the pressure signal associated with an ascending stair or descending stair, and the second indication is detected in response to detecting a change in the charge change signal associated with the user ascending stair or descending stair.
4. The apparatus of claim 3, wherein the circuitry is configured to detect a change in the charge variation signal associated with the user's ascending stair or descending stair by extraction and analysis of features of the charge variation signal.
5. The apparatus of claim 4, wherein the analysis of the characteristic of the charge-variation signal comprises:
detecting a peak in the amplitude of the charge variation signal that exceeds a threshold;
detecting a pattern of the charge variation signal; or
Combinations of the above.
6. The apparatus of claim 3, wherein the circuitry is configured to enable counting of up stairs or down stairs associated with the user based on the pressure signal and the charge change signal.
7. The apparatus of claim 3, wherein the circuitry is configured to:
setting a baseline value of the pressure signal during a quiescent state; and
at the end of the user ascending or descending stairs:
determining a difference between a current value of the pressure signal and the baseline value;
determining a change in floor based on a comparison between the difference and a second pressure threshold indicative of the change in the pressure signal associated with the user on the previous floor or the next floor; and
increasing a count of floors ascended or descended by the user based on the determination of a floor change.
8. The apparatus of claim 1, wherein the electrostatic charge change sensor comprises:
at least one electrode;
an amplifier having an input coupled to the at least one electrode; and
an analog-to-digital converter coupled to an output of the amplifier for providing the charge variation signal.
9. The apparatus of claim 1, comprising an integrated circuit including the circuit arrangement, the pressure sensor, and the electrostatic charge variation sensor.
10. A system, comprising:
an application processor;
sensing circuitry coupled to the application processor, the sensing circuitry comprising:
a pressure sensor that, in operation, generates a pressure signal;
a charge sensor that, in operation, generates a charge signal; and
control circuitry coupled to the pressure sensor and the charge sensor, wherein the control circuitry detects a level change based on the pressure signal and the charge signal in operation.
11. The system of claim 10, wherein the control circuitry, in operation,
detecting a first indication of a change in level based on the pressure signal;
detecting a second indication of a change in level based on the charge signal; and
in response to detecting the first indication and the second indication during a threshold time interval, determining an occurrence of a level change.
12. The system of claim 11, wherein the control circuitry, in operation:
detecting the first indication based on a comparison of a pressure gradient to a first pressure gradient threshold.
13. The system of claim 12, wherein the first pressure gradient threshold is indicative of a pressure gradient associated with ascending and descending stairs.
14. The system of claim 11, wherein the control circuitry, in operation:
detecting the second indication based on features extracted from the charge signal.
15. The system of claim 11, wherein the control circuitry, in operation:
detecting the second indication based on:
a comparison of a peak value of the amplitude of the charge signal to a charge signal threshold;
a pattern detected in the charge signal; or
Combinations of the above.
16. The system of claim 11, wherein the control circuitry, in operation, counts changes in stride-level associated with a user based on the determined occurrence of level changes.
17. The system of claim 16, wherein the control circuitry, in operation:
setting a baseline value of the pressure signal in response to detecting a stationary state; and
in response to an indication that the user has ascended the stairs or descended the stairs:
determining a difference between a current value of the pressure signal and the baseline value;
determining a change in floor based on a comparison between the difference and a second pressure threshold indicative of the change in the pressure signal associated with the user on the previous floor or the next floor; and
increasing a count of floors ascended or descended by the user based on the determination of a floor change.
18. A method, comprising:
generating a pressure signal using a pressure sensor of the device;
generating a charge signal using a charge sensor of the device; and
detecting a user level change based on the pressure signal and the charge signal.
19. The method of claim 18, comprising:
detecting a first indication of a change in user level based on the pressure signal;
detecting a second indication of a change in user level based on the charge signal; and
in response to detecting the first indication and the second indication during a threshold time interval, determining an occurrence of a user level change.
20. The method of claim 19, comprising:
detecting the first indication based on a comparison of a pressure gradient to a first pressure gradient threshold.
21. The method of claim 20, wherein the first pressure gradient threshold is indicative of a pressure gradient associated with ascending or descending stairs.
22. The method of claim 19, comprising:
detecting the second indication based on features extracted from the charge signal.
23. The method of claim 19, comprising detecting the second indication based on:
a comparison of a peak value of the amplitude of the charge signal to a charge signal threshold;
a pattern detected in the charge signal; or
Combinations of the above.
24. The method of claim 19, comprising: counting changes in stride-level associated with the user based on the occurrences of user-level changes.
25. The method of claim 24, comprising:
setting a baseline value of the pressure signal in response to detecting a stationary state; and
in response to an indication that the user has ascended the stairs or descended the stairs:
determining a difference between a current value of the pressure signal and the baseline value;
determining a change in floor based on a comparison between the difference and a second pressure threshold indicative of the change in the pressure signal associated with the user on the previous floor or the next floor; and
increasing a count of floors ascended or descended by the user based on the determination of a floor change.
26. A non-transitory computer readable medium having contents to configure an electronic device to perform a method, the method comprising:
generating a pressure signal using a pressure sensor of the device;
generating a charge signal using a charge sensor of the device; and
detecting a change in user level based on the pressure signal and the charge signal.
