Target site personnel flow determination method and device and computer storage medium

Abstract

The embodiment of the application discloses a kind of target place personnel flow determination method, device and computer storage medium;Determination method includes: determining the effective area corresponding to target place;According to the image data in the effective area corresponding to the target place, the trajectory information of personnel in the effective area in the preset time period is obtained;According to the trajectory information of personnel in the effective area in the preset time period, the number of times of personnel entering the target place in the preset time period is determined.This embodiment of the application can determine the target place personnel flow without installing other equipment in the target place, which saves cost.

Description

Technical Field

[0001] This application relates to the field of computer applications, and in particular to a method, apparatus, and computer storage medium for determining the flow of people in a target location. Background Technology

[0002] Currently, some venues use motion sensor modules to count pedestrian traffic, while others use cameras at entrances to capture images. However, both methods require the installation of motion sensor modules or cameras in the areas where pedestrian traffic needs to be measured, increasing the cost of hardware purchases and subsequent maintenance. Summary of the Invention

[0003] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.

[0004] This application provides a method, apparatus, and computer storage medium for determining the flow of people at a target location. The flow of people at the target location can be determined without the need to install other equipment, thus saving costs.

[0005] This application provides a method for determining the flow of people in a target location, including:

[0006] Determine the effective area corresponding to the target location;

[0007] Based on the image data collected in the effective area corresponding to the target location, the trajectory information of the people in the effective area within a preset time period is obtained;

[0008] Based on the trajectory information of people in the effective area within the preset time period, determine the number of times people enter the target location within the preset time period.

[0009] Optionally, determining the number of times a person enters the target location within the preset time period based on the trajectory information of people in the effective area within the preset time period includes:

[0010] For each person located in the effective area within the preset time period, the following processing is performed: the person's trajectory information is matched with a specific image acquisition device. If the match is successful, the number of times the person enters the target location within the preset time period is adjusted according to the location of the specific image acquisition device and the acquisition time of the person's image.

[0011] The specific image acquisition device is predetermined based on road network information and is located on the necessary path to the target location, and there are no other image acquisition devices between the specific image acquisition device and the target location on this necessary path.

[0012] Optionally, adjusting the number of people entering the target location within the preset time period based on the location of the successfully matched specific image acquisition device and the time when the person's image was acquired includes:

[0013] Based on the location of the specific image acquisition device that was successfully matched, the theoretical passage time for the person is determined;

[0014] The actual passage time of the person is determined by the difference between the acquisition times of two consecutive images of the person captured by the matched specific image acquisition device.

[0015] Calculate the time difference between the actual passage time and the theoretical passage time. When the time difference is within a preset range, increase the number of people entering the target location within the preset time period.

[0016] Optionally, there are two successfully matched specific image acquisition devices, distributed on different sides of the target location; there is only one path between the two successfully matched specific image acquisition devices, and the target location is located on this path;

[0017] The step of determining the theoretical travel time of a person based on the location of the matched specific image acquisition device includes: dividing the length of the path between the two matched specific image acquisition devices by the speed obtained based on the person's trajectory information to obtain the theoretical travel time;

[0018] The step of increasing the number of people entering the target location within the preset time period includes: increasing the number of people entering the target location within the preset time period by 1.

[0019] Optionally, there are two successfully matched specific image acquisition devices, distributed on different sides of the target location; there are multiple paths between the two successfully matched specific image acquisition devices, and the target location is located on at least one of these paths;

[0020] The step of determining the theoretical travel time of a person based on the location of a successfully matched specific image acquisition device includes: dividing the length of each path between two successfully matched specific image acquisition devices by the speed obtained based on the person's trajectory information to obtain the theoretical travel time of each path;

[0021] The step of calculating the time difference between the actual travel time and the theoretical travel time, and increasing the number of people entering the target location within the preset time period when the time difference is within a preset range, includes:

[0022] Remove theoretical travel times that are longer than the actual travel time, and calculate the time difference between the actual travel time and the remaining theoretical travel times.

[0023] Determine the minimum value among the calculated time differences, and subtract the minimum value from the time differences other than the minimum value to obtain the time differences between n paths. Record the number x of the path time differences within the preset interval.

[0024] If at least one of the calculated time differences falls within the preset interval, then the number of people entering the target location within the preset time period will be increased.

[0025] Optionally, only one specific image acquisition device is successfully matched;

[0026] The step of determining the theoretical travel time of a person based on the location of a successfully matched specific image acquisition device includes: dividing twice the length of the path between the successfully matched specific image acquisition device and the target location by the speed obtained based on the person's trajectory information to obtain the travel time;

[0027] The step of increasing the number of people entering the target location within the preset time period includes: increasing the number of people entering the target location within the preset time period by 1.

[0028] Optionally, obtaining the trajectory information of people in the effective area within a preset time period based on image data collected in the effective area corresponding to the target location includes:

[0029] Based on the image data collected in the effective area corresponding to the target location, personnel are grouped and filed; based on the grouping and filing results, the trajectory information of different personnel in the effective area within the preset time period is obtained.

[0030] Optionally, the determination of the effective area corresponding to the target location includes:

[0031] If there is only one target location within the preset geographical range, then the preset geographical range shall be regarded as the effective area corresponding to that target location.

