Passenger flow statistics method, device, electronic equipment and storage medium

Abstract

The present application discloses a passenger flow statistics method, device, electronic device and storage medium, which belongs to the field of data statistics and is used to improve the accuracy of regional passenger flow statistics. The method includes: obtaining characteristic information of people in a preset area within a preset time period, screening out second-type people other than first-type people from the people based on the characteristic information; determining second-type people with the same facial feature information and / or body feature information as the same third-type person; if the movement trajectory of any third-type person in the time interval is the same as the movement trajectory of a fourth-type person, and the distance between the position information of any third-type person and the position information of the fourth-type person at a preset time point in the time interval is less than a preset distance threshold, then determining that the fourth-type person and any third-type person are the same third-type person; and determining the passenger flow in the preset area within the preset time period based on the number of third-type people.

Description

Technical Field

[0001] This application belongs to the field of data statistics, and specifically relates to a passenger flow statistics method, device, electronic device and storage medium. Background Art

[0002] For scenarios like shopping malls and supermarkets, if the effective customer flow in each area can be counted, administrators can achieve efficient management of the area based on the regional statistical results. For example, administrators can configure store staff and merchandise based on the regional statistical results, which is conducive to the refined management of the layout of personnel and items in shopping malls or supermarkets. The existing method for determining customer flow routes and customer flow hot spots is to determine the area to which each mobile device belongs based on the coordinate data of the mobile devices (shopping carts) in the area, thereby counting the number of mobile devices in each area and obtaining the customer flow in each area.

[0003] However, the above-mentioned existing passenger flow routes and passenger flow hot zone determination methods actually count mobile devices (shopping carts), so the passenger flow statistics have the problem of low accuracy. Summary of the Invention

[0004] The embodiments of the present application provide a passenger flow statistics method, device, electronic device and storage medium, which can solve the problem of low accuracy in counting passenger flow in a statistical area.

[0005] In a first aspect, an embodiment of the present application provides a method for counting passenger flow, the method comprising: obtaining characteristic information of persons in a preset area within a preset time period, the characteristic information comprising clothing characteristic information, facial characteristic information, body characteristic information and location information; screening out a second type of persons other than the first type of persons from the persons based on the characteristic information, the first type of persons comprising staff and / or persons corresponding to non-biological bodies; determining the second type of persons having the same facial characteristic information and / or body characteristic information as the same third type of persons; if there is a fourth type of person among the second type of persons whose corresponding third type cannot be determined based on the facial characteristic information and body characteristic information, determining the fourth type of person based on the location information of the fourth type of person The movement trajectory of the fourth type of personnel is determined according to the time point corresponding to the location information of the fourth type of personnel, and the time interval corresponding to the movement trajectory of the fourth type of personnel is determined; according to the location information corresponding to the third type of personnel, the movement trajectory of the third type of personnel within the time interval is determined; if the movement trajectory of any third type of personnel within the time interval is the same as the movement trajectory of the fourth type of personnel, and the distance between the location information of any third type of personnel and the location information of the fourth type of personnel at the preset time point within the time interval is less than the preset distance threshold, then it is determined that the fourth type of personnel and any third type of personnel are the same third type of personnel; according to the number of the third type of personnel, the passenger flow in the preset area within the preset time period is determined.

[0006] In a second aspect, an embodiment of the present application provides a passenger flow statistics device, which includes: an acquisition module for acquiring characteristic information of people in a preset area within a preset time period, wherein the characteristic information includes clothing characteristic information, facial characteristic information, body characteristic information and location information; a screening module for screening out a second type of people other than the first type of people from the people based on the characteristic information, wherein the first type of people includes staff and / or people corresponding to non-biological objects; a first determination module for determining the second type of people with the same facial characteristic information and / or body characteristic information as the same third type of people; a second determination module for determining, if there is a fourth type of person among the second type of people whose corresponding third type cannot be determined based on the facial characteristic information and body characteristic information, based on the location information of the fourth type of people. Determine the movement trajectory of the fourth type of personnel, and determine the time interval corresponding to the movement trajectory of the fourth type of personnel according to the time point corresponding to the position information of the fourth type of personnel; a third determination module is used to determine the movement trajectory of the third type of personnel within the time interval according to the position information corresponding to the third type of personnel. If the movement trajectory of any of the third type of personnel within the time interval is the same as the movement trajectory of the fourth type of personnel, and the distance between the position information of any of the third type of personnel and the position information of the fourth type of personnel at the preset time point within the time interval is less than the preset distance threshold, then it is determined that the fourth type of personnel and any of the third type of personnel are the same third type of personnel; a fourth determination module is used to determine the passenger flow in the preset area within the preset time period according to the number of the third type of personnel.

