People flow density control method, system and equipment for smart park

Abstract

The invention relates to the technical field of public place people flow density control, in particular to a people flow density control method, system and device for a smart park, and aims to improve the accuracy of people flow density detection. The people flow density control method for the smart park provided by the invention comprises the following steps: tracking a current two-dimensional coordinate point of each tourist by using a UWB positioning technology; clustering all the two-dimensional coordinate points by adopting a DBSCAN algorithm to obtain a plurality of clusters; calculating the density of the two-dimensional coordinate points in each cluster; and sending first early warning information according to the density of the two-dimensional coordinate points. According to the method, the characteristic of high UWB positioning penetrating power is utilized, the shielding problem which cannot be overcome when people flow detection is carried out by utilizing a camera device and an infrared sensing device in the prior art is solved, the accuracy of people flow density detection is effectively improved, and in addition, the calculation amount is also reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of crowd density control in public places, and particularly relates to a method, system and device for crowd density control in a smart park. Background Art

[0002] With the advancement of urbanization, parks, as important places for urban residents to relax and entertain, have an increasing crowd density. Especially during holidays and weekends, the peak crowd hours are particularly obvious. Such a high-density crowd not only brings huge challenges to park management but also hides potential safety hazards, such as increasing the risk of public safety incidents such as crowding and stampeding.

[0003] To effectively address this challenge, park management departments have begun to introduce advanced intelligent monitoring and management systems. These systems use technical means such as video monitoring and infrared sensing to monitor the crowd density in the park in real time and perform data analysis. Through image processing and recognition algorithms, the system can automatically identify and calculate the crowd density in the monitored area. When the crowd density exceeds the set threshold, the system will immediately trigger an early warning mechanism to remind the management staff to take corresponding measures, such as dispatching additional staff to guide the flow of people, restricting the number of people entering the park, closing some areas or scenic spots, etc., to effectively avoid safety problems caused by over-concentration of the crowd.

[0004] However, in some parks, due to the complex terrain with high and low levels, and in addition, various buildings and trees in the park are likely to block the camera devices and infrared sensing devices, which will affect the accuracy of crowd density detection. In addition, the appearance of special weather conditions such as fog will further affect the accuracy of crowd density detection. Summary of the Invention

[0005] In order to solve the above problems in the prior art, the present invention proposes a method, system and device for crowd density control in a smart park, which improves the accuracy of crowd density detection.

[0006] In the first aspect of the present invention, a method for crowd density control in a smart park is proposed, and the method includes: Using UWB (Ultra Wide Band) positioning technology to track the two-dimensional coordinate points where each tourist is currently located; Adopting the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm to cluster all the two-dimensional coordinate points to obtain several clusters; Calculating the density of the two-dimensional coordinate points in each cluster; Send a first warning message according to the density of the two-dimensional coordinate points.

[0007] Preferably, the step of "clustering all the two-dimensional coordinate points by using the DBSCAN algorithm to obtain a plurality of clusters" includes: Cluster all the two-dimensional coordinate points by using the DBSCAN algorithm according to a preset neighborhood radius and a preset first minimum number of samples to obtain one or more first clusters; Calculate the convex hull of each of the first clusters respectively to obtain corresponding convex polygons; Map all the convex polygons onto the park electronic map; a plurality of monitoring areas are preset in the park electronic map, and the categories of the monitoring areas include: narrow areas and wide areas; Determine whether each convex polygon overlaps with a certain monitoring area and the overlapping area exceeds a preset percentage of the total area of the monitoring area; if so, divide the convex polygon into a high-risk area or a low-risk area according to the category to which the monitoring area belongs; otherwise, divide the convex polygon into the high-risk area; For each convex polygon whose category is the low-risk area, cluster the two-dimensional coordinate points included in the convex polygon by using the DBSCAN algorithm according to the preset neighborhood radius and the preset second minimum number of samples to obtain one or more second clusters.

[0008] Preferably, the step of "calculating the density of the two-dimensional coordinate points in each cluster" includes: If the convex polygon corresponding to a certain first cluster belongs to the low-risk area, calculate the number of the two-dimensional coordinate points included in each corresponding second cluster and the convex hull area of each second cluster, and then calculate the density of the two-dimensional coordinate points in each second cluster; If the convex polygon corresponding to a certain first cluster belongs to the high-risk area, calculate the number of the two-dimensional coordinate points included in the first cluster and the convex hull area of the first cluster, and then calculate the density of the two-dimensional coordinate points in the first cluster.

[0009] Preferably, the step of "sending a first warning message according to the density of the two-dimensional coordinate points" includes: If the convex polygon corresponding to a certain first cluster belongs to the high-risk area and the density of the two-dimensional coordinate points in the first cluster is greater than a preset first density, send a first warning message; If the density of the two-dimensional coordinate points in a certain second cluster is greater than a preset second density, send the first warning message; Wherein, the preset first density is less than the preset second density.

[0010] Preferably, the method further includes: Calculating one or more target points that a tourist can reach within a preset time period according to the current moving direction and moving speed of each tourist, in combination with the road distribution in the park; Using the DBSCAN algorithm to cluster the target points of all tourists to obtain one or more third clusters; Calculating the density of the two-dimensional coordinate points in each of the third clusters, and sending a second warning message according to the calculation result.

[0011] Preferably, the sending of the first warning message includes: Notifying the tourists in the first designated area through the park broadcast to slow down or stop moving; Notifying the management personnel to arrive at the first designated area; The sending of the second warning message includes: Notifying the management personnel to pay attention to or restrict the flow of people in the second designated area; Wherein, The first designated area is the park area corresponding to the first cluster or the second cluster that triggers the first warning message; The second designated area is the park area corresponding to the third cluster that triggers the second warning message.

[0012] Preferably, the method further includes: Drawing a crowd density distribution map in the park according to the density of the two-dimensional coordinate points in each cluster, and using different colors in the distribution map to represent the levels of crowd density; Sending the crowd density distribution map to the mobile terminal.

[0013] Preferably, the step of "using the DBSCAN algorithm to cluster all the two-dimensional coordinate points to obtain several clusters" includes: Clustering all the two-dimensional coordinate points using the DBSCAN algorithm according to a preset neighborhood radius and a preset first minimum number of samples to obtain one or more first clusters; The step of "calculating the density of the two-dimensional coordinate points in each cluster" includes: Calculating the number of the two-dimensional coordinate points included in each of the first clusters respectively, and the convex hull area of each of the first clusters, and then calculating the density of the two-dimensional coordinate points in each of the first clusters; The step of "sending the first warning message according to the density of the two-dimensional coordinate points" includes: Judging whether the density of the two-dimensional coordinate points in each of the first clusters is greater than a preset value, and if so, sending the first warning message.

[0014] In a second aspect of the present invention, a crowd density control system for a smart park is proposed. The system includes: A number of UWB positioning tags for tourists to wear; A number of UWB base stations for detecting the coordinates of the UWB positioning tags and uploading them to the central server; The central server for executing the computer program of the method described above.

[0015] In a third aspect of the present invention, a computer-readable storage device is proposed, which stores a computer program that can be loaded and executed by a processor for the method described above.

[0016] The present invention has the following beneficial effects: The crowd density control method for a smart park proposed by the present invention first uses UWB positioning technology to track the two-dimensional coordinate points of each tourist, and then judges the degree of crowd gathering based on these two-dimensional coordinate points. Because UWB positioning technology has strong penetration ability and can penetrate many media such as brick walls, glass, wooden boards, and leaves, it solves the occlusion problem that cannot be overcome in the prior art when using camera devices and infrared induction devices for crowd detection, and effectively improves the accuracy of crowd density detection. In addition, compared with identifying human figures and counting from images, using UWB positioning and counting will greatly reduce the amount of computation.

[0017] The convex polygon area corresponding to the first cluster obtained by clustering is divided into a high-risk area or a low-risk area; for the low-risk area, in order to prevent unnecessary warnings from being triggered, clustering is performed again to obtain a second cluster, and it is judged according to the density of the two-dimensional coordinate points in the second cluster to determine whether to send the first warning information; for the high-risk area, it is directly judged according to the density of the two-dimensional coordinate points in the first cluster, and a lower alarm threshold (the preset first density) is selected to more strictly control the crowd density in the high-risk area.

[0018] The present invention also predicts one or more target points that each tourist can reach within a preset time period, clusters all the target points, detects the density of the clusters obtained by clustering, and then sends a second warning information, so that the management personnel can pay attention to the areas where crowd gathering may occur in advance and take some necessary restrictive measures in advance.

[0019] Drawing a crowd density distribution map and sending it to the mobile terminal can allow tourists or administrators to intuitively understand the crowd gathering situation in various parts of the park, thereby avoiding serious gathering risks.

[0020] Therefore, the present invention not only improves the accuracy of crowd density detection, but also can issue more accurate warnings, avoiding both gathering risks such as stampedes and overly sensitive warnings. Description of the Drawings

[0021] Figure 1 It is a schematic diagram of the main steps of the first embodiment of the method for controlling the crowd density in a smart park in the present invention; Figure 2 It is a schematic diagram of the main steps of the second embodiment of the method for controlling the crowd density in a smart park in the present invention; Figure 3 It is a schematic diagram of the main steps of the third embodiment of the method for controlling the crowd density in a smart park in the present invention. Detailed implementation manners

[0022] The preferred implementation manners of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these implementation manners are only used to explain the technical principle of the present invention and are not intended to limit the protection scope of the present invention.

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0024] It should be noted that in the description of the present invention, the terms "first" and "second" are only for the convenience of description and do not indicate or imply the relative importance of the devices, elements, or parameters, and thus should not be construed as limiting the present invention. In addition, the term "and / or" in the present invention is only a description of the associated relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after unless otherwise specified.

[0025] Figure 1 It is a schematic diagram of the main steps of the first embodiment of the method for controlling the crowd density in a smart park in the present invention. As Figure 1 shown, the control method of this embodiment includes steps A10 - A40: Step A10: Use the UWB positioning technology to track the two-dimensional coordinate points where each tourist is currently located.

[0026] Step A20: Use the DBSCAN algorithm to cluster all the two-dimensional coordinate points to obtain several clusters. This step may specifically include steps A21 - A25: Step A21: According to a preset neighborhood radius and a preset first minimum number of samples, use the DBSCAN algorithm to cluster all two-dimensional coordinate points to obtain one or more first clusters.

[0027] In this embodiment, the preset neighborhood radius (Eps) is 1 meter, and the preset first minimum number of samples (MinPts) is 5.

[0028] Step A22: Calculate the convex hull of each first cluster respectively to obtain the corresponding convex polygon.

[0029] The obtained convex polygon contains all the two-dimensional coordinate points in the first cluster and is the convex polygon with the smallest area.

[0030] Step A23: Map all the convex polygons onto the park electronic map, in which several monitoring areas are preset in advance, and the categories of the monitoring areas include: narrow areas and wide areas.

[0031] In this embodiment, the areas prone to crowd gathering are taken as monitoring areas in advance and divided into two categories: narrow areas and wide areas. Narrow areas such as the mountaintop viewing area, narrow sections leading to a certain scenic spot, indoor entertainment venues or exhibition halls, etc., which are areas with small areas and prone to crowd gathering. Wide areas such as the square dance area, outdoor performance viewing area, etc., which are areas with large areas but relatively concentrated crowds.

[0032] Step A24: Determine whether each convex polygon overlaps with a certain monitoring area and the overlapping area exceeds a preset percentage of the total area of the monitoring area; if so, classify the convex polygon according to the category to which the monitoring area belongs; otherwise, classify the convex polygon as a narrow area.

[0033] For example, if a certain convex polygon overlaps with the location of a certain square dance area and the area of the overlapping part exceeds 80% of the square dance area, then classify this convex polygon as a low-risk area.

[0034] Another example, if a certain convex polygon overlaps with the location of a certain exhibition hall and the area of the overlapping part exceeds 80% of the area of the exhibition hall, then classify this convex polygon as a high-risk area. If the convex polygon is entirely located within the exhibition hall, it means that more than 80% of the area of the exhibition hall has tourists distributed. If a part of the convex polygon is still located outside the exhibition hall, it may be that there are tourists gathering around the exhibition hall, preparing to enter the exhibition hall or just coming out of it. At this time, classify this convex polygon as a high-risk area so as to more strictly control the crowd density in this area in the subsequent steps.

[0035] For a convex polygon that does not overlap with any monitored area or whose overlapping area does not reach 80%, it may be a crowd gathering caused by an unexpected event. At this time, this convex polygon is also regarded as a high-risk area so as to attract attention in the subsequent steps and then strictly control the crowd density in this area.

[0036] Step A25: For each convex polygon whose category is a low-risk area, according to the preset neighborhood radius and the preset second minimum sample number, use the DBSCAN algorithm to cluster the two-dimensional coordinate points included in this convex polygon to obtain one or more second clusters.

[0037] When performing the first clustering in step A21, considering that the narrow area can accommodate fewer tourists within the preset neighborhood radius, the preset first minimum sample number is also set to a relatively small value so that the program can detect in a timely manner the narrow areas where there may be a risk of gathering. For example, if there are 5 people on a 2-meter-long narrow path, attention needs to be paid. At this time, in the DBSCAN algorithm, the neighborhood radius needs to be set to 1 meter and the minimum sample number to 5 to divide these 5 coordinate points into the first cluster.

[0038] However, for a wide area, it is actually relatively loose to accommodate 5 people within a circular area with a radius of 1 meter. If the density of the two-dimensional coordinate points in the first cluster is calculated, it may be found that there is no need to send the first warning message at all, and in this way, the possible local gathering phenomenon in this area will be missed. Therefore, in this embodiment, a second clustering is performed on the convex polygons whose category is a wide area to detect the possible local areas with a risk of gathering, and the preset second minimum sample number takes a larger value, such as 10.

[0039] Step A30: Calculate the density of the two-dimensional coordinate points in each cluster. This step may specifically include steps A31 - A32: Step A31: If the convex polygon corresponding to a certain first cluster belongs to a low-risk area, calculate the number of two-dimensional coordinate points included in each corresponding second cluster and the convex hull area of each second cluster, and then calculate the density of the two-dimensional coordinate points in each second cluster.

[0040] Step A32: If the convex polygon corresponding to a certain first cluster belongs to a high-risk area, calculate the number of two-dimensional coordinate points included in this first cluster and the convex hull area of this first cluster, and then calculate the density of the two-dimensional coordinate points in this first cluster.

[0041] Step A40: Send the first warning message according to the density of the two-dimensional coordinate points. This step may specifically include steps A41 - A42: Step A41: If the category to which the convex polygon corresponding to a first cluster belongs is a high-risk area, and the density of the two-dimensional coordinate points in the first cluster is greater than a preset first density, a first warning message is sent.

[0042] Step A42: If the density of the two-dimensional coordinate points in a second cluster is greater than a preset second density, a first warning message is sent.

[0043] For example, the park broadcasts a notice to the visitors in the first designated area to slow down or stop moving to avoid further gathering of people. At the same time, the management personnel are notified to arrive at the first designated area for guidance or evacuation.

[0044] The first designated area is the park area corresponding to the first cluster or the second cluster that triggers the first warning information. Because high-risk areas are more prone to stampede accidents, in this embodiment, the preset first density is set to be smaller than the preset second density, so as to more strictly control the density of people in high-risk areas.

[0045] Figure 2 Schematic diagram of the main steps of the second embodiment of the method for controlling the density of people in a smart park in the present invention. Figure 2 As shown, the control method of this embodiment includes steps B10-B50: Among them, steps B10-B40 correspond to steps A10-A40 in the above-mentioned embodiment 1, respectively, and are not repeated here.

[0046] Step B50: predict one or more target points that each tourist can reach within a preset time, cluster all the target points, perform density detection on the clusters obtained by clustering, and then send a second warning information.

[0047] Step B50 may specifically include steps B51-B53: Step B51, based on the current moving direction and moving speed of each tourist and the road distribution in the park, calculate one or more target points that the tourist can reach within a preset time.

[0048] For example, tourist A's current moving direction is westward, and the moving speed is 50 meters per minute. If there is only one east-west road at tourist A's current location, it can be predicted that tourist A will move 500 meters westward within a preset time (such as 10 minutes), which corresponds to a target point 500 meters westward.

[0049] For example, if tourist B moves at a speed of 40 meters per minute, but there is a fork in the road ahead of tourist B, then there are two possible destinations that tourist B can reach in 10 minutes, and both destinations are 400 meters away from tourist B. The 400 meters here is usually not a straight-line distance, but the distance traveled along the road in the park.

[0050] Step B52: Use the DBSCAN algorithm to cluster the target points of all tourists to obtain one or more third clusters.

[0051] Step B53: Calculate the density of the two-dimensional coordinate points in each third cluster and send a second warning message according to the calculation results.

[0052] Through this prediction method, it is possible to know in advance which scenic spots may have a crowd gathering. At this time, the management personnel can timely monitor the flow direction of the crowd through video surveillance and other means and impose restrictions when necessary.

[0053] In this embodiment, sending the second warning message includes: notifying the management personnel to pay attention to or restrict the flow of people in the second designated area.

[0054] Among them, the second designated area is the park area corresponding to the third cluster that triggers the second warning message.

[0055] Figure 3 It is a schematic diagram of the main steps of the third embodiment of the method for controlling the flow density of people in a smart park in the present invention. As Figure 3 shown, the control method of this embodiment includes steps C10 - C70: Among them, steps C10 - C50 respectively correspond to steps B10 - B50 in the second embodiment above and will not be elaborated here.

[0056] Step C60: Draw a flow density distribution map of the park according to the density of the two-dimensional coordinate points in each cluster, and use different colors in the distribution map to represent the levels of the flow density.

[0057] In the previous steps, the density of the two-dimensional coordinate points was calculated for some first clusters (the corresponding convex polygon areas are high-risk areas), and the density of the two-dimensional coordinate points in some second clusters was also calculated. These are all areas considered to have potential gathering risks after clustering. Since each tourist wears a UWB tag, the calculated density of the two-dimensional coordinate points is the flow density. The flow density is classified according to the level of high and low, and is displayed in the corresponding areas on the map with different colors. For example, if the convex polygon area corresponding to a certain cluster is currently a high-density area, it is displayed in red, and if the convex polygon area corresponding to another cluster is currently a medium-density area, it is displayed in yellow. For the convex polygon area corresponding to the predicted third cluster, it can be displayed in a lighter yellow. In addition, for the remaining areas where the corresponding density has not been calculated, the original color is maintained, indicating that there is no crowd gathering.

[0058] Step C70: Send the flow density distribution map to the mobile terminal for tourists or administrators to view at any time.

[0059] In an alternative embodiment, if the terrain in the park is relatively simple and flat, the control method of steps D10 - D40 can be adopted as follows: Step D10: Use UWB positioning technology to track the two-dimensional coordinate points where each tourist is currently located.

[0060] Step D20: According to the preset neighborhood radius and the preset first minimum sample number, use the DBSCAN algorithm to cluster all the two-dimensional coordinate points to obtain one or more first clusters.

[0061] Step D30: Calculate the number of two-dimensional coordinate points included in each first cluster and the convex hull area of each first cluster respectively, and then calculate the density of the two-dimensional coordinate points in each first cluster.

[0062] Step D40: Determine whether the density of the two-dimensional coordinate points in each first cluster is greater than the preset value. If so, send a first warning message.

[0063] Although the above steps are described in the above order in the above several embodiments, those skilled in the art can understand that in order to achieve the effects of this embodiment, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in a reversed order, and these simple changes are all within the protection scope of the present invention.

[0064] Furthermore, based on the above method embodiments, the present invention also provides an embodiment of a crowd density control system for a smart park. The control system of this embodiment includes: a plurality of UWB positioning tags, a plurality of UWB base stations, and a central server.

[0065] Among them, the UWB positioning tags are for tourists to wear; the UWB base stations are for detecting the coordinates of the UWB positioning tags and uploading them to the central server; the central server is for executing the computer program of the method as described above.

[0066] Even further, the present invention also provides an embodiment of a computer-readable storage device. The computer program capable of being loaded and executed by a processor as described above is stored in the storage device of this embodiment.

[0067] The computer-readable storage device may include: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0068] Those skilled in the art should be able to realize that the method steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in the form of electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered as exceeding the scope of the present invention.

[0069] So far, the technical solution of the present invention has been described in combination with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

Claims

1. A method for controlling crowd density in a smart park, characterized in that: The method comprises: Use UWB positioning technology to track the current two-dimensional coordinate point of each tourist; Using the DBSCAN algorithm to cluster all the two-dimensional coordinate points to obtain a number of clusters; Calculating the density of the two-dimensional coordinate points in each cluster; The first warning information is sent according to the density of the two-dimensional coordinate points.