[0032] If there are multiple target locations within a preset geographical area, then the location of each target location is taken as a discrete point, and a Veno map is generated within the preset geographical area. The area corresponding to each polygon in the Veno map is taken as the effective area corresponding to the target location contained in that polygon.

[0033] This application embodiment also provides a device for determining the flow of people in a target location, including: a memory and a processor;

[0034] The memory is used to store the program for determining the flow of people at the target location;

[0035] The processor is configured to read and execute the program for determining the flow of people in the target location, and execute the aforementioned method for determining the flow of people in the target location.

[0036] This application embodiment also provides a computer storage medium for storing a program for determining the flow of people in a target location; when the program for determining the flow of people in a target location is read and executed, the above-described method for determining the flow of people in a target location is performed.

[0037] This application embodiment can obtain the trajectory information of people by collecting image data in the effective area corresponding to the target location. Then, based on the trajectory information, the number of times people enter the target location within a preset time period can be determined. There is no need to install cameras or human body sensing devices in the target location. The existing image acquisition equipment in the effective area can be used to complete the statistics of the flow of people in the target location, saving costs.

[0038] After reading and understanding the accompanying diagrams and detailed descriptions, the other aspects can be understood. Attached Figure Description

[0039] The accompanying drawings are used to provide an understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0040] Figure 1 This is a flowchart illustrating a method for determining the flow of people at a target location according to an embodiment of this application.

[0041] Figure 2a This is one of the schematic diagrams showing only one path in two specific image acquisition devices in the embodiments of this application;

[0042] Figure 2b This is the second schematic diagram of two specific image acquisition devices with only one path in the embodiments of this application;

[0043] Figure 3 This is a schematic diagram showing multiple paths in two specific image acquisition devices in the embodiments of this application;

[0044] Figure 4 This is a schematic diagram showing only one specific image acquisition device in an embodiment of this application;

[0045] Figure 5 This is a schematic diagram showing that there are specific image acquisition devices in multiple directions at the target location in the embodiments of this application;

[0046] Figure 6 A schematic diagram of a device for determining the flow of people at a target location provided in an embodiment of this application;

[0047] Figure 7 The flowchart in Example 1 shows how to determine the flow of people in public restrooms with and without cameras at the entrance in different ways.

[0048] Figure 8a This is one of the schematic diagrams illustrating the division of the effective region in Example 2;

[0049] Figure 8b This is the second schematic diagram illustrating the division of the effective region in Example 2;

[0050] Figure 8c This is the third illustration of the effective region division in Example 2;

[0051] Figure 9 This is a flowchart for determining the flow of people in multiple public toilets in Example 2. Detailed Implementation

[0052] The embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments of this application and the features therein can be arbitrarily combined with each other.

[0053] The steps illustrated in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases the steps shown or described may be performed in a different order than that presented here.

[0054] This application provides a method for determining the flow of people in a target location, such as... Figure 1 As shown, steps S110-S130 are included:

[0055] S110. Determine the effective area corresponding to the target location;

[0056] S120. Based on the image data collected in the effective area corresponding to the target location, obtain the trajectory information of people in the effective area within a preset time period;

[0057] S130. Based on the trajectory information of people in the effective area within the preset time period, determine the number of times people enter the target location within the preset time period.

[0058] In this embodiment, by collecting image data in the effective area corresponding to the target location, the trajectory information of people can be obtained, and then the number of times people enter the target location within a preset time period can be determined based on the trajectory information. This embodiment does not require the installation of cameras or human body sensing devices in the target location. The existing image acquisition equipment in the effective area can be used to complete the statistics of the flow of people in the target location, saving costs.

[0059] In this embodiment, dividing the determined number of people by the length of a preset time period yields the number of people entering the target location per unit time, i.e., the personnel flow, or personnel density. After determining the effective area of ​​the target location, steps S120 and S130 can be performed multiple times; for example, steps S120 and S130 can be performed periodically, with each period as a preset time period, to obtain the number of people entering the target location in each period, thereby providing a data basis for further decision-making based on personnel flow.

[0060] In this embodiment, the collected image data may include photos or images taken by a camera or similar device, and / or videos taken by a camera or similar device; the target location may be a place where the flow of people to be monitored is located, or a specific type of place, such as but not limited to public toilets; the start and end times, duration, etc. of the preset time period can be set as needed.

[0061] In one exemplary embodiment, step S110 may include:

[0062] If there is only one target location within the preset geographical range, then the preset geographical range will be used as the effective area corresponding to that target location.

[0063] If there are multiple target locations within a preset geographical area, the location of each target location is used as a discrete point to generate a Veno map within the preset geographical area. The area corresponding to each polygon in the Veno map is then taken as the effective area corresponding to the target location contained in that polygon.

[0064] This embodiment is applicable to situations where each target location has a clear location within a preset geographical range. It can divide the target locations within the preset geographical range into effective areas. If there are M target locations in this area, then this area will be divided into M effective areas, each corresponding to one of the M target locations.