[0007] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0008] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0009] In an embodiment of the present application, characteristic information of persons in a preset area within a preset time period is obtained, the characteristic information including clothing characteristic information, facial characteristic information, body characteristic information and position information; based on the characteristic information, a second type of persons other than the first type of persons are screened out from the persons, the first type of persons including staff and / or persons corresponding to non-biological objects; the second type of persons with the same facial characteristic information and / or body characteristic information are determined as the same third type of persons; if there is a fourth type of person among the second type of persons whose corresponding third type of person cannot be determined based on the facial characteristic information and body characteristic information, the movement trajectory of the fourth type of person is determined based on the position information of the fourth type of person, and the time interval corresponding to the movement trajectory of the fourth type of person is determined based on the time point corresponding to the position information of the fourth type of person; based on the first type of person The location information corresponding to the three types of personnel is used to determine the movement trajectory of the third type of personnel within the time interval. If the movement trajectory of any of the third type of personnel within the time interval is the same as the movement trajectory of the fourth type of personnel, and the distance between the location information of any of the third type of personnel and the location information of the fourth type of personnel at the preset time point within the time interval is less than the preset distance threshold, then it is determined that the fourth type of personnel and any of the third type of personnel are the same third type of personnel; based on the number of the third type of personnel, the passenger flow in the preset area within the preset time period is determined, the personnel in the preset area can be identified, and the personnel in the preset area are deduplicated to obtain the third type of personnel, so that the passenger flow in the preset time period and the preset area can be determined based on the number of the third type of personnel, thereby reducing the error in the passenger flow statistics process and improving the accuracy of the passenger flow statistics. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0011] Figure 1 This is a flow chart of a passenger flow statistics method provided in an embodiment of the present application;

[0012] Figure 2 This is a flow chart of another method for counting passenger flow provided in an embodiment of the present application;

[0013] Figure 3 This is a schematic diagram of the structure of a passenger flow statistics device provided in an embodiment of the present application;

[0014] Figure 4 It is a structural diagram of an electronic device according to another embodiment of the present application. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0016] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0017] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0018] The passenger flow statistics method, device, electronic device and storage medium provided in the embodiments of the present application are described in detail below with reference to the accompanying drawings through specific embodiments and their application scenarios.

[0019] Figure 1 A method for counting passenger flow provided by an embodiment of the present invention is shown. The method can be executed by an electronic device, which may include a server and / or a terminal device. In other words, the method can be executed by software or hardware installed on the electronic device, and the method includes the following steps:

[0020] Step 102: Obtain characteristic information of people in a preset area within a preset time period.

[0021] The feature information includes clothing feature information, face feature information, body feature information and location information.

[0022] Specifically, within a preset area, photos of people in the preset area can be obtained at at least one time point within a preset time period through a camera pre-set in the preset area. After obtaining the photos of the people, clothing feature information and facial feature information in the pictures can be extracted according to the deep learning algorithm. Facial feature information includes but is not limited to feature information such as the corners of the mouth, nose, eyes, eyebrows, forehead, and hair. Faces are divided into four categories: front face, wearing a mask, side face, and large depression angle. Human body feature information in the picture can also be extracted according to the deep learning algorithm. The human body is divided into three directions: front, back, and side, such as the hunchback condition of the person and the height of the person.

[0023] Step 104: Based on the characteristic information, a second type of personnel other than the first type of personnel is screened from the personnel.

[0024] The first type of personnel includes staff and / or personnel corresponding to non-living objects.

[0025] Specifically, since staff members and persons corresponding to non-living objects (people on billboards, people on packaging bags, etc.) do not fall within the statistical scope of passenger flow, if staff members and / or persons corresponding to non-living objects are included in the statistics of passenger flow in the area, the statistics of passenger flow in the area will be inaccurate. Therefore, based on the feature information, the first type of persons can be eliminated from the personnel to obtain the second type of persons. The first type of persons includes staff members and / or persons corresponding to non-living objects. For example, as an example, the first type of persons among the personnel can be identified based on the clothing feature information of the persons, and the first type of persons can be eliminated to obtain the second type of persons. As another example, the first type of persons among the personnel can be identified based on the facial feature information and / or body feature information of the persons, and the first type of persons can be eliminated to obtain the second type of persons.

