JP7216631B2 - TERMINAL DEVICE, SYSTEM, PASSING NUMBER MEASUREMENT METHOD, AND COMPUTER PROGRAM - Google Patents

Description

The present invention relates to a terminal device, a system, a passing number measuring method, and a computer program.

A technique for estimating the number of people passing by is known (see Patent Document 1, for example). This technology converts acoustic information collected by microphones installed near passages into signal strength (power) and compares it with previously recorded acoustic data to estimate the number of people passing through.

JP 2012-181631 A

With the above-mentioned technology, the number of people passing by is measured from the footsteps of passers-by based on the acoustic information collected by microphones installed near passages. , environmental noise such as the sound of rain may be collected as noise. When environmental noise is collected as noise, it may not be possible to accurately measure the number of passing moving objects.
The present invention has been made in consideration of such circumstances, and its object is to provide a terminal device, a system, and a passing number measurement that can improve the measurement accuracy of one or both of the number of moving objects and the direction of movement. The object is to provide a method and a computer program.

(1) In one aspect of the present invention, a distance sensor unit that measures a distance, and a measurement result group including a plurality of measurement results obtained by the measurement by the distance sensor unit, based on the measurement time, a plurality of a computing unit that extracts one or more blocks containing measurement results and approximates a plurality of measurement results included in each of the extracted one or more blocks; an estimating unit that derives one or both of the number of moving objects measured by the distance sensor unit and the direction of movement based on an approximation result of a plurality of measurement results ; The terminal device determines whether or not the number of moving objects is plural based on the length of each of the blocks .
(2) In one aspect of the present invention, in the terminal device according to (1) above, the calculation unit removes measurement results including errors from a plurality of the measurement results, and removes the measurement results including errors. Based on the measurement time, one or a plurality of blocks including a plurality of measurement results are extracted from the remaining measurement result group.
( 3 ) An aspect of the present invention is the terminal device according to (1) or ( 2) above, wherein the computing unit comprises a time series of a plurality of the measurement results included in each of the one or more blocks and the estimating unit derives the moving direction of the moving object based on the gradient of the approximate expression derived by the computing unit.
( 4 ) In one aspect of the present invention, in the terminal device according to ( 3 ) above, the computing unit performs continuous deriving a difference between the two measurement results, deriving a statistical value from the plurality of the derived differences, deleting one of the plurality of the measurement results based on the difference and the statistical value, An approximation formula is derived based on the time series of the plurality of measurement results included in each of the one or the plurality of blocks obtained by deleting any one of the plurality of measurement results.

( 5 ) In one aspect of the present invention, a distance sensor unit that measures a distance, and a measurement result group including a plurality of measurement results obtained by the measurement by the distance sensor unit, based on the measurement time, a plurality of a computing unit that extracts one or more blocks containing measurement results and approximates a plurality of measurement results included in each of the extracted one or more blocks; an estimating unit that derives one or both of the number of moving objects measured by the distance sensor unit and the direction of movement based on an approximation result of a plurality of measurement results ; A system for determining whether the number of moving objects is plural based on the length of each of the blocks .

( 6 ) One aspect of the present invention is a measurement method executed by a terminal device having a distance sensor unit that measures distance, the measurement result including a plurality of measurement results obtained by the measurement performed by the distance sensor unit. extracting one or more blocks containing a plurality of measurement results from the group based on the measurement time, and approximating the plurality of measurement results included in each of the extracted one or more blocks; deriving one or both of the number of moving objects measured by the distance sensor unit and the moving direction based on an approximation result of a plurality of measurement results included in each of the one or more blocks; or determining whether the number of moving objects is plural based on the length of each of the plurality of blocks .

( 7 ) According to one aspect of the present invention, a block including a plurality of measurement results obtained by the distance sensor section is selected from a measurement result group including a plurality of measurement results obtained by the measurement by the distance sensor unit, based on the measurement time. or a step of extracting a plurality and approximating a plurality of measurement results included in each of the extracted one or more blocks; and an approximation result of the plurality of measurement results included in each of the one or more blocks by the approximating step a step of deriving one or both of the number of moving objects measured by the distance sensor unit and the direction of movement based on the length of each of the one or more blocks; , and determining whether there is more than one.

According to the present invention, it is possible to provide a terminal device, a system, a passing number measuring method, and a computer program that can improve the measurement accuracy of one or both of the number of moving objects and the direction of movement.

FIG. 2 is a block diagram showing a terminal device included in the number-of-passes measuring system according to the embodiment of the present invention; It is a figure which shows an example of passer count information. FIG. 4 is a diagram for explaining an example of block determination; FIG. 10 is a diagram for explaining a process of acquiring divided records from a valid block; FIG. It is a figure which shows an example of operation|movement of the terminal device which concerns on this embodiment. FIG. 11 is a block diagram showing a transit number measuring system according to a modification of the embodiment of the present invention; It is a figure which shows an example of passer-related information. It is a figure which shows an example of terminal information. It is a figure which shows an example of setting information. It is a figure which shows an example of operation|movement of the number-of-passes measuring system based on the modification of embodiment. FIG. 11 is a diagram for explaining an application example of the number-of-passes measuring system according to a modification of the embodiment; FIG. 10 is a diagram showing an example 1 of distance values acquired by a terminal device according to a modification of the embodiment; It is a figure which shows the example 1 of a process of the terminal device which concerns on the modification of embodiment. It is a figure which shows the example 2 of a process of the terminal device which concerns on the modification of embodiment. FIG. 12 is a diagram showing an example 2 of distance values acquired by the terminal device according to the modified example of the embodiment; FIG. 12 is a diagram illustrating example 3 of processing of a terminal device according to a modification of the embodiment; FIG. 12 is a diagram showing an example 4 of processing of the terminal device according to the modified example of the embodiment; FIG. 12 is a diagram illustrating example 5 of processing of a terminal device according to a modification of the embodiment; FIG. 11 is a diagram showing an example 3 of distance values acquired by a terminal device according to a modified example of the embodiment; FIG. 12 is a diagram illustrating an example 6 of processing of the terminal device according to the modified example of the embodiment; FIG. 12 is a diagram illustrating an example 7 of processing of a terminal device according to a modification of the embodiment;

Next, the terminal device, the system, the number-of-passes measuring method, and the computer program of this embodiment will be described with reference to the drawings. The embodiments described below are merely examples, and embodiments to which the present invention is applied are not limited to the following embodiments.
In addition, in all the drawings for explaining the embodiments, the same reference numerals are used for the parts having the same functions, and repeated explanations are omitted.
In addition, "based on XX" in the present application means "based on at least XX", and includes cases based on other elements in addition to XX. Moreover, "based on XX" is not limited to the case of using XX directly, but also includes the case of being based on what has been calculated or processed with respect to XX. "XX" is an arbitrary element (for example, arbitrary information).

(embodiment)
(Terminal device)
A pass measurement system 100 according to the embodiment of the present invention includes a terminal device 1 .
FIG. 1 is a block diagram showing a terminal device included in a passing number measuring system according to an embodiment of the present invention. The terminal device 1 according to the embodiment derives the number of objects that have passed through the measurement range and the moving direction of the objects.
The terminal device 1 is realized as a smart phone, a mobile terminal, a personal computer, a tablet terminal device, a wristwatch type terminal device, or other information processing equipment. The terminal device 1 includes, for example, a moving object detection unit 10, a processing unit 11, a distance sensor unit 12, a calculation unit 13, an estimation unit 14, and a storage unit 15.
The moving object detection unit 10 detects the presence of a moving object (hereinafter referred to as "moving object"). For example, the moving object detection unit 10 includes an imaging device, and detects the object when a moving object exists around the terminal device 1 . The moving object includes a passerby existing in an area detectable by the moving object detection unit 10 . When detecting a moving object, the moving object detection unit 10 outputs a moving object detection notification, which is a signal for notifying that the moving object has been detected, to the processing unit 11 .
The distance sensor unit 12 measures a distance and outputs a distance value, which is the distance measurement result, to the processing unit 11 . For example, the distance sensor unit 12 measures the distance between the moving object and the terminal device 1 .