2. The method for controlling the flow density of people in a smart park according to claim 1, characterized in that: The step of "using the DBSCAN algorithm to cluster all the two-dimensional coordinate points to obtain a plurality of clusters" includes: According to a preset neighborhood radius and a preset first minimum number of samples, a DBSCAN algorithm is used to cluster all of the two-dimensional coordinate points to obtain one or more first clusters; Calculate the convex hull of each of the first clusters respectively to obtain the corresponding convex polygon; Mapping all the convex polygons onto an electronic map of the park; a plurality of monitoring areas are pre-set in the electronic map of the park, and the categories of the monitoring areas include: narrow areas and wide areas; Determine whether each of the convex polygons overlaps with a certain monitoring area, and whether the overlapping area exceeds a preset percentage of the total area of ​​the monitoring area; if so, classify the convex polygon into a high-risk area or a low-risk area according to the category to which the monitoring area belongs; otherwise, classify the convex polygon into the high-risk area; For each convex polygon belonging to the low-risk area, the two-dimensional coordinate points contained in the convex polygon are clustered using the DBSCAN algorithm according to the preset neighborhood radius and the preset second minimum number of samples to obtain one or more second clusters.

3. The crowd density control method for a smart park according to claim 2 is characterized in that: The step of "calculating the density of the two-dimensional coordinate points in each cluster" includes: If the category to which the convex polygon corresponding to a certain first cluster belongs is the low-risk area, then the number of the two-dimensional coordinate points contained in each corresponding second cluster and the convex hull area of ​​each second cluster are calculated, and then the density of the two-dimensional coordinate points in each second cluster is calculated; If the convex polygon corresponding to a certain first cluster belongs to the high-risk area, the number of the two-dimensional coordinate points contained in the first cluster and the convex hull area of ​​the first cluster are calculated, and then the density of the two-dimensional coordinate points in the first cluster is calculated.

4. The method for controlling the flow density of people in a smart park according to claim 3, characterized in that: The step of "sending the first warning information according to the density of the two-dimensional coordinate points" includes: If the category to which the convex polygon corresponding to a certain first cluster belongs is the high-risk area, and the density of the two-dimensional coordinate points in the first cluster is greater than a preset first density, sending a first warning message; If the density of the two-dimensional coordinate points in a certain second cluster is greater than a preset second density, sending the first warning information; The preset first density is smaller than the preset second density.

5. The method for controlling the flow density of people in a smart park according to claim 4, characterized in that: The method further comprises: According to the current moving direction and moving speed of each tourist, combined with the road distribution in the park, calculate one or more target points that the tourist can reach within a preset time; Clustering the target points of all tourists using the DBSCAN algorithm to obtain one or more third clusters; The density of the two-dimensional coordinate points in each of the third clusters is calculated, and the second warning information is sent according to the calculation result.

6. The method for controlling the flow density of people in a smart park according to claim 5, characterized in that: The sending of the first warning information comprises: Notify visitors in the first designated area via park broadcasts to slow or stop movement; Notify the management personnel to arrive at the first designated area; The sending of the second warning information comprises: Notify management to monitor or limit the flow of people in the second designated area; in, The first designated area is a park area corresponding to the first cluster or the second cluster that triggers the first warning information; The second designated area is a park area corresponding to the third cluster that triggers the second warning information.

7. The method for controlling the flow density of people in a smart park according to claim 6, characterized in that: The method further comprises: Draw a crowd density distribution map in the park according to the density of the two-dimensional coordinate points in each cluster, wherein different colors are used to represent the level of crowd density in the distribution map; The crowd density distribution map is sent to a mobile terminal.

8. The method for controlling the flow density of people in a smart park according to claim 1, characterized in that: The step of "using the DBSCAN algorithm to cluster all the two-dimensional coordinate points to obtain a plurality of clusters" includes: According to a preset neighborhood radius and a preset first minimum number of samples, a DBSCAN algorithm is used to cluster all of the two-dimensional coordinate points to obtain one or more first clusters; The step of "calculating the density of the two-dimensional coordinate points in each cluster" includes: Calculating the number of the two-dimensional coordinate points contained in each of the first clusters and the convex hull area of ​​each of the first clusters, and then calculating the density of the two-dimensional coordinate points in each of the first clusters; The step of "sending the first warning information according to the density of the two-dimensional coordinate points" includes: It is determined whether the density of the two-dimensional coordinate points in each of the first clusters is greater than a preset value, and if so, the first warning information is sent.

9. A crowd density control system for a smart park, characterized in that: The system comprises: Several UWB positioning tags for tourists to wear; Several UWB base stations, used to detect the coordinates of the UWB positioning tags and upload them to a central server; The central server is a computer program for executing the method according to any one of claims 1-8.

10. A computer-readable storage device, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 8.

Images