[0026] Step 106: Determine the second-type persons who have the same facial feature information and / or body feature information as the same third-type persons.

[0027] Specifically, after obtaining the second type of personnel, the second type of personnel can be deduplicated, and can be identified based on the facial feature information and / or body feature information of the second type of personnel, and the second type of personnel with the same facial feature information and / or body feature information can be determined as the same third type of personnel. As an example, among the second type of personnel, if two second type personnel are identified as having the same facial features, then the two second type personnel are determined to be the same third type of personnel. As another example, if three second type personnel are identified as having the same facial features and / or body features, then the three second type personnel are determined to be the same third type of personnel.

[0028] Step 108: If there is a fourth type of person among the second type of people whose corresponding third type of person cannot be determined based on the facial feature information and body feature information, the movement trajectory of the fourth type of person is determined based on the position information of the fourth type of person, and the time interval corresponding to the movement trajectory of the fourth type of person is determined based on the time point corresponding to the position information of the fourth type of person.

[0029] Specifically, if there is a fourth type of person among the second type of people whose corresponding third type of person cannot be determined based on facial feature information and body feature information, it is necessary to perform deduplication operation on the fourth type of person. The movement trajectory of the fourth type of person and the time interval corresponding to the movement trajectory of the fourth type of person can be determined based on the location information of the fourth type of person and the time point corresponding to the location information of the fourth type of person.

[0030] Step 110: Based on the location information corresponding to the third type of personnel, determine the movement trajectory of the third type of personnel within the time interval. If the movement trajectory of any of the third type of personnel within the time interval is the same as the movement trajectory of the fourth type of personnel, and the distance between the location information of any of the third type of personnel and the location information of the fourth type of personnel at a preset time point within the time interval is less than a preset distance threshold, then determine that the fourth type of personnel and any of the third type of personnel are the same third type of personnel.

[0031] Based on the location information corresponding to the third type of personnel, the movement trajectory of the third type of personnel within the time interval can be predicted. If the movement trajectory of any third type of personnel within the time interval is the same as the movement trajectory of the fourth type of personnel, and at the preset time point, the distance between the location information of the third type of personnel and the location information of the fourth type of personnel is less than the preset distance threshold, then it is determined that the fourth type of personnel and the third type of personnel are the same person.

[0032] In this way, by obtaining the movement trajectory of the fourth type of personnel and the movement trajectory of the third type of personnel, if the movement trajectory of any third type of personnel within the time interval is the same as the movement trajectory of the fourth type of personnel, and at the preset time point, the distance between the position information of the third type of personnel and the position information of the fourth type of personnel is less than the preset distance threshold, then it is determined that the fourth type of personnel and the third type of personnel are the same person, thereby achieving deduplication of unidentifiable fourth type personnel, reducing errors in the passenger flow statistics process, and improving the accuracy of passenger flow statistics.

[0033] Step 112: Determine the passenger flow in the preset area within the preset time period according to the number of the third type of people.

[0034] Specifically, after deduplicating the second type of personnel and the fourth type of personnel except the first type of personnel, the number of the third type of personnel is obtained, and the number of the third type of personnel can be determined as the passenger flow in the preset time period and the preset area.

[0035] The passenger flow statistics method provided by the embodiment of the present invention obtains characteristic information of people in a preset area within a preset time period, the characteristic information including clothing characteristic information, facial characteristic information, body characteristic information and position information; based on the characteristic information, a second type of people other than the first type of people are screened out from the people, the first type of people including staff and / or people corresponding to non-biological objects; the second type of people with the same facial characteristic information and / or body characteristic information are determined as the same third type of people; if there is a fourth type of person among the second type of people whose corresponding third type of person cannot be determined based on the facial characteristic information and body characteristic information, the movement trajectory of the fourth type of person is determined based on the position information of the fourth type of person, and the time point of the movement trajectory of the fourth type of person is determined based on the time point corresponding to the position information of the fourth type of person corresponding time interval; according to the location information corresponding to the third type of personnel, the movement trajectory of the third type of personnel in the time interval is determined; if the movement trajectory of any third type of personnel in the time interval is the same as the movement trajectory of the fourth type of personnel, and the distance between the location information of any third type of personnel and the location information of the fourth type of personnel at the preset time point in the time interval is less than the preset distance threshold, then it is determined that the fourth type of personnel and any third type of personnel are the same third type of personnel; according to the number of third type of personnel, the passenger flow in the preset area within the preset time period is determined, the identification of personnel in the preset area is realized, and the deduplication of personnel in the preset area is realized, and the number of third type personnel in the preset time period and the preset area can be obtained to determine the passenger flow in the preset time period and the preset area, thereby improving the accuracy of passenger flow statistics.