[0065] In this embodiment, the Veno diagram can also be called a Thiessen polygon. Any position in a polygon is closer to a discrete point in the same polygon than to any other discrete point. Any position on an edge of a polygon is equidistant from the discrete points on either side of that edge.

[0066] In other embodiments, the effective area corresponding to the target location can be determined in other ways, such as taking the target location as the center and using a circular area with a set radius as the effective area; or by directly specifying the vertex coordinates of a rectangular area to set the effective area; this application does not limit the specific method of determining the effective area.

[0067] In one exemplary embodiment, step S120 may include:

[0068] Based on the image data collected in the effective area corresponding to the target location, personnel are grouped and filed; based on the grouping and filing results, the trajectory information of different personnel in the effective area within the preset time period is obtained.

[0069] In this embodiment, the purpose of file aggregation is to perform a deduplication operation on personnel, thereby increasing the accuracy of image data.

[0070] In this embodiment, there are two ways to aggregate and file personnel: one is to aggregate and file personnel in multiple effective areas together based on the image data collected by the image acquisition devices in multiple effective areas, and then obtain the aggregation and filing results for each effective area based on the overall aggregation and filing results; the other is to aggregate and file the image data collected by the image acquisition devices in each effective area independently.

[0071] In one exemplary embodiment, step S130 may include:

[0072] For each person located in the effective area within the preset time period, the following processing is performed: the person's trajectory information is matched with a specific image acquisition device. If the match is successful, the number of times the person enters the target location within the preset time period is adjusted according to the location of the specific image acquisition device and the acquisition time of the person's image.

[0073] The specific image acquisition device is predetermined based on road network information and is located on the necessary path to the target location, and there are no other image acquisition devices between the specific image acquisition device and the target location on the necessary path.

[0074] In this embodiment, the specific image acquisition device refers to a camera, etc., located near the target location. These devices are positioned along the necessary paths for personnel entering and exiting the target location. If personnel have entered the target location, they will inevitably pass by at least one specific image acquisition device. The specific image acquisition device can be predetermined through, but is not limited to, manual designation. In other embodiments, the specific image acquisition device can be defined as needed; for example, it can be an image acquisition device located less than a preset distance threshold from the target location.

[0075] In this embodiment, for a specific image acquisition device that has been successfully matched, it can be further judged based on its location and the time when the image of the person was acquired. Based on the judgment result, it can be decided how many times to increase the number of people or decide not to change the number of people.

[0076] In this embodiment, if a person's trajectory information is successfully matched with a specific image acquisition device, it means that the person's trajectory has reached the location of the matched specific image acquisition device, and therefore, the person has a certain probability of having entered the target location. In this embodiment, the trajectory information only indicates which image acquisition devices captured the person's image at what time. Since there are no image acquisition devices at the entrance of the target location, the trajectory information alone cannot definitively determine whether the person has entered the target location. Matching the trajectory information with specific image acquisition devices can filter out people who may have entered the target location, and it allows for the selection of specific image acquisition devices from multiple devices for subsequent judgment; for example... Figure 5 In the scenario shown, there are three specific image acquisition devices, A, B, and D. For example, if a person walks from A to D, then by matching the person's trajectory information, A and D can be selected from A, B, and D for subsequent judgment.

[0077] In this embodiment, if a person's trajectory information fails to match a specific image acquisition device, it means that the person has not been to the vicinity of the target location within the preset time period, and therefore it is even less likely that the person has entered the target location. Therefore, there is no need to adjust the number of times the person enters the target location within the preset time period.

[0078] In one optional embodiment, there are two specific image acquisition devices, located on opposite sides of the target location along the path. In this case, there may be only one path between the two specific image acquisition devices A and B, for example, but not limited to... Figure 2a and Figure 2b The scenario is as follows: Target location C is located on the path from A to B. There are no other image acquisition devices on path AC from specific image acquisition device A to target location C, meaning that specific image acquisition device A is closest to target location C on AC. Similarly, there are no other image acquisition devices on path BC from specific image acquisition device B to target location C, meaning that specific image acquisition device B is closest to target location C on BC. Multiple paths can exist between two specific image acquisition devices A and B, such as, but not limited to, [other paths]. Figure 3 As shown, the target location C is located on at least one of the multiple paths.

[0079] In another optional scenario of this embodiment, if the target location C has an image acquisition device D on only one side, and there are no other image acquisition devices on the path DC from image acquisition device D to C, then the image acquisition device D is determined to be a specific image acquisition device, such as, but not limited to, [other examples]. Figure 4 The situation is shown below.

[0080] In another embodiment, the target location C is located at the intersection of multiple paths, such as, but not limited to, Figure 5As shown, the image acquisition devices A, B, and D closest to the target location C on these multiple paths AC, BC, and DC can be identified as specific image acquisition devices. If the trajectory information of a person matches the specific image acquisition devices A and D, it means that the person is moving from the location of specific image acquisition device A to specific image acquisition device D, passing through the target location C. If the trajectory information of a person matches the specific image acquisition devices B and A, it means that the person is moving from the location of specific image acquisition device B to specific image acquisition device A, passing through the target location C. Other cases can be deduced similarly, and will not be elaborated here.