The storage unit 15 is implemented by a HDD (Hard Disk Drive), flash memory, RAM (Random Access Memory), ROM (Read Only Memory), or the like. The storage unit 15 stores passer count information 15a and setting information 15c. The passerby count information 15a and the setting information 15c may be stored on the cloud.
The passer-by count information 15a is information in a table format that associates measurement results with measurement date and time information. The measurement results include information indicating the number of passers-by and information indicating the direction of movement. Information indicating the movement direction may be represented by a direction toward the terminal device 1 and a direction away from the terminal device 1 .
FIG. 2 is a diagram showing an example of passer-by count information. An example of the passer-by count information 15a includes, as measurement results, the number of passers-by "***", the direction of movement "***", and measurement date and time information "***/***/***/* *:**” are associated. An example of the passerby count information 15a is associated with the number of passers "+++", the direction of movement "+++", and the measurement date and time information "++++/++/++/++:++" as the measurement results. ing. Returning to FIG. 1, the description continues.
The setting information 15c is information in a table format that associates a total time interval, a distance threshold, a valid block threshold, an invalid value threshold, a block length threshold, and a valid tilt threshold. The tally time interval is the time interval for tallying the number of passers-by and their moving directions. The distance threshold, valid block threshold, invalid value threshold, block length threshold, and valid tilt threshold will be described later. Here, the total time may be stored in the setting information 15c instead of or together with the total time interval. The counting time is the time for counting the number of passers-by and their moving directions. Further, the setting information 15c may store the time interval information for measuring the distance by the distance sensor unit 12 mounted on the terminal device 1, or may be stored in the passer-by count information 15a of the storage unit 15 of the terminal device 1. Either one or both of the information indicating the retention period of the information and the number of information may be stored. The information stored in the setting information 15c is registered when the passage number measuring system 100 is used.

The processing unit 11 , the calculation unit 13 , and the estimation unit 14 are implemented by executing a program (software) stored in the storage unit 15 by a hardware processor such as a CPU (Central Processing Unit). Some or all of these functional units are hardware (circuits) such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), GPU (Graphics Processing Unit) (including circuitry), or by cooperation between software and hardware. The program may be stored in advance in a storage device such as a HDD (Hard Disk Drive) or flash memory, or may be stored in a removable storage medium such as a DVD or CD-ROM. It may be installed by being worn.
The processing unit 11 controls and manages overall operations of the terminal device 1 . The processing unit 11 acquires the moving object detection notification output by the moving object detection unit 10, and activates the distance sensor unit 12 based on the acquired moving object detection notification. The processing unit 11 causes the activated distance sensor unit 12 to start measuring the distance. The processing unit 11 acquires the distance value output by the distance sensor unit 12 and outputs the acquired distance value to the calculation unit 13 .

The calculation unit 13 acquires the distance value output by the processing unit 11 . The calculation unit 13 uses a block extraction algorithm from measurement results including time-series distance values, which are time-series data of acquired distance values, to include distance values that are determined to be distance values to passers-by. Extract the data group of measurement results. The calculation unit 13 removes distance values including errors such as the influence of noise from the distance sensor unit 12 from the extracted measurement results. Details of the block extraction algorithm will be described later.
The calculation unit 13 uses a passer-by grouping algorithm to block the time-series distance values based on changes in the time-series distance values obtained by removing the distance values including errors such as the effects of noise. conduct. The details of the passerby grouping algorithm will be described later. The calculation unit 13 outputs the results of blocking the time-series distance values to the estimation unit 14 .

The estimating unit 14 acquires the results of blocking the time-series distance values output by the computing unit 13, and based on the acquired results of blocking the time-series distance values, estimates the values of the passers-by. Estimate the number of people.
When the estimation result of the number of passers-by is one or less, the estimation unit 14 derives the inclination of the time-series distance value based on the result of blocking the time-series distance value. . For example, the estimation unit 14 derives the slope of the time-series distance values by an approximation method such as the least squares method. The estimation unit 14 derives the moving direction of the passerby based on the derived slope of the approximate expression. The estimation unit 14 outputs to the processing unit 11 information indicating the count value of the passerby and information indicating the moving direction of the passerby.
When the estimated number of passers-by is greater than two, the estimating unit 14 blocks the time-series distance values based on the results of blocking the time-series distance values. Split the result into multiple split records. The estimating unit 14 removes outliers from a record group that is a plurality of measured values included in each of the plurality of divided records. The estimating unit 14 performs evaluation by deriving an approximation formula using an approximation method such as the least-squares method based on the remaining records from which the outliers have been removed from the plurality of records included in the record group. After the evaluation of all divided records is completed, the estimating unit 14 derives the count value of the passerby and the moving direction of the passerby based on the slope of the derived approximate expression. The estimation unit 14 outputs information indicating the count value of the passers-by and information indicating the moving direction of the passers-by to the processing unit 11 .
The processing unit 11 has a clock function. The processing unit 11 acquires the time information when it acquires the information indicating the count value of the passerby output by the estimation unit 14 and the information indicating the moving direction of the passerby. The processing unit 11 associates the acquired time information, the information indicating the count value of the passerby, and the information indicating the moving direction of the passerby, and stores them in the passerby count information 15 a of the storage unit 15 .

(block extraction algorithm)
Details of the block extraction algorithm described above will be described.
In the block extraction algorithm, the calculation unit 13 extracts the measurement results (data group) including time-series distance values, which are the time-series data of the distance values output by the distance sensor unit 12, from the influence of noise contained in the measurement results. If a distance value containing an error such as is included, the measurement value is removed. A distance value including an error such as the influence of noise is called an invalid value, and a measured value other than the invalid value is called an effective value. Here, valid values may include outliers.
The block extraction algorithm causes the calculation unit 13 to invalidate a value indicating infinity among the plurality of distance values output by the distance sensor unit 12 . For example, the block extraction algorithm causes the calculation unit 13 to invalidate distance values equal to or greater than the distance threshold among the plurality of distance values output by the distance sensor unit 12 . The distance threshold is set based on the distance sensor unit 12 and the assumed position of the passerby. The block extraction algorithm causes the calculation unit 13 to remove invalid values from multiple distance values. The block extraction algorithm causes the computing unit 13 to extract one or more records containing continuous valid values from the plurality of distance values remaining after removing the invalid values from the plurality of distance values. The block extraction algorithm causes the computing unit 13 to treat one or more records as blocks.

A specific description will be given. The calculation unit 13 functions as follows by executing a block extraction algorithm.
(1) The computing unit 13 extracts one or more blocks from the data group.
(2) The calculation unit 13 checks whether or not the number of valid value records included in each of the extracted one or more blocks is equal to or greater than a preset valid block threshold. The calculation unit 13 determines that the number of valid value records is equal to or greater than the valid block threshold as valid blocks. The calculation unit 13 determines an invalid block that the number of valid value records is less than the valid block threshold. Here, the effective block threshold is set in advance based on values that can be recognized as a passerby data group.
FIG. 3 is a diagram for explaining an example of block determination. FIG. 3 shows data group example 1, data group example 2, data group example 3, and data group example 4 as examples of data groups. Here, as an example, a case where the effective block threshold is set to "5" is shown.