[0036] It should be noted that the execution entity of each step of the passenger flow counting method provided in this embodiment can be the same device, or the method can be executed by different devices. For example, the execution entity of steps 102 and 104 can be device 1, and the execution entity of step 106 can be device 2; for another example, the execution entity of step 102 can be device 1, and the execution entity of steps 104 and 106 can be device 2; and so on.

[0037] In a possible implementation, screening the second type of personnel other than the first type of personnel from the personnel according to the characteristic information includes:

[0038] Identify the staff member according to the clothing feature information, and identify the person corresponding to the non-biological object according to the facial feature information and the body feature information to obtain the first type of person;

[0039] The first type of personnel is deleted from the personnel to obtain the second type of personnel.

[0040] Specifically, since the staff in the area (such as cleaning staff, security personnel, etc.) usually wear work clothes, the clothing feature information of the personnel can be identified through a preset clothing recognition model. If the clothing feature information of the person is identified as work clothes, the person is determined to be a staff member.

[0041] Before counting the passenger flow in the area, the facial feature information and / or body feature information of the non-living person corresponding to the non-living person in the preset area (people on billboards, people with packaging bags, etc.) can be used to train a person recognition model. When counting the passenger flow in the preset area, the facial feature information and / or body feature information of the person can be identified by the non-living person recognition model to determine whether the person is the non-living person corresponding to the non-living person.

[0042] After obtaining the first type of personnel (staff, personnel corresponding to non-biological objects), the first type of personnel are deleted from the personnel to obtain the second type of personnel, and the second type of personnel are the statistical objects of the passenger flow in the preset area within the preset time period.

[0043] In this way, by identifying the clothing feature information, facial feature information and body feature information of the personnel, the first type of personnel is screened out, and the first type of personnel is deleted from the personnel, and the second type of personnel used to count the passenger flow can be obtained. Deleting the first type of personnel can make the staff and non-biological personnel not be included in the passenger flow, thereby improving the accuracy of passenger flow statistics.

[0044] In a possible implementation, after determining, based on the facial feature information and / or body feature information, the persons of the second type having the same facial feature information and / or body feature information as the same third type of persons, the method further includes:

[0045] A feature information database is established for the second-type personnel who belong to the same third-type personnel, wherein any of the feature information databases includes feature information corresponding to the second-type personnel who belong to the same third-type personnel.

[0046] Specifically, a feature information database is established for each third type of personnel, that is, a feature information database is established for the second type of personnel belonging to the same third type of personnel, and the feature information of all second type personnel corresponding to each third type of personnel is aggregated into the feature information database. Any feature information database includes the feature information corresponding to the same third type of personnel.

[0047] In this way, by establishing a feature information database for the second type of personnel belonging to the same third type of personnel, the feature information of the second type of personnel belonging to the same third type of personnel can be aggregated into the same feature information database, which facilitates the acquisition of personnel feature information.

[0048] In one implementation, after determining that the fourth type of person and any of the third type of persons are the same third type of person, the method further includes:

[0049] The characteristic information of the fourth type of personnel is aggregated into a characteristic information database of any of the third type of personnel.

[0050] Specifically, after determining the third type of personnel corresponding to the fourth type of personnel, the fourth type of personnel can be marked through the feature information library corresponding to the third type of personnel, and the feature information of the fourth type of personnel can be aggregated into the feature information library of the third type of personnel.

[0051] In this way, by aggregating the characteristic information of the fourth type of personnel into the characteristic information database of any of the third type of personnel, the deduplication of personnel and the aggregation of their characteristic information are achieved, which can reduce the error in passenger flow statistics, facilitate data acquisition, and improve the accuracy of passenger flow statistics.

[0052] In a possible implementation, determining the passenger flow in the preset area within the preset time period according to the number of the third type of people includes:

[0053] According to the location information of the third type of personnel and the time point corresponding to the location information of the third type of personnel, if there are N third type of personnel leaving the preset area and returning to the preset area within the preset time period and the time interval is greater than the preset time threshold, then the sum of N and the number of the third type of personnel is calculated, and the sum is determined as the passenger flow in the preset area within the preset time period.

[0054] Specifically, considering that some people may leave the preset area for a short time after entering the preset area, in order to reduce errors in the passenger flow statistics process, a minimum time threshold for leaving is set. When the leaving time is less than the time threshold, it is considered that the person has not left the area. That is, based on the location information of the third type of person and the time point corresponding to the location information of the third type of person, if there are N third type of people leaving the preset area and returning to the preset area within the preset time period, and the time interval is greater than the preset time threshold, where N is a non-negative integer, then the sum of N and the number of third type of people is calculated, and the sum is determined as the passenger flow in the preset area within the preset time period. For example, if the number of third type of people in the preset area within the preset time period is 50, and the preset time threshold is set to 5 minutes, if there are 5 people leaving the preset area and returning to the preset area 6 minutes later within the preset time period, then it is considered that the 5 people have left the preset area. At this time, the passenger flow in the preset area is calculated to be 55. For a third type of person whose time interval between leaving the preset area and returning to the preset area is less than or equal to the preset time threshold, it is considered that the third type of person has not left the preset area.

[0055] In this way, based on the location information of the third type of personnel and the time point corresponding to the location information of the third type of personnel, if there are N third type personnel leaving the preset area and returning to the preset area within the preset time period and the time interval is greater than the preset time threshold, then the sum of N and the number of third type personnel is calculated, and the sum is determined as the passenger flow in the preset area within the preset time period. Taking into account the situation where some personnel enter the area and leave for a short time, a preset time threshold is set. The time threshold is used to determine whether the third type of personnel has left the preset area, which reduces the error in the passenger flow statistics process and improves the accuracy of passenger flow statistics.

[0056] In a possible implementation, the method further includes:

[0057] Determining the age group of the third type of person based on the facial feature information and / or body feature information corresponding to the third type of person, wherein the age group includes the elderly stage, the adult stage, and the childhood stage;

[0058] Determining, based on the third type of people corresponding to each age group, the passenger flow corresponding to each age group in a preset area within a preset time period;

[0059] Determine the movement trajectory of the third type of personnel according to the position information of the third type of personnel.

[0060] Specifically, based on the facial feature information and / or body feature information corresponding to each third-type person, the age group to which the third-type person belongs can be determined. For example, if the number of facial wrinkles of the third-type person is greater than the first preset wrinkle number threshold, the age group to which the third-type person belongs is considered to be the elderly stage. If the height of the third-type person is lower than the preset height threshold, the age group to which the third-type person belongs is considered to be the childhood stage. If the number of facial wrinkles of the third-type person is less than or equal to the first preset wrinkle number threshold and greater than the second preset wrinkle number threshold, and the height is greater than the first preset height threshold, the age group described by the third-type person is determined to be the adult stage. If the height of the third-type person is greater than the second preset height threshold, it can be determined that the age group to which the third-type person belongs is the adult stage.

[0061] According to the number of the third type of people corresponding to each age group in the preset area within the preset time period, the passenger flow corresponding to each age group in the preset area within the preset time period can be determined.

[0062] According to the location information of each third type of person in a preset time period and a preset area, the movement trajectory of each third type of person can be determined.

[0063] In this way, by determining the age group to which each third type of person belongs based on the facial feature information and / or body feature information corresponding to the third type of person, and determining the passenger flow corresponding to each age group based on the number of third type of people corresponding to each age stage, the age group to which each third type of person belongs can be determined, the passenger flow corresponding to each age group can be obtained, and the movement trajectory of each third type of person can be obtained based on the location information of each third type of person.

[0064] In a possible implementation, if the preset area is a shopping mall area, the method further includes:

[0065] Determining the stay time of the third type of personnel in the preset area based on the movement trajectory information and location information of the third type of personnel;

[0066] The positions of the merchandise and store staff within the preset area are planned and configured based on the age group, movement trajectory, and residence time corresponding to the third type of personnel.

[0067] Specifically, if the preset area is a shopping mall, the residence time of the third type of personnel in the preset area can be determined based on the time point corresponding to the first position point and the time point corresponding to the last position point of the third type of personnel in the preset area within the preset time period, and the staff and goods can be configured based on the regional statistical results (number of people of each age group, trajectory, residence time) and the association information between items and areas. For example, if in the toy product area within the preset area, the trajectory of the third type of personnel whose age group is children is always in the toy product area, and the number of the third type of personnel whose age group is children exceeds the preset number threshold, the number of staff in the toy product area can be adjusted so that the number of staff in the toy product area can meet the needs of the third type of personnel whose age group is children. This is conducive to the refined management of the layout of personnel and items by shopping malls or supermarkets.

[0068] Figure 2 : This is a flow chart of a passenger flow statistics method provided in an embodiment of the present application, which includes the following steps:

[0069] Step 202: Acquire characteristic information of people within a preset area within a preset time period.

[0070] Specifically, the feature information includes clothing feature information, face feature information and body feature information.

[0071] Specifically, within a preset area, photos of people in the preset area can be obtained at at least one time point within a preset time period through a camera pre-set in the preset area. After obtaining the photos of the people, the clothing feature information and facial feature information in the pictures can be extracted according to the deep learning algorithm. The facial feature information includes but is not limited to feature information such as the corners of the mouth, nose, eyes, eyebrows, forehead, and hair. The faces are divided into four categories: front face, wearing a mask, side face, and large depression angle. The human body feature information in the picture can also be extracted according to the deep learning algorithm. The human body is divided into three directions: front and back. In this way, the feature information of people in the preset area within the preset time period can be obtained, and the regional passenger flow can be directly counted based on the feature information of the people, which can improve the accuracy of passenger flow statistics.

[0072] Step 204: Identify the first type of personnel from the personnel, and remove the first type of personnel from the personnel to obtain the second type of personnel.

[0073] Specifically, since staff members and persons corresponding to non-living objects (people on billboards, people on packaging bags, etc.) do not fall within the statistical scope of passenger flow, if staff members and / or persons corresponding to non-living objects are included in the statistics of passenger flow in the area, the statistics of passenger flow in the area will be inaccurate. Since staff members in the area (such as cleaning staff, security personnel, etc.) usually wear work clothes, the clothing feature information of the person can be identified through a preset clothing recognition model. If the clothing feature information of the person is identified as work clothes, the person is determined to be a staff member.

[0074] Before counting the passenger flow in the area, the facial feature information and / or body feature information of the non-living person corresponding to the non-living person in the preset area (people on billboards, people with packaging bags, etc.) can be used to train a person recognition model. When counting the passenger flow in the preset area, the facial feature information and / or body feature information of the person can be identified by the non-living person recognition model to determine whether the person is the non-living person corresponding to the non-living person.

[0075] After obtaining the first type of personnel (staff and non-living objects), the first type of personnel is removed from the personnel to obtain the second type of personnel. The second type of personnel is the statistical object of the passenger flow in the preset area during the preset time period. In this way, by removing the staff and non-living objects from the personnel to obtain the second type of personnel, the error in the passenger flow counting process is reduced and the accuracy of the passenger flow counting is improved.

[0076] Step 206: Based on the characteristic information of the second type of personnel, a characteristic information database is established for the second type of personnel and duplicate information of the second type of personnel is removed.

[0077] Specifically, after obtaining the second type of personnel, the second type of personnel can be deduplicated, and can be identified based on the facial feature information and / or body feature information of the second type of personnel, and the second type of personnel with the same facial feature information and / or body feature information can be determined as the same third type of personnel. As an example, among the second type of personnel, if two second type personnel are identified to have the same facial features, then the two second type personnel are determined to be the same third type of personnel. As another example, if three second type personnel are identified to have the same facial features and / or body features, then the three second type personnel are determined to be the same third type of personnel. For each of the third type personnel, a feature information database is established, wherein any of the feature information databases includes feature information corresponding to the same third type of personnel.

[0078] In this way, by deduplicating the second type of personnel and establishing a feature information database, data acquisition can be facilitated, errors in the passenger flow statistics process can be reduced, and the accuracy of the passenger flow statistics process can be improved.

[0079] Step 208: De-duplicate the second feature personnel for whom the feature information database has not been successfully established.

[0080] Specifically, if there is a fourth type of person among the second type of people whose feature information database cannot be established based on facial feature information and body feature information, the movement trajectory of the fourth type of person and the time interval corresponding to the movement trajectory of the fourth type of person can be determined based on the location information of the fourth type of person and the time point corresponding to the location information of the fourth type of person. Based on the location information corresponding to the third type of person, the movement trajectory of the third type of person within the time interval can be predicted. If the movement trajectory of any third type of person within the time interval is the same as the movement trajectory of the fourth type of person, and at the preset time point, the distance between the location information of the third type of person and the location information of the fourth type of person is less than the preset distance threshold, then it is determined that the fourth type of person and the third type of person are the same person. The fourth type of person can be marked through the feature information database corresponding to the third type of person, and the feature information of the fourth type of person can be aggregated into the feature information database of the third type of person.

[0081] In this way, by deduplicating the personnel whose feature information database cannot be established based on their facial feature information and body feature information according to their location information, the error in passenger flow statistics can be reduced and the accuracy of passenger flow statistics can be improved.

[0082] Step 210: Based on the number of third type personnel, the passenger flow within the preset time period and the preset area is counted, and a time threshold for allowing departure from the preset area is set. If the time for the third type personnel to leave the preset area is less than the time threshold, it is considered that the third type personnel has not left the area.

[0083] Specifically, the number of third-type personnel in the preset area within the preset time period is the passenger flow in the preset area within the preset time period. Taking into account that some personnel leave the preset area for a short time after entering the preset area, in order to reduce errors in the passenger flow statistics process, a minimum time threshold allowed for leaving is set. When the departure time is less than this time threshold, it is considered that the person has not left the area. That is, based on the location information of the third-type personnel and the time point corresponding to the location information of the third-type personnel, if there are N third-type personnel leaving the preset area and returning to the preset area within the preset time period, and the time interval is greater than the preset time threshold, then the sum of N and the number of third-type personnel is calculated, and the sum is determined as the passenger flow in the preset area within the preset time period.

[0084] In this way, the passenger flow in the preset area within the preset time period can be directly determined according to the number of the third type of personnel, thereby improving the accuracy of passenger flow statistics.

[0085] Step 212: Calculate the number of the third type of people in the elderly stage, adult stage, and child stage within the preset area, and plan and configure the positions of the merchandise and store staff within the preset area based on the calculation results.

[0086] Based on the facial feature information and / or body feature information corresponding to each third-type person, the age group to which the third-type person belongs can be determined. For example, if the number of facial wrinkles of the third-type person is greater than a first preset wrinkle number threshold, the age group to which the third-type person belongs is considered to be the elderly stage. If the height of the third-type person is lower than the preset height threshold, the age group to which the third-type person belongs is considered to be the childhood stage. If the number of facial wrinkles of the third-type person is less than or equal to the first preset wrinkle number threshold and greater than the second preset wrinkle number threshold, and the height is greater than the first preset height threshold, the age group described by the third-type person is determined to be the adult stage. If the height of the third-type person is greater than the second preset height threshold, it can be determined that the age group to which the third-type person belongs is the adult stage.

[0087] Based on the number of the third type of people corresponding to each age group in the preset time period and in the preset area, the passenger flow corresponding to each age group in the preset area within the preset time period can be determined, and based on the location information of each third type of people in the preset time period and in the preset area, the movement trajectory of each third type of people can be determined.

[0088] If the preset area is a shopping mall, the residence time of the third type of personnel in the preset area can be determined based on the time point corresponding to the first position point and the time point corresponding to the last position point of the third type of personnel in the preset area within the preset time period, and the staff and goods can be configured based on the regional statistical results (number of people of each age group, trajectory, residence time) and the association information between items and areas. For example, if in the toy product area within the preset area, the trajectory of the third type of personnel whose age group is children is always in the toy product area, and the number of the third type of personnel whose age group is children exceeds the preset number threshold, the number of staff in the toy product area can be adjusted so that the number of staff in the toy product area can meet the needs of the third type of personnel whose age group is children. This is conducive to the refined management of the layout of personnel and items by shopping malls or supermarkets.

[0089] The embodiment provided by the present application uses clothing detection, personnel detection corresponding to non-living objects, etc. to automatically eliminate staff members and personnel corresponding to non-living objects during the process of passenger flow statistics, without the need for manual elimination, thereby ensuring the accuracy of passenger flow statistics. In addition, when determining the passenger flow within a preset time period and a preset area, the facial feature information, body feature information and / or location information of the personnel are used to deduplicate the personnel, thereby ensuring the accuracy of passenger flow statistics. The number of personnel, movement trajectory and residence time corresponding to each age group in the preset area can also be effectively identified. The preset area administrator can carry out refined management of the layout of personnel and items based on the statistical results.

[0090] It should be noted that the passenger flow statistics method provided in the embodiments of the present application can be executed by a passenger flow statistics device, or a control module in the passenger flow statistics device that is used to execute the passenger flow statistics method. In the embodiments of the present application, the passenger flow statistics device provided in the embodiments of the present application is described by taking the passenger flow statistics device executing the passenger flow statistics method as an example.

