JP2016018346A - Handheld information equipment, program, and method that detect careless walking state using acceleration sensor alone - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide handheld information equipment, and a program and method that detect a careless walking state using an acceleration sensor alone.SOLUTION: Handheld information equipment that includes a display and acceleration sensor and detects a careless walking state in which a user is walking while viewing the display includes terminal posture decision means that calculates a gravity vector on the basis of acceleration data obtained at time i, and decides whether a roll angle and pitch angle associated with the gravity vector fall within a predetermined angle range, walking peak decision means that calculates a vertical component acceleration relevant to the gravity vector, and decides whether a peak (maximum or minimum) of the vertical component acceleration occurs at intervals of a predetermined time, and careless walking decision means that, if the terminal posture decision means and walking peak decision means make a decision of truth, decides that the user is in the careless walking state.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a technique for detecting a user's walk using an acceleration sensor.

  The acceleration sensor is generally mounted on a portable information device such as a smartphone or a tablet terminal that is always carried by a user. In such a portable information device, an acceleration sensor can be used to detect the number of steps depending on the application and to determine whether the display is held vertically or horizontally.

  Conventionally, there is a technique for detecting the number of steps of a pedestrian carrying the device using triaxial acceleration data output from an acceleration sensor (see, for example, Patent Document 1). According to this technique, a gravitational direction calculating means for calculating an acceleration component in the gravitational direction from acceleration data at time i, and an acceleration plane for approximately deriving an acceleration surface caused by arm swing from acceleration data according to the passage of time. Counting the number of steps from the approximation means, the longitudinal acceleration calculation means for calculating the longitudinal acceleration component orthogonal to the gravity direction and the normal direction of the acceleration plane from the acceleration data, and the time when the longitudinal acceleration becomes 0 as one step And a step count counting means.

  There is also a technique for detecting the number of steps of a pedestrian carrying the device using triaxial geomagnetic data output from a geomagnetic sensor (see, for example, Patent Document 2). According to this technology, the fluctuation angle calculation means for calculating the fluctuation angle from the latest of the geomagnetic vector from the geomagnetic data corresponding to the passage of time, the minimum point detection means for detecting the time point when the fluctuation angle becomes the minimum, the fluctuation angle Step count counting means for counting a plurality of points of time when the minimum is as the number of steps.

  Furthermore, there is a technique for automatically estimating a user's movement state by using a combination of an acceleration sensor, a microphone, and a GPS (Global Positioning System) that can be mounted on a mobile phone (see Non-Patent Document 1, for example). According to this technique, in addition to human activity states such as running, walking, and stopping, it is possible to estimate riding states such as bicycles, trains, buses, and automobiles.

JP 2011-090548 A JP 2011-090549 A

A. Kobayashi, Kengo Iwamoto, Satoshi Nishiyama, “Shaka: User movement state estimation method using mobile phone”, IPSJ Journal, vol.50 (No.1), pp.193-208, 2009 , [Online], [Search June 27, 2014], Internet <URL: http://ci.nii.ac.jp/naid/10021819284>

  In recent years, the behavior of “walking smartphone (while inadvertently walking)” (inadvertent walking state) in which a smartphone is operated while walking on a road with a lot of traffic is becoming a problem. This behavior may cause an accident in which the user who is operating becomes inadvertent with respect to the surroundings and comes into contact with other people or vehicles that come and go. Telecom operators selling smartphones are also advertising to refrain from walking smartphones as much as possible.

  According to the techniques described in Patent Documents 1 and 2, the number of steps is merely detected on the assumption that the user is walking. Moreover, according to the technique described in Non-Patent Document 1, it is only possible to detect the user's walking state in daily life. With either technique, the behavioral state of the walking smartphone cannot be detected.

  On the other hand, if the inventor of this application can detect a careless walking state with a portable information device, an alarm is clearly indicated to a user who is inadvertently walking and urged to stop such an action. I thought it was possible. On the other hand, it is not preferable from the viewpoint of power consumption of the portable information device to keep starting another sensor or camera separately only to detect the careless walking state.

