CN117690077A

CN117690077A - People flow monitoring method, system, equipment and storage medium

Info

Publication number: CN117690077A
Application number: CN202311643487.0A
Authority: CN
Inventors: 连桄雷; 王筝; 叶维晶; 卢天发
Original assignee: Ropt Technology Group Co ltd
Current assignee: Ropt Technology Group Co ltd
Priority date: 2023-12-01
Filing date: 2023-12-01
Publication date: 2024-03-12

Abstract

The application provides a people flow monitoring method, a system, equipment and a storage medium, and relates to the technical field of security protection. In the application, a video platform acquires real-time video streams through cameras in all channels leading to subareas in a target area; the computing platform carries out target detection on the real-time video stream of each channel, carries out similarity discrimination according to image characteristics in continuous multiframes, and tracks to obtain the motion vector of each target; aiming at a target corresponding to the channel, calculating an included angle between a movement vector of the target and a preset direction vector of the channel; determining a target moving direction according to the included angle, and further determining a people flow rate change value of the corresponding subarea; and the service platform generates a people flow control scheme for one type of subareas with the people flow exceeding a preset threshold according to the people flow change value of each subarea. The scheme can be conveniently and simply applied to realizing accurate people flow monitoring in scenic spots of multiple scenic spots, timely triggers people flow management and control, and ensures travel experience and public safety of tourists.

Description

People flow monitoring method, system, equipment and storage medium

Technical Field

The present disclosure relates to the field of security technologies, and in particular, to a method, a system, an apparatus, and a storage medium for monitoring traffic.

Background

With the development of society and the improvement of living standard, more and more people consider travel as a leisure, entertainment and relaxation mode. The condition that tourists at hot tourist attractions are exploded often occurs in holidays. There are a plurality of minute scenery spots in the scenic spot generally, when the visitor in the scenic spot is exploded, if unable accurate effectively monitor the people flow condition of each minute scenery spot in the scenic spot, visitor's trip experience and public security all can receive the influence.

In the related art, the people flow in the scenic spot is monitored in real time by adopting real-time positioning modes such as RFID electronic tickets, GPS positioning and the like. However, the RFID/GPS requires that each tourist carries an RFID carrier/mobile positioning device with him, which has high implementation cost, poor controllability and related to user privacy, and unstable positioning signals also cause low monitoring accuracy under the condition of large traffic, so that traffic control cannot be performed in time when traffic sudden increase occurs at each sub-scenic spot in a scenic spot.

Disclosure of Invention

In order to solve the problems in the related art, the application provides a people flow monitoring method, a system, equipment and a storage medium, which are convenient and simple to use, are suitable for realizing accurate people flow monitoring in scenic spots of multiple scenic spots, trigger people flow management and control in time, and guarantee tourist traveling experience and public safety.

In a first aspect, the present application provides a method for monitoring traffic, the method comprising:

s1, acquiring real-time video streams through cameras deployed in various channels in a target area, wherein each channel leads to at least one sub-area in the target area;

s2, target detection is carried out on a real-time video stream corresponding to any channel, and the initial positions and the final positions of a plurality of targets detected in the real-time video stream in continuous multiframes are determined; calculating respective motion vectors of the plurality of targets according to the respective initial positions and final positions of the plurality of targets;

s3, calculating an included angle between a motion vector of any target detected in the real-time video of any channel and a preset direction vector of the channel; determining the moving direction of the target according to the included angle, and determining the people flow rate change value of at least one sub-area corresponding to the channel according to the moving direction;

s4, generating a people flow control scheme according to the people flow change value of each subarea determined in real time and the subarea of which the current people flow exceeds a preset threshold value.