Data group example 1 will be described. The calculation unit 13 extracts one record containing consecutive effective values, and treats the extracted record as a block. The calculation unit 13 counts the number of valid values included in the block, and compares the count result with the valid block threshold. Here, the number of valid values included in the block is 4, which is less than the valid block threshold, so the extracted record is determined to be an invalid block.
Data group example 2 will be described. The calculation unit 13 extracts one record containing consecutive effective values, and treats the extracted record as a block. The calculation unit 13 counts the number of valid values included in the block, and compares the count result with the valid block threshold. Here, the number of valid values included in the block is 24, which is equal to or greater than the valid block threshold, so the extracted record is determined to be a valid block.
Data group example 3 will be described. The calculation unit 13 extracts two records containing consecutive effective values, and handles each of the two extracted records as a block. Here, from the top of FIG. 2, it is set as a first block and a second block. The calculation unit 13 counts the number of valid values included in the first block, and compares the counting result with the valid block threshold. Here, the number of valid values included in the first block is 11, which is equal to or greater than the valid block threshold, so the first block is determined to be a valid block. The calculation unit 13 counts the number of valid values included in the second block, and compares the counting result with the valid block threshold. Here, since the number of valid values included in the second block is 10, which is equal to or greater than the valid block threshold, the second block is determined to be a valid block.
The calculation unit 13 counts the invalid values between the first block and the second block, and determines whether or not the result of counting the invalid values is equal to or greater than the invalid value threshold. The invalid value threshold is preset based on the number of invalid values that can be recognized as not being in the passerby data set. When the invalid value is continuously obtained for the invalid value threshold value or more, the calculation unit 13 determines that the error is not caused by the passerby. That is, when the result of counting invalid values is equal to or greater than the invalid value threshold, the calculation unit 13 treats the first block and the second block as separate valid blocks.
When the result of counting the invalid value is less than the invalid value threshold, the calculation unit 13 determines that there is a possibility that a passerby is passing through. When the result of counting the invalid values is less than the invalid value threshold, the calculating unit 13 calculates the first block, the second block, and one or more invalid values between the first block and the second block. are treated as one valid block. The case where the invalid value threshold is set to 5 will be described below. In the case of data group example 3, the number of invalid values between the first block and the second block is three, which is less than the invalid value threshold. are treated as one valid block.

Data group example 4 will be described. The calculation unit 13 extracts two records containing consecutive effective values, and handles each of the two extracted records as a block. Here, from the top of FIG. 2, they are referred to as a first block and a second block. The calculation unit 13 counts the number of valid values included in the first block, and compares the counting result with the valid block threshold. Here, the number of valid values included in the first block is 11, which is equal to or greater than the valid block threshold, so the first block is determined to be a valid block. The calculation unit 13 counts the number of valid values included in the second block, and compares the counting result with the valid block threshold. Here, the number of valid values included in the second block is 8, which is equal to or greater than the valid block threshold, so the second block is determined to be a valid block.
The calculation unit 13 counts the invalid values between the first block and the second block, and determines whether or not the result of counting the invalid values is equal to or greater than the invalid value threshold. When the result of counting the invalid values is equal to or higher than the invalid value threshold, the calculation unit 13 treats the first block and the second block as separate valid blocks. When the result of counting the invalid values is less than the invalid value threshold, the calculating unit 13 calculates the first block, the second block, and one or more invalid values between the first block and the second block. are treated as one valid block. In the case of data group sequence 4, the number of invalid values between the first block and the second block is five, which is equal to or greater than the invalid value threshold. are treated as separate valid blocks.

(passer grouping algorithm)
Next, the details of the passerby grouping algorithm described above will be described.
The passer-by grouping algorithm causes the calculation unit 13 to execute a block extraction algorithm to derive time-series changes in valid value records included in the extracted valid blocks. The passer-by grouping algorithm causes the estimation unit 14 to estimate the number of passers-by and their moving directions based on the time-series changes in the valid value records derived by the calculation unit 13 . The calculating unit 13 and the estimating unit 14 function as follows by executing a passerby grouping algorithm.
The calculator 13 derives the length of the effective block. The length of a valid block may be represented by time, or may be represented by the sum of valid values and invalid values included in the valid block. As an example, a case where the length of a valid block is represented by time will be described below. The calculation unit 13 determines whether or not the result of deriving the effective block length is greater than or equal to a preset block length threshold. When determining that the effective block length derivation result is less than the block length threshold value, the calculation unit 13 determines that the effective block was obtained by one person passing through. When the calculation unit 13 determines that the result of deriving the length of the effective block is equal to or greater than the block length threshold value, the effective block is obtained by two or more (multiple persons) passing through the effective block. I judge.

In the following, the case where the calculation unit 13 determines that the block is an effective block obtained by passing by one person and the case that the block is determined to be an effective block obtained by passing by a plurality of people will be described separately.
A case will be described where the calculation unit 13 determines that the block is a valid block obtained by passing by one person. In this case, the calculation unit 13 removes outliers from the record group, which is a plurality of measured values included in the effective block. Here, an outlier is a value that greatly deviates from other values. An example of processing for removing outliers from a record group will be described. When a plurality of records included in a record group are arranged in the order of measurement, record R1, record R2, . The calculation unit 13 derives a difference value (R(x+1)-Rx (x is an integer of 1<x)) between adjacent records among record R1, record R2, . . . , and record Rn. . The calculation unit 13 derives statistical values such as the average value m and the standard deviation σ from the data group including the derived multiple difference values (R(x+1)−Rx). The estimating unit 14 calculates m−Xσ<(R(x+1)−Rx)<m+Xσ( (X is an arbitrary value specified in advance). When the estimating unit 14 can extract the difference value (R(x+1)-Rx) outside the range of m-Xσ<(R(x+1)-Rx)<m+Xσ, the record (R(x+1 )) is deleted from the record group.

The calculation unit 13 approximates a record by deriving an approximation formula using an approximation method such as the least-squares method based on the remaining records from which outliers are removed from the plurality of records included in the record group. . The estimation unit 14 derives the moving direction of the passerby based on the slope of the approximate expression derived by the calculation unit 13 .
The estimating unit 14 determines that the passerby is moving away from the terminal device 1 when the slope of the derived approximation formula is equal to or greater than a first effective slope threshold specified in advance. The estimating unit 14 determines that the passerby is moving toward the terminal device 1 when the gradient of the derived approximation formula is less than the second effective gradient threshold specified in advance. The estimating unit 14 determines that an object other than a passer-by has been detected when the gradient of the derived approximate expression is greater than the second effective gradient threshold and less than the first effective gradient threshold. The first effective tilt threshold and the second effective tilt are the first tilt obtained when the passerby moves away from the terminal device 1 and the direction in which the passerby approaches the terminal device 1. It is set in advance based on the second tilt obtained when moving to .
For example, when the predesignated first effective slope threshold is 0.2 and the slope of the derived approximate expression is 0.3, the estimation unit 14 determines the direction in which the passer moves away from the terminal device 1. determine that it is moving to When the second effective slope threshold specified in advance is −0.2, and the slope of the derived approximate expression is −0.3, the estimation unit 14 determines the direction in which the passerby approaches the terminal device 1. determine that it is moving to
If the slope of the derived approximation formula is larger than the second effective slope threshold of -0.2 and less than the first effective slope threshold of 0.2, the estimating unit 14 selects a record corresponding to this approximation formula. If it is a group, it is determined that a non-passer has been detected. If it is determined that an object other than a passerby is detected, the estimation unit 14 processes it as no passerby.

A case where the calculation unit 13 determines that the block is a valid block obtained by a plurality of people passing through will be described. In this case, the calculation unit 13 divides the record group, which is the plurality of measured values included in the effective block, into the number of divided records, which is the number of records specified in advance. The calculation unit 13 acquires a plurality of divided records by overlapping the number of duplicate records, which is the number of records specified in advance, and dividing the record group by the number of divided records.
FIG. 4 is a diagram for explaining the process of acquiring divided records from valid blocks. FIG. 4 shows an example in which a valid block contains 20 measurements, the number of split records is 8, and the number of duplicate records is 2. In FIG. In this example, the calculation unit 13 divides the effective block by overlapping two records, which is the number of duplicate records, for every eight records, which is the number of divided records, to divide the effective block into divided record #1. , divided record #2 and divided record #3.

The calculation unit 13 removes outliers from a record group that is a plurality of measured values included in each of the plurality of divided records. An example of processing for removing outliers from a record group will be described. When a plurality of records included in a record group are arranged in the order of measurement, record R1, record R2, . The estimating unit 14 derives a difference value (R(x+1)-Rx (x is an integer of 1<x)) between adjacent records among record R1, record R2, . . . , and record Rn. . The calculation unit 13 derives a statistical value such as an average value m and a standard deviation σ from a data group including a plurality of derived difference values (R(x+1)−Rx).
The calculation unit 13 calculates m−Xσ<(R(x+1)−Rx)<m+Xσ based on the derived multiple difference values (R(x+1)−Rx), the derived average value m, and the standard deviation σ. A difference value (R(x+1)-Rx) outside the range of (X is an arbitrary value specified in advance) is extracted. When the estimating unit 14 can extract the difference value (R(x+1)-Rx) outside the range of m-Xσ<(R(x+1)-Rx)<m+Xσ, the record (R(x+1 )) is deleted from the record group.

