KR101609813B1 - Apparatus and method for counting step in smartphone - Google Patents

Abstract

A walking-water detecting apparatus and method for detecting a walking-number in a smartphone environment are disclosed. The walking data detecting apparatus according to an embodiment of the present invention includes a data obtaining unit for obtaining an acceleration value according to an action of the terminal holder by an acceleration sensor of a terminal; A walking behavior determination unit for determining a type of an action of the terminal holder from the acceleration value obtained by the data acquisition unit; When the type of the behavior of the terminal holder determined by the pedestrian judgment unit is a walk, the acceleration value obtained by the data acquisition unit is analyzed to calculate an average of the highest value of the acceleration value and an average of the sum of the highest and lowest points of the acceleration value A walking acceleration data analyzing unit for calculating a walking acceleration data; A threshold value range setting unit for calculating a threshold value range from an average of a maximum value of the acceleration values calculated by the walking acceleration data analysis unit and an average value of the maximum value and the minimum value of the acceleration value; And a walking number detecting unit that detects a walking number from the acceleration value obtained by the data obtaining unit based on the threshold value range calculated by the threshold value setting unit.

Description

[0001] APPARATUS AND METHOD FOR COUNTING STEP IN SMARTPHONE [0002]

The present invention relates to a walking water detecting technique, and more particularly, to a walking water detecting device and method for detecting a walking water in a smartphone environment.

Walking is one of the most frequent movements in everyday life of a person and is a physical exercise that involves a very complex mechanism for various parts of the body. Since gait information can be used as data for momentum calculation and calorie calculation, studies on the measurement of gait are actively under way.

As a method of detecting the number of gait, there is a technique using a wearable sensor that attaches an inertial sensor such as an acceleration sensor or a geomagnetic sensor to a specific body part such as a waist, a leg or a foot. Since the wearable sensor is fixed on a specific body part where the body change is conspicuous during walking, the number of gaits detected through the sensor can be relied on with a small error. However, wearing such a wearable sensor on a specific body part has a problem that it is difficult for the user to observe the walking for a long time in daily life because the user may feel inconvenience. In addition, the user must purchase a separate wearable sensor.

In recent years, the spread of smartphones has been increasing, and since smart phones are always carried in everyday life, researches are being conducted to replace wearable sensors with smart phones in order to measure the user's momentum. By replacing the wearable sensor with a smart phone, the user can easily and conveniently access the device, so that a variety of exercise measurement services using a smart phone are provided, and accordingly, interest in health tends to increase.

However, unlike a wearable sensor that fixes on a specific body part, since the smartphone is not fixed to a specific body part, the method of measuring the exercise amount using the smart phone has a problem that accuracy is much lower than that of the wearable sensor because there are many noise data and variable. Therefore, in order to detect high-accuracy gait, existing gait measurement studies using a smartphone have a smartphone in a specific area or detect a gait under a restrictive condition such as a constant speed, a flat surface, and a straight line distance. However, the gait pattern is very irregular. Even if the motion is the same, noise and road surface conditions are different, and when the attachment position of the acceleration sensor is different, a completely different value is measured.

One problem to be solved by the present invention is to provide an apparatus and method for detecting a walking number in real time in a smartphone environment.

Another problem to be solved by the present invention is to provide a device and method for detecting a walking number only when a smartphone owner is walking.

Another object of the present invention is to provide an apparatus and method for detecting the number of gait that detects the number of gaits regardless of the position of the smartphone.

According to an aspect of the present invention, there is provided a walking data detecting apparatus comprising: a data obtaining unit obtaining an acceleration value according to an action of a terminal holder by an acceleration sensor of a terminal; A walking behavior determination unit for determining a type of an action of the terminal holder from the acceleration value obtained by the data acquisition unit; When the type of the behavior of the terminal holder determined by the pedestrian judgment unit is a walk, the acceleration value obtained by the data acquisition unit is analyzed to calculate an average of the highest value of the acceleration value and an average of the sum of the highest and lowest points of the acceleration value A walking acceleration data analyzing unit for calculating a walking acceleration data; A threshold value range setting unit for calculating a threshold value range from an average of a maximum value of the acceleration values calculated by the walking acceleration data analysis unit and an average value of the maximum value and the minimum value of the acceleration value; And a walking number detecting unit that detects a walking number from the acceleration value obtained by the data obtaining unit based on the threshold value range calculated by the threshold value setting unit.