In one possible implementation manner, the step S4 includes:

s41, updating the historical people flow according to the people flow change value for any subarea, and determining the current people flow of the subarea; judging whether the subareas are one type of subareas or not by using a preset threshold value corresponding to each subarea;

s42, under the condition that the first sub-area exists, calculating the people flow saturation of the second sub-area, wherein the people flow saturation of each people flow of each second sub-area does not exceed the corresponding preset threshold value, and the people flow saturation is the ratio between the current people flow of the second sub-area and the corresponding preset threshold value;

s43, sequencing the people flow saturation of each second-class subarea from small to large, and performing people flow management and control on the first-class subarea based on sequencing at least one target subarea adjacent to the first-class subarea in a plurality of second-class subareas positioned at the front target position, wherein the management and control measures comprise: and carrying out route recommendation on the target subarea.

In one possible implementation manner, the step S2 includes:

s21, adopting a given target detection model to detect the head of any frame in the real-time video stream, and taking the detected head characteristic as the image characteristic of the corresponding target;

s22, aiming at any detected target, adopting a discriminant correlation filter constructed according to the image characteristics of the target, performing similarity discrimination in the next frame of any frame, and determining the position of the target in the next frame according to the discrimination result;

s23, calculating the movement vector of the target according to the initial position and the final position of the target in the continuous multi-frame.

In a possible implementation, in case the channel leads from the first sub-area to the second sub-area, the step S3 comprises:

s31, calculating an included angle between a moving vector of a target detected from the real-time video stream corresponding to the channel and a preset direction vector of the channel, wherein the preset direction vector points to the second sub-area from the first sub-area;

s32, under the condition that the cosine value of the included angle is larger than 0, determining that the moving direction of the target moves from a first subarea to a second subarea, and adding 1 to the inflow quantity of the second subarea;

and under the condition that the cosine value of the included angle is smaller than 0, determining the moving direction of the target to move from the second subarea to the first subarea, and adding 1 to the outflow quantity of the second subarea.

In one possible embodiment, the method further comprises:

according to the people flow rate of each subarea at different moments in a selected historical time period, counting to obtain the people flow rate change trend in the historical time period;

and predicting the traffic variation value in the future time period corresponding to the historical time period according to the traffic variation trend in the historical time period, and carrying out traffic early warning according to the prediction result.

In one possible embodiment, in case the channel is used for connecting the sub-area and the target area inlet or for connecting the sub-area and the target area outlet, the method further comprises:

gate statistical data of an outlet/inlet of a target area are obtained from a service system, and the variation value of the flow of people in each subarea in the target area is determined according to the gate statistical data.

In a second aspect, there is provided a people flow monitoring system, the system comprising: the system comprises a video platform, a computing platform and a service platform;

the video platform is used for: pushing real-time video streams collected by cameras deployed in various channels in a target area to the computing platform, wherein each channel leads to at least one sub-area in the target area;

the computing platform is used for: target detection is carried out on a real-time video stream corresponding to any channel, and the initial position and the final position of each target in a continuous multiframe, which are detected in the real-time video stream, are determined; calculating respective motion vectors of the plurality of targets according to the respective initial positions and final positions of the plurality of targets;

the computing platform is further for: calculating an included angle between a motion vector of any target detected in a real-time video of any channel and a preset direction vector of the channel; determining the moving direction of the target according to the included angle, and determining the people flow rate change value of at least one sub-area corresponding to the channel according to the moving direction;

the service platform is used for: and acquiring the people flow rate change value of each subarea determined in real time by the computing platform, and generating a people flow rate control scheme aiming at a type of subareas of which the current people flow rate exceeds a preset threshold value.

In a third aspect, there is provided a computing device comprising a memory and a processor, the memory storing at least one program, the at least one program being executable by the processor to implement the method of people flow monitoring as provided in the first aspect.

In a fourth aspect, there is provided a computer readable storage medium having stored therein at least one program that is executed by a processor to implement the method of people flow monitoring as provided in the first aspect.