27. The non-transitory computer-readable medium of claim 26, wherein the method comprises:
detecting a first indication of a change in user level based on the pressure signal;
detecting a second indication of a change in user level based on the charge signal; and
in response to detecting the first indication and the second indication during a threshold time interval, determining an occurrence of a user level change.
28. The non-transitory computer-readable medium of claim 27, wherein the method comprises: counting changes in stride-level associated with the user based on the occurrences of user-level changes.
29. The non-transitory computer-readable medium of claim 26, wherein the content comprises instructions executed by sensor signal processing circuitry of the electronic device.
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| IT102020000005425A IT202000005425A1 (en) | 2020-03-13 | 2020-03-13 | DEVICE AND METHOD OF DETECTION OF ACTIVITY AND USER CONTEXT |
| IT102020000005425 | 2020-03-13 | ||
| US17/198,160 | 2021-03-10 | ||
| US17/198,160 US20210285773A1 (en) | 2020-03-13 | 2021-03-10 | User context and activity detection device and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113390387A true CN113390387A (en) | 2021-09-14 |
Family
ID=77617565
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110276091.1A Pending CN113390387A (en) | 2020-03-13 | 2021-03-15 | User context and activity detection device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113390387A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030136191A1 (en) * | 2001-11-19 | 2003-07-24 | Tomoharu Tsuji | Movement-detecting altimeter |
| CN1955978A (en) * | 2002-10-29 | 2007-05-02 | 索尼株式会社 | Gait waveform feature extracting method and individual identification system |
| KR20130138481A (en) * | 2012-06-11 | 2013-12-19 | 강영훈 | Motion detection sensor |
| US20190101387A1 (en) * | 2014-09-09 | 2019-04-04 | Apple Inc. | Electronic Devices with Pressure Sensors for Characterizing Motion |
-
2021
- 2021-03-15 CN CN202110276091.1A patent/CN113390387A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030136191A1 (en) * | 2001-11-19 | 2003-07-24 | Tomoharu Tsuji | Movement-detecting altimeter |
| CN1955978A (en) * | 2002-10-29 | 2007-05-02 | 索尼株式会社 | Gait waveform feature extracting method and individual identification system |
| KR20130138481A (en) * | 2012-06-11 | 2013-12-19 | 강영훈 | Motion detection sensor |
| US20190101387A1 (en) * | 2014-09-09 | 2019-04-04 | Apple Inc. | Electronic Devices with Pressure Sensors for Characterizing Motion |
Non-Patent Citations (3)
| Title |
|---|
| FICKER T: "Charging by walking", 《INSTITUTE OF PHYSICS PUBLISHING》 * |
| FICKER T: "Charging by walking", 《INSTITUTE OF PHYSICS PUBLISHING》, 21 January 2006 (2006-01-21), pages 410 - 417, XP020095006, DOI: 10.1088/0022-3727/39/2/025 * |
| LI M, ETC., ESTIMATION OF TEMPORAL GAIT PARAMETERS USING A HUMAN BODY ELECTROSTATIC SENSING-BASED METHOD, pages 2 - 5 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2625370C2 (en) | Method and device for detecting lift movement | |
| US10504031B2 (en) | Method and apparatus for determining probabilistic context awareness of a mobile device user using a single sensor and/or multi-sensor data fusion | |
| Andò et al. | An event polarized paradigm for ADL detection in AAL context | |
| US11096593B2 (en) | Method for generating a personalized classifier for human motion activities of a mobile or wearable device user with unsupervised learning | |
| US11598649B2 (en) | System and method for detecting steps with double validation | |
| US20210285773A1 (en) | User context and activity detection device and method | |
| CN105512650B (en) | A kind of capacitance type fingerprint detection circuit, sensor and equipment | |
| EP2967445A1 (en) | Dynamic control of sampling rate of motion to modify power consumption | |
| CN109009138B (en) | Gait recognition method and recognition device | |
| EP2973457A2 (en) | Methods and architecture for determining activity and activity types from sensed motion signals | |
| KR101418333B1 (en) | Apparatus and method for recognizing user activity | |
| WO2014145994A2 (en) | Intermediate motion signal extraction to determine activity | |
| TWI502167B (en) | Method for counting step and electronic apparatus using the same | |
| CN114225363B (en) | Wearable system and method for sensing and monitoring user swimming activity | |
| CN104237949B (en) | Existing equipment, sensor and the method for the user of access point for detecting motor vehicle opening | |
| CN113390387A (en) | User context and activity detection device and method | |
| CN109620241B (en) | Wearable device and motion monitoring method based on same | |
| CN108965585B (en) | User identity recognition method based on smart phone sensor | |
| JP2022532487A (en) | Accurate step count measurement method using human body capacity | |
| CN107203259B (en) | Method and apparatus for determining probabilistic content awareness for mobile device users using single and/or multi-sensor data fusion | |
| CN115202489A (en) | System for detecting touch gesture of user, device including the same, and method | |
| US9906845B2 (en) | Sensing device and corresponding apparatus and method | |
| US11747908B2 (en) | System and method for controlling a functionality of a device based on a user gesture | |
| EP4140406A1 (en) | Enhanced human activity recognition | |
| WO2023005857A1 (en) | Step counting method, step counting system and computer-readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |