JP5922638B2 - Pedestrian number estimation device, pedestrian number estimation system, and pedestrian number estimation method - Google Patents

Description

  The present invention relates to a pedestrian number estimation device, a pedestrian number estimation system, and a pedestrian number estimation method for estimating the number of pedestrians in a predetermined area.

2. Description of the Related Art Conventionally, there is a portable terminal device that includes a position measuring unit that measures a current location such as a GPS (Global Positioning System) sensor, and such a portable terminal device has a server that provides a predetermined service with measured position information and measurement. Time information indicating the time is transmitted. The server receives and stores position information and time information transmitted from the mobile terminal device.
Here, a method for estimating a population in a predetermined region using the position information and the time information stored in a server is known (for example, see Patent Document 1).
In the floating population specifying system of Patent Document 1, the positioning point and positioning time at which the current location of the mobile terminal is measured are stored, and the fluid population in the mesh region obtained by dividing the map is calculated based on the stored positioning point and positioning time. Estimated. Specifically, based on the stored positioning points and positioning times for the selected mesh area, the number of visitors and the number of persons estimated to have bases such as home or office in the mesh area (base users) Number). And the fluid population of the selected mesh area | region is calculated | required by deducting the number of base users from the number of visitors. According to this method, for example, since it is not necessary to manually investigate the number of people on the road, the cost for estimating the fluidized population can be greatly reduced.

JP 2013-97471 A

By the way, for example, it is required to estimate the number of pedestrians in a predetermined area in order to use for road advertisements, store opening plans, and the like.
However, in the above fluid population identification system of Patent Document 1, a person who passes a predetermined area, for example, by a train or a car may be counted as a fluid population, so that the number of pedestrians can be accurately estimated. is not.

  An object of the present invention is to provide a pedestrian number estimation device, a pedestrian number estimation system, and a pedestrian number estimation method that can accurately estimate the number of pedestrians.

The pedestrian number estimation device of the present invention is a storage means in which identification information for identifying a user, position information indicating the current location of the user's mobile terminal device, and time information are stored in association with each other as one piece of measurement information. A user extraction unit that extracts users located in the target area in the target period based on the measurement information stored in the storage unit, and a number of extracted users that calculates the number of users extracted by the user extraction unit For the user extracted by the calculation unit and the user extraction unit, a movement state is calculated based on a plurality of pieces of measurement information stored in the storage means, and whether the movement state corresponds to a predetermined movement condition A moving state determining unit for determining, and an excluded number calculating unit for calculating the number of users determined by the moving state determining unit that the moving state does not correspond to the predetermined moving condition Calculating the number of walking users in the target area in the target period based on the number of users calculated by the extracted number calculating unit and the number of users calculated by the excluded number calculating unit; A pedestrian number estimating unit that estimates the number of pedestrians in the target area in the target period based on the number of people, the movement state determination unit for the user extracted by the user extraction unit, The moving speed before and after the time when the vehicle is located in the target area in the target period is calculated based on a plurality of pieces of measurement information stored in the storage means, and both the moving speeds before and after the first threshold are greater than or equal to the first threshold value. In this case, it is determined that the predetermined moving condition is not met when both the front and rear moving speeds are equal to or lower than a second threshold value that is slower than the first threshold value .
In the pedestrian number estimation device of the present invention, identification information for identifying a user, position information indicating the current location of the user's mobile terminal device, and time information are stored in association with each other as one piece of measurement information. A storage unit, a user extraction unit that extracts users located in the target area in the target period based on the measurement information stored in the storage unit, and the number of users extracted by the user extraction unit is calculated For the user extracted by the extracted number calculating unit and the user extracting unit, the movement state is calculated based on a plurality of pieces of measurement information stored in the storage unit, and the movement state corresponds to a predetermined movement condition. A movement state determination unit that determines whether or not the movement state determination unit calculates the number of users who are determined that the movement state does not meet the predetermined movement condition Calculate the number of walking users in the target area in the target period based on the number of users calculated by the departure part, the number of users calculated by the extracted number calculating part, and the number of users calculated by the excluded number calculating part, Based on the number of walking users, a pedestrian number estimating unit that estimates the number of pedestrians in the target area in the target period, and a user located in a surrounding area surrounding the target area in the target period, Peripheral user extraction unit that extracts based on measurement information stored in the storage unit, and whether the user has passed the target area during the target period for the user extracted by the peripheral user extraction unit, the storage unit A traffic determination unit that is determined based on a plurality of measurement information stored in the user, and a user that is determined to have passed the target area during the target period by the traffic determination unit A supplementary number calculation unit that calculates the number of people, the pedestrian number estimation unit, the number of users calculated by the extracted number calculation unit, the number of users calculated by the exclusion number calculation unit, and the The number of walking users is calculated based on the number of users calculated by the supplementary number calculation unit.

  According to the present invention, it is possible to accurately estimate the number of pedestrians in the target area in the target period.

It is a block diagram which shows the structure of the pedestrian number estimation system which concerns on embodiment. It is a flowchart which shows the pedestrian number estimation process which concerns on embodiment. It is a flowchart which shows the exclusion number-of-people calculation process which concerns on embodiment. It is the figure which showed an example of the log | history of the positional information on one user on the map. It is a flowchart which shows the supplementary number calculation process which concerns on embodiment. It is the figure which showed on a map the other example of the log | history of the positional information on one user. It is a figure which shows an example of the walking user number of persons for every hour in one day. It is a figure which shows an example of kernel density distribution information.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
[Configuration of pedestrian number estimation system]
FIG. 1 is a block diagram showing a configuration of a pedestrian number estimation system 1 according to the present embodiment.
As shown in FIG. 1, a pedestrian number estimation system 1 includes a plurality of portable terminal devices 2 connected to a network 4 so as to be capable of wireless communication, and a pedestrian number estimation device 3 connected to a network 4 such as the Internet. And an analyst terminal device 5 connected to the pedestrian number estimating device 3 via a LAN (Local Area Network) or the like so as to be communicable. The analyst terminal device 5 may be communicably connected to the pedestrian number estimating device 3 via the network 4.

  The mobile terminal device 2 is, for example, a smartphone (multifunctional mobile phone), a mobile phone, a tablet terminal, or the like, and includes a position measurement unit 23 that measures the current location. The portable terminal device 2 transmits measurement information including position information obtained by measuring the current location and time information indicating measurement time when the position information is measured to the pedestrian number estimating device 3 via the network 4.

The pedestrian number estimation device 3 is configured by, for example, one server or a plurality of servers, receives measurement information transmitted from the plurality of mobile terminal devices 2, and stores the received measurement information. Then, the number of pedestrians in the target area in the target period is estimated based on the stored measurement information. Here, the target period is a period for estimating the number of pedestrians, and the target area is an area for estimating the number of pedestrians.
The analyst terminal device 5 is, for example, a PC (Personal Computer), and is operated by an analyst who performs analysis using the pedestrian number estimation device 3. The analyst terminal device 5 transmits an operation signal corresponding to the operation of the analyst to the pedestrian number estimation device 3. It should be noted that by operating the analyst terminal device 5, the target period and target area in which the pedestrian number estimating device 3 estimates the number of pedestrians can be set to an arbitrary period and region.

[Configuration of mobile terminal device]
The portable terminal device 2 is possessed and used by a user registered in the pedestrian number estimation system 1. The portable terminal device 2 includes a display unit 21, an input unit 22, a position measurement unit 23, a time measurement unit 24, a storage unit (terminal side storage unit) 25, a transmission / reception unit 26, and a control unit 29.
The display unit 21 includes a display panel such as a liquid crystal panel, and displays a predetermined image under the control of the control unit 29.
The input unit 22 includes a button provided on the outer surface of the casing of the mobile terminal device 2, a touch panel provided according to an image display area on the display unit 21, and the like. Then, the input unit 22 determines a user's input operation on the buttons and the touch panel, and outputs an operation signal corresponding to the determined input operation to the control unit 29.

  The position measurement unit 23 measures position information (latitude, longitude) of the current location of the mobile terminal device 2 (in other words, the current location of the user) under the control of the control unit 29, and outputs the measured position information to the control unit 29. . As the position measuring means 23, a GPS sensor (Global Positioning System) is used. The GPS sensor receives GPS signals (satellite signals) from at least three GPS satellites among a plurality of GPS satellites orbiting the earth's satellite orbit, and measures the position information of the current location of the mobile terminal device 2. .

The time measuring unit 24 includes a crystal resonator, measures the current time using an oscillation signal (reference signal: 1 Hz) output from the crystal resonator, and outputs the current time to the control unit 29.
The storage unit 25 is configured by a flash memory or the like, and stores various programs and information necessary for the operation of the mobile terminal device 2. The storage unit 25 stores, for example, a user ID (identification information) that identifies a user who uses the mobile terminal device 2 in the pedestrian number estimation system 1.
The transmission / reception means 26 is a communication module that wirelessly communicates with the network 4. The transmission / reception unit 26 transmits information output from the control unit 29 to the network 4 and outputs information received from the network 4 to the control unit 29 under the control of the control unit 29.

[Configuration of control means]
The control means 29 controls the operation of the mobile terminal device 2 and is constituted by a CPU. The control unit 29 functions as a measurement information generation unit 291 and a measurement information transmission unit 292 when the CPU executes a program stored in the storage unit 25.
For example, the measurement information generation unit 291 periodically acquires the position information measured by the position measurement unit 23 and time information indicating the measurement time, and associates the acquired position information and time information with the user ID. One piece of measurement information is generated.
The measurement information transmission unit 292 estimates the pedestrian number by controlling the transmission / reception means 26 with the measurement information generated by the measurement information generation unit 291 when the mobile terminal device 2 accesses the pedestrian number estimation device 3 or the like. Transmit to device 3.

[Configuration of pedestrian number estimation device]
The pedestrian number estimation device 3 includes a storage unit 31, a transmission / reception unit 32, and a control unit 35.
The storage means 31 is configured by an HDD (Hard Disk Drive), a flash memory, or the like, and stores various programs and information necessary for the operation of the pedestrian number estimating device 3. The storage means 31 stores, for example, map information and measurement information received from a plurality of portable terminal devices 2.
The transmission / reception means 32 is a communication module that communicates with the mobile terminal device 2 via the network 4 or communicates with the analyst terminal device 5. The transmission / reception unit 32 outputs the received information to the control unit 35 under the control of the control unit 35 and transmits the information output from the control unit 35 to the network 4 or the analyzer terminal device 5.

[Configuration of control means]
The control means 35 controls the operation of the pedestrian number estimation device 3 and is constituted by a CPU. In the control unit 35, the CPU executes the pedestrian number estimation program stored in the storage unit 31, whereby the storage control unit 351, the user extraction unit 352, the extracted number calculation unit 353, the movement state determination unit 354, the excluded number It functions as a calculation unit 355, a surrounding user extraction unit 356, a traffic determination unit 357, a supplementary number calculation unit 358, and a pedestrian number estimation unit 359.
The storage control unit 351 stores the measurement information received from the plurality of mobile terminal devices 2 in the storage unit 31.
The user extraction unit 352 extracts users located in the target area during the target period based on the measurement information stored in the storage unit 31. The target period and the target area can be set to an arbitrary period and area by operating the analyzer terminal device 5. The shape of the target area may be a rectangle or a circle.
The extracted number calculating unit 353 calculates the number of users (extracted number) extracted by the user extracting unit 352.

The movement state determination unit 354 calculates the movement state for the user extracted by the user extraction unit 352 based on a plurality of pieces of measurement information stored in the storage unit 31, and the calculated movement state is set to a predetermined movement condition. Determine if it applies.
Specifically, the predetermined movement condition is a predetermined speed condition, and the movement state determination unit 354 is when the user extracted by the user extraction unit 352 is located in the target area in the target period. The moving speed before and after the time (target time) is calculated based on the measurement information stored in the storage unit 31. Then, it is determined whether the calculated moving speed meets a predetermined speed condition. Here, the predetermined speed condition is set to a speed condition capable of determining that the user is walking. According to this, when it is determined that the moving speed before and after the target time does not meet the predetermined speed condition, it can be determined that the user is not walking before and after the target time. A user who is not walking before and after the target time has a high probability of not walking even at the target time, and therefore can be determined not to walk at the target time.
The excluded number calculating unit 355 calculates the number of users (excluded number) of users determined by the moving state determining unit 354 that the moving state does not correspond to the predetermined moving condition.
Specifically, the excluded number calculation unit 355 determines the number of users whose moving speeds before and after the target time are determined not to satisfy the predetermined speed condition, that is, the number of users who can be determined not to walk at the target time. Is calculated.

The peripheral user extraction unit 356 extracts users located in the peripheral area surrounding the target area during the target period based on the measurement information stored in the storage unit 31. The area and shape of the surrounding area can be set to an arbitrary area and shape by operating the analyzer terminal device 5. Further, the area of the surrounding area can be changed according to the target area. For example, when the target area is a suburb, the area of the surrounding area can be set larger than in the case where the target area is the city center.
The traffic determination unit 357 determines, based on a plurality of pieces of measurement information stored in the storage unit 31, whether or not the user extracted by the peripheral user extraction unit 356 has passed the target area during the target period.
The supplementary number calculation unit 358 calculates the number of users (supplementary number of people) determined by the traffic determination unit 357 to have passed the target area during the target period.

The pedestrian number estimation unit 359 subtracts the number of supplements calculated by the supplementary number calculation unit 358 from the number of extractions calculated by the extraction number calculation unit 353 minus the number of exclusions calculated by the exclusion number calculation unit 355. By adding, the number of users walking in the target area during the target period (the number of walking users) is calculated.
The storage control unit 351 stores the number of walking users calculated by the pedestrian number estimation unit 359 in the storage unit 31.
The pedestrian number estimation unit 359 includes a distribution information generation unit 3591. When the storage unit 31 stores the number of walking users calculated for a plurality of periods, the distribution information generation unit 3591 performs kernel density estimation in the time axis direction for the number of walking users in each period. Generate kernel density distribution information for walking users.
Then, the pedestrian number estimation unit 359 multiplies the number of walking users in each period indicated by the generated kernel density distribution information, for example, by the ratio of the population to the total number of users (rebate). Thereby, the number of pedestrians walking in the target area during each period is estimated.

[Pedestrian number estimation processing]
FIG. 2 is a flowchart showing the pedestrian number estimation process.
In the process shown in FIG. 2, the number of pedestrians is estimated for a plurality of consecutive periods. Here, the plurality of consecutive periods are 24 periods (0 hour range, 1 hour range,..., 23:00 range) obtained by dividing one day every hour.
The control means 35 sets the target period to the 0 o'clock range (SA11). Then, the control means 35 initializes the extracted number, the excluded number, and the supplementary number to “0” (SA12).

Next, the user extraction unit 352 extracts users located in the target area during the target period based on the measurement information stored in the storage unit 31 (SA13: user extraction step). Specifically, the user extraction unit 352 includes the time indicated by the time information in the target period (0:00:00 to 0:59:59), and the position indicated by the position information is the target area ( For example, measurement information included in a region surrounded by a circle having a radius of 200 m is acquired from the storage unit 31. Then, the user identified by the user ID included in the acquired measurement information is extracted.
Then, the extracted number calculating unit 353 calculates the number of extracted users (extracted number) by the user extracting unit 352 (SA14: extracted number calculating step). Even when a plurality of pieces of measurement information are acquired for the same user, the number of extracted persons is one.

[Exclusion number calculation process]
Next, the control means 35 executes excluded number person calculation processing (SA15).
FIG. 3 is a flowchart showing the excluded person count calculation process.
The excluded number calculation unit 355 selects one of the users extracted in SA13 (SA21).

Next, the movement state determination unit 354 measures, for the selected user, the movement speed before and after the time (target time) when the user is located in the target area during the target period. Calculation is performed based on the information (SA22).
Specifically, the movement state determination unit 354 includes, for the selected user, measurement information in which the time indicated by the time information is included in the target period and the position indicated by the position information is included in the target area. Is acquired from the storage means 31. Then, the time indicated by the acquired measurement information is set as the target time.
Further, the storage unit 31 acquires position information measured at the previous time closest to the time one hour before the target time and the subsequent time closest to the time one hour after the target time. Then, the distance from the position at the target time to the position at the previous time is calculated, and the calculated moving speed before the target time is calculated by dividing the calculated distance by the time interval between the target time and the previous time. Moreover, the distance from the position at the target time to the position at the later time is calculated, and the calculated moving speed after the target time is calculated by dividing the calculated distance by the time interval between the target time and the later time.
The previous time is not limited to the time closest to the time one hour before the target time, and may be any time as long as it is earlier than the target time. For example, the time closest to the target time may be 5 minutes before the target time, or the time closest to the target time. Similarly, the later time is not limited to the time closest to the time one hour after the target time, and may be any time as long as it is later than the target time. For example, it may be the closest time 5 minutes after the target time, or may be the time closest to the target time.

FIG. 4 is a diagram showing an example of the position information history of one user stored in the storage unit 31 on a map.
A position P indicated by a point on the map indicates a position indicated by the position information of one user stored in the storage unit 31. In this example, the position P1 is a position measured during the target period, and is included in the target area A1. The position P0 is a position measured at the previous time closest to the time one hour before the measurement time of the position P1. The position P2 is a position measured at a later time that is closest to the time one hour after the measurement time of the position P1.
In this case, the movement state determination unit 354 sets the measurement time at the position P1 as the target time. Then, the distance from P1 to P0 is calculated, and the calculated distance is divided by the time interval between the target time and the previous time to calculate the moving speed before the target time. Further, the distance from P1 to P2 is calculated, and the calculated distance is divided by the time interval between the target time and the later time to calculate the moving speed after the target time.

Next, the movement state determination unit 354 determines whether both of the movement speeds before and after the target time are equal to or higher than the first threshold (SA23: movement state determination step).
The first threshold value is set to a reference value that can be determined that the user is on a vehicle such as a train or a car, for example, 6.0 m / s (21.6 km / h).
That is, when it is determined YES in SA23, the user can determine that he / she is on the vehicle before and after the target time, and therefore, the user is highly likely to be on the vehicle at the target time and can determine that he / she is not walking. .

When it is determined NO in SA23, the movement state determination unit 354 determines whether both of the movement speeds before and after the target time are equal to or less than a second threshold value that is slower than the first threshold value (SA24: movement state determination step).
The second threshold value is set to a reference value that can be determined that the user stays in the office or the like and is not moving, for example, 0.1 m / s (360 m / h).
That is, when it is determined YES in SA24, the user can determine that he / she has not moved before and after the target time, so it is highly likely that the user has not moved even at the target time, and can be determined not to be walking.
That is, when it is determined YES at SA23, or when YES is determined at SA24, the movement state determination unit 354 determines that the movement speed before and after the target time does not meet the predetermined speed condition.

When it is determined YES at SA23, or when YES is determined at SA24, the excluded number calculating unit 355 counts up one excluded number (SA25: excluded number calculating step).
After the process of SA25, or when it is determined NO in SA24, the excluded number calculation unit 355 determines whether all of the users extracted in SA13 have been selected (SA26).
When it is determined NO in SA26, the excluded number calculation unit 355 selects one of the users not selected yet from the users extracted in SA13 (SA27). And the control means 35 returns a process to SA22.
Then, the processing of SA25 is executed for all the users extracted in SA13 according to the determination results of SA23 and SA24. Thereby, the number of excluded people is calculated. That is, the number of users who are not walking among the users located in the target area during the target period can be calculated.
And if it determines with YES by SA26, the control means 35 will complete | finish a process.

[Supplement number calculation processing]
Next, the control means 35 executes a supplementary number calculation process (SA16).
FIG. 5 is a flowchart showing the supplementary number calculation process.
The peripheral user extraction unit 356 extracts users located in the peripheral area surrounding the target area during the target period based on the measurement information stored in the storage unit 31 (SA31). Specifically, the peripheral user extraction unit 356 includes the time indicated by the time information in the target period, and the position indicated by the position information is a peripheral area of the target area (for example, a radius of 400 m concentric with the target area). The measurement information included in the area surrounded by the circumference (excluding the target area) is acquired from the storage unit 31, and the user identified by the user ID included in the acquired measurement information is extracted.
Then, the supplementary number calculator 358 selects one of the users extracted in SA31 (SA32).

Next, the traffic determination unit 357 determines, based on a plurality of pieces of measurement information stored in the storage unit 31, whether the user has passed the target area during the target period for a user who is located in the peripheral area during the target period. (SA33).
Specifically, when there are two or more pieces of measurement information measured in the surrounding area in the target period, the traffic determination unit 357 includes line segments that connect the positions indicated by the position information included in these measurement information, When passing through the target area, the user determines that the user has passed the target area during the target period.
FIG. 6 is a diagram showing another example of the position information history of one user stored in the storage unit 31 on a map.
In this example, the positions P3 and P4 are positions measured in the target period and are included in the surrounding area A2.
In this example, since the line segment L1 connecting the positions P3 and P4 passes through the target area A1, the passage determination unit 357 determines that the user has passed the target area A1 during the target period.

When it is determined YES in SA33, the supplementary number calculating unit 358 increments the supplementary number by one (SA34).
After the process of SA34 or when it is determined NO in SA33, the supplementary number calculation unit 358 determines whether all of the users extracted in SA31 have been selected (SA35).
When it is determined NO in SA35, the supplementary number calculation unit 358 selects one of the users that have not been selected among the users extracted in SA31 (SA36). And the control means 35 returns a process to SA33.
Then, the process of SA34 is executed for all the users extracted in SA31 according to the determination result of SA33. Thereby, the supplementary number is calculated. That is, the time indicated by the time information is included in the target period and the measurement information including the position indicated by the position information in the target area is not stored in the storage unit 31, but the target area passes through the target period. It is possible to calculate the number of users who can be estimated to have been.
And if it determines with YES by SA35, the control means 35 will complete | finish a process.

  Next, returning to FIG. 2, the pedestrian number estimating unit 359 adds the supplementary number calculated in SA16 to the number calculated by subtracting the excluded number calculated in SA15 from the extracted number calculated in SA14. The number of walking users indicating the number of users walking in the target area during the target period is calculated. The storage control unit 351 stores the target period and the calculated number of walking users in the storage unit 31 in association with each other.

Next, the control means 35 determines whether the target period is around 23:00 (SA18). When it is determined NO in SA18, the control unit 35 sets the target period to the next period (SA19). And the control means 35 returns a process to SA12.
Then, the processing of SA12 to SA17 is executed for all 24 periods. Accordingly, the number of walking users per hour in one day is stored in the storage unit 31.
FIG. 7 is a bar graph showing an example of the number of walking users per hour stored in the storage means 31. The horizontal axis indicates time, and the vertical axis indicates the number of walking users.
In this example, a central area station is the target area. The peak of the number of walking users is located at the 8:00 to 19:00 commuting hours. The number of walking users is “0” between 1 o'clock and 4 o'clock.

When YES is determined in SA18, the distribution information generation unit 3591 performs kernel density estimation in the time axis direction for the number of walking users per hour stored in the storage unit 31, and the kernel density of the number of walking users is determined. Distribution information is generated (SA20).
Specifically, the distribution information generation unit 3591 calculates the kernel function K expressed by the equation (1) in the time axis direction in the data for one person with respect to the number of walking users stored every hour in the storage unit 31. The kernel density distribution information is generated by giving the distribution expressed by (x) and superimposing all the distributions.

  FIG. 8 is a diagram illustrating an example of kernel density distribution information. The kernel density distribution information is calculated based on the number of walking users for each time indicated by the bar graph of FIG. In the bar graph of FIG. 7, the number of walking users is “0” from 1 o'clock to 4 o'clock, but in the kernel density distribution information shown in FIG. 8, the walking user is also from 1 o'clock to 4 o'clock. The number of people does not become “0”.

  Next, the pedestrian number estimation unit 359 multiplies the number of walking users in each period indicated by the kernel density distribution information generated in SA20, for example, by the ratio of the population to the total number of users (rebate). Thereby, the number of pedestrians walking in the target area in each period is estimated (SA29: pedestrian number estimation step). And the control means 35 complete | finishes a process.

[Effects of Embodiment]
According to this embodiment, the following operational effects can be obtained.
The pedestrian number estimating unit 359 calculates the number of walking users by subtracting the number of users (excluded number) calculated by the excluded number calculating unit 355 from the number of users calculated by the extracted number calculating unit 353 (extracted number). (SA17).
According to this, since the number of users who are not walking is subtracted from the number of users located in the target area in the target period, the number of walking users in the target area in the target period can be accurately calculated. As a result, the number of pedestrians in the target area in the target period can be accurately estimated.

The movement state determination unit 354 stores, in the storage unit 31, the movement speed before and after the time (target time) when the user extracted by the user extraction unit 352 is located in the target area during the target period. It is calculated based on a plurality of measurement information (SA22), and it is determined whether the preceding and following moving speeds meet a predetermined speed condition (SA23, SA24).
According to this, a user who is not walking before and after the target time can be determined. A user who is not walking before and after the target time has a high probability of not walking even at the target time, and therefore can be determined not to walk at the target time.
According to this, the determination of the user who is not walking can be calculated based only on the measurement information stored in the storage unit 31. For this reason, it is not necessary to newly acquire another information, and determination can be performed easily.

The movement state determination unit 354 determines whether the movement speed before and after the user is extracted by the user extraction unit 352 when both the front and rear movement speeds are equal to or higher than the first threshold (YES in SA23). When it is equal to or less than 2 threshold values (YES in SA24), it is determined that the front and rear moving speeds do not satisfy the predetermined speed condition.
According to this, since the user who is not walking can be determined only by comparing the moving speed with the threshold value, the processing load on the pedestrian number estimating device 3 can be reduced.

The pedestrian number estimation unit 359 adds the number of users (supplementary number) calculated by the supplementary number calculation unit 358 to the number of users calculated by the extraction number calculation unit 353 (extraction number), and the number of walking users Is calculated (SA17).
According to this, measurement information in which the time indicated by the time information is included in the target period and the position indicated by the position information is included in the target area is included in the number of users walking in the target area in the target period. Although not stored in the storage means 31, it is possible to add the number of users who can be estimated to have passed the target area during the target period. For this reason, the number of walking users in the target area in the target period can be calculated more. As a result, the number of pedestrians in the target area in the target period can be estimated more accurately.

The distribution information generation unit 3591 performs kernel density estimation in the time axis direction for the number of walking users in a plurality of periods, and generates kernel density distribution information for the number of walking users (SA20). Then, the pedestrian number estimating unit 359 estimates the number of pedestrians based on the kernel density distribution information (SA29).
According to this, even when the measurement information is not stored in the storage unit 31, the number of walking users is estimated based on the number of walking users in other periods. Thereby, for example, during the period in which the measurement information is not stored in the storage unit 31, it is possible to provide useful information for the user as compared with the case where the number of pedestrians is all “0”.

[Other Embodiments]
In addition, this invention is not limited to the structure of the said embodiment, A various deformation | transformation implementation is possible within the range of the summary of this invention.
In the embodiment, the movement state determination unit 354 calculates the movement speed before and after the time when the user is located in the target area in the target period (target time) for the user extracted by the user extraction unit 352. Although it has been determined whether the forward and backward movement speeds meet a predetermined speed condition, the present invention is not limited to this.
For example, the predetermined movement condition is set as a predetermined movement route, and the movement state determination unit 354 determines the movement route for the user extracted by the user extraction unit 352 based on a plurality of pieces of measurement information stored in the storage unit 31. To determine whether the movement route meets a predetermined route condition. Here, the predetermined route condition is set to a route condition (for example, a sidewalk) that can be determined that the user is walking.

Specifically, the movement state determination unit 354 acquires the positions before and after the target time based on the measurement information stored in the storage unit 31 for the user who is located in the target area during the target period. And a movement path | route is calculated by connecting the position of object time, and the position before and behind object time.
According to this, for example, a user on a vehicle such as a train or an automobile is determined that the movement route does not meet the predetermined route condition. Thereby, the user who is not walking can be determined.
Further, the determination of a user who is not walking can be calculated based only on the measurement information stored in the storage unit 31. For this reason, it is not necessary to newly acquire another information, and determination can be performed easily.
Note that the movement state determination unit 354 may determine whether the movement route corresponds to a predetermined route condition in addition to the determination of whether the preceding and following movement speeds correspond to a predetermined speed condition.

In the embodiment, the distribution information generation unit 3591 performs kernel density estimation in the time axis direction to generate kernel density distribution information for the number of walking users in each period (one hour period in one day). In addition to this, kernel density estimation may be performed in the latitude direction and longitude direction to generate kernel density distribution information.
In this case, the user extraction unit 352 extracts users located respectively in a plurality of areas obtained by dividing a predetermined area including the target area.
Then, the pedestrian number estimation unit 359 calculates the number of walking users in each of the plurality of regions, and the distribution information generation unit 3591 calculates the time axis direction, the latitude direction, and the number of walking users in each period and each region, and Kernel density estimation is performed in the longitude direction, and kernel density distribution information is generated. Then, the pedestrian number estimating unit 359 estimates the number of pedestrians based on the generated kernel density distribution information.
According to this, the number of walking users in the area around the target area can be reflected in the number of walking users in the target area, and the number of pedestrians in the target area can be estimated more accurately.
The distribution information generation unit 3591 may generate kernel density distribution information by performing kernel density estimation in at least one of the latitude direction and the longitude direction excluding the time axis direction.

  In the embodiment, in SA17, the pedestrian number estimation unit 359 adds the number of users calculated by the supplementary number calculation unit 358 (supplementary number) to the number of users calculated by the extraction number calculation unit 353 (extraction number). Is added to calculate the number of walking users. However, for example, when the number of extracted users is large, it is not necessary to add the supplementary number.

  In the embodiment, at SA20, the distribution information generation unit 3591 generates kernel density distribution information, and at SA29, the pedestrian number estimation unit 359 estimates the number of pedestrians based on the kernel density distribution information. However, for example, when the number of walking users is large, the number of pedestrians may be estimated based on the number of walking users calculated in SA17 without generating the kernel density distribution information.

  In the embodiment, as shown in the flowchart of FIG. 3, the moving speed calculation process (SA22) and the moving speed determination process (SA23, SA24) are sequentially performed for each user to calculate the number of excluded people. However, the present invention is not limited to this. For example, the excluded number may be calculated by first performing the moving speed calculation process for all users and calculating the number of users whose moving speed does not meet the moving speed determination condition.

  In the embodiment, the position information included in the measurement information is measured by the position measurement unit 23 of the mobile terminal device 2, but the present invention is not limited to this. For example, the pedestrian number estimating device 3 may acquire the position of the base station on the network 4 with which the mobile terminal device 2 is communicating, and the acquired position may be the position information.

  DESCRIPTION OF SYMBOLS 1 ... Pedestrian number estimation system, 2 ... Portable terminal device, 21 ... Display means, 22 ... Input means, 23 ... Position measuring means, 24 ... Time measuring means, 25 ... Memory | storage means, 26 ... Transmission / reception means, 29 ... Control means, 291 ... Measurement information generation unit, 292 ... Measurement information transmission unit, 3 ... Pedestrian number estimating device, 31 ... Storage unit, 32 ... Transmission / reception unit, 35 ... Control unit, 351 ... Storage control unit, 352 ... User extraction unit, 353 ... extracted number calculating unit, 354 ... moving state determining unit, 355 ... excluded number calculating unit, 356 ... peripheral user extracting unit, 357 ... passage determining unit, 358 ... supplementary number calculating unit, 359 ... pedestrian number estimating unit, 3591 ... Distribution information generation unit, 4... Network, 5.

Claims (9)