The technical scheme provided by the application at least comprises the following technical effects:

in the technical scheme, a video platform acquires real-time video streams through cameras in all channels leading to subareas in a target area; the computing platform carries out target detection on the real-time video stream of each channel, carries out similarity discrimination according to the characteristics in continuous multiframes, and tracks to obtain the motion vector of each target; aiming at a target corresponding to the channel, calculating an included angle between a movement vector of the target and a preset direction vector of the channel; determining a target moving direction according to the included angle, and further determining a people flow rate change value of the corresponding subarea; and the service platform generates a people flow control scheme for one type of subareas with the people flow exceeding a preset threshold according to the people flow change value of each subarea. The scheme can be conveniently and simply applied to realizing accurate people flow monitoring in scenic spots of multiple scenic spots, timely triggers people flow management and control, and ensures travel experience and public safety of tourists.

Drawings

Fig. 1 is a schematic diagram of a people flow monitoring system according to an embodiment of the present application;

FIG. 2 is a schematic illustration of a scenic spot according to an embodiment of the present application;

fig. 3 is a schematic flow chart of a method for monitoring a flow of people according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a real-time video streaming picture according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a head detection model provided in an embodiment of the present application;

FIG. 6 is a schematic diagram of a people flow statistics principle provided in an embodiment of the present application;

FIG. 7 is a schematic view of an included angle provided by an embodiment of the present application;

fig. 8 is a schematic hardware structure of a computing device according to an embodiment of the present application.

Detailed Description

To further illustrate the embodiments, the present application provides the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate embodiments and together with the description, serve to explain the principles of the embodiments. With reference to these matters, one of ordinary skill in the art would understand other possible embodiments and the advantages of the present application. The components in the figures are not drawn to scale and like reference numerals are generally used to designate like components. The term "at least one" in this application means one or more, the term "plurality" in this application means two or more, for example, a plurality of sub-regions means two or more sub-regions.

The utility model provides a people flow monitoring system and method to the problem that exists among the correlation technique, can solve the people flow statistics problem of each sub-scenic spot in the scenic spot to in time report an emergency and ask for help or increased vigilance to the sub-scenic spot that the people flow exceeds standard, and provide people flow management and control scheme. The technical scheme of the present application will be further described with reference to the accompanying drawings and the specific embodiments.

Example 1

The embodiment of the application provides a people flow monitoring system, which comprises: video platform, computing platform and business platform. The people flow monitoring system is applied to the target area to monitor and control the people flow in real time. The target area is illustratively an area with a certain interior channel plan, such as a scenic spot, urban area, etc. The target area includes a plurality of sub-areas, e.g., a plurality of sub-points within a scenic spot, different building areas within a city.

In the embodiment of the application, the people flow monitoring system can conduct accurate people flow statistics on all subareas inside the target area.

The video platform pushes real-time video streams collected by cameras deployed in all channels in a target area to the computing platform, and each channel leads to at least one sub-area in the target area; the computing platform detects targets aiming at the real-time video stream corresponding to any channel, and determines the initial positions and the final positions of a plurality of targets detected in the real-time video stream in continuous multiframes; calculating respective motion vectors of the plurality of targets according to respective initial positions and final positions of the plurality of targets; the method comprises the steps that a computing platform calculates an included angle between a moving vector of a target and a preset direction vector of a channel aiming at any target detected in a real-time video of any channel; determining the moving direction of the target according to the included angle, and determining the people flow change value of at least one sub-area corresponding to the channel according to the moving direction; the service platform acquires the people flow rate change value of each subarea determined in real time by the computing platform, and generates a people flow rate control scheme aiming at a type of subareas of which the current people flow rate exceeds a preset threshold value.

Fig. 1 is a schematic diagram of a traffic monitoring system provided in an embodiment of the present application, where each camera is respectively connected to a video platform of the traffic monitoring system, the video platform pushes a real-time video stream to a computing platform for traffic statistics and analysis, and pushes a traffic statistics result to a service platform; and the service platform pre-warns the sub-areas (scenic spots) with the exceeding traffic according to the traffic statistics result and generates a corresponding traffic control scheme, and the sub-areas are shunted by corresponding measures.