The calculation unit 13 derives an approximation formula using an approximation method such as the least squares method based on the remaining records from which the outliers are removed from the plurality of records included in the record group. The estimation unit 14 derives the moving direction of the passerby based on the slope of the approximate expression derived by the calculation unit 13 . The estimating unit 14 determines that the passerby is moving away from the terminal device 1 when the slope of the derived approximation formula is equal to or greater than a first effective slope threshold specified in advance. The estimating unit 14 determines that the passerby is moving toward the terminal device 1 when the gradient of the derived approximation formula is less than the second effective gradient threshold specified in advance. If the slope of the derived approximation formula is larger than the second effective slope threshold and less than the first effective slope threshold, the estimating unit 14 determines that the record group that corresponds to this approximation formula is not a passer. is detected. The first effective tilt threshold and the second effective tilt are the first tilt obtained when the passerby moves away from the terminal device 1 and the direction in which the passerby approaches the terminal device 1. It is set in advance based on the second tilt obtained when moving to .
When the record group is divided into the number of divided records, the number of duplicate records is duplicated, so when calculating the approximate expression by the least squares method, it is possible to easily grasp the change in the distance value when multiple people pass by.
For example, when the predesignated first effective slope threshold is 0.2 and the slope of the derived approximate expression is 0.3, the estimation unit 14 determines the direction in which the passer moves away from the terminal device 1. determine that it is moving to When the second effective slope threshold specified in advance is −0.2, and the slope of the derived approximate expression is −0.3, the estimation unit 14 determines the direction in which the passerby approaches the terminal device 1. determine that it is moving to
If the slope of the derived approximation formula is larger than the second effective slope threshold of −0.2 and less than the first effective slope threshold of 0.2, the estimation unit 14 detects a non-passer. I judge. If it is determined that an object other than a passerby is detected, the estimation unit 14 processes it as no passerby.

Furthermore, the estimation unit 14 counts the passers-by based on the gradients derived from each of the plurality of divided records. The estimating unit 14 arranges the divided records in the order of measurement, and evaluates them according to the following evaluation rules based on the sign of the slope derived from each of the two continuous divided records.
(1) If the sign of the gradient derived based on each of the two continuous divided records has the same sign, the estimating unit 14 determines that the two divided records are obtained by the same person passing through them. It is determined that the block is a divided block. In this case, the estimation unit 14 counts as if one person passed.
(2) The estimating unit 14 derives the slope based on each of the two consecutive divided records, and among the slopes of each of the two consecutive divided records, the sign of the divided record indicates the sign of the divided record. If the sign of the immediately preceding divided record is different from positive or negative, it is determined that the divided record was obtained by the appearance of a passer different from that of the immediately preceding divided record. In this case, the estimation unit 14 deletes the divided record.
(3) Based on the rule shown in (2), the estimating unit 14 determines that the sign of the slope derived based on the next split record following the deleted split record is the slope derived based on the deleted split record. If the sign is the same as the sign of , or if the sign of the slope derived based on the split record immediately before the deleted split record is the same as the sign of the slope, it was obtained by the appearance of another passer. Determine that there is. In this case, the estimation unit 14 counts the passer as having passed. After completing the evaluation of all the divided records, the estimation unit 14 outputs information indicating the count value of the passerby and information indicating the direction of movement of the passerby to the processing unit 11 based on the evaluation result.

(Operation of terminal device)
FIG. 5 is a diagram showing an example of the operation of the terminal device according to this embodiment. FIG. 5 shows that the calculation unit 13 of the terminal device 1 extracts one or more effective blocks from the data group by executing the block extraction algorithm, and the calculation unit 13 executes the passer-by grouping algorithm. , shows the operation after it is determined that the valid block is obtained by passing by a plurality of people. Specifically, FIG. 5 shows a method for the estimating unit 14 of the terminal device 1 to obtain divided records from a valid block and evaluate the obtained divided records.
(Step S100)
In the terminal device 1, the calculation unit 13 acquires the earliest divided record in time series among all the divided records included in the effective block, and starts the evaluation from the acquired divided record.
(Step S101)
In the terminal device 1, the calculation unit 13 derives the inclination based on the division record obtained first. The estimating unit 14 evaluates by obtaining the positive or negative sign of the slope derived by the calculating unit 13 .
(Step S102)
In the terminal device 1, the estimation unit 14 validates the first obtained divided record.
(Step S103)
In the terminal device 1, the estimation unit 14 derives the moving direction of the passer based on the inclination derived by the calculation unit 13 in step S101. In step S<b>101 , the estimation unit 14 counts up the number of passers based on whether the sign of the slope derived by the calculation unit 13 is positive or negative.
(Step S104)
In the terminal device 1, the calculation unit 13 determines whether or not the next divided record exists.
(Step S105)
In the terminal device 1, the calculation unit 13 acquires the next divided record when determining that the next divided record exists in step S104. Here, description will be made by replacing the following divided record with the divided record. The calculation unit 13 derives the inclination based on the obtained division record. The estimating unit 14 evaluates by obtaining the positive or negative sign of the slope derived by the calculating unit 13 .

(Step S106)
In the terminal device 1, the estimation unit 14 confirms whether or not the division record immediately preceding the division record acquired by the calculation unit 13 is processed as valid.
(Step S107)
In the terminal device 1, the estimating unit 14, when the divided record immediately before the divided record is processed as being valid, obtains the slope sign of the immediately preceding split record processed as valid and the slope sign of the split record. are the same.
(Step S108)
In the terminal device 1, the estimating unit 14 processes the divided record as a valid record when determining that the sign of the gradient of the immediately preceding divided record is the same as the sign of the gradient of the divided record.
(Step S109)
In the terminal device 1, the estimating unit 14 determines that the divided record is a record obtained by measuring the same passers as the immediately preceding divided record processed as valid. The estimation unit 14 does not perform count-up processing. The process proceeds to step S104.

(Step S110)
In the terminal device 1, when the estimation unit 14 determines in step S107 that the sign of the gradient of the immediately preceding divided record is different from the sign of the gradient of the divided record, the divided record is deleted as an invalid record. process. By treating the split record as an invalid record, it becomes a state in which it cannot be referred to when evaluating other split records. The process proceeds to step S104.
(Step S111)
In the terminal device 1, if the estimating unit 14 determines in step S106 that the divided record immediately preceding the divided record is not processed as being valid, the gradient sign of the immediately preceding divided record and the gradient sign of the divided record are the same. If it is determined that the sign of the gradient of the immediately preceding divided record is the same as the sign of the gradient of the divided record, the process proceeds to step S102.
(Step S112)
In the terminal device 1, when the estimating unit 14 determines that the sign of the slope of the immediately preceding divided record and the sign of the slope of the divided record are not the same, the sign of the slope of the last divided record determined to be an effective block is and the sign of the slope of the divided record are the same. If it is determined that the sign of the slope of the divided record finally determined to be a valid block is the same as the sign of the slope of the divided record, the process proceeds to step S102. If it is determined that the sign of the slope of the divided record finally determined to be a valid block is not the same as the sign of the slope of the divided record, the process proceeds to step S110.
(Step S113)
In the terminal device 1, if the next divided record does not exist in step S104, the calculation unit 13 determines that the evaluation of all divided records has been completed, and terminates the evaluation of the divided records.