According to an embodiment of the present invention, the acceleration value correcting unit may further include an acceleration value correcting unit for correcting an acceleration value from an average of the gravitational acceleration values indicated by the acceleration sensor of the terminal.

According to another aspect of the present invention, it is possible to further include a lock interval setting unit that sets a interval during which no walk is detected for a predetermined time.

According to another aspect of the present invention, the walking behavior determining unit may SVM-convert the acceleration value obtained by the data obtaining unit to extract a feature, and determine the type of the behavior of the terminal holder using the GMM.

According to another aspect of the above embodiment, the walking may be at least one of walking and running.

According to another aspect of the present invention, there is provided a method of detecting a walking number, comprising: obtaining an acceleration value according to an action of the terminal holder by an acceleration sensor of a terminal; Determining a type of the behavior of the terminal holder from the obtained acceleration value; Calculating an average of a maximum value of the acceleration values and an average value of the maximum and minimum values of the acceleration values by analyzing the obtained acceleration values when the determined type of behavior of the terminal holder is walking; Calculating a threshold value range from an average of a maximum value of the calculated acceleration values and a sum of a maximum value and a minimum value of the acceleration values; And detecting a walking number from the obtained acceleration value based on the calculated threshold value range.

According to an embodiment of the present invention, the method may further include correcting an acceleration value from an average of gravitational acceleration values indicated by acceleration sensors of the terminal.

According to another aspect of the present invention, the method may further include setting a lock interval that does not detect the number of walking for a predetermined period of time.

According to another aspect of the present invention, in the step of determining the type of the walking behavior, the acquired acceleration value may be SVM-converted to extract the characteristic, and the type of the behavior of the terminal holder may be determined using the GMM.

According to another aspect of the above embodiment, the walking may be at least one of walking and running.

According to another aspect of the present invention, there is provided a computer readable recording medium storing a program for executing a method of detecting a walking number according to an embodiment of the present invention.

As described above, according to the embodiment of the present invention, it is possible to detect the walking number only when the user is walking by using the behavior recognition in the smartphone environment.

According to an embodiment of the present invention, it is possible to detect the walking water with high accuracy regardless of the position of the smartphone.

1 is a block diagram showing a configuration of a walking water detecting apparatus according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating detection of a walking number according to an embodiment of the present invention.
3 is a flowchart illustrating a method of detecting a walking number according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail with reference to the accompanying drawings. However, these drawings are only for illustrating the contents and scope of the technical idea of the present invention, and the technical scope of the present invention is not limited or changed. It will be apparent to those of ordinary skill in the art that various changes and modifications can be made within the scope of the technical idea of the present invention based on these examples.

In addition, terms and words used in the present specification are terms selected in consideration of functions in the embodiments, and the meaning of the terms may be changed according to the intention or custom of the invention. Therefore, the terms used in the following embodiments are defined according to their definitions when they are specifically defined in this specification, and unless otherwise defined, they should be construed in a sense generally recognized by ordinary artisans.

1 is a block diagram illustrating a configuration of a walking-water detecting apparatus according to an embodiment of the present invention.

1, the walking data detection apparatus 100 includes an acceleration value correction unit 110, a data acquisition unit 120, a walking behavior determination unit 130, a walking acceleration data analysis unit 140, (150) and a walking-water detecting unit (170). The configuration of the walking water detecting device 100 shown in Fig. 1 is an example, and the walking water detecting device 100 may have only a part of the modules shown in Fig. 1 and / Other modules may be additionally provided. For example, the walking-water detecting apparatus 100 may further include a communication unit having a communication function for communication with another apparatus.

The acceleration value correcting unit 110 provides a function of correcting the acceleration value from the average of the gravity acceleration values indicated by the acceleration sensor of the terminal. Here, 'average of gravitational acceleration values' means an average of gravitational acceleration values in a state in which there is no acceleration, that is, in a state where there is no movement of the terminal. In general, in the absence of acceleration, the acceleration value is 9.8 m / s2, which is the gravitational acceleration value. However, since the gravitational acceleration value has a deviation due to the error of the sensor built in the terminal, the erroneous walking number can be detected. Therefore, the acceleration value is corrected from the average of the gravitational acceleration values. For example, the average value of 30 acceleration values is calculated to extract the gravitational acceleration value of the terminal, and the acceleration value is calibrated by calculating the actual gravitational acceleration value and the error.