[0081] In this embodiment, the trajectory information of a person may include a sequence of acquisition parameters corresponding to that person. The acquisition parameters include the acquisition time when the image data of the person was acquired and the identifier of the image acquisition device performing the acquisition. The acquisition parameters are ordered in the sequence according to the acquisition time. For example, in one instance, the sequence of acquisition parameters included in the trajectory information of person A consists of the following seven acquisition parameters: (14:18:35, A), (14:21:56, B), (14:25:07, D), (14:28:22, E), (14:32:11, F), (14:35:18, A), and (14:39:03, G). This sequence indicates that person A's trajectory passes through image acquisition devices A, B, D, E, F, A, and G sequentially from 14:18:35 to 14:39:03.

[0082] In one embodiment of this invention, matching a person's trajectory information with a specific image acquisition device may include: matching a sequence of acquisition parameters with the specific image acquisition device. A successful match means that the sequence of acquisition parameters contains two adjacent acquisition parameters that include the identifier of the specific image acquisition device; that is, if the trajectory information indicates that the person has passed through two specific image acquisition devices consecutively, or passed through one specific image acquisition device twice consecutively, then the match is successful. For example, if the identifiers of the specific image acquisition devices are A and B, in the sequence of acquisition parameters for person A, the first parameter (14:18:35, A) and the second parameter (14:21:56, B) each contain the identifier of a specific image acquisition device and are adjacent in the sequence. Therefore, these two acquisition parameters are successfully matched, which means that person A has passed through specific image acquisition devices A and B sequentially, and there is a certain possibility that they entered the target location C during this period. Although sequence number 6 (14:35:18, A) also contains the identifier of a specific image acquisition device, the adjacent acquisition parameters (14:32:11, F) and (14:39:03, G) do not contain the identifier of a specific image acquisition device. This means that person A only passed by image acquisition device A but did not move towards the target location. Therefore, sequence number 6 did not match successfully. For example, in person B's sequence, the identifiers of the image acquisition devices in two adjacent acquisition parameters are both the identifier of a specific image acquisition device, A. This means that person B passed by specific image acquisition device A, went to a certain location, and then returned, and there is a possibility that they entered the target location C.

[0083] The following are examples of unsuccessful matching: (1) There are no acquisition parameters containing the identifier of a specific image acquisition device. For example, if the identifier of a specific image acquisition device is H and I, and no acquisition parameter in Person A's sequence contains H or I, this means that Person A did not pass by any image acquisition device near the target location within the preset time period, and therefore must not have entered the target location. (2) Although there are acquisition parameters containing the identifier of a specific image acquisition device in the sequence, these acquisition parameters exist in isolation in the sequence, and the adjacent acquisition parameters do not contain the identifier of the specific image acquisition device. For example, if the identifier of a specific image acquisition device is D and G, and although the 3rd and 7th acquisition parameters in Person A's sequence contain D and G respectively, these two acquisition parameters exist in isolation. This means that after Person A passes by image acquisition device D, they did not move towards the target location, but passed by other image acquisition devices before reaching image acquisition device G, and therefore did not enter the target location.

[0084] In this embodiment, after a successful match, the number of people entering the target location within a preset time period can be adjusted based on the location of the specific image acquisition device and the acquisition time in the matched acquisition parameters. For example, if the acquisition parameters (14:20:35,A) and (14:21:56,B) in the trajectory information of person A are successfully matched, further judgment is made based on the location of the specific image acquisition devices A and B, as well as the acquisition times of 14:20:35 and 14:21:56, to determine how many more people to enter or whether to keep the number of people unchanged.

[0085] In other embodiments of this example, other methods can be used to match trajectory information with specific image acquisition devices. For example, the trajectory information that indicates the person's route can be determined based on the positions of the image acquisition devices that the person passes through in sequence. If the person's route coincides with the path between two specific image acquisition devices, it indicates that the person may have entered the target location, and the person's trajectory information is successfully matched with the specific image acquisition devices on the covered path.

[0086] In one embodiment of this invention, adjusting the number of people entering the target location within a preset time period based on the location of the successfully matched specific image acquisition device and the time when the person's image was acquired may include:

[0087] Based on the location of the specific image acquisition device that was successfully matched, the theoretical passage time for the person is determined;

[0088] The actual passage time of the person is determined based on the capture time of two consecutive images captured by the matched specific image acquisition device;

[0089] Calculate the time difference between the actual travel time and the theoretical travel time. When the time difference is within a preset range, increase the number of people entering the target location within the preset time period.

[0090] In this embodiment, the length of the path traveled by a person can be determined based on the location of a specific image acquisition device. The person's travel speed can be calculated based on their trajectory information. The theoretical travel time can be obtained from the travel distance and speed. The acquisition time is the actual time when the person's image is captured. The actual travel time can be obtained from the difference between two consecutive acquisition times. The time difference between the actual travel time and the theoretical travel time represents the extra time actually spent, which can be considered as the person's dwell time on the path. By comparing this dwell time with a preset interval, it can be determined whether the dwell time is the time spent by the person entering the target location.

[0091] In this embodiment, the preset interval can be obtained in any of the following ways:

[0092] One approach is to obtain the information based on the person's historical image data. For example, if the person has previously been photographed by cameras at the entrance of other similar target locations, the historical duration of the person's single stay at the same type of target location can be obtained based on the time difference between the person's entry and exit from the target location. A preset interval can be determined based on the time intervals of the multiple historical durations obtained. Alternatively, a preset interval can be obtained by adjusting the value of one or more historical durations by a predetermined percentage.

[0093] Another approach is to statistically analyze the length of time people with the same age, height, and gender spend in the same type of target location on a single visit, thus obtaining a preset range.

[0094] The methods for obtaining the preset interval are not limited to the two methods mentioned above, and this application does not restrict the methods for obtaining the preset interval.

[0095] In this embodiment, the stay time is within a preset range, which means that the possibility of people entering the target location is very high. Therefore, the number of people entering the target location within the preset time period can be increased accordingly.

[0096] In one optional embodiment, two specific image acquisition devices are successfully matched and distributed on different sides of the target location; there is only one path between the two successfully matched specific image acquisition devices, and the target location is located on this path, such as, but not limited to, [other paths]. Figure 2a or Figure 2b The situation shown, or Figure 5 Any two specific image acquisition devices in the situation shown;

[0097] In this optional scheme, determining the person's theoretical travel time based on the location of the successfully matched specific image acquisition devices includes: dividing the length of the path between the two successfully matched specific image acquisition devices by the speed v obtained based on the person's trajectory information to obtain the theoretical travel time; for example... Figure 2a If the path length from a specific image acquisition device A to B is s, then the theoretical travel time is s / v;

[0098] Increasing the number of people entering the target location within a preset time period includes: increasing the number of people entering the target location within the preset time period by 1.

[0099] In another optional embodiment, two specific image acquisition devices are successfully matched and distributed on different sides of the target location; there are multiple paths between the two successfully matched specific image acquisition devices, and the target location is located on at least one of these paths, such as, but not limited to, [paths to, but not limited to, the paths provided]. Figure 3 The situation shown;

[0100] Based on the location of the successfully matched specific image acquisition devices, the theoretical travel time for the person is determined by dividing the length of each path between the two successfully matched specific image acquisition devices by the speed obtained from the person's trajectory information; for example... Figure 3 In the case shown, the theoretical travel time of each of the three paths is obtained by dividing the lengths s1, s2, and s3 of the three paths by the speed v.

[0101] Calculate the time difference between the actual travel time and the theoretical travel time. When the time difference is within a preset range, increase the number of people entering the target location within the preset time period, including:

[0102] Remove theoretical travel times that are greater than the actual travel time, and calculate the time difference between the actual travel time and the remaining theoretical travel times; for example, assuming that s1 / v, s2 / v, and s3 / v are all no greater than the actual travel time, then three time differences can be obtained;

[0103] Determine the minimum value among the calculated time differences, and subtract the minimum value from the time differences other than the minimum value to obtain the time differences between n paths. Record the number x of the path time differences within the preset interval.

[0104] If at least one of the calculated time differences falls within the preset interval, then the number of people entering the target location within the preset time period will be increased.

[0105] In this optional solution, since the time difference between routes may be calculated as the time spent at the target location, the probability of this error needs to be eliminated. The error rate is the proportion of the number of errors x to the number of route time checks n. Therefore, when at least one time difference is within the preset interval, the number of personnel is not increased by 1, but rather increased by [missing information].

[0106] In this optional scheme, if there is only one theoretical travel time that is not greater than the actual travel time, then there will be only one calculated time difference. In this case, the time difference between paths can be discontinued, and it can be directly determined whether the time difference is within the preset range. If it is, the number of people will be increased by 1.

[0107] In another alternative embodiment, the specific image acquisition device that is successfully matched is one, such as, but not limited to, [other devices]. Figure 4 As shown in the diagram; based on the location of the successfully matched specific image acquisition device, the theoretical travel time for the person is determined by dividing twice the length of the path between the successfully matched specific image acquisition device and the target location by the speed v obtained from the person's trajectory information. For example... Figure 4The value is 2s / v;

[0108] Increasing the number of people entering the target location within a preset time period includes: increasing the number of people entering the target location within the preset time period by 1.

[0109] This application also provides a device for determining the flow of people at a target location, such as... Figure 6 As shown, it includes: a memory 61 and a processor 62;

[0110] The memory 61 is used to store the program for determining the flow of people at the target location;

[0111] The processor 62 is used to read and execute a program for determining the flow of people in a target location, and to execute the method for determining the flow of people in a target location in any of the above embodiments.

[0112] This application also provides a computer storage medium for storing a program for determining the flow of people in a target location; when the program for determining the flow of people in a target location is read and executed, it performs the method for determining the flow of people in a target location as described in any of the above embodiments.

[0113] The embodiments of this application are illustrated below with two examples.

[0114] Example 1

[0115] This example provides a method for determining the flow of people in public toilets. It can determine the flow of people in two types of public toilets (those with cameras at the entrance and those without cameras) in an area in different ways.

[0116] The method in this example is as follows: Figure 7 As shown, it includes steps S201-S210.

[0117] S201. Define the preset geographical scope; In this example, each administrative region can be defined as a preset geographical scope.

[0118] S202. Obtain a list of public toilet locations within a preset geographical range.