Illustratively, the target area in the embodiments of the present application is a scenic spot, and the sub-areas within the target area are scenic spots. Fig. 2 is a schematic diagram of a scenic spot according to an embodiment of the present application, referring to fig. 2, the scenic spot includes N entrances and exits, M scenic spots, and K channels, where N, M and K are positive integers arbitrarily conforming to the scenic spot planning. In the scenic spot shown in fig. 2, there are 3 entrances (F, G and H), 5 sub-scenic spots (A, B, C, D and E indicated by circles), and 6 channels (indicated by straight line segments) between the sub-scenic spots. A camera (represented by a triangle) is arranged on the channel between any two scenic spots.

In one possible implementation, the mounting height and angle of the camera cover the entire channel width to prevent personnel from passing by where no pictures are acquired; the camera is installed at a preset overlook angle, so that the situation that a plurality of targets in a picture are mutually shielded is prevented. According to the installation mode, accuracy of target detection and people flow statistics can be improved.

The operations performed by each platform in the traffic monitoring system and the specific interaction flow between each platform will be further described in example 2 below.

The people flow monitoring system provided by the embodiment of the application can be conveniently and simply applied to realizing accurate people flow monitoring in scenic spots of multiple scenic spots, timely triggers people flow management and control, and ensures tourist traveling experience and public safety.

Example 2

The embodiment of the application provides a people flow monitoring method, which is applied to the people flow monitoring system and can accurately monitor and control the people flow of scenic spots of multiple scenic spots. The following describes the method for monitoring the traffic flow according to the embodiment of the present application in detail with reference to the implementation environments and system architectures shown in fig. 1-2.

Fig. 3 is a flow chart of a method for monitoring traffic of people according to an embodiment of the present application, and referring to fig. 3, the method for monitoring traffic of people includes the following steps S1 to S4, which are executed by corresponding platforms in the traffic monitoring system shown in fig. 2.

Step S1, a video platform collects real-time video streams through cameras deployed in various channels in a target area, and each channel leads to at least one sub-area in the target area.

The video platform further pushes the real-time video stream to the computing platform for people flow statistics and analysis.

In this embodiment of the present application, any frame of the real-time video stream includes a corresponding channel. Fig. 4 is a schematic diagram of a real-time video streaming picture provided in an embodiment of the present application, as shown in fig. 4, a rectangular picture photographs a channel (shown by a curve) between a sub-scenic spot a and a sub-scenic spot B at a top view angle, and a tourist 1 and a tourist 2 are detected in the channel. Tourists can walk to the right (scenery spot A) from the left (scenery spot B), and can walk to the left (scenery spot B) from the right (scenery spot A).

Step S2, the computing platform carries out target detection on a real-time video stream corresponding to any channel, and determines respective initial positions and final positions of a plurality of targets detected in the real-time video stream in continuous multiframes; and calculating the movement vector of each of the plurality of targets according to the initial position and the final position of each of the plurality of targets.

In the embodiment of the present application, step S2 includes the following steps S21 to S23.

And S21, adopting a given target detection model to detect the head of any frame in the real-time video stream, and taking the detected head characteristic as the image characteristic of the corresponding target.

The target detection model adopted in the embodiment of the application is a head detection model trained by using an NWPU crowd positioning data set, and can detect smaller heads compared with a YOLO series model, and is suitable for detection scenes with larger numbers of people and larger areas. After the image frame is input into the head detection model, a confidence level predictor of the model predicts the confidence level of a head region in the image frame to obtain a confidence level map, and a binarization module of the model divides the confidence level map into independent instance map maps for inference classification; specifically, after a threshold value diagram is obtained for each confidence diagram through online learning by adopting a threshold value module, a frame and a center of each independent instance area are obtained through prediction.

FIG. 5 is a schematic diagram of a head detection model according to an embodiment of the present application, referring to FIG. 5, after an image frame is input as an input image into the head detection model, a confidence map is obtained by a confidence predictor; the confidence map is input into a binarization module after gradient separation. The binarization model comprises a threshold learner and a binarization layer, and a threshold map is obtained after the confidence map is input into the threshold learner; and the threshold value map and the confidence map are input into the binarization layer together to obtain an independent instance map.

