TWI672642B - People count statistic system and method thereof - Google Patents

Abstract

The embodiment of the invention provides a person-time statistical system and a method thereof. In the embodiment of the present invention, the total trajectory of a person in a certain area is divided into different moving trajectory sections according to the speed change of a single individual, and the movement of all the personnel in a certain place is performed through statistics. The trajectory section information, in turn, shows the location of the road traffic jam or the normal location of the walking passengers in the sightseeing area. Therefore, it can be further used as a basis for improvement of transportation facilities and reference for feedback, store design and capacity design.

Description

Personnel statistics system and method thereof

The present invention relates to a traffic statistics technique, and in particular to a person-time statistics system and method thereof.

The prior art statistics on road traffic, such as the section between two expressway interchanges, are detected by vehicle detectors, (eTag) radio frequency identification (RFID) readers, surveillance cameras, and the like. And to calculate the average speed of the entire road section, and to indicate the current level of traffic congestion of this section in different colors according to different speed intervals, so as to facilitate the use of passers-by to grasp the real-time road information. However, sometimes pedestrians and traffic management units need more complete information, such as the normal traffic jam time, traffic distance and average speed, traffic parameters between the inner and outer lanes, passenger trips, etc., as users and traffic related units. Corresponding reference information. In addition, the above prior art mainly adopts a fixed network communication mode, which can only achieve the statistical analysis of the fixed-point trains, and the extensive deployment of the terminal detection equipment will greatly increase the system construction cost. Therefore, the traffic statistics of government agencies are limited to high and fast Roads and urban main roads, and their transportation costs are relatively high. The statistics of the number of people on the road are also important, because the trend of people in sightseeing spots determines the opportunities and costs of the merchants' exhibitions, and the attractions and people interact with each other and change with each other. For example, a place to stop a crowd may be a popular attraction or business. If you can distinguish passengers from staying or passing by, you can dynamically count the number of people staying. However, the above prior art cannot be applied to this.

On the other hand, the rapid progress of electronic products has made mobile terminal products (such as smart phones, car-mounted devices, etc.) popular, and combined with Global Positioning System (GPS) technology, the services can be accurately positioned. Individuals and objects play an important role in the application of human life. For example, the mobile APP program can be used to calculate and record sports miles, and the on-board machine can be used to monitor the distribution and operation of items or personnel. Through GPS technology, assuming that the target is at a certain position P on the surface of the earth, a Cartesian coordinate position ( P = ( x , y , z )) corresponding to the center of the Earth can be obtained, where the x-axis is from the center of the earth through the longitude. In the 0 degree direction, the y axis is from the center of the earth through the east longitude 90 degrees, and the z axis is from the center of the earth through the north pole direction. After reference to the earth coordinate system, the earth longitude ( λ ) and latitude of this position P can be converted ( ) coordinates, here to Said. If the positioning device can obtain the position respectively at times t ₁ and t ₂ versus , the displacement of the terminal device between time t ₁ and t ₂ and from position P ₁ to P ₂ The value can be determined by conventional techniques. For example, use the long arc distance on the earth's great circle: , where R is the radius of the earth, and θ is the angle between the two points P ₁ and P ₂ respectively to the line of the center of the earth. In addition, the azimuth angle α between the two points can be obtained, which starts from 0° in true north and 360 degrees in a clockwise rotation from north to southeast and northwest. The common mobile APP program uses the GPS technology, because the movement mode of the personnel is more complicated than the movement mode of the vehicle, and the starting and ending points cannot be determined correctly and effectively. Therefore, each time the user's travel record requires manual operation to open and close, it is inconvenient.

In view of this, the present invention provides a person-time statistical system and a method thereof for determining a road traffic jam location distribution and a population normal stay location distribution based on a person's traveling condition.

The method of population statistics of the present invention comprises the following steps. Get information about the location of a person in a certain area. Corresponding to the travel switching condition according to the position information of the person, the total trajectory of the area is divided into at least one moving trajectory section, and the traveling condition in each moving trajectory section is maintained, and the total trajectory is based on the person being in the area. Location information. The distribution of the number of people in the area is determined according to the movement track segment, the area related information, the time period in which the person position information is recorded, and the traveling condition in the area.