[0119] S203. Traverse all public toilets and execute step S204 for each public toilet.

[0120] S204. Determine if there is a camera that can directly capture the entrance to the public toilet. If there is, proceed to step S209; otherwise, proceed to step S210.

[0121] S205. For public toilets without cameras that can directly capture the entrance, within a preset geographical range, generate a Venn diagram using the location of each public toilet as a discrete point. Each polygon in the Venn diagram serves as the effective area corresponding to the respective public toilet.

[0122] After performing steps S201-S205, steps S206-S210 can be performed separately within each preset time period. The preset time period can be set according to the monitoring requirements.

[0123] S206. Perform personnel clustering on images collected within a preset time period in the effective area. This step is for deduplication.

[0124] S207. Establish an analysis task for the cameras (i.e., specific image acquisition devices) near each public toilet.

[0125] S208. Obtain the trajectory information of the personnel within a preset time period based on the data aggregation results, and proceed to step S210 based on the trajectory information.

[0126] S209. For public toilets with cameras at the entrance, draw tripwires at the entrance of the public toilet to establish an analysis task for the cameras at the entrance of the public toilet, and proceed to step S210.

[0127] S210. Determine the number of people entering each public restroom within a preset time period. For public restrooms with cameras at the entrance, the number of people can be determined based on the images captured at the entrance. For public restrooms without cameras at the entrance, the location of cameras near the restroom and the time when images of people were captured can be used to analyze whether people entered the restroom within the preset time period, and the number of people can be adjusted accordingly.

[0128] In this example, based on the number of people entering the public toilet as determined in step S210, cleaning staff can be recommended to clean the public toilet accordingly.

[0129] Example 2

[0130] This example provides a method for determining the flow of people in each public toilet. This example is designed for a situation where there are multiple public toilets without cameras at their entrances in an area.

[0131] This example includes two phases: the first phase is to determine the effective area for each public toilet; the second phase is to determine the number of times each public toilet is entered.

[0132] In this example, the effective area is defined as follows: when multiple public toilets exist, if any location N in an area S is closer to the designated public toilet than to any other public toilet, then area S is the effective area corresponding to the designated public toilet. This calculation method is basically the same as the Venn diagram delineation method. The specific delineation method is as follows:

[0133] (1) Assume that there is only one public toilet within the preset geographical range, and the effective area corresponding to the public toilet is the preset geographical range.

[0134] (2) Assume there are only two public toilets, WC1 and WC2, in the jurisdiction; Figure 8a As shown, the perpendicular bisector of the line segment formed by the positions of WC1 and WC2 divides the preset geographical area into two regions, where the region containing WC1 is Y( Figure 8a The area marked with a slant line is the valid region corresponding to WC1, and the other part, the region where WC2 is located, is the valid region corresponding to WC2.

[0135] (3) Assuming there are M public toilets (M≥3) within the jurisdiction, randomly select the locations of three public toilets WC1, WC2, and WC3; the perpendicular bisector of the line segment formed by the locations of WC1 and WC2 intersects the perpendicular bisector of the line segment formed by the locations of WC1 and WC3 at point Q. The area enclosed by the two perpendicular bisectors and the outline of the preset geographical range, including the location of WC1, is the effective area Y corresponding to WC1, as shown below. Figure 8b The area shown is marked with diagonal lines.

[0136] Within the valid area Y corresponding to WC1, select another public toilet, WC4. The perpendicular bisector of the line segment formed by the positions of WC1 and WC4 divides area Y into two parts. The part Z containing WC1 is the valid area corresponding to WC1. Figure 8c The grid line area shown; the rest of Y, i.e., the area where WC4 is located ( Figure 8c The area marked with a slant (in the diagram) is the valid area corresponding to WC4. Repeat this step to continuously divide the valid area until there are no other public toilets within the valid area corresponding to WC1. This is the final valid area for WC1. The same process can be applied to other public toilets to obtain the valid areas for each public toilet within the preset geographical range.

[0137] The second phase of this example is as follows: Figure 9 As shown, it includes steps S301-S313.

[0138] S301. Obtain a list of cameras within a preset geographical range.

[0139] S302. Create an analysis task for all cameras within the preset geographic range.

[0140] S303. Archive images of people captured by the camera within a preset time period.

[0141] In this step, data aggregation is performed to remove duplicates of people within a preset geographical area, thereby increasing data accuracy.

[0142] S304. Based on the data aggregation results, obtain the trajectory information of people in each effective area within the preset time period.

[0143] In this step, the speed v of a person walking or riding in a vehicle can also be obtained based on the trajectory information.

[0144] Next, the number of times each public toilet within the preset geographical area will be entered will be determined. The following explanation uses determining the number of times public toilet x will be an example. For each person in the effective area of ​​public toilet x within the preset time period, steps S305-S312 will be performed. The execution process of steps S305-S312 will be illustrated below using person A as an example; other people in the effective area of ​​public toilet x can refer to this process.

[0145] S305. Based on the trajectory information of person A, determine the theoretical travel time for person A along the path to public toilet x.