Meanwhile, the terminal may be a personal mobile communication terminal, a personal digital assistant (PDA), a smart phone, a tablet, a laptop, a notebook, And the like, can be used for all terminals capable of carrying out various functions using an application program including a wireless communication while being portable by an individual.

The data acquisition unit 120 provides a function of acquiring an acceleration value according to an action of a terminal holder by an acceleration sensor of the terminal. Herein, the 'act of the terminal holder' means that the terminal holder takes one of the actions related to the walking with the terminal being carried, that is, the walking, the running and the stopping. The terminal holder can perform actions such as walking, running, and stopping while holding the terminal. At this time, if the terminal moves by the action of the terminal holder, the acceleration sensor of the terminal can detect the movement of the terminal and obtain the acceleration value.

The pedestrian judgment unit 130 provides a function of determining the type of the behavior of the terminal holder from the acceleration value obtained by the data acquisition unit 120. [ Specifically, the type of behavior of the terminal holder before detecting the walking number is determined in order to filter the general fluctuation, that is, the noise data, rather than the walking. The behavior of terminal holders is classified into three types: walking, running, and stopping. Here, if the type of the behavior of the terminal holder is a walking act or a run behavior, it is judged to be a walking behavior.

Meanwhile, unlike the wearable type wearable sensor, the terminal user including the smart phone does not carry the terminal considering the direction of the terminal. Therefore, in order to extract the acceleration value received by the terminal, the gravity component included in the 3-axis acceleration data is removed do.

Equation (1) represents a formula for eliminating the gravity component.

Here, gi (k) is a value obtained by removing the gravitational acceleration value from the acceleration values of the X, Y and Z axes, (k-1) is the immediately preceding acceleration value,? Is an arbitrary constant value, . i is one of the X, Y, and Z axes.

Then, SVM (Signal Vector Magnitude) is applied to the 3-axis acceleration signal acquired from the terminal to convert it into one representative value. The data transmitted from the acceleration sensor of the terminal is data indicating coordinates in three directions of X, Y and Z, and is data which has not undergone any processing. Since the acceleration sensor can measure the gravitational acceleration, a gravitational acceleration value of 9.8 m / s2 toward the bottom is always detected at the stop state. Therefore, since the three-axis acceleration acquires signals of different waveforms depending on the direction of the sensor and the ground, the direction of the terminal according to the position of the terminal greatly affects it. Therefore, to improve the directionality of the sensor and treat it as a representative value, SVM is applied to convert it into energy value. SVM is a method of processing X, Y, Z axis data of 3-axis acceleration sensor as one value.

Equation 2 represents a method of processing X, Y, Z axis data of a three-axis acceleration sensor into one value.

Here, acc is a signal vector magnitude (SVM) signal value, and X, Y, and Z denote acceleration values in the X, Y, and Z axis directions, respectively.

For the pedestrian judgment, 10 features such as 5th linear prediction coefficient, 1 linear prediction error, 3 standard deviation in 1 second, and 1 average crossing ratio are extracted from the transformed signal using SVM, and Gaussian Mixture Model ) Is used to determine the walking behavior.

Meanwhile, the method of determining the type of the behavior of the terminal holder is not necessarily limited thereto, but may be applied to a method of determining the type of behavior of the terminal holder. For example, another type of sensor built in the terminal may be used to determine the type of behavior of the terminal holder. Specifically, the type of the behavior of the terminal holder can be determined using the GPS sensor of the terminal. That is, the speed can be measured at a predetermined time interval using the coordinates of the GPS, and the type of the terminal holder's behavior can be determined according to the speed. If the measured speed is equal to or higher than the maximum walking speed of the person, it can be determined that the vehicle is running. If the measured speed is less than the maximum walking speed, it can be determined that the vehicle is a walking.