  Accordingly, an object of the present invention is to provide a portable information device, a program, and a method for detecting an inattentive walking state using only an acceleration sensor.

According to the present invention, the portable information device includes a display and an acceleration sensor, and detects a careless walking state in which the user is walking while visually checking the display,
Terminal attitude determination means for calculating a gravity vector from acceleration data at time i and determining whether each of a roll angle and a pitch angle with respect to the gravity vector is within a predetermined angle range;
Walking peak determination means for calculating a vertical component acceleration with respect to a gravity vector and determining whether or not a peak (maximum or minimum) of the vertical component acceleration occurs at every predetermined time interval;
And a careless walking determination means for determining that the terminal posture determination means and the walking peak determination means are in an inadvertent walking state when determined to be true.

According to another embodiment of the portable information device of the present invention,
The terminal posture determination means determines whether the user is holding the device vertically or horizontally by the direction of the gravity vector with respect to the long side and the short side of the display, and converts the coordinates of the terminal posture as a reference for the roll angle and the pitch angle. preferable.

According to another embodiment of the portable information device of the present invention,
About acceleration data
The vertical component acceleration is within the first predetermined acceleration range;
The longitudinal component acceleration is within the second predetermined acceleration range;
An axial acceleration determining means for determining whether the left / right component acceleration is within a third predetermined acceleration range;
It is also preferable that the careless walking determination means further determines that it is in the careless walking state when it is determined to be true by the axial acceleration determination means.

According to another embodiment of the portable information device of the present invention,
The first predetermined acceleration range with respect to the vertical component acceleration is
It is also preferable that the second predetermined acceleration range for the longitudinal component acceleration and the third predetermined acceleration range for the lateral component acceleration are wider.

According to another embodiment of the portable information device of the present invention,
The walking peak determination means calculates a moving average value every time the vertical component acceleration is detected, sets an upper fluctuation threshold value and a lower fluctuation threshold value with the moving average value as a center, and the vertical component acceleration is determined as an upper fluctuation threshold value and a lower fluctuation threshold value. It is also preferable that the determination is true only when the timing of alternately exceeding is generated every predetermined time interval.

According to another embodiment of the portable information device of the present invention,
It is also preferable that the walking peak determination means determine true only when the number of times it is determined that a peak has occurred continues for a predetermined number of steps or more.

According to another embodiment of the portable information device of the present invention,
It is also preferable that the walking peak determination means further calculates a time difference ΔTm between peaks and determines that it is true only when the standard deviation of the time difference ΔTm is equal to or less than a predetermined threshold value.

According to another embodiment of the portable information device of the present invention,
When the backlight of the display is lit, it further has an operation state determination means for determining that the user operation state is present,
It is also preferable that the careless walking determination unit determines that the user is in the careless walking state only when the operation state determination unit determines that the state is true.

According to another embodiment of the portable information device of the present invention,
It is also preferable that the operation state determination unit determines that the user operation state is in effect when a specific application is activated or when a user tap event is detected.

According to the present invention, there is provided a program for causing a computer mounted on a portable information device having a display and an acceleration sensor to function so as to detect an inadvertent walking state in which a user is walking while viewing the display. ,
Terminal attitude determination means for calculating a gravity vector from acceleration data at time i and determining whether each of a roll angle and a pitch angle with respect to the gravity vector is within a predetermined angle range;
Walking peak determination means for calculating a vertical component acceleration with respect to a gravity vector and determining whether or not a peak (maximum) of the vertical component acceleration occurs at predetermined time intervals;
When the terminal posture determination unit and the walking peak determination unit determine true, the computer functions as an inattentive walking determination unit that determines that the terminal is in an inadvertent walking state.

According to the present invention, a portable information device having a display and an acceleration sensor detects a careless walking state while a user is walking while visually recognizing the display,
Calculating a gravity vector from acceleration data at time i, determining whether each of a roll angle and a pitch angle with respect to the gravity vector is within a predetermined angle range;
Calculating a vertical component acceleration with respect to the gravity vector, determining whether or not a peak (maximum) of the vertical component acceleration occurs every predetermined time interval;
When it is determined to be true by the terminal posture determination unit and the walking peak determination unit, it is determined that the user is in an inadvertent walking state.

  According to the portable information device, program, and method of the present invention, it is possible to detect an inattentive walking state using only the acceleration sensor.

It is a functional block diagram of the portable information device in this invention. It is explanatory drawing showing the coordinate system of portable information equipment. It is explanatory drawing showing the angle range of the roll angle and pitch angle of portable information equipment. It is a graph which detects a walking peak from the magnitude | size of a vertical component acceleration. It is explanatory drawing showing each component acceleration in the coordinate system of a walking user. It is explanatory drawing showing a response | compatibility with the coordinate system of a portable information device, and a walking user's coordinate system. It is a graph showing that each component acceleration exists in the predetermined acceleration range.

  Below, the form for implementing this invention is demonstrated in detail using drawing.

  FIG. 1 is a functional configuration diagram of a portable information device according to the present invention.

  According to FIG. 1, a portable information device 1 possessed by a user is a terminal such as a smartphone, and includes an acceleration sensor 10 and a display 11 that is visually recognized by the user. The portable information device 1 of the present invention can clearly indicate an alarm to the user when the user is in an inadvertent walking state (walking smartphone or smartphone while walking) while viewing the display.

The acceleration sensor 10 detects acceleration, that is, a change in speed per unit time. Since the acceleration sensor 10 of the present invention needs to detect the terminal posture (tilt), it outputs a three-dimensional (three-axis) acceleration.
The display 11 is turned on only when the user operates or visually recognizes from the viewpoint of power consumption. The display 11 is a touch panel type, and can accept user operations when the backlight is on.

  FIG. 2 is an explanatory diagram showing a coordinate system of the portable information device.

The acceleration vector a _i detected at time i is expressed as follows.
a _i = (x _i , y _i , z _i )
Moreover, according to FIG. 2, the reference axis of the terminal posture (tilt) is expressed as follows.
Horizontal (short) direction right direction of information equipment x-axis positive direction: rotation around x-axis = pitch
The vertical (longitudinal) upward direction of the information device is the y-axis positive direction: rotation around the y-axis = roll
The upward direction of the information device is in the positive z-axis direction: rotation around the z-axis = yaw

  The portable information device 1 further includes a terminal posture determination unit 12, a walking peak determination unit 13, an axial acceleration determination unit 14, an operation state determination unit 15, a careless walking determination unit 16, and an application 17. . These functional components are realized by executing a program that causes a computer mounted on the portable information device to function.

[Terminal posture determination unit 12]
The terminal posture determination unit 12 calculates the gravity vector g _i from the acceleration data at time i. As a result, the terminal posture can be determined as “gravity vector g _i = vertical downward”. It is difficult to accurately measure only the acceleration components (g _x , g _y , g _z ) in the direction of gravity from the acceleration data from the acceleration sensor. Therefore, as an approximation of the gravity vector, a moving average of acceleration vectors observed in a predetermined time range (for example, 2 seconds or longer) sufficiently long with respect to the walking cycle is used. Here, the gravity vector g _i at time i is expressed as follows.
freq: Sampling rate of acceleration sensor g _i = (g _xi , g _yi , g _zi )
= Σn ( _ap ) / n (n> 2freq, p = i-n + 1,..., I)
(Normalize to | g _i | = 1)
In addition to the acceleration sensor, a gyroscope (angular velocity sensor) may be used. A change in the direction of the gravity vector calculated by the acceleration sensor can be tracked.

The terminal posture determination unit 12 determines whether the user has vertical / horizontal holding based on the orientation of the gravity vector with respect to the long side and short side of the display, and converts the coordinates of the terminal posture that serves as a reference for the roll angle and the pitch angle.
When the device is held vertically by tilting it to the left, the coordinates of the terminal posture are converted as follows.
x = -y
y = x
z = z
If the device is held vertically by tilting it to the right, the coordinates of the terminal posture are converted as follows.
x = y
y = -x
z = z

In addition, it can determine from _gxi and _gyi whether it fell to the left or it fell to the right.
| g _xi | <| g _yi |
| g _xi |> | g _yi |: Horizontally held g _xi <0: Tilt to the left g _xi > 0: Tilt to the right

  FIG. 3 is an explanatory diagram showing an angle range of a roll angle and a pitch angle of the portable information device.

According to Fig.3 (a), the angle range of a roll angle is represented. The viewpoint is viewed from the y-axis negative side (lower side) of the information device. It is determined whether or not the absolute value of the lateral component g _xi of the gravity vector is equal to or less than the threshold value A.
When the roll angle posture angle range is ± α, the threshold value A = sin (α)
That is, in the case of | g _xi | ≦ sin (α), it is determined that there is a high possibility that the posture is a posture in a careless walking state.

FIG. 3B shows the angle range of the pitch angle. The viewpoint is viewed from the x-axis negative side (left side) of the information device. For the pitch angle, the rotation angle of the longitudinal acceleration component of the gravity vector is calculated.
Longitudinal / vertical acceleration component: g _i ′ = (g _yi , g _zi )
Terminal bottom vector: u = (0, -1)
Angle between g _i 'and u: φ
φ = acos (g _i '· u / | g _i ' || u |) ("·" is an inner product)
= Acos (-g _zi / | g _i '|)
Betaup: terminal from a horizontal state "cause" that threshold indicating an upper limit of angle which can Betadown: When reverse to "defeat" threshold g _yi ≧ 0 indicating an upper limit of angle which can, φ ≦ βdown
When g _yi <0, φ ≦ βup
That is, when φ based on g _yi is in the range of β, it is determined that there is a high possibility that the posture is a posture in an inadvertent walking state.

In calculating the roll angle, the angle with the terminal bottom vector u similar to the calculation of the pitch angle is not used. This is because, when the state that caused 90 degrees terminal from the horizontal state, despite it should be determined that there is likely a posture when the inadvertent walking state, (the gravity vector g _i is the y-axis This is because g _xi can appear in any direction 360 degrees around the origin in FIG. 3 (a). At this time, if the angle with the terminal bottom vector u similar to the calculation of the pitch angle is used, it may be erroneously determined that the posture is not in the careless walking state.

The terminal posture determination unit 12 determines whether or not it is within the following two angle ranges.
The roll angle with respect to the gravity vector is within the angle range α. The pitch angle with respect to the gravity vector is within the angle range β. If these two conditions are satisfied, the posture of the portable information device may be inadvertently walking. Is determined to be high.
The determination result is output to the careless walking determination unit 16.

[Walking peak determination unit 13]
The walking peak determination unit 13 calculates a vertical component acceleration with respect to the gravity vector, and determines whether or not a peak (maximum or minimum) of the vertical component acceleration occurs at every predetermined time interval. The interval between the peaks of the vertical component acceleration is detected as one step of the user.

  FIG. 4 is a graph for detecting a walking peak from the magnitude of the vertical component acceleration.

The walking peak determination unit 13 detects the vertical component acceleration a _vi at each time i as follows.
_{a vi = a i · g i} = x i g xi + y i g yi + z i g zi

The walking peak determination unit 13 calculates a moving average value (smoothing curve) b _i every time the vertical component acceleration a _vi is detected, and uses the moving average value as the center for an upper fluctuation threshold (b + D) and a lower fluctuation threshold. (BD) is set, and it is determined to be true only when the vertical component acceleration alternately exceeds the upper fluctuation threshold and the lower fluctuation threshold at every predetermined time interval.

Specifically, according to FIG. 4, the maximum and maximum value a _vk (t ≦ k ≦ u) is detected as a peak at the timing when all the following conditions are satisfied. As time elapses, i changes from s->t-> u.
(1) a _vs <b _s -D
(2) a _vt <b _t + D
(3) a _vu < _bu- D
(4) s <t <u
Alternatively, the above-described (1) to (3) may be read as follows, and a _vk (t ≦ k ≦ u) having a minimum and minimum value may be detected as a peak.
(1) a _vs <b _s + D
(2) a _vt <b _t −D
(3) a _vu <b _u + D

It is also preferable that the walking peak determination unit 13 counts the number of consecutive steps as the time difference between peaks is equal to or less than a threshold value U (for example, 1 second). Further, it is determined to be true only when the number of times it is determined that a peak has occurred continues for a predetermined number N of steps.
For m = 1 to j, ΔTm = Tm−Tm−1 <U (U = 1 second)
j ≧ N (N = 8 steps)

  Furthermore, the walking peak determination unit 13 determines true only when the standard deviation of the time difference ΔTm is equal to or less than the predetermined threshold value V. This is because it can be determined that the peak is generated at a fixed period peculiar to walking as the variation in the time difference ΔTm between the peaks is small.

  The walking peak determination unit 13 outputs the determination result to the careless walking determination unit 16.

[Axial acceleration determination unit 14]
The axial acceleration determination unit 14 is optional, and further determines whether or not the axial acceleration based on the user walking is within a predetermined range in addition to the terminal posture determination. The axial acceleration determination unit 14 decomposes the acceleration data into a vertical acceleration component, a longitudinal acceleration component, and a lateral acceleration component.

FIG. 5 is an explanatory diagram showing each component acceleration in the coordinate system of the walking user. According to FIG. 5, the coordinate system of the walking user is
Vector indicating the user's vertical downward direction: g _i
Vector to the right of the user: r _i
Vector indicating the user's front: f _i
Each component of acceleration a _i is expressed as follows.
Vertical component acceleration at time i: a _vi
Left-right component acceleration at time i: a _{ri
Longitudinal} component acceleration at time i: a _fi
The acceleration vector (a _fi , a _ri , a _vi ) consisting of the above three components is obtained by _changing the acceleration vector a _i = (x _i , y _i , z _i ) shown in the coordinate system of the portable information device to the coordinates of the walking user. It can be said that it has been converted to a system.

  FIG. 6 is an explanatory diagram showing the correspondence between the coordinate system of the portable information device and the coordinate system of the walking user.

According to FIG. 6, the following relationships of g _i , fbase, f _i , and r _i are represented.
The left / right component acceleration a _ri is calculated as follows.
fbase = (f _bx , f _by , f _bz ) = (0, 1, 0): definition in front of the terminal r _i = (r _xi , r _yi , r _zi ): reference vector indicating the right side of the walking user
= G _i × fbase: (“×” is the outer product)
_{= (G yi f bz -f by} g zi, g zi f bx -f bz g xi, g xi f by -f bx g yi)
= ( _{-F by} g _zi , 0, g _xi f _by )
_{a ri = a i · r i} = x i r xi + y i r yi + z i r zi
= X _i r _xi + z _i r _zi

The longitudinal component acceleration a _fi is calculated as follows.
f _i = (f _xi , f _yi , f _zi ): reference vector indicating the front of the walking user = r _i × g _i
= (R _{yig zi} -g _{yr zi} , r _{zig xi} -g _{zir xi} , r _xi g _y i -g _x r _y i)
a _fi = a _i・ f _{i
= X i f xi + y i} f yi + z i f zi

  FIG. 7 is a graph showing that each component acceleration is within a predetermined acceleration range.

The axial acceleration determination unit 14 determines whether or not the following conditions are satisfied for the acceleration data.
FIG. 7A: The vertical component acceleration a _vi is within the first predetermined acceleration range (Vmin <a _vi <Vmax).
FIG. 7B: The longitudinal component acceleration a _fi is within the second predetermined acceleration range (Fmin <a _fi <Fmax).
FIG. 7C: the left-right component acceleration a _ri is within the third predetermined acceleration range (Rmin <a _ri <Rmax).
Only when all the conditions are satisfied, it is determined that there is a possibility of inadvertent walking.

When in a careless walking state, the user is walking while holding the portable information device in front of him. In the case of inadvertent walking, the vertical (gravity direction) component acceleration changes greatly due to walking, while the information device itself is gripped so as not to shake by hand, so the longitudinal component acceleration and the left / right component The change in acceleration is small. Therefore, each predetermined acceleration range is set according to the following relationship.
First predetermined acceleration range with respect to vertical component acceleration (wide)>
A second predetermined acceleration range for the longitudinal component acceleration (narrow),
Third predetermined acceleration range for the left / right component acceleration (narrow)

  The axial acceleration determination unit 14 outputs the determination result to the careless walking determination unit 16.

[Operation state determination unit 15]
The operation state determination unit 15 determines that the user operation state is present when the backlight of the display is lit. This is assumed to be in a state where the user is viewing the display, and if the user is walking, it is considered that the user is in a careless walking state.

  Moreover, it is also preferable that the operation state determination unit 15 determines that the user application is in the user operation state when a specific application is activated or when a user tap event is detected. A specific application that is most activated in a walking smartphone is, for example, a browser. If the user is walking when the browser is activated on the portable information device, it is considered that the user is inadvertently walking.

  Moreover, as a specific application activated by a walking smartphone, for example, there is an SNS game. When the game is activated on the portable information device, the user performs operations such as tapping, scrolling, and flicking. In such a case, if the user is walking, it is considered that the user is in a careless walking state.

According to the operation state determination unit 15, even in the careless walking state, the relevance rate increases (decrease in false detections), but the recall rate decreases (increase in detection omissions) according to the following order (1) to (3). ).
(1) Illumination of backlight of display (2) Activation of specific application (3) Operation such as tap, scroll, and flick By this, it is possible to detect only the careless walking state as reliably as possible.

[Inattentional walking determination unit 16]
The careless walking determination unit 16 determines that it is in the “careless walking state” at least when it is determined to be true by the terminal posture determination unit 12 and the walking peak determination unit 13.
In addition, the careless walking determination unit 16 determines that it is in the “careless walking state” when it is determined to be true by the axial acceleration determination unit 14 and / or the operation state determination unit 15. May be.
The determination result is output to the application 17.

[Application 17]
When it is determined by the careless walking determination unit 16 that the application 17 is in the “careless walking state”, the application 17 displays a warning on the display. This prompts the user to stop “walking smartphone (while walking)”.

  According to the present invention, the user's careless walking state is continuously determined. If the application 17 detects an inattentive walking state even after warning the user, the specific application being activated may be stopped or the user operation may be stopped.

  As described above in detail, according to the portable information device, program, and method of the present invention, it is possible to detect an inattentive walking state using only the acceleration sensor.

  According to the various embodiments of the present invention described above, those skilled in the art can easily make various changes, modifications and omissions within the scope of the technical idea and the viewpoint of the present invention. The above description is merely an example, and is not intended to be restrictive. The invention is limited only as defined in the following claims and the equivalents thereto.

DESCRIPTION OF SYMBOLS 1 Portable information device 10 Acceleration sensor 11 Display 12 Terminal posture determination part 13 Walking peak determination part 14 Axial acceleration determination part 15 Operation state determination part 16 Careless walk determination part 17 Application

Claims (11)

A portable information device that has a display and an acceleration sensor, and detects a careless walking state while the user is walking while visually recognizing the display,
Terminal attitude determination means for calculating a gravity vector from acceleration data at time i and determining whether each of a roll angle and a pitch angle with respect to the gravity vector is within a predetermined angle range;
Walking peak determination means for calculating a vertical component acceleration with respect to the gravity vector, and determining whether or not a peak (maximum or minimum) of the vertical component acceleration occurs every predetermined time interval;
A portable information device comprising: an inadvertent walking determination unit that determines that the terminal posture determination unit and the walking peak determination unit are true when the terminal posture determination unit and the walking peak determination unit are true. The terminal posture determination means determines whether the user has vertical / horizontal holding according to the orientation of the gravity vector with respect to the long side and short side of the display, and determines the terminal posture coordinates serving as a reference for the roll angle and pitch angle. The portable information device according to claim 1, wherein the portable information device is converted. About the acceleration data,
The vertical component acceleration is within the first predetermined acceleration range;
The longitudinal component acceleration is within the second predetermined acceleration range;
An axial acceleration determining means for determining whether the left / right component acceleration is within a third predetermined acceleration range;
The portable information according to claim 1 or 2, wherein the careless walking determination means further determines that the careless walking state is in the inadvertent walking state when it is determined to be true by the axial acceleration determination means. machine. The first predetermined acceleration range for the vertical component acceleration is:
4. The portable information device according to claim 3, wherein the portable information device is wider than a second predetermined acceleration range for the front-rear component acceleration and a third predetermined acceleration range for the left-right component acceleration. The walking peak determination means calculates a moving average value every time vertical component acceleration is detected, sets an upper fluctuation threshold value and a lower fluctuation threshold value with the moving average value as a center, and the vertical component acceleration is determined as an upper fluctuation threshold value and a lower fluctuation value. The portable information device according to any one of claims 1 to 4, wherein the portable information device is determined to be true only when a timing at which the threshold value is alternately exceeded occurs at every predetermined time interval. 8. The walking peak determining means further determines true only when the number of times it is determined that the peak has occurred continues for a predetermined number of steps or more. Portable information equipment. The walking peak determination means further calculates a time difference ΔTm between peaks, and determines that it is true only when the standard deviation of the time difference ΔTm is equal to or less than a predetermined threshold value. The portable information device according to item. When the backlight of the display is lit, it further includes an operation state determination unit that determines that the display is in the user operation state,
The inattentive walking determination means further determines that the inadvertent walking state is present only when the operation state determination means determines to be true. The portable information device described. The portable type according to claim 8, wherein the operation state determination unit further determines that the specific application is activated or is in a user operation state when a user tap event is detected. Information equipment. A program for causing a computer mounted on a portable information device having a display and an acceleration sensor to function so as to detect an inattentive walking state in which a user is walking while viewing the display,
Terminal attitude determination means for calculating a gravity vector from acceleration data at time i and determining whether each of a roll angle and a pitch angle with respect to the gravity vector is within a predetermined angle range;
Walking peak determination means for calculating a vertical component acceleration with respect to the gravity vector, and determining whether or not a peak (maximum) of the vertical component acceleration occurs every predetermined time interval;
A program that causes a computer to function as an inadvertent walking determination unit that determines that the terminal is in an inadvertent walking state when the terminal posture determination unit and the walking peak determination unit determine true. A method for detecting a careless walking state in which a user is walking while visually recognizing the display by a portable information device having a display and an acceleration sensor,
Calculating a gravity vector from acceleration data at time i, determining whether each of a roll angle and a pitch angle with respect to the gravity vector is within a predetermined angle range;
Calculating a vertical component acceleration with respect to the gravity vector, and determining whether or not a peak (maximum) of the vertical component acceleration occurs every predetermined time interval;
An inattentive walking state detection method, wherein when the terminal posture determination unit and the walking peak determination unit determine true, the inattentional walking state is determined.

Images