The human-statistical system of the present invention includes at least one positioning device, a geographic parameter database, and a back-end server. The positioning device obtains the location information of the person in a certain area. The geographic parameter database provides geographic location information. The backend server compares the travel switching condition according to the position information of the person, and divides the total track of the area into at least one moving track segment, and the traveling condition dimension in each moving track segment Hold, and the total trajectory is based on the location information of the person in this area. The backend server determines the distribution of the people in the area according to the moving track section, the area related information, the time period in which the person position information is recorded, and the traveling condition in the area.

Based on the above, the embodiment of the present invention first analyzes the traveling condition and method of the personnel, and divides the total trajectory into different moving trajectory sections by using the speed change and/or the azimuth change, and then counting the moving trajectory area of all the people in the area, and then Get the location of the vehicle or personnel and the distribution of the stay. In this way, the cost of the fixed-point detector can be eliminated, and the cost distribution can be provided, and the distribution of the person meeting the actual demand can be provided.

The above described features and advantages of the invention will be apparent from the following description.

1‧‧‧ personage statistics system

101‧‧‧ Positioning device

102‧‧‧Backend server

103‧‧‧Travel parameter database

104‧‧‧ Geographical Parameter Database

S201~S217, S501~S504, S701~S705‧‧‧ steps

1 is a schematic diagram of a person-time counting system in accordance with an embodiment of the present invention.

2 is a flow chart of a method for counting people's statistics - moving track segments according to an embodiment of the invention.

Fig. 3 is a diagram illustrating a speed-time relationship between a road and a car.

FIG. 4 is a diagram illustrating a moving track section of FIG. 3.

FIG. 5 is a flow chart of a method for counting people-personal times according to an embodiment of the present invention.

Figure 6 is a diagram illustrating the statistical distribution of the traffic jam starting point of Figure 3.

7 is a flow chart of a person-statistic method-data query according to an embodiment of the present invention. Cheng Tu.

1 is a schematic diagram of a person ranking system 1 in accordance with an embodiment of the present invention. Referring to FIG. 1, the person-time counting system 1 includes one or more positioning devices 101, a back-end server 102, a travel parameter database 103, and a geographic parameter database 104.

The positioning device 101 supports a positioning tracker, a smart phone, and an in-vehicle device of at least one type of satellite navigation system (for example, a Global Positioning System (GPS), a Global Navigation Satellite System (GLONAS), a Beidou satellite navigation system, etc. And used to record location information (for example, latitude and longitude, etc.). In this embodiment, the positioning device 101 supports third-generation (3G), fourth-generation (4G) mobile communication, narrow-band Internet of Things (NB-IoT), long-distance (Long Range, LoRa) communication, and the like. Technology (with communication chips, transceivers or circuits) to periodically transmit the location information it records.

The backend server 102 can be a computing device such as a computer host, a server, or a workstation. Further, the backend server 102 supports the same communication technology as the positioning device 101 to obtain the location information of each of the positioning devices 101.

The travel parameter database 103 records the action switching condition, the traveling mode identification condition, the speed, the azimuth angle, the starting point time, the starting point position, the starting point azimuth, the originating point time, the origin point position, the apocalyptic azimuth, the traveling average speed, and the traveling speed. Information such as standard deviation. The geographic parameter database 104 records geographical location information of several geographic regions (eg, area code, area range, roads, parks, transportation facilities, road speed limits, administrative areas, etc.).

In order to facilitate the understanding of the operational flow of the present invention, various embodiments will be described in detail below. FIG. 2 is a flow chart showing a method for counting people's statistics-moving track segments according to an embodiment of the invention. Referring to FIG. 2, in the following, the method described in the embodiment of the present invention will be described with reference to each device in FIG. The various processes of the method can be adjusted accordingly according to the implementation situation, and are not limited thereto.