The gait acceleration data analysis unit 140 provides a function of analyzing the acceleration values obtained by the case data acquisition unit 120 and calculating an average of the highest points of the acceleration values and an average of the highest and lowest points of the acceleration values . In this case, when the type of the behavior of the terminal holder determined by the pedestrian determination unit 130 is a walking act, that is, a walk or a run, the acceleration value obtained by the data acquisition unit 120 is analyzed, The average of the peak of the peak value and the average of the peak and the peak of the acceleration value.

The threshold value range setting unit 150 provides a function of calculating a threshold value range from an average of a maximum value of the acceleration values calculated by the walking acceleration data analysis unit 140 and an average of the maximum value and the minimum value of the acceleration value . The threshold value may vary depending on whether the type of walking is walking or running. Here, the average of the highest points of the acceleration values becomes the maximum value of the threshold value, and the average of the maximum value and the lowest point of the acceleration value becomes the minimum value of the threshold value.

Equation (3) represents the maximum value of the threshold value which is the average of the peak of the acceleration value.

Equation (4) represents the minimum value of the threshold value which is the average of the sum of the maximum value and the minimum value of the acceleration value.

Equation (5) represents the range of the threshold value.

In Equation (3) to Equation (5), acc (p) means the highest point of the acceleration value and acc (t) means the lowest point of the acceleration value. And, WorR means Walking or Running. The MINaccWorR value is the average of the sum of the maximum and minimum points of the acceleration value, and the MAXaccWorR value is the average of the maximum value of the acceleration value. The threshold value means a threshold value, and the threshold value exists between the MINaccWorR value and the MAXaccWorR value, that is, below the average of the peak value of the acceleration value from the average of the sum of the peak value and the lowest value of the acceleration value.

The walking number detection unit 170 provides a function of detecting a walking number from the acceleration value acquired by the data acquisition unit 120. [ At this time, the number of steps is detected on the basis of the threshold value range calculated by the threshold value range setting unit 150.

Meanwhile, the walking-water detecting apparatus 100 according to an embodiment of the present invention may further include a lock interval setting unit 160.

Referring to FIG. 1, the lock interval setting unit 160 provides a function of setting a section that does not detect the number of walking for a predetermined period of time. Since the walking of a person has a specific walking interval time, when the walking number is detected once considering the best walking speed that a person can take, the walking number is not detected within the corresponding time, that is, within the locking interval. For example, the lock interval is 400ms for a walk action and 300ms for a run action.

FIG. 2 is a diagram illustrating detection of a walking number according to an embodiment of the present invention.

Referring to FIG. 2, the graph shows the acceleration value acquired by the acceleration sensor of the terminal. The number of gait is detected within a threshold value range between an average of the sum of the maximum and minimum points of the acceleration value and an average of the maximum value of the acceleration value. Once the number of gait is detected, the lock interval is set in consideration of the best walking speed that a person can take, and the gait is not detected in the lock interval.

In the embodiment, the sampling period for detecting the walking number is 50 ms. If the acceleration value is obtained for each sampling period and the obtained acceleration value is within the threshold value range and is not the lock interval, the walking number is detected. The asterisk indicates that the acceleration value was obtained and that the obtained acceleration value was within the threshold range but was not detected as the walking number because it was within the lock interval.

3 is a flowchart illustrating a method of detecting a walking number according to an embodiment of the present invention. The procedures described below including embodiments of the present invention can be implemented in various forms. The walking water detection method shown in FIG. 3 may be a method of detecting the walking water using the walking water detecting apparatus 100 of FIG. 1 or an electronic apparatus having the walking water detecting apparatus 100 shown in FIG. Therefore, in order to avoid unnecessary repetition, the gait detection method will be briefly described, and the matters not described in detail here can be applied to the same things described with reference to FIG. 1 to FIG.

1 to 3, an acceleration value is corrected from an average of gravity acceleration values indicated by an acceleration sensor of a terminal (S301).

Next, an acceleration value according to an action of the terminal holder is obtained by an acceleration sensor of the terminal (S302).

Next, the type of the behavior of the terminal holder is determined from the obtained acceleration value (S303). At this time, the obtained acceleration value is SVM-converted to extract the characteristic, and the type of the terminal holder's behavior can be determined using the GMM. And detects the number of walking when the type of walking is one of walking or running.

Next, if the determined type of behavior of the terminal holder is a gait, the obtained acceleration value is analyzed to calculate an average of the maximum value of the acceleration value and an average value of the maximum value and the minimum value of the acceleration value (S304). On the other hand, if the determined behavior of the terminal holder is not walking, the acceleration value is obtained again (S302).