S22, aiming at any detected target, adopting a discriminant correlation filter constructed according to the image characteristics of the target, performing similarity discrimination in the next frame of any frame, and determining the position of the target in the next frame according to the discrimination result.

The embodiment of the application adopts a Discriminant Correlation Filter (DCF) algorithm to track the target. The target is a person target, for example, a guest, a worker, or the like.

Specifically, the DCF algorithm extracts features in the region where the target is located and in the background region, and trains the discriminant correlation filter by the extracted image features (head features are used in this application). The discriminant correlation filter is applied to the new image frame (next frame), a response map of the next frame to the image features of the object is calculated, and the position of the object is determined by finding peaks in the response map. Based on this principle, tracking can be performed in successive multiframes according to the head characteristics of the target, starting from the target entry screen, tracking to the target exit screen. In this process, the first position where the object appears is the initial position, and the last position where the object appears is the final position.

Illustratively, when a certain target (guest) enters the video screen, the initial position where the target is entered is denoted as P1 (x 1, y 1) from the target detection model, and a new target ID is assigned thereto. The target is then tracked by the DCF algorithm until the target leaves the picture, the final position of which in the picture is finally noted as P2 (x 2, y 2). Of course, in the case where the camera supports acquisition of depth data, the position may be represented by three-dimensional coordinates P1 (x 1, y1, z 1), including, in addition to the abscissa "x1, y1" indicating the planar position, the depth coordinate "z1" indicating the relative distance to the camera.

Illustratively, the direction vector of the initial position pointing to the final position, i.e. the motion vector of the target, the motion vector can be expressed as:

the embodiment of the application provides a schematic diagram of a people flow statistics principle. Referring to fig. 6, the video picture passes from left to right, from sub-point B to sub-point a. The arrow from left to right in the center indicates the inflow direction of the sub-spot a, and the direction from right to left is the direction of the sub-spot a to the sub-spot B, and is the outflow direction of the sub-spot a.

Referring to fig. 6, in consecutive multiframes, guest 1 goes from the B spot to the a spot, guest 2 goes from the a spot to the B spot, and the rectangular box in fig. 6 indicates the guest's position in a certain frame. From the initial and final positions of guest 1, a guest 1 motion vector, represented by the uppermost arrow 10, may be determined; from the initial and final positions of guest 2, a guest 1 motion vector, indicated by the lowermost arrow 20, may be determined.

Step S3, calculating an included angle between a motion vector of a target and a preset direction vector of a channel by a calculation platform aiming at any target detected in a real-time video of any channel; and determining the moving direction of the target according to the included angle, and determining the people flow change value of at least one sub-area corresponding to the channel according to the moving direction.

In the present embodiment, channels can be divided into two categories: one is a channel connecting the two sub-regions and one is a channel connecting the outlet/inlet and the sub-regions.

In one possible embodiment, in the case of a channel connecting two sub-areas, the traffic variation values of the two sub-areas can be determined depending on the direction of movement. Specifically, the flow rate change value includes the inflow amount and outflow amount of the subareas.

Specifically, in the case where the channel leads from the first sub-region to the second sub-region, step S3 includes S31 and S32.

S31, calculating an included angle between a motion vector of a target detected from a real-time video stream corresponding to the channel and a preset direction vector of the channel, wherein the preset direction vector points to the second sub-area from the first sub-area.

The preset direction vector can be set according to the statistical requirements and the channel direction, and the first subarea and the second subarea correspond to different scenic spots.

Illustratively, a direction vector from a point P3 on the sub-point B side to a point P4 on the sub-point B side is a preset direction vector (see an arrow 30 labeled inflow direction in fig. 6).

S32, under the condition that the cosine value of the included angle is larger than 0, determining that the moving direction of the target moves from the first subarea to the second subarea, and adding 1 to the inflow quantity of the second subarea; and under the condition that the cosine value of the included angle is smaller than 0, determining the moving direction of the target to move from the second subarea to the first subarea, and adding 1 to the outflow quantity of the second subarea.

In the embodiment of the application, the included angle ranges from-180 degrees to +180 degrees.

Specifically, the motion vector may be calculated according to the following formula (1)And a preset direction vector +.>The cosine of the included angle theta.

When cos (theta) is larger than 0, judging that the motion vector and the preset direction vector are in the same direction, and adding 1 to the inflow quantity of the second subarea; when cos (θ) <0, it can be determined that the motion vector and the preset direction vector are different, the number of second sub-area flows is increased by 1. Similarly, when the sub-scenic spot B is counted, the preset direction vector points to the sub-scenic spot B from the sub-scenic spot A, and when the cosine value of the included angle is larger than 0, the inflow quantity of the first sub-area is increased by 1; when the cosine value of the included angle is smaller than 0, the outflow quantity of the second subarea is increased by 1.

Referring to fig. 7, corresponding to a movement vector (indicated by an arrow 10 in fig. 6) of a guest 1, a movement direction (indicated by an arrow 20 in fig. 6) of a guest 2, and a preset direction vector (indicated by an arrow 30 in fig. 6), an included angle 1 in fig. 7 is an included angle corresponding to the movement direction of the guest 1, an included angle 2 in fig. 7 is an included angle corresponding to the movement direction of the guest 2, and according to a range of cosine function values (the included angle is smaller than 0 on the left side of a dotted line and larger than 0 on the right side of the dotted line), it is known that the guest 2 moves to the left side, and the outflow number of the scenic spots a on the right side is increased by 1; tourist 1 moves to the right, and the inflow quantity of the sub-scenic spots A on the right is increased by 1.

In the embodiment of the application, when the channel is used for connecting the sub-area and the target area entrance or for connecting the sub-area and the target area exit, the traffic variation value can be determined by gate statistics of the exit/entrance. In this example, the computing platform obtains gate statistics for the exit/entrance of the target area from the business system, and determines the traffic variance values for each sub-area within the target area based on the gate statistics.

Illustratively, referring to FIG. 2, the path between the attraction A and the exit/entrance F is denoted as R _AF Due to R _AF Since the gate is a gate route, a camera is not required, and statistics can be performed by using a gate of the gate. Specifically, the gate is used for accessing the service system, so that the total number of people entering the scenic spot (scenic spot) and leaving the scenic spot (scenic spot) at the current moment T can be counted.

And S4, generating a personnel flow control scheme by the service platform according to the personnel flow change value of each subarea determined in real time and the subarea of which the current personnel flow exceeds a preset threshold value.

In the embodiment of the present application, step S4 includes the following steps S41 to S43.

S41, updating the historical people flow according to the people flow change value for any subarea, and determining the current people flow of the subarea; judging whether the subareas are one type of subareas or not by using a preset threshold value corresponding to each subarea.

Specifically, for any subarea, according to the variation values of the people flow corresponding to all channels leading to the subarea, the historical people flow is updated. The process of updating the traffic will be described below by taking the scenic spot a shown in fig. 2 as an example.

Referring to fig. 2, there are 4 channels to the scenic spot a, one of which connects the entrance F, and the other 3 routes connect the scenic spots B, C and E, respectively. The four channels are respectively marked as R _AF 、R _AB 、R _AC And R is _AE Assuming that the historical people flow of the scenic spot A at the initial moment is X, after the time T, aiming at R _AF Recorded (recorded)The number of inflow and the number of outflow are denoted AFin and AFout, respectively. Similarly, the number of inflow and outflow recorded for the other 3 channels are respectively: ABin, ABout, ACin, ACou, AEin and AEout. Based on the above, the traffic flow of the scenery spot A updated at the time T is sum (A) =X+ABin-ABout+ACin-ACout+AEin-AEout.

Specifically, each sub-area is provided with a preset threshold value used by the sub-area, and the preset threshold value is equivalent to the maximum number of people which can be accommodated in the scenic spots aiming at the scenic spots. For the scenery spot A, the updated traffic sum (A) at the current moment T is compared with a preset threshold value max (A) used by the current moment T, and when sum (A) > max (A), the traffic of the scenery spot A exceeds the standard, and the scenery spot A belongs to a sub-area. At this time, an alarm can be further given for a type of sub-region.