The main purpose of this embodiment is to correctly distinguish the various travel conditions in the total trajectory of the movement (for example, stop, walk, fast walk, running, or stop when using the vehicle, traffic lights, traffic jams, vehicles, etc.) . The flow mainly uses the loop to determine the instantaneous dynamics (for example, speed, azimuth, etc.) of each input device 101 to determine the current position as a starting point, an ending point, or a certain point in the traveling condition. When the process starts, the backend server 102 to perform the initialization process (step S201), which comprises at least (1) initializing parameters of action, (2) setting the traveling condition observation interval (△ t _S), and (3) the initialization sequence The number n is 0. Thereafter, the rear end of the server 102 each recursive sequence number is incremented (step S202), and the positioning apparatus 101 acquired from the current location and time t _n P _n (step S203), then the record has been acquired over a time t _{n -1} position information P _n-1 and related parameters (step S204). Next, the back end server 102 can obtain the instantaneous displacement d _n,n-1 and the instantaneous speed v _n at the current time from the position and time input by the positioning device 101 twice (step S205). Backend server 102 then calculated according to the traveling condition observation interval mobile switching condition S ₁ (step S206). Regarding the design of the travel switching condition S ₁ , taking road traffic as an example, please refer to FIG. 3 , assuming that the total trajectory of the target vehicle in a certain section is shown at the top of the figure, and the corresponding instantaneous speed-time relationship diagram is below the figure. . Changes in the speed curve of the vehicle usually reflect the traffic conditions of the road. For example, a series of slowdowns, stops, and re-accelerations may be performed by a vehicle in response to a traffic jam or traffic sign red light. It can be seen that the analysis of the trajectory change process of all the vehicles passing through the road section can further confirm the traffic status of the road. Based on the concept of this invention, embodiments of the present invention to maintain the trajectories of the section definition persons (e.g., persons, cars, bicycles, etc.) as a traveling condition of the traveling condition, and the mobile switching condition S ₁ total track the moving object travels through Disassembled into multiple combinations of travel conditions, as shown in Figure 4. The backend server 102 needs to calculate the time, the position and the azimuth, the average speed of the traveling condition node (the starting point and the origin point) corresponding to each traveling condition according to the positioning information returned by the positioning device 101. Information such as speed standard deviation, same travel condition, and current displacement between the previous travel status node is stored and stored, for example, in the travel parameter database 103 or other storage medium. The design consideration of the traveling condition switching condition S ₁ is as follows: If it is desired to distinguish different moving track segments during the traveling, it is theoretically possible to determine whether the target is in a stopped or moving state by observing whether the instantaneous moving speed of the observer is zero, but actually The above manner may cause misjudgment due to the stability of the positioning device 101 or the target person walking around in a certain place. In addition, if applied to a high-speed moving target person, the traveling condition may correspond to different traffic states, such as a car, a traffic jam, and the like. In addition, the instantaneous speed of the vehicle may vary drastically due to the travel conditions of the stop and go. Therefore, if a fixed instantaneous speed is used as the switching threshold, it is easily misjudged by human factors, road conditions, and the like. In view of this, the embodiment of the present invention recognizes the change of the traveling condition by comparing the current time t = t _n with the trajectory parameter before the last time t _n-1 . Suppose that a certain target person is performing a certain travel condition k, and defines the positioning time point and position of the nth time obtained by t _n and P _n for the target person's traveling condition k, and n 1, where t ₁ and P ₁ are the first acquisition time point and position (starting point) of the target person's traveling condition k and n =1. Then, a traffic condition observation interval (Δ t _S ) parameter which is adjusted by visual practice or actual situation is given, and the embodiment of the present invention observes the time interval before the previous time t = t _{n -1} and traces the observation interval Δ t _S forward. Changes in the movement path:

(1) Change in speed

By the difference between the current instantaneous velocity ( v _n ) and the average velocity (ie, the velocity change), the travel conditions of the different types can be distinguished. Therefore, the backend server 102 can calculate the average value ( v _{X , n} ) of the velocity in this observation interval (ie, the average velocity) and the standard deviation ( σ _{V , n} ) (ie, the standard deviation of the velocity), and will travel The switching condition S _{1 is} designed as | v _n - v _{X , n} |> K _{S 11} × σ _{V , n} (i.e., speed switching condition). When the instantaneous speed v _n satisfies the travel switching condition S ₁ , that is, the difference between the instantaneous speed v _n and the average speed (ie, the speed change) is excessive, and the current time point can be regarded as the starting point of different traveling conditions (in other words, this The time point is also the point of the previous travel condition, where K _{S 11} is a threshold that can be adjusted according to the actual or actual conditions to adjust the speed difference. In other words, the speed switching condition is that the speed change (| v _n - v _{X , n} |) after the time point corresponding to the starting point position of the moving track section (a certain traveling condition) is greater than the speed change threshold value ( K _{S 11} × σ _{V , n} ), and the speed change threshold value is related to the speed standard deviation σ _{V , n} between the time point corresponding to the starting point position and the current time point.

(2) azimuthal change

In areas where there is no clear road, such as a square or a park, the statistics of the number of people usually need to consider the direction of the target person's travel, while there are obviously different requirements for the statistics of the people on the road. Thus, the backend server 102 can calculate the difference between the current instantaneous azimuth ( α _n ) and the azimuth mean (ie, the azimuthal variation) to distinguish the different types of travel conditions. By calculating the azimuth mean value ( α _{X , n} ) and the standard deviation ( σ _{α , n} ) in the travel condition observation interval, the travel switching condition S ₁ can be designed as | α _n - α _{X , n} |> K _{S 12} × σ _{α , n} (ie, azimuth switching condition). When the instantaneous azimuth angle α _n satisfies the switching condition S ₁ , which means that the target person turns and causes a large change in the instantaneous azimuth angle, it can be regarded as different traveling conditions (if the azimuth statistical result in the observation interval has a large standard deviation) , it means that the moving direction of the target personnel is relatively unclear), and K _{S 12} is a parameter that can be adjusted according to the actual or actual conditions to adjust the threshold value of the azimuth offset degree. In other words, the azimuth switching condition is that the azimuth angle change (| α _n - α _{X , n} |) after the time point corresponding to the starting position of the self-initial state is greater than the azimuth angle threshold value ( K _{S 12} × σ _{α , n} ), and the orientation The angular variation threshold value is related to the azimuthal standard deviation σ _{α , n} between the time point corresponding to the starting point position and the current time point.

It can be seen that if it is not necessary to consider the moving direction of the target, the traveling switching condition S ₁ can adopt the speed switching condition (| v _n - v _{X , n} |> K _{S 11} × σ _{V , n} ); In the moving direction, the traveling switching condition S ₁ can adopt a combination speed switching condition (| v _n - v _{X , n} |> K _{S 11} × σ _{V , n} ) and azimuth switching condition (| α _n - α _{X , n} | > K _{S 12} × σ _{α , n} ).

Returning to FIG. 2, if the travel switching condition S ₁ is not satisfied, it means that the movement is maintained in the same traveling condition. At this time, the backend server 102 calculates the traveling mode identification condition (including the traveling mode reset condition S ₂ and the traveling mode switching condition S ₃ ) (steps S213, S214). The main purpose of this stage is to confirm the way of travel of the current travel situation (for example, walking, jogging or using vehicles, etc.), and calculate the travel condition related parameters according to the travel mode, that is, the decision to adjust the movement track section according to the judgment result of using the vehicle. . If the travel mode reset condition S _{2 is} designed to: detect whether the target person is completely stopped, and after the target person completely stops, the next action condition preset travel mode will be reset to walking, then the travel mode can be reset. The condition S _{2 is} set to v _{X , n} < K _{S 21} × V _WALK , where V _WALK is the walking speed, and K _{S 21} is a parameter that can be set according to practice or actual conditions. In other words, the traveling mode reset condition S ₂ is that the average speed v _{X , n} after the time point corresponding to the starting point position of a certain moving track section (traveling condition) is smaller than the walking moving threshold value K _{S 21} × V _WALK , and this walking movement The threshold value is related to the walking speed. On the other hand, the design of the personnel travel mode switching is that before the target person completely stops, the current travel condition will travel in the same manner as the previous travel condition, and once the travel mode switching condition S ₃ is detected, The way the travel of the entire travel situation is set is the new travel mode. For example, in the process, it is determined whether the target person uses the vehicle (step S215): It is assumed that in the travel condition observation section, the minimum statistical area category of the target person's location is the road, and the target person maintains a certain average speed ( v _{X , n} And its value is higher than the normal jogging speed ( V _RUN ), the way of traveling of the target person is recognized as using a vehicle (for example, a tool such as a car, a locomotive or a bicycle) (step S216). Therefore, the traveling mode switching condition S ₃ can be designed as ( σ _{V , n} < K _{S 31} and v _{X , n} > K _{S 32} × V _RUN ), where σ _{V , n} is the speed standard deviation of the traveling condition observation interval and K _{S 31} and K _{S 32} are parameters that can be set according to actual or actual conditions, so as to eliminate the short-term running sprint and other conditions through the setting of relevant parameters. In other words, the traveling mode switching condition S ₃ is the speed standard deviation σ _V after the time point corresponding to the starting position of a certain traveling condition _{, n is} smaller than the variation threshold K _{S 31} and the average speed v _{X , n is} greater than the tool moving threshold ( K _{S 32} × V _RUN ), and this variation threshold and tool movement threshold are related to the jogging speed.