Next, the threshold value range is calculated from the average of the maximum of the calculated acceleration values and the average of the maximum and minimum points of the acceleration values (S305).

Next, a lock section that does not detect the number of walking is set for a predetermined time (S306).

Next, the walking number is detected from the acceleration value obtained on the basis of the calculated threshold range (S307, S308).

In addition, the present invention can be stored in a computer-readable recording medium on which a program for execution by a computer is recorded. At this time, the computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. Program instructions to be recorded on the medium may be those specially designed and constructed for the proposed invention or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks, and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. The medium may be a transmission medium such as an optical or metal line, a wave guide, or the like, including a carrier wave for transmitting a signal designating a program command, a data structure, or the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa. In addition, the computer-readable recording medium may be distributed to network-connected computer devices so that computer-readable codes can be stored and executed in a distributed manner.

It will be apparent to those skilled in the art that various modifications, substitutions and substitutions are possible, without departing from the scope and spirit of the invention as disclosed in the accompanying claims. will be. Therefore, the embodiments disclosed in the present invention and the accompanying drawings are intended to illustrate and not to limit the technical spirit of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments and the accompanying drawings . The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents thereof should be construed as falling within the scope of the present invention.

100: Walking water detection device
110: Acceleration value correcting unit
120: Data acquisition unit
130:
140: Walking acceleration data analysis unit
150: threshold value range setting unit
160: Lock interval setting unit
170:

Claims (11)

A data obtaining unit for obtaining an acceleration value according to an action of the terminal holder by an acceleration sensor of the terminal;
A walking behavior determination unit for determining a type of an action of the terminal holder from the acceleration value obtained by the data acquisition unit;
When the type of the behavior of the terminal holder determined by the pedestrian judgment unit is a walk, the acceleration value obtained by the data acquisition unit is analyzed to calculate an average of the highest value of the acceleration value and an average of the sum of the highest and lowest points of the acceleration value A walking acceleration data analyzing unit for calculating a walking acceleration data;
A threshold value range setting unit for calculating a threshold value range from an average of a maximum value of the acceleration values calculated by the walking acceleration data analysis unit and an average value of the maximum value and the minimum value of the acceleration value; And
A walking number detection unit for detecting a walking number from an acceleration value obtained by the data obtaining unit based on a threshold value range calculated by the threshold value setting unit;
/ RTI >
Further comprising an acceleration value correcting unit for obtaining an error between an average of the gravitational acceleration values obtained in the absence of the mobile terminal and an actual gravitational acceleration value and correcting the acceleration value.
delete The method according to claim 1,
And a lock section setting section for setting a section that does not detect the number of gait for a predetermined period of time.
The method according to claim 1,
Wherein the walking behavior determining unit extracts a characteristic by SVM-transforming the acceleration value obtained by the data obtaining unit, and determines the type of the behavior of the terminal holder using the GMM.
The method according to claim 1,
Wherein the walking is at least one of walking and running.
Correcting an acceleration value by obtaining an error between an average of the gravitational acceleration values obtained in the absence of movement of the terminal and an actual gravitational acceleration value;
Obtaining an acceleration value according to an action of the terminal holder by an acceleration sensor of the terminal;
Determining a type of the behavior of the terminal holder from the obtained acceleration value;
Calculating an average of a maximum value of the acceleration values and an average value of the maximum and minimum values of the acceleration values by analyzing the obtained acceleration values when the determined type of behavior of the terminal holder is walking;
Calculating a threshold value range from an average of a maximum value of the calculated acceleration values and a sum of a maximum value and a minimum value of the acceleration values; And
Detecting a walking number from the obtained acceleration value based on the calculated threshold value range;
And detecting the number of gaits.
delete The method according to claim 6,
And setting a lock section that does not detect the number of gait for a predetermined period of time.
The method according to claim 6,
Wherein the behavior type determination step SVM-converts the obtained acceleration value to extract a feature, and determines the type of the behavior of the terminal holder using the GMM.
The method according to claim 6,
Wherein the walking is at least one of walking and running.
A computer-readable recording medium having recorded thereon a program for executing a method according to any one of claims 6 to 10.

Images