[0146] In this step, for example Figure 2a or Figure 2b As shown, in the scenario where there are two specific image acquisition devices (cameras in this example) A and B near the public toilet x, which is the target location C, there is only one path between A and B, and the public toilet x is on this path. The path length between A and B is s. Then, the time that person A would normally spend crossing the path between A and B is the theoretical travel time.

[0147] In this step, for example Figure 3 The scenario depicts a public toilet (x) near target location C, near two specific image acquisition devices (cameras in this example), A and B. There are three paths between A and B; some paths do not pass through toilet x, while others do. The lengths of the three paths between A and B are s1, s2, and s3, respectively. The theoretical travel time for person A to normally traverse these three paths is as follows:

[0148] In this step, for example Figure 4 As shown, there is a specific image acquisition device (camera in this example) D near the public toilet x, which is the target location C. The path length from D to the public toilet x is s. Then, the time that person A would normally take to travel through these three paths are three theoretical travel times:

[0149] In this step, Figure 5 The situation shown can be equivalent to two specific image acquisition devices that have been successfully matched. Figure 2a or Figure 2b The calculation is performed based on the situation shown.

[0150] S306. Calculate the time difference.

[0151] In this step, the actual passage time is obtained by the difference in the acquisition time of the images of person A captured by the two cameras on both sides of the path where public toilet x is located. The time difference obtained by subtracting the theoretical passage time from the actual passage time can be regarded as the time that person A stays in the path.

[0152] In this step, for Figure 2a or Figure 2b In the case where cameras A and B capture images of person A (i.e., the actual travel time) as time, the time difference is calculated. The time difference can be considered as the time that person A stays in public toilet x.

[0153] In this step, for Figure 3 In the scenario where A and B capture person A's image, the time difference is 'time'. First, we eliminate the theoretical travel time exceeding 'time', as this implies that person A's actual travel time is shorter than the theoretical value, making it impossible for them to have time to use the restroom. For the remaining theoretical travel times, we calculate the time difference. In this example, assuming the theoretical travel time for all three paths is no greater than 'time', we can obtain three time differences t1, t2, and t3 as follows:

[0154]

[0155] Determine the minimum value among t1, t2, and t3, let's say it's t1. Subtract this minimum value from the other time differences to get the time difference tm between paths, that is: tm1 = t2 - t1; tm2 = t3 - t1.

[0156] S307. Determine whether the duration of a single toilet visit by person A has been collected. If it has been collected, use the duration of a single toilet visit as a preset range and proceed to step S310; if it has not been collected, proceed to step S308.

[0157] S308. Perform structured processing on the attribute data (such as height range, age range, gender, etc.) of people within the preset geographical range.

[0158] S309. Identify personnel with the same attribute data as Person A, obtain a preset range based on the length of a single toilet visit of the identified personnel, and proceed to step S310.

[0159] S310. Determine if the time difference is within the preset interval [t] min ,t max If it is not present, proceed to step S311; if it is present, proceed to step S312.

[0160] In this step, for Figure 3 If any time difference falls within the preset interval, proceed to step 312.

[0161] S311. Exclude the trajectory information of person A, that is, determine that person A has not entered the public toilet x.

[0162] S312. Determine whether person A has entered public toilet x or has the probability of having entered public toilet x, and accordingly increase the number of people entering public toilet x within a preset time period, P.

[0163] In this step, for Figure 2a or Figure 2b ,as well as Figure 4 In the case where the time difference t is within the preset interval [t] min ,t max Add 1 to the number of people in the time period P.

[0164] In this step, for Figure 3 In this case, first determine whether tm1 and tm2 are within the preset interval [t min ,t max Within [t], recorded in [t] min ,t max The number of time differences x between paths within a given interval is denoted as follows: if only one of tm1 and tm2 is within the preset interval, then x is 1; if neither tm1 nor tm2 is within the preset interval, then x is 0; if both tm1 and tm2 are within the preset interval, then x = 2. The number of time differences between paths is denoted as n, where n = 2.

[0165] When any one of the time differences t1, t2, and t3 falls within the preset interval [t min ,t max Within the time frame, the number of personnel (P) plus...

[0166] For each person in the valid area corresponding to public toilet x within the preset time period, after completing steps S305-S312, step S313 can be performed:

[0167] S313. Obtain the total number of people entering the public toilet within the preset time period, i.e., the final number of people P after each person goes through S305-S312.

[0168] For other public toilets within the preset geographical area, the total number of people entering within the preset time period can be obtained by following the steps above.

[0169] This application describes several embodiments, but these descriptions are exemplary and not restrictive, and it will be apparent to those skilled in the art that many more embodiments and implementations are possible within the scope of the embodiments described herein. Although many possible combinations of features are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are also possible. Unless specifically limited, any feature or element of any embodiment may be used in combination with, or may replace, any feature or element of any other embodiment.

[0170] This application includes and contemplates combinations of features and elements known to those skilled in the art. The embodiments, features, and elements disclosed in this application may also be combined with any conventional features or elements to form a unique inventive scheme as defined by the claims. Any feature or element of any embodiment may also be combined with features or elements from other inventive schemes to form another unique inventive scheme as defined by the claims. Therefore, it should be understood that any feature shown and / or discussed in this application may be implemented individually or in any suitable combination. Therefore, the embodiments are not limited except by the limitations imposed by the appended claims and their equivalents. Furthermore, various modifications and changes may be made within the scope of the appended claims.