In addition, since in a certain traveling situation, the target person may cross a plurality of different statistical areas, and these areas may have different uses in statistics, such as belonging to different road sections, towns or counties, etc., and need individual count. Therefore, if the travel status record only contains the starting point, the statistical area information passed in the travel situation will be lost when counting the number of people. In view of this, the embodiment of the present invention divides a certain area painting into a plurality of statistical areas that do not cover each other. For example, defining a target area as a road, park, or transportation facility, and storing the statistical area data by the geographic parameter database 104, and the data content includes at least an area code, a regional range, a regional type (road or non-road), and a region. Speed limit and other parameters. When calculating the parameters related to the progress status at the current time, the area data of the different statistical areas are included in the data record (step S217). On the other hand, if the travel switching condition S ₁ is satisfied, the state of the traveling condition is changed. At this time, the above time ( t = t _{n -1} ) is taken as the time point of the current point (or end point) of the current traveling condition k (step S208), and the traveling status data is output to the person statistical process for analyzing the number of times of the person (steps) S212), and the current time (t = t _n) as a start point position of the next position of the traveling condition, and resets the sequence number is 1 (n = 1) (step S209). The backend server 102 then determines whether the instantaneous traveling condition satisfies the traveling mode reset condition S ₂ (step S210); if so, resets the traveling mode of the next traveling state to the foot (step S211). Thereafter, the above-mentioned target position input and parameter calculation flow is repeated (ie, returning to step S202), and a series of travel status information of a certain person is generated immediately (mainly including the time, position, and other travel of each moving track section; Apply parameters (for example, azimuth of the starting point, all passing the marked area code, etc.) and divide the total track of this area of interest into segments of moving track segments.

For example, in a certain interest target area, taking the central block road section above the schematic diagram of FIG. 4 as an example, the turning point of different speed changes will form the starting point of a certain traveling condition (ie, the origin of the previous traveling condition), As shown below, the speed within each travel condition is substantially maintained. Regarding the traffic condition of the segmentation result of the total trajectory, if it is assumed that the average speed of the traveling condition k-3 is close to or even exceeds the road speed limit, it may represent that the road is smooth; the average traveling speed of the traveling condition k-2 is about the speed limit of the road section. Sixty percent may represent the car or prepare for the brakes in response to the traffic jam; the k-1 speed of the travel condition is close to 0, representing a red light such as a traffic jam or stop. To clearly clarify the meaning of each moving track segment, it is necessary to further analyze the average speed of the traveling condition corresponding to the regional characteristics to obtain an accurate interpretation. For example, if the average speed of a certain traveling condition reaches 80% of the speed limit of the road section, it is regarded as a smooth road; 50% to 80% is regarded as a lot of vehicles; and 50% or less is regarded as a congestion. For pedestrians, classification can also be performed. For example, the walking speed is generally about 5 km/h, and the speed of jogging is about 10 km/hr. If the speed of the jogging speed is less than 40%, it can be regarded as a walking state. Shopping The possibility of things, while more than 40% is regarded as a fast moving travel route, such as driving or sports.