S42, under the condition that one type of subarea exists, calculating the people flow saturation of the two types of subareas, wherein the people flow saturation of each type of subarea does not exceed the corresponding preset threshold value, and the people flow saturation is the ratio between the current people flow of the two types of subareas and the corresponding preset threshold value.

In the embodiment of the application, the subareas which can be used for shunting in the current scenic spot are evaluated by calculating the people flow saturation of the second subarea with the number of other people not exceeding the standard. Optionally, the preset threshold value used by each sub-area can be preset according to the occupation size of the area, and can be dynamically adjusted according to the in-out speed of the passenger flow.

Specifically, the subarea is a scenic spot, and the people flow saturation of the scenic spot p is calculated by the following formula (2).

S43, sequencing the people flow saturation of each second-class subarea from small to large, and performing people flow control on the first-class subarea based on sequencing at least one target subarea adjacent to the first-class subarea in a plurality of second-class subareas positioned at the front target position, wherein the control measures comprise: and carrying out route recommendation on the target subarea.

Specifically, for a first-class subarea with a person flow exceeding the standard, one or more target subareas adjacent to the first-class subarea can be selected from the second-class subarea as a diversion target. For example, referring to fig. 2, for the scenic spot a, the traffic saturation of 3 scenic spots, namely, scenic spots B, C, E adjacent to the scenic spot a, is calculated respectively, and route recommendation with the lowest traffic saturation is selected from the traffic saturation, so that the purpose of guiding tourists is achieved. Based on the method, pedestrian flow control can be flexibly carried out on the scenic spots with the exceeding pedestrian flow in real time, and the traveling experience and public safety of tourists are ensured.

In the embodiment of the application, route recommendation can be performed on the target subarea through modes such as broadcast notification, short message pushing, APP message pushing and the like, and further, tourists who are in a type of subarea or who are going to a type of subarea can be recommended, so that personnel flow control is realized. Specifically, guests who are heading for a class of sub-areas may be determined based on detected targets in the pathway to the class of sub-areas, such that the persuasion information is displayed or played in real-time at the waypoints.

Through the above process, the technical scheme provided by the embodiment of the application can record the people flow (the number of tourists) of each scenic spot at each moment in detail.

In one possible implementation mode, the method provides a further people flow prediction scheme on the basis of the real-time monitoring and continuous recording of people flow, and the timeliness of people flow early warning can be improved by analyzing the people flow change trend in a period of time and taking an analysis result as a prediction basis.

Specifically, the computing platform calculates and obtains the variation trend of the people flow in the historical time period according to the people flow of each subarea at different moments in the selected historical time period; and the service platform predicts the traffic variation value in the future time period corresponding to the historical time period according to the traffic variation trend in the historical time period, and performs traffic early warning according to the prediction result.

Illustratively, the computing platform counts the number of guests that change from time T to time t+Δt (Δt in hours or minutes) over a historical period of time for a sub-attraction or for the entire attraction. Taking a historical time period from 3 pm to 10 pm of the scenic spot A as an example, the calculated traffic flow change trend is expressed by increment: delta (a) =his (a, t+1) -his (a, T). his (a, t+Δt) represents the historical number of visitors (historical pedestrian traffic) at time t+Δt for the attraction a.

The calculated increment can be used as a trend parameter corresponding to the historical time period to predict the flow of people in a future time period, namely, the time period from 3 pm to 10 pm in the future. For example, the number of visitors at time T of the scenic spot a is sum (a, T), and then the above increment can be used to predict the traffic of people at the next time t+Δt, the prediction mode being shown in equation (3).

When the prediction result sum (A, T+DeltaT) is larger than a preset threshold corresponding to the current scenery spot, the traffic can be early warned.