Storage means for storing identification information for identifying the user, position information indicating the current location of the user's mobile terminal device, and time information in association with each other and stored as one piece of measurement information;
A user extraction unit that extracts users located in the target area in the target period based on the measurement information stored in the storage unit;
An extracted number calculating unit for calculating the number of users extracted by the user extracting unit;
For the user extracted by the user extraction unit, a movement state is calculated based on a plurality of pieces of measurement information stored in the storage unit, and it is determined whether the movement state satisfies a predetermined movement condition A determination unit;
An excluded number calculating unit that calculates the number of users determined by the moving state determining unit to determine that the moving state does not correspond to the predetermined moving condition;
Based on the number of users calculated by the extracted number calculation unit and the number of users calculated by the exclusion number calculation unit, the number of walking users in the target area in the target period is calculated, and the number of walking users And a pedestrian number estimating unit for estimating the number of pedestrians in the target area in the target period ,
The movement state determination unit is configured to store a plurality of movement speeds stored in the storage unit before and after the time when the movement state determination unit is located in the target area during the target period for the user extracted by the user extraction unit. Calculated based on the measurement information, and when the front and rear moving speeds are both equal to or higher than the first threshold, and when the front and rear moving speeds are both equal to or lower than the second threshold, which is lower than the first threshold, The pedestrian number estimating device, characterized in that it is determined that it does not correspond to any of the moving conditions . Storage means for storing identification information for identifying the user, position information indicating the current location of the user's mobile terminal device, and time information in association with each other and stored as one piece of measurement information;
A user extraction unit that extracts users located in the target area in the target period based on the measurement information stored in the storage unit;
An extracted number calculating unit for calculating the number of users extracted by the user extracting unit;
For the user extracted by the user extraction unit, a movement state is calculated based on a plurality of pieces of measurement information stored in the storage unit, and it is determined whether the movement state satisfies a predetermined movement condition A determination unit;
An excluded number calculating unit that calculates the number of users determined by the moving state determining unit to determine that the moving state does not correspond to the predetermined moving condition;
Based on the number of users calculated by the extracted number calculation unit and the number of users calculated by the exclusion number calculation unit, the number of walking users in the target area in the target period is calculated, and the number of walking users Pedestrian number estimating unit for estimating the number of pedestrians in the target area in the target period ,
In the target period, a peripheral user extraction unit that extracts a user located in a peripheral area surrounding the target area based on measurement information stored in the storage unit;
For the user extracted by the peripheral user extraction unit, a passage determination unit that determines whether or not the target area has been passed during the target period based on a plurality of measurement information stored in the storage unit;
A supplementary number calculating unit that calculates the number of users determined to have passed the target area in the target period by the traffic determination unit,
The pedestrian number estimating unit is based on the number of users calculated by the extracted number calculating unit, the number of users calculated by the excluded number calculating unit, and the number of users calculated by the supplementary number calculating unit. The pedestrian number estimating device characterized in that the number of walking users is calculated . In the pedestrian number estimating device according to claim 1 ,
In the target period, a peripheral user extraction unit that extracts a user located in a peripheral area surrounding the target area based on measurement information stored in the storage unit;
For the user extracted by the peripheral user extraction unit, a passage determination unit that determines whether or not the target area has been passed during the target period based on a plurality of measurement information stored in the storage unit;
A supplementary number calculating unit that calculates the number of users determined to have passed the target area in the target period by the traffic determination unit,
The pedestrian number estimating unit is based on the number of users calculated by the extracted number calculating unit, the number of users calculated by the excluded number calculating unit, and the number of users calculated by the supplementary number calculating unit. And calculating the number of walking users. In the pedestrian number estimating device according to any one of claims 1 to 3,
The predetermined movement condition includes a predetermined route condition,
The movement state determination unit calculates a movement route based on a plurality of pieces of measurement information stored in the storage unit for the user extracted by the user extraction unit, and the movement route satisfies the predetermined route condition. A device for estimating the number of pedestrians, wherein it is determined whether or not it corresponds. In the pedestrian number estimating device according to any one of claims 1 to 4 ,
The number of walking users is calculated for a plurality of periods,
The pedestrian number estimating unit is
With respect to the number of walking users in each period, a kernel density estimation is performed in the time axis direction, and a distribution information generation unit that generates kernel density distribution information of the number of walking users is provided.
The pedestrian number estimating device, wherein the number of pedestrians is estimated based on the kernel density distribution information. In the pedestrian number estimating device according to any one of claims 1 to 5 ,
The user extraction unit extracts users located respectively in a plurality of areas obtained by dividing a predetermined area including the target area,
The pedestrian number estimating unit is
Calculate the number of walking users in each of the plurality of areas,
For the number of walking users in each region, a kernel density estimation is performed in at least one of the latitude direction and the longitude direction, and a distribution information generation unit that generates kernel density distribution information of the number of walking users is provided.
The pedestrian number estimating device, wherein the number of pedestrians is estimated based on the kernel density distribution information. A pedestrian number estimating system comprising the pedestrian number estimating device according to any one of claims 1 to 6 and the portable terminal device,
The portable terminal device
Timekeeping means,
A position measuring means for measuring the current location;
Terminal-side storage means for storing the identification information;
A measurement information generation unit that generates one measurement information in which the identification information, the position information measured by the position measurement unit, and the time information indicating the measurement time are associated with each other;
A measurement information transmission unit that transmits the measurement information generated by the measurement information generation unit to the pedestrian number estimation device,
The pedestrian number estimating device is
A pedestrian number estimation system comprising: a storage control unit that stores measurement information received from the portable terminal device in the storage unit. Pedestrian of the pedestrian number estimation device comprising storage means for storing identification information for identifying a user, position information indicating the current location of the user's mobile terminal device, and time information in association with each other and stored as one measurement information A method for estimating the number of people,
A user extraction step of extracting a user located in the target area in the target period based on the measurement information stored in the storage unit;
An extraction number calculation step for calculating the number of users extracted in the user extraction step;
For the user extracted in the user extraction step, a movement state is calculated based on a plurality of pieces of measurement information stored in the storage means, and the movement state determines whether the movement state meets a predetermined movement condition A determination step;
An excluded number calculating step of calculating the number of users determined that the moving state does not correspond to the predetermined moving condition in the moving state determining step;
Based on the number of users calculated in the extraction number calculation step and the number of users calculated in the exclusion number calculation step, the number of walking users in the target area in the target period is calculated, and the number of walking users Pedestrian number estimation step for estimating the number of pedestrians in the target area in the target period ,
In the moving state determination step, a plurality of moving speeds before and after the time when the user is located in the target area in the target period are stored in the storage unit for the user extracted in the user extraction step. Calculated based on the measurement information, and when the front and rear moving speeds are both equal to or higher than the first threshold, and when the front and rear moving speeds are both equal to or lower than the second threshold, which is lower than the first threshold, A method for estimating the number of pedestrians, wherein it is determined that the movement condition is not met. Pedestrian of the pedestrian number estimation device comprising storage means for storing identification information for identifying a user, position information indicating the current location of the user's mobile terminal device, and time information in association with each other and stored as one measurement information A method for estimating the number of people,
A user extraction step of extracting a user located in the target area in the target period based on the measurement information stored in the storage unit;
An extraction number calculation step for calculating the number of users extracted in the user extraction step;
For the user extracted in the user extraction step, a movement state is calculated based on a plurality of pieces of measurement information stored in the storage means, and the movement state determines whether the movement state meets a predetermined movement condition A determination step;
An excluded number calculating step of calculating the number of users determined that the moving state does not correspond to the predetermined moving condition in the moving state determining step;
Based on the number of users calculated in the extraction number calculation step and the number of users calculated in the exclusion number calculation step, the number of walking users in the target area in the target period is calculated, and the number of walking users Pedestrian number estimating step for estimating the number of pedestrians in the target area in the target period ,
In the target period, a peripheral user extraction step of extracting a user located in a peripheral area surrounding the target area based on measurement information stored in the storage unit;
A passage determination step for determining whether or not the user has passed the target area during the target period based on a plurality of pieces of measurement information stored in the storage unit, for the user extracted in the peripheral user extraction step;
A supplementary number calculating step of calculating the number of users determined to have passed the target area in the target period in the traffic determination step,
The pedestrian number estimation step is based on the number of users calculated in the extraction number calculation step, the number of users calculated in the exclusion number calculation step, and the number of users calculated in the supplement number calculation step. And calculating the number of walking users .

Images