Although the case where the terminal device 1 includes one distance sensor unit 12 has been described in the above-described embodiment, the present invention is not limited to this example. For example, the terminal device 1 may include a plurality of distance sensor units.
In the above-described embodiment, the case where the moving direction of the passerby is determined based on the first effective tilt threshold and the second effective tilt threshold has been described, but the present invention is not limited to this example. For example, the moving direction of the passer may be determined based on one effective tilt threshold, or the moving direction of the passer may be determined based on three or more effective tilt thresholds.
In the embodiments described above, the number of duplicate records may be changed based on external factors such as noise, number of passers-by, and the like. By increasing the number of duplicate records, even if the measured value changes abruptly, the change can be followed. Reducing the number of duplicate records can improve resistance to noise.
According to the terminal device 1 according to the present embodiment, the terminal device 1 includes one or more distance sensor units, and a measurement including a plurality of measurement results obtained by each of the one or more distance sensor units. From the result group, based on the measurement time, one or more blocks containing a plurality of measurement results are extracted, and a plurality of measurement results included in each of the extracted one or more blocks are approximated by a calculation unit an estimating unit that derives one or both of the number of moving objects measured by the distance sensor unit and the direction of movement based on an approximation result of a plurality of measurement results included in each of the one or more blocks. . With this configuration, the terminal device 1 continuously measures the distance between the terminal device 1 and the passerby. The terminal device 1 can analyze the distance measurement results by a block extraction algorithm and a passerby grouping algorithm. Deriving one or both of the number of moving objects measured by each of the one or more distance sensor units and the direction of movement based on the approximation results of the plurality of measurement results included in each of the one or more blocks By doing so, it is possible to improve the measurement accuracy of one or both of the number of moving objects and the direction of movement.

(Modification of embodiment)
(Terminal device)
FIG. 6 is a block diagram showing a passing number measuring system according to a modification of the embodiment of the present invention. A transit number measuring system 100a according to a modification of the embodiment includes a terminal device 1a and a server 2 . FIG. 6 shows a terminal device 1a, a server 2, a user U who acquires measurement results, and a terminal device 1b used by the user U. FIG.
The terminal device 1a, the terminal device 1b, and the server 2 communicate via the network NW. The network NW includes, for example, the Internet, a WAN (Wide Area Network), a LAN (Local Area Network), a provider device, a radio base station, and the like.
The terminal device 1 a differs from the terminal device 1 described above in that it includes a communication unit 16 and includes a processing unit 11 a instead of the processing unit 11 .

(Terminal device 1a)
The terminal device 1a is realized as a smart phone, a mobile terminal, a personal computer, a tablet terminal device, a wristwatch type terminal device, or other information processing equipment. The terminal device 1a includes, for example, a moving object detection unit 10, a processing unit 11a, a distance sensor unit 12, a calculation unit 13, an estimation unit 14, a storage unit 15, and a communication unit 16.
The processing unit 11a has the following functions in addition to the functions of the processing unit 11 described above. The processing unit 11a maintains the hibernation state until a preset time. The processing unit 11a returns from the hibernation state at a preset time, includes at least part of the information contained in the passerby count information 15a stored in the storage unit 15, and sends the server 2 as a destination. create passer-by count notification information. The processing unit 11 a outputs the created passer-by count notification information to the communication unit 16 .
The processing unit 11a acquires the transfer information output by the communication unit, and reflects the changed contents of the setting information included in the acquired transfer information by processing them. For example, the processing unit 11 a reflects the changed content of the setting information in the setting information 15 c stored in the storage unit 15 .

The communication unit 16 is implemented by a communication module. The communication unit 16 communicates with an external communication device via the network NW. The communication unit 16 may communicate using a communication method such as a wired LAN (Local Area Network). Further, the communication unit 16 may communicate by a communication method such as wireless LAN, Bluetooth (registered trademark), or LTE (registered trademark). The communication unit 16 holds communication information necessary for communicating with the server 2 via the network NW. The communication unit 16 acquires the passer-by count notification information output by the processing unit 11 a and transmits the acquired passer-by count notification information to the server 2 . The communication unit 16 receives the transfer information transmitted by the server 2 and outputs the received transfer information to the processing unit 11a.

(Terminal device 1b)
The terminal device 1b is realized as a smart phone, a mobile terminal, a personal computer, a tablet terminal device, a wristwatch type terminal device, or other information processing equipment.
The terminal device 1b includes a terminal device ID and information requesting the passerby count information when the user performs an operation to request the passerby count information on the terminal device 1b, and the destination is the server 2. Create a Passenger Count Information Request. The terminal device 1 b transmits the created passerby count information request to the server 2 . The terminal device 1b receives the passerby count information response transmitted by the server 2, and acquires the passerby count information contained in the received passerby count information response. The terminal device 1b processes and outputs the acquired passerby count information. For example, the terminal device 1b may display the processing result of the passer-by count information on a display unit (not shown).

(server 2)
The server 2 is implemented by a device such as a personal computer, server, smart phone, tablet computer, or industrial computer. The server 2 includes a processing unit 21, a storage unit 25, a communication unit 27, and an input/output unit 29, for example.
The storage unit 25 is implemented by an HDD, flash memory, RAM, ROM, or the like. The storage unit 25 stores passer-related information 25a, terminal information 25b, and setting information 25c. Passer-related information 25a, terminal information 25b, and setting information 25c may be stored on the cloud.
The passer-related information 25a is information in a table format that associates the terminal device ID of the terminal device that transmitted the measurement result and the measurement date and time information, the measurement result, and the measurement date and time information. The measurement results include information indicating the number of passers-by and information indicating the direction of movement.
FIG. 7 is a diagram showing an example of passer-related information. An example of the passer-related information 25a includes the terminal device ID “M0001”, the number of passers “***” as the measurement result, the direction of movement “***”, and the measurement date and time information “*** /**/**/**:**” are associated. An example of the passer-by related information 25a includes the terminal device ID "M0002", the number of passers "+++" as the measurement result, the movement direction "+++", and the measurement date and time information "++++/++/++/ ++:++" are associated.

The terminal information 25b is information in a table format that associates terminal device IDs, IP addresses, and MAC addresses. FIG. 8 is a diagram showing an example of terminal information. An example of the terminal information 25b is associated with a terminal device ID "M0001", an IP address "***", and a MAC address "***". An example of the terminal information 25b is associated with a terminal device ID "M0002", an IP address "+++", and a MAC address "++++". The information stored in the terminal information 25b is registered when using the pass measurement system 100a.
The setting information 25c is table-format information that associates a terminal device ID, an aggregation time interval, a notification time interval, a distance threshold, an effective block threshold, an invalid value threshold, a block length threshold, and an effective inclination threshold. is.
FIG. 9 is a diagram showing an example of setting information. An example of the setting information 25c includes a terminal device ID “M0001”, a tally time interval “**:**”, a notification time interval “**:**”, a distance threshold “**”, and an effective block A threshold "**", an invalid value threshold "**", a block length threshold "**", and a valid slope threshold "**" are associated. An example of the setting information 25c includes a terminal device ID “M0002”, a tally time interval “++:++”, a notification time interval “++:++”, a distance threshold “++”, and an effective block threshold “++ , an invalid value threshold “++”, a block length threshold “++”, and a valid slope threshold “++”.
Here, in the setting information 25c, the total time may be stored instead of the total time interval or together with the total time interval, or the notification time may be stored instead of the notification time interval or together with the notification time interval. Further, the setting information 25c may store time interval information for the distance sensor 12 mounted on the terminal device 1a to measure the distance between the moving object and the terminal device 1a. Either one or both of the information indicating the holding period of the information held in the passer-by count information 15a and the number of pieces of information may be stored. The information stored in the setting information 25c is registered when using the passage number measuring system 100a. Returning to FIG. 6, the description is continued.

The processing unit 21 and the input/output unit 29 are implemented by, for example, a hardware processor such as a CPU executing a program (software) stored in the storage unit 25 . Also, some or all of these functional units may be realized by hardware (including circuitry) such as LSI, ASIC, FPGA, and GPU, or by cooperation between software and hardware. may be implemented. The program may be stored in advance in a storage device such as an HDD or flash memory, or may be stored in a removable storage medium such as a DVD or CD-ROM. may be installed.
The processing unit 21 controls and manages the overall operation of the server 2 . The processing unit 21 acquires the passerby count notification information output by the communication unit 27, and based on the acquired passerby count notification information, identifies the terminal device that has transmitted the passerby count notification information. The processing unit 21 refers to one or both of an IP address and a MAC address for communicating with each of one or more terminal devices from the terminal information 25b stored in the storage unit 25, and obtains one or more terminal equipment. The processing unit 21 associates the information indicating the identified terminal device with the acquired passer count notification information, and stores them in the passer-related information 25 a of the storage unit 25 .