On the side of the backend server 102, each travel condition accumulates the number of times according to the position, road direction, time period, and speed classification of each node (such as start, run, etc.), and is stored in the travel parameter database 103. In the subsequent query, the data of the cumulative number of people may be obtained according to the selected section block, direction, time period, speed classification, and type of the traveling node.

Regarding the person-time statistical process (ie, step S212 of FIG. 2), referring to FIG. 5, after the process starts, the back-end server 102 must first set the statistical classification in the travel parameter database 103 (step S501), which is the minimum of a certain parameter. Statistical classification / grouping units. For example, in terms of time, it is defined as a time period every 15 minutes, that is, it can be divided into 96 time periods every day. For example, for the target speed, the driving part can be divided into traffic jams, cars, and smooth, and the walking part can be divided into staying, passing, and the like. Through the classification of the travel parameters, the travel status data generated by the travel progress capture process (ie, the flow of FIG. 2) of the single target trajectory will be input as the travel status record (step S502), so as to facilitate subsequent rapid finding of suitable statistics. Fill in the fields. The backend server 102 further obtains the number of times that meet the above conditions according to the position of the traveling node (ie, the position of the moving track segment starting point) and the belonging statistical area (geographic location information), time period, direction, and speed classification (traveling status classification). The value is incremented (step S503), and this person count value is incremented by one to update the content recorded by the travel parameter database 103 (step S504). And so on, returning to step S503 to receive the travel data generated by the travel extraction process from other single target trajectories, And sorting the corresponding statistical values in the travel parameter database 103 according to the node position, the belonging statistical area, the time period, the direction, the speed, and the like in the travel status data, and after accumulating, updating the numerical record corresponding to the travel parameter database 103 . By sequentially obtaining a large number of target personnel's travel status data, the distribution of the people in this statistical area can be obtained.

In the query, the embodiment of the present invention can also effectively extract all the statistical fields of the query area. Referring to FIG. 7, the backend server 102 receives the input content of the selected query geographic range and time (step S701), and can query the area code of all the statistical regions in the geographic range according to the geographic location information of the geographic parameter database 104 ( Step S702). Then, the backend server 102 obtains the coordinates and the person count value in the corresponding statistical area according to the selected area code and the time (step S703), and can output the distribution report of the people in the statistical area according to the query result. (Step S704). The backend server 102 will confirm that all the statistical area population distribution reports are completed (step S705), and then the query is ended.

For example, taking FIG. 6 as an example, if the average speed of the vehicle in the time period when the vehicle passes through the central block section is selected, the distribution of the space in the space will be as shown in the figure. The chart is shown. The distance from the peak of the chart to the intersection at the front can be used to determine the red light stop at this time.

It should be noted that, according to different query conditions, the distribution results of the number of people in a specific road section, an outdoor place, and the like (including the traffic jam situation, the degree of public gathering, etc.) are obtained.

In summary, the embodiments of the present invention provide instant and automated analysis of personnel In the way of travel, the total trajectory of a person in a certain area is divided into different trajectory sections according to the speed change of a single individual, and then the trajectory section information of all the people passing through the statistic is displayed, thereby showing the distribution of the road traffic position. Or the normal location of pedestrians in the sightseeing area can be further used as a basis for improvement of transportation facilities and reference for feedback, store design and capacity design.

The embodiment of the invention has at least the following effects: the embodiment of the invention uses the positioning device to detect the position of the personnel, so as to reduce the high construction and maintenance costs required for widely deploying various types of fixed-point detectors.

The embodiment of the present invention uses an automated method to observe the change of the speed or azimuth of the movement track of the person in a viewing condition observation section of a visual practice adjustment width, and correctly find the origin and the origin of the movement track segment, thereby avoiding the use. A single threshold value results in a misinterpretation of the dynamics of the person.