[0171] Furthermore, in describing representative embodiments, the specification may have presented methods and / or processes as a specific sequence of steps. However, the method or process should not be limited to the specific order of steps described herein, to the extent that it does not depend on such a specific order. As will be understood by those skilled in the art, other sequences of steps are also possible. Therefore, the specific order of steps set forth in the specification should not be construed as a limitation of the claims. Moreover, the claims concerning the method and / or process should not be limited to the steps performed in the written order, and those skilled in the art will readily understand that these orders can be varied and still remain within the spirit and scope of the embodiments of this application.

[0172] It will be understood by those skilled in the art that all or some of the steps, systems, or apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

Claims

1. A method of determining a flow of people at a target site, characterized by, include: Determine the effective area corresponding to the target location; Based on the image data collected in the effective area corresponding to the target location, the trajectory information of the people in the effective area within a preset time period is obtained; Based on the trajectory information of people in the effective area within the preset time period, determine the number of times people enter the target location within the preset time period, including: For each person located in the effective area within the preset time period, the following processing is performed: the person's trajectory information is matched with a specific image acquisition device. If the match is successful, the number of times a person enters the target location within the preset time period is adjusted according to the location of the specific image acquisition device and the acquisition time of the person's image. This includes: determining the person's theoretical passage time based on the location of the specific image acquisition device. The actual passage time of the person is determined by the difference between the acquisition times of two consecutive images of the person captured by the matched specific image acquisition device. Calculate the time difference between the actual passage time and the theoretical passage time. When the time difference is within a preset range, increase the number of people entering the target location within the preset time period. The specific image acquisition device is predetermined based on road network information and is located on the necessary path to the target location, and there are no other image acquisition devices between the specific image acquisition device and the target location on this necessary path.

2. The method as described in claim 1, characterized in that, There are two successfully matched specific image acquisition devices, located on different sides of the target location; there is only one path between the two successfully matched specific image acquisition devices, and the target location is located on this path; The step of determining the theoretical travel time of a person based on the location of the matched specific image acquisition device includes: dividing the length of the path between the two matched specific image acquisition devices by the speed obtained based on the person's trajectory information to obtain the theoretical travel time; The step of increasing the number of people entering the target location within the preset time period includes: increasing the number of people entering the target location within the preset time period by 1.

3. The method of claim 1, wherein, There are two successfully matched specific image acquisition devices, which are located on different sides of the target location; there are multiple paths between the two successfully matched specific image acquisition devices, and the target location is located on at least one of these paths; The step of determining the theoretical travel time of a person based on the location of a successfully matched specific image acquisition device includes: dividing the length of each path between two successfully matched specific image acquisition devices by the speed obtained based on the person's trajectory information to obtain the theoretical travel time of each path; The step of calculating the time difference between the actual travel time and the theoretical travel time, and increasing the number of people entering the target location within the preset time period when the time difference is within a preset range, includes: Remove theoretical travel times that are longer than the actual travel time, and calculate the time difference between the actual travel time and the remaining theoretical travel times. Determine the minimum value among the calculated time differences, and subtract the minimum value from the time differences other than the minimum value to obtain the time differences between n paths. Record the number x of the path time differences within the preset interval. If at least one of the calculated time differences is within the preset interval, the number of people entering the target site within the preset time period is increased .

4. The method of claim 1, wherein, Only one specific image acquisition device was successfully matched. The step of determining the theoretical travel time of a person based on the location of a successfully matched specific image acquisition device includes: dividing twice the length of the path between the successfully matched specific image acquisition device and the target location by the speed obtained based on the person's trajectory information to obtain the travel time; The step of increasing the number of people entering the target location within the preset time period includes: increasing the number of people entering the target location within the preset time period by 1.

5. The determination method according to any one of claims 1 to 4, characterized in that, The step of obtaining the trajectory information of people in the effective area within a preset time period based on image data collected in the effective area corresponding to the target location includes: Based on the image data collected in the effective area corresponding to the target location, personnel are grouped and filed; based on the grouping and filing results, the trajectory information of different personnel in the effective area within the preset time period is obtained.

6. The method of any one of claims 1 to 4, wherein, The effective area corresponding to the target location includes: If there is only one target location within the preset geographical range, then the preset geographical range shall be regarded as the effective area corresponding to that target location. If there are multiple target locations within a preset geographical area, then the location of each target location is taken as a discrete point, and a Veno map is generated within the preset geographical area. The area corresponding to each polygon in the Veno map is taken as the effective area corresponding to the target location contained in that polygon.

7. A device for determining a flow of people at a target site, comprising: Memory and processor; characterized in that: The memory is used to store the program for determining the flow of people at the target location; The processor is configured to read and execute the program for determining the flow of people in a target location, and execute the method for determining the flow of people in a target location as described in any one of claims 1-6.

8. A computer storage medium for storing a program for determining the flow of people in a target location; wherein the program for determining the flow of people in a target location, when read and executed, performs the method for determining the flow of people in a target location as described in any one of claims 1-6.

Images