The processing unit 21 acquires the passer-by count information request output by the communication unit 27, and extracts from the passer-related information 25a stored in the storage unit 25 based on the terminal device ID included in the acquired passer-by count notification information. , acquires the measurement result associated with the terminal device ID and the measurement date and time information. The processing unit 21 creates a passerby count information response including the obtained measurement result and the measurement date and time information and destined for the terminal device that transmitted the passerby count information request, and sends the created passerby count information response to: Output to the communication unit 27 .
When the setting information included in the setting information 25c stored in the storage unit 25 is changed, the processing unit 21 includes information indicating the changed content of the setting information, and addresses the terminal device corresponding to the setting information. Create forwarding information. The processing unit 21 outputs the created transfer information to the communication unit 27 . The processing unit 21 acquires one or both of an IP address and a MAC address for communicating with each of one or a plurality of terminal devices from the terminal information 25b stored in the storage unit 25, and acquires the acquired IP Communication is performed with each of one or a plurality of terminal devices based on either one or both of the address and the MAC address.
The input/output unit 29 changes and/or confirms the setting information of the terminal device 1a.

The communication unit 27 is implemented by a communication module. The communication unit 27 communicates with an external communication device via the network NW. The communication unit 27 may communicate using a communication method such as a wired LAN, for example. Further, the communication unit 27 may communicate using a communication method such as wireless LAN, Bluetooth (registered trademark), or LTE (registered trademark). The communication unit 27 can communicate with each of one or more terminal devices whose information is managed by the server 2 . The communication unit 27 receives the passerby count notification information transmitted by the terminal device 1 a and outputs the received passerby count notification information to the processing unit 21 . The communication unit 27 receives the passerby count information request transmitted by the terminal device 1 b and outputs the received passerby count information request to the processing unit 21 . The communication unit 27 acquires the passerby count information response output by the processing unit 21, and transmits the acquired passerby count information response to the terminal device 1b. The communication unit 27 acquires the transfer information output by the processing unit 21 and transmits the acquired transfer information to the terminal device 1a.

(Operation of passing number measurement system)
An example of the operation of the number-of-passes measuring system according to the modified example of the present embodiment will be described. FIG. 5 described above can be applied to the method for the terminal device 1a to obtain divided records from a valid block and evaluate the obtained divided records. Here, the processing unit 11a of the terminal device 1a associates the time information, the information indicating the count value of the passers-by, and the information indicating the moving direction of the passers-by, and stores the pass-by count information 15a in the storage unit 15. Processing after storing will be described.
FIG. 10 is a diagram showing an example of the operation of the number-of-passes measuring system according to the modification of the embodiment.
(Step S201)
In the terminal device 1a, the processing unit 11a returns from the hibernation state at a preset time, includes at least part of the information contained in the passer count information 15a stored in the storage unit 15, Create passer count notification information addressed to server 2 . Here, at least part of the information included in the passer-by count information 15a is information that is not notified to the server 2 among the information included in the passer-by count information 15a.
(Step S202)
In the terminal device 1 a , the processing unit 11 a outputs the created passer-by count notification information to the communication unit 16 . The communication unit 16 acquires the passer-by count notification information output by the processing unit 11 a and transmits the acquired passer-by count notification information to the server 2 .
(Step S203)
In the server 2 , the communication unit 27 receives the passerby count notification information transmitted by the terminal device 1 a and outputs the received passerby count notification information to the processing unit 21 . The processing unit 21 acquires the passerby count notification information output by the communication unit 27, and based on the acquired passerby count notification information, identifies the terminal device that has transmitted the passerby count notification information. The processing unit 21 associates the information indicating the identified terminal device with the acquired passer count notification information, and stores them in the passer-related information 25 a of the storage unit 25 .

(Step S204)
When the user operates the terminal device 1b to request the passer count information, the terminal device 1b receives the terminal device ID of the terminal device 1a, which is the target of the passer count information request, and the passer count information. A passerby count information request destined for server 2 containing information requesting information.
(Step S205)
The terminal device 1 b transmits the created passerby count information request to the server 2 .
(Step S206)
In the server 2 , the communication unit 27 receives the passerby count information request transmitted by the terminal device 1 b and outputs the received passerby count information request to the processing unit 21 . The processing unit 21 acquires the passerby count information request output by the communication unit 27, and acquires the terminal device ID included in the passerby count information request. The processing unit 21 acquires the measurement result stored in association with the acquired terminal device ID and the measurement date and time information, and includes the terminal device ID, the acquired measurement result, and the measurement date and time information, and the terminal device 1b Create a Passenger Count Information Reply destined for .
(Step S207)
In the server 2 , the processing unit 21 outputs the created passerby count information response to the communication unit 27 . The communication unit 27 acquires the passerby count information response output by the processing unit 21, and transmits the acquired passerby count information response to the terminal device 1b.
(Step S208)
The terminal device 1b receives the passerby count information response transmitted by the server 2, acquires the received passerby count information response, and acquires the terminal device ID included in the acquired passerby count information response, the measurement result, and the measurement result. Acquire date and time information. The terminal device 1b processes and outputs the acquired terminal device ID, measurement result, and measurement date and time information.

In the modified example of the above-described embodiment, the passage number measuring system 100a includes one terminal device 1a, but the present invention is not limited to this example. For example, there may be a plurality of terminal devices 1a. With this configuration, the server 2 can store the passerby count information in the passerby related information 25a based on the passerby count notification information transmitted by each of the plurality of terminal devices 1a. By transmitting a passerby count information request, the terminal device 1b can acquire the passerby count information notified by any one of the plurality of terminal devices 1a.
In the modification of the above-described embodiment, the passer-by count information request includes the terminal device ID, and the server 2 creates the passer-by count information response including the passer-by count information corresponding to the terminal device ID. Although described, it is not limited to this example. For example, the passer-by count information request may include the measurement date and time information in addition to the terminal device ID. In this case, the server 2 creates a passerby count information response including the passerby count information corresponding to the combination of the terminal device ID and the measurement date/time information. Also, instead of the measurement date/time information, a range of measurement dates/times may be included. In this case, the server 2 creates a passer-by count information response including the passer-by count information corresponding to the combination of the terminal device ID and the measurement date and time range.
In the modified example of the embodiment described above, the terminal device 1a may delete the information notified to the server 2 from the information included in the passer-by count information 15a. By configuring in this way, the storage capacity of the terminal device 1a can be secured.
According to the passing number measuring system 100a according to the modification of the present embodiment, in addition to the effects of the passing number measuring system 100 according to the above-described embodiment, the communication function of the terminal device 1a is used to transmit the measurement results to the server. 2, etc., can be sent to an external DB. Therefore, the user U of the terminal device 1b can confirm the measurement result by acquiring the measurement result from the server 2 via the network NW.

(Application example)
An application example of the number-of-passes measuring system 100a according to a modification of the embodiment will be described.
FIG. 11 is a diagram for explaining an application example of the number-of-passes measuring system according to a modification of the embodiment.
The terminal device 1a is installed in an outdoor environment where the road width is limited, such as a mountain trail. In the terminal device 1a, the distance sensor unit 12 estimates the number of target objects 4 such as objects passing through the measurement range MR, which is a range in which the distance can be measured, and the moving direction of the target object 4. FIG. An example of the target object 4 is a passerby. The terminal device 1 a reflects the estimated result of the number of the objects 4 and the moving direction of the objects 4 in the passer-by count information 15 a stored in the storage unit 15 .
As shown in FIG. 11, the terminal device 1a is installed by being tied to an existing pile on the side of the road R or a post of a guide plate. An example of the terminal device 1a is of portable size. The terminal device 1a is installed at an angle with respect to the horizontal plane including the road R. For example, the terminal device 1a may be installed such that the measurement range MR of the distance sensor unit 12 of the terminal device 1a includes both ends of the road R.
The terminal device 1a measures the distance to the target object 4 in chronological order, and executes a passerby grouping algorithm and a block extraction algorithm. Estimate direction.