The embodiments of the present invention perform individual statistics through different travel status node positions, directions, time periods, and travel modes to filter out the flow distribution statistics that the user wants.

Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention, and any one of ordinary skill in the art can make some changes and refinements without departing from the spirit and scope of the present invention. The scope of the invention is defined by the scope of the appended claims.

Claims (4)

A person-time statistical method includes: obtaining location information of a person in an area; and comparing at least one travel switching condition according to the position information of the person, to divide the total track of the area into at least one moving track section, wherein each The traveling condition in the moving track section is maintained, and the total track is based on the location information of the person in the area; and the time period according to the at least one moving track section, the related information of the area, and the location information of the person is recorded, And the travel status in the area determines the distribution of the person in the area, wherein after obtaining the location information of the person in the area, the method further includes: comparing the at least one travel mode according to the location information of the person to determine whether the person uses the a vehicle; and a decision to adjust the at least one moving track segment based on a determination result of using the vehicle, wherein the at least one traveling switching condition and the at least one traveling mode identifying condition are based on a speed change and an azimuth change of the person, Determining whether different travel conditions and travel modes in the total trajectory are used And the at least one travel switching condition includes a speed switching condition and an azimuth switching condition, wherein the speed change condition is that the speed change is greater than a speed change threshold value after a corresponding time point of the starting position of the moving track segment And the speed changes The threshold value is related to a speed standard deviation between the time point corresponding to the starting point position and the current time point, and the azimuth angle switching condition is that the azimuth angle change is greater than an azimuth angle change threshold value after the corresponding time point of the starting point position, and the The azimuth change threshold value is related to the azimuth standard deviation between the corresponding time point of the starting point position and the current time point. The method for counting people according to claim 1, wherein the at least one traveling mode identifying condition comprises a traveling mode reset condition and a traveling mode switching condition, the traveling mode reset condition is from a moving track section The starting point position corresponds to an average speed after the time point is less than a walking movement threshold value, and the walking movement threshold value is related to the walking walking speed, and the traveling mode switching condition is that the speed standard deviation after the corresponding starting point position is less than a variation threshold value And the average speed is greater than a tool movement threshold, and the variation threshold and the tool movement threshold are related to the jogging speed. A person-time statistical system includes: at least one positioning device that obtains location information of a person in an area; a geographic parameter database that provides geographical location information; and a back-end server that compares at least one according to the location information of the person Tracing a switching condition to divide the total trajectory of the region into at least one moving trajectory segment, wherein a traveling condition within each of the moving trajectory segments is maintained, and the total trajectory is based on location information of the person in the region, The backend server determines the distribution of the area according to the at least one moving track segment, the geographical location information of the area, the time period for recording the location information of the person, and the traveling status in the area, The backend server identifies a condition according to the position information of the person by comparing at least one traveling manner to determine whether the person uses the vehicle, and adjusts the at least one moving track segment according to the judgment result of using the vehicle, wherein The at least one travel switching condition and the at least one travel mode identification condition are based on the speed change and the azimuth change of the person to determine whether different travel conditions and travel modes in the total trajectory use the vehicle, wherein the at least one travel switch The condition includes a speed switching condition and an azimuth switching condition, wherein the speed change is greater than a speed change threshold value after a time point corresponding to a starting position of the moving track segment, and the speed change threshold value is related to The starting position corresponds to a standard deviation of the speed between the time point and the current time point, and the azimuth switching condition is that the azimuth change is greater than an azimuth change threshold value after the corresponding time point of the starting position, and the azimuth change threshold is The value is related to the time point corresponding to the starting point to the current time point Azimuth standard deviation. The person-time statistical system of claim 3, wherein the at least one travel mode identification condition comprises a travel mode reset condition and a travel mode switching condition, the travel mode reset condition is from a moving track section The starting point position corresponds to an average speed after the time point is less than a walking movement threshold value, and the walking movement threshold value is related to the walking walking speed, and the traveling mode switching condition is that the speed standard deviation after the corresponding starting point position is less than a variation threshold value And the average speed is greater than a tool movement threshold, and the variation threshold and the tool movement threshold are related to the jogging speed.