The technical scheme that this application provided can be convenient and simple be applicable to realize accurate people flow monitoring in the scenic spot of many minutes scenic spots, triggers people flow management and control in time, ensures visitor's trip experience and public safety. And the real-time video picture is subjected to target detection and tracking, so that the people flow of each scenic spot in the scenic spot can be accurately calculated, and when the people flow exceeds the standard, alarming and drainage can be timely carried out. Further, people flow trend analysis is supported according to the historical people flow of each scenic spot, so that future people flow is accurately predicted, and pedestrian early warning is improved for people flow storm which possibly occurs in the future.

The application provides a computing device which can be implemented as a related platform in the people flow monitoring system and is used for executing part or all of the steps in the people flow monitoring method. Fig. 8 is a schematic diagram of a hardware structure of a computing device provided in an embodiment of the present application, where, as shown in fig. 8, the computing device includes a processor 801, a memory 802, a bus 803, and a computer program stored in the memory 802 and capable of running on the processor 801, where the processor 801 includes one or more processing cores, the memory 802 is connected to the processor 801 through the bus 803, and the memory 802 is used to store program instructions, where the processor implements all or part of the steps in the foregoing method embodiments provided in the present application when the processor executes the computer program.

Further, as an executable scheme, the computing device may be a computer unit, and the computer unit may be a computing device such as a desktop computer, a notebook computer, a palm computer, and a cloud server. The computer unit may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the constituent structures of the computer unit described above are merely examples of the computer unit and are not limiting, and may include more or fewer components than those described above, or may combine certain components, or different components. For example, the computer unit may further include an input/output device, a network access device, a bus, etc., which is not limited in this embodiment of the present application.

Further, as an implementation, the processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like that is a control center of the computer unit, connecting various parts of the entire computer unit using various interfaces and lines.

The memory may be used to store the computer program and/or modules, and the processor may implement the various functions of the computer unit by running or executing the computer program and/or modules stored in the memory, and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for a function; the storage data area may store data created according to the use of the cellular phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.

The present application also provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the methods described above in the embodiments of the present application.

The modules/units integrated with the computer unit may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each method embodiment described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a software distribution medium, and so forth. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of the legislation and the patent practice in the jurisdiction.

While this application has been particularly shown and described with references to preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the application as defined by the appended claims.

Claims

1. A method of monitoring traffic, the method comprising:

2. The people flow monitoring method according to claim 1, characterized in that the step S4 includes:

3. The people flow monitoring method according to claim 1, characterized in that the step S2 includes:

4. The method according to claim 1, wherein in case the channel leads from the first sub-area to the second sub-area, the step S3 comprises:

5. The method of people flow monitoring according to claim 1, characterized in that the method further comprises:

6. The people flow monitoring method according to claim 1, characterized in that in case the channel is used for connecting a sub-area with a target area inlet or for connecting a sub-area with a target area outlet, the method further comprises:

7. A people flow monitoring system, the system comprising: the system comprises a video platform, a computing platform and a service platform;

8. The people flow monitoring system of claim 7, wherein the service platform is configured to:

updating the historical people flow according to the people flow change value for any subarea, and determining the current people flow of the subarea; judging whether the subareas are one type of subareas or not by using a preset threshold value corresponding to each subarea;

under the condition that the first subarea exists, calculating the people flow saturation of the second subarea, wherein the people flow saturation of each subarea does not exceed the corresponding preset threshold value, and the people flow saturation is the ratio between the current people flow of the second subarea and the corresponding preset threshold value;

sequencing the people flow saturation of each class II subarea from small to large, and performing people flow control on the class II subareas based on sequencing at least one target subarea adjacent to the class II subareas in a plurality of class II subareas positioned at the front target position, wherein the control measures comprise: and carrying out route recommendation on the target subarea.

9. A computing device comprising a memory and a processor, the memory storing at least one program, the at least one program being executable by the processor to implement the method of people flow monitoring of any of claims 1 to 6.

10. A computer readable storage medium, wherein at least one program is stored in the storage medium, the at least one program being executed by a processor to implement the method of people flow monitoring according to any one of claims 1 to 6.