A specific description will be given. The processing unit 11 a of the terminal device 1 a acquires the distance value output by the distance sensor unit 12 and outputs the acquired distance value to the calculation unit 13 .
12 is a diagram illustrating an example 1 of distance values acquired by the terminal device according to the modification of the embodiment; FIG. FIG. 12 shows an example of the relationship between elapsed time [s] and distance value [m]. Here, the elapsed time is the elapsed time from when the measurement was started. FIG. 12 shows, as an example, measurement results of distance values when the target object 4 moves away from the terminal device 1a. According to FIG. 12, in the terminal device 1a, the distance sensor unit 12 acquires the distance value about three seconds after the distance sensor unit 12 starts measuring the distance after the moving object detection unit 10 detects the moving object. I know you are. It can be seen that distance values between 3 seconds and 3.2 seconds are invalid values.
Further, according to FIG. 12, it can be seen that the effective block length is about 3 seconds. If the block length threshold is set to 5 seconds, the estimating unit 14 determines that the block is an effective block obtained by passing by one person.

13 is a diagram illustrating an example 1 of processing of the terminal device according to the modification of the embodiment; FIG. The computing unit 13 of the terminal device 1a uses a block extraction algorithm to extract a data group of measurement results including a distance value determined to be a distance value between a passerby, and from the extracted data group of measurement results, Distance values including errors such as the influence of noise from the distance sensor unit 12 are removed. FIG. 13 shows the results of removing distance values including errors such as the effects of noise from the distance sensor unit 12 from the measurement results. In FIG. 13, the vertical axis is the difference value between adjacent records, and the horizontal axis is the elapsed time from the start of measurement. A solid line including a black broken line portion indicates a difference value of the measured values shown in FIG. 12 . Let m be the average value of the distance values, σ be the standard deviation, and X be the coefficient indicating the 90% confidence interval. Three solid lines parallel to the horizontal axis are m + X σ, m, m-Xσ is shown. Difference values obtained by removing difference values less than m−Xσ and difference values greater than m+Xσ are indicated by solid lines.
FIG. 14 is a diagram illustrating example 2 of processing of the terminal device according to the modification of the embodiment; In FIG. 14, the vertical axis is the distance value [m] and the horizontal axis is the elapsed time [s]. FIG. 14 is obtained by removing measured values corresponding to difference values less than m−Xσ and measurement values corresponding to difference values greater than m+Xσ in FIG. 12 . In other words, FIG. 14 shows the result of blocking the time-series distance values obtained by removing the distance values including the influence of noise.
The estimating unit 14 derives the inclination of the time-series distance values based on the result of the time-series blocking of the distance values. For example, the estimation unit 14 derives the slope of the time-series distance values by an approximation method such as the least squares method. In the case of FIG. 14, the slope value is 1.1014. If the first effective tilt threshold is set to 0.2, the estimation unit 14 estimates that one passer has moved away from the terminal device 1a.

15 is a diagram illustrating an example 2 of distance values acquired by the terminal device according to the modification of the embodiment; FIG. FIG. 15 shows an example of the relationship between elapsed time [s] and distance value [m]. Here, the elapsed time is the elapsed time from when the measurement was started. As an example, FIG. 15 shows an example of measurement results acquired when a plurality of objects pass through the measurement range MR of the distance sensor unit 12 of the terminal device 1a in the same direction. Here, as an example, an example of the measurement result obtained when the target object 4a and the target object 4b pass in the direction away from the terminal device 1a is shown.
According to FIG. 15, in the terminal device 1a, after the moving object detection unit 10 detects the moving object, the distance sensor unit 12 starts measuring the distance, and about 4.5 seconds later, the distance sensor unit 12 detects the distance value. is obtained. It can be seen that distance values between 4.5 seconds and 4.8 seconds are invalid values. Further, according to FIG. 15, it can be seen that the effective block length is about 5 seconds. If the block length threshold is set to 5 seconds, the estimating unit 14 determines that the block is an effective block obtained by multiple people passing through.
16 is a diagram illustrating example 3 of processing of the terminal device according to the modification of the embodiment; FIG. The estimating unit 14 divides a group of records included in a valid block into groups of divided records specified in advance. The estimating unit 14 acquires a plurality of divided records by overlapping a predetermined number of duplicate records and dividing the record group by the number of divided records.
As illustrated in FIG. 16, the estimation unit 14 acquires the sixth divided record from the first divided record. The estimating unit 14 removes the distance value including the influence of noise from the record group, which is a plurality of measurement values included in each of the plurality of divided records. FIG. 16 shows the result of removing the distance value including the influence of noise from the record group included in each of the plurality of divided records. In FIG. 16, the vertical axis is the difference value between adjacent records, and the horizontal axis is the elapsed time from the start of measurement. A solid line including a black broken line portion indicates a difference value of the measured values shown in FIG. 15 . In each of the first to sixth split records, let m be the average value of the distance values, σ be the standard deviation, and X be the coefficient indicating the 90% confidence interval. The solid lines indicate m+Xσ, m, and m−Xσ from the top. Difference values obtained by removing difference values less than m−Xσ and difference values greater than m+Xσ are indicated by solid lines.

17 is a diagram illustrating an example 4 of processing of the terminal device according to the modification of the embodiment; FIG. In FIG. 17, the vertical axis is the distance value [m] and the horizontal axis is the elapsed time [s]. FIG. 17 is obtained by removing the measured values corresponding to the difference values less than m−Xσ and the measured values corresponding to the difference values m+Xσ in FIG. In other words, FIG. 17 shows the result of blocking the time-series distance values obtained by removing the distance values including the influence of noise.
The estimating unit 14 derives the inclination of the time-series distance values based on the result of the time-series blocking of the distance values. For example, the estimation unit 14 derives the slope of the time-series distance values by an approximation method such as the least squares method. The estimation unit 14 derives the slope of the time-series distance values included in each of the first to sixth divided records. As a result, as shown in FIG. 17, the slope of the time-series distance values included in the first split record is 0.8793, and the slope of the time-series distance values included in the second split record is , −0.3409, and the slope of the time-series distance values included in the third divided record is 0.8011. Further, as shown in FIG. 17, the slope of the time-series distance value included in the fourth split record is 1.0656, and the slope of the time-series distance value included in the fifth split record is 1.264, and the slope of the time-series distance value included in the sixth divided record is 1.1825.
18 is a diagram illustrating example 5 of processing of the terminal device according to the modification of the embodiment; FIG. FIG. 18 shows the results of evaluating the slopes of the time-series distance values contained in each of the first to sixth divided records based on the aforementioned evaluation rule.
The estimating unit 14 determines that the sign of the gradient of the second divided record is different from the sign of the gradient of the first divided record, so that the second divided record has a different passer than the first divided record. It is judged that it is obtained by doing. Therefore, the estimation unit 14 deletes the second divided record.
The estimating unit 14 determines that the first divided record, the third divided record, the fourth divided record, the fifth divided record, and the sixth divided record, other than the deleted second divided record, have the same positive or negative signs for the slopes. Therefore, it is estimated that the two passers-by moved away from the terminal device 1a.

19 is a diagram illustrating an example 3 of distance values acquired by the terminal device according to the modification of the embodiment; FIG. FIG. 19 shows an example of the relationship between elapsed time [s] and distance value [m]. Here, the elapsed time is the elapsed time from when the measurement was started. FIG. 19 shows an example of measurement results obtained when a plurality of objects pass through the measurement range MR of the distance sensor section 12 of the terminal device 1a in different directions. Here, as an example, an example of the measurement result obtained when the target object 4a and the target object 4b move so as to intersect (pass each other) within the measurement range MR of the distance sensor unit 12 of the terminal device 1a is shown. .
According to FIG. 19, in the terminal device 1a, after the moving object detection unit 10 detects the moving object, the distance sensor unit 12 starts measuring the distance, and about 5.5 seconds later, the distance sensor unit 12 detects the distance value. is obtained. It can be seen that distance values between 5.5 seconds and 5.8 seconds are invalid values. Further, according to FIG. 19, it can be seen that the effective block length is about 5 seconds. If the block length threshold is set to 5 seconds, the estimating unit 14 determines that the block is an effective block obtained by multiple people passing through.
The estimating unit 14 divides a group of records included in a valid block into groups of divided records specified in advance. The estimating unit 14 acquires a plurality of divided records by overlapping the number of duplicate records specified in advance and dividing the record group by the number of divided records. The estimation unit 14 acquires the seventh divided record from the first divided record. The estimating unit 14 removes distance values including the influence of noise from a record group that is a plurality of measurement values included in each of the plurality of divided records. Let m be the average value of the distance values, σ be the standard deviation, and X be the coefficient indicating the 90% confidence interval. The solid lines indicate m+Xσ, m, and m−Xσ from the top. Difference values less than m−Xσ and greater than m+Xσ are removed.

FIG. 20 is a diagram illustrating example 6 of processing of the terminal device according to the modification of the embodiment. In FIG. 20, the vertical axis is the distance value [m] and the horizontal axis is the elapsed time [s]. FIG. 20 is obtained by removing the measured values corresponding to the difference values less than m−Xσ and the measured values corresponding to the difference values m+Xσ in FIG. In other words, FIG. 20 shows the result of blocking the time-series distance values obtained by removing the distance values including the influence of noise.
The estimating unit 14 derives the inclination of the time-series distance values based on the result of the time-series blocking of the distance values. For example, the estimation unit 14 derives the slope of the time-series distance values by an approximation method such as the least squares method. The estimation unit 14 derives the slope of the time-series distance values included in each of the first to seventh divided records. As a result, as shown in FIG. 20, the slope of the time-series distance values included in the first split record is 0.6597, and the slope of the time-series distance values included in the second split record is , 1.0277, and the slope of the time-series distance values included in the third divided record is 0.9944. Further, as shown in FIG. 20, the slope of the time-series distance values included in the fourth split record is −1.1277, and the slope of the time-series distance values included in the fifth split record is , −0.9861, the gradient of the time-series distance values contained in the sixth divided record is −0.7876, and the gradient of the time-series distance values contained in the seventh divided record is − 0.7876.

21 is a diagram illustrating example 7 of processing of the terminal device according to the modification of the embodiment; FIG. FIG. 21 shows the results of evaluating the slope of the time-series distance values contained in each of the first to seventh divided records based on the above-described evaluation rule.
The estimating unit 14 determines that the sign of the gradient of the fourth divided record is different from the sign of the gradient of the third divided record, so that the fourth divided record has a different passer than the third divided record. It is judged that it is obtained by doing. Therefore, the estimation unit 14 deletes the fourth division record.
Consider records other than the fourth divided record deleted by the estimation unit 14 . The positive and negative signs of the slopes of the first to third divided records are the same, and the positive and negative signs of the fifth to seventh divided records are the same. Further, the positive/negative sign of the first to third divided records differs from that of the fifth to seventh divided records. In this case, the estimation unit 14 estimates that one passerby moves away from the terminal device 1a and one passerby moves closer to the terminal device 1a, so that a total of two passers have passed.
In the modified example of the embodiment, as an example, the case where the terminal device 1a detects one or two passers has been described, but the present invention is not limited to this example. It can also be applied when there are three or more passers.
Here, as an example of application, the case where the number-of-passes measurement system 100a is applied to an outdoor environment with a limited road width such as a mountain trail has been described, but this is not the only case. For example, the number-of-passes measurement system 100 can also be applied to an outdoor environment with a limited road width, such as a mountain trail.

Although the embodiment of the present invention has been described in detail above with reference to the drawings, the specific configuration is not limited to this embodiment, and design changes and the like are included within the scope of the present invention.
For example, a computer program for realizing the functions of the devices described above may be recorded in a computer-readable recording medium, and the program recorded in this recording medium may be read and executed by a computer system. Note that the “computer system” referred to here may include hardware such as an OS and peripheral devices.
In addition, "computer-readable recording medium" includes writable nonvolatile memories such as flexible discs, magneto-optical discs, ROMs and flash memories, portable media such as DVDs (Digital Versatile Discs), and computer system built-in media. A storage device such as a hard disk that
Furthermore, "computer-readable recording medium" means a volatile memory (e.g., DRAM (Dynamic Random Access Memory)), which holds the program for a certain period of time, is also included.
Further, the above program may be transmitted from a computer system storing this program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in a transmission medium. Here, the "transmission medium" for transmitting the program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line.
Further, the program may be for realizing part of the functions described above.
Further, it may be a so-called difference file (difference program) that can realize the above-described functions in combination with a program already recorded in the computer system.

DESCRIPTION OF SYMBOLS 1, 1a, 1b... Terminal device, 2... Server, 10... Moving body detection part, 11, 11a... Processing part, 12... Distance sensor part, 13... Calculation part, 14... Estimation part, 15... Storage part, 15a... Passage Person count information 15c Setting information 16 Communication unit 21 Processing unit 25 Storage unit 25a Passer-related information 25b Terminal information 25c Setting information 27 Communication unit 29 Input/output Part, 100, 100a... Passing number measurement system

Claims (7)

a distance sensor that measures distance;
One or more blocks including a plurality of measurement results are extracted based on the measurement time from a measurement result group including a plurality of measurement results obtained by the distance sensor unit, and the extracted one or more blocks A computing unit that approximates a plurality of measurement results included in each of
Deriving one or both of the number of moving objects measured by the distance sensor unit and the moving direction based on the approximation result of the plurality of measurement results included in each of the one or more blocks by the calculation unit. comprising an estimator and
The terminal device , wherein the calculation unit determines whether or not the number of moving objects is plural based on the length of each of the one or more blocks . The computing unit removes measurement results containing errors from the plurality of measurement results, and a block containing a plurality of measurement results from a group of measurement results remaining after removing the measurement results containing errors, based on the measurement time. The terminal device according to claim 1, extracting one or a plurality of The computing unit derives an approximation formula based on the time series of the plurality of measurement results included in each of the one or more blocks,
The terminal device according to claim 1 or 2 , wherein the estimation unit derives the movement direction of the moving object based on the slope of the approximate expression derived by the calculation unit. The computing unit derives a difference between the two consecutive measurement results based on the time series of the plurality of measurement results included in each of the one or more blocks, and calculates statistics from the plurality of derived differences. derive a value, and delete any of the plurality of measurement results based on the difference and the statistical value;
The approximation formula is derived based on the time series of the plurality of measurement results included in each of the one or more blocks obtained by deleting any of the plurality of measurement results. terminal equipment. a distance sensor that measures distance;
One or more blocks including a plurality of measurement results are extracted based on the measurement time from a measurement result group including a plurality of measurement results obtained by the distance sensor unit, and the extracted one or more blocks A computing unit that approximates a plurality of measurement results included in each of
Deriving one or both of the number of moving objects measured by the distance sensor unit and the moving direction based on the approximation result of the plurality of measurement results included in each of the one or more blocks by the calculation unit. comprising an estimator and
The system , wherein the calculation unit determines whether or not the number of moving objects is plural based on the length of each of the one or more blocks . A measurement method performed by a terminal device including a distance sensor unit that measures distance,
One or more blocks including a plurality of measurement results are extracted based on the measurement time from a measurement result group including a plurality of measurement results obtained by the distance sensor unit, and the extracted one or more blocks approximating a plurality of measurements contained in each of
Deriving one or both of the number of moving objects measured by the distance sensor unit and the direction of movement based on the approximation result of a plurality of measurement results included in each of the one or more blocks in the approximating step and
determining whether the number of moving objects is plural based on the length of each of the one or more blocks;
A passing number measurement method having a to the computer,
One or a plurality of blocks including a plurality of measurement results are extracted based on the measurement time from a measurement result group including a plurality of measurement results obtained by measurement by the distance sensor unit, and the extracted one or more blocks approximating a plurality of measurements within each;
Deriving one or both of the number of moving objects measured by the distance sensor unit and the direction of movement based on the approximation result of a plurality of measurement results included in each of the one or more blocks in the approximating step and
determining whether the number of moving objects is plural based on the length of each of the one or more blocks;
computer program that causes the

Images