[0091] Figure 3 FIG. 1 is a schematic diagram of the structure of a passenger flow statistics device according to an embodiment of the present invention. Figure 3 As shown, the passenger flow statistics device 300 includes: an acquisition module 310 , a screening module 320 , a first determination module 330 , a second determination module 340 , a third determination module 350 , and a fourth determination module 360 ​​.

[0092] An acquisition module 310 is used to acquire characteristic information of persons in a preset area within a preset time period, wherein the characteristic information includes clothing characteristic information, facial characteristic information, body characteristic information and location information; a screening module 320 is used to screen out a second type of persons other than the first type of persons from the persons based on the characteristic information, wherein the first type of persons includes staff members and / or persons corresponding to non-biological objects; a first determination module 330 is used to determine the second type of persons with the same facial characteristic information and / or body characteristic information as the same third type of persons; a second determination module 340 is used to determine the movement of the fourth type of persons based on the location information of the fourth type of persons if there is a fourth type of person among the second type of persons whose corresponding third type cannot be determined based on the facial characteristic information and body characteristic information. The fourth determination module 360 ​​is used to determine the passenger flow in the preset area within the preset time period based on the number of the third type of personnel.

[0093] In one possible implementation, the screening module 320 is used to identify the staff member based on the clothing feature information, and to identify the person corresponding to the non-biological body based on the facial feature information and the body feature information to obtain the first type of person; and to delete the first type of person from the person to obtain the second type of person.

[0094] In a possible implementation, the first determination module 330 is configured to establish a feature information database for the second-type personnel belonging to the same third-type personnel, wherein any of the feature information databases includes feature information corresponding to the second-type personnel belonging to the same third-type personnel.

[0095] In a possible implementation, the third determining module 350 is configured to aggregate the characteristic information of the fourth type of personnel into any characteristic information database of the third type of personnel.

[0096] In one possible implementation, the fourth determination module 360 ​​is used to calculate the sum of N and the number of third-type personnel based on the location information of the third-type personnel and the time point corresponding to the location information of the third-type personnel, and determine the sum as the passenger flow in the preset area within the preset time period if the time interval between when N third-type personnel leave the preset area and when they return to the preset area is greater than the preset time threshold.

[0097] In one possible implementation, the fourth determination module 360 ​​is used to determine the age group to which the third type of personnel belongs based on the facial feature information and / or body feature information corresponding to the third type of personnel, wherein the age group includes the elderly stage, the adult stage and the childhood stage; determine the passenger flow corresponding to each age group in a preset area within a preset time period based on the third type of personnel corresponding to each age group; and determine the movement trajectory of the third type of personnel based on the location information of the third type of personnel.

[0098] In one possible implementation, if the preset area is a shopping mall area, the fourth determination module 360 ​​is used to determine the residence time of the third type of personnel in the preset area based on the movement trajectory information and location information of the third type of personnel; and plan and configure the positions of the goods and store staff in the preset area based on the age group, movement trajectory and residence time corresponding to the third type of personnel.

[0099] The passenger flow counting device in the embodiments of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc., and the embodiments of the present application do not specifically limit this.

[0100] The passenger flow statistics device in the embodiment of the present application can be a device with an operating system. The operating system can be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0101] The passenger flow statistics device provided in the embodiment of the present application can achieve Figure 1-2 To avoid repetition, the various processes implemented in the method embodiment will not be described again here.

[0102] Alternatively, as Figure 4 As shown, an embodiment of the present application further provides an electronic device 400, including a processor 401 and a memory 402, wherein the memory 402 stores a program or instruction that can be run on the processor 401, and when the program or instruction is executed by the processor 401, it implements: obtaining feature information of people in a preset area within a preset time period, the feature information including clothing feature information, facial feature information, body feature information and location information; based on the feature information, screening out a second type of people other than the first type of people from the people, the first type of people including staff and / or people corresponding to non-biological objects; determining the second type of people with the same facial feature information and / or body feature information as the same third type of people; if there is a fourth type of people among the second type of people whose corresponding third type cannot be determined based on the facial feature information and body feature information, type personnel, determine the movement trajectory of the fourth type personnel according to the location information of the fourth type personnel, and determine the time interval corresponding to the movement trajectory of the fourth type personnel according to the time point corresponding to the location information of the fourth type personnel; determine the movement trajectory of the third type personnel within the time interval according to the location information corresponding to the third type personnel, if the movement trajectory of any of the third type personnel within the time interval is the same as the movement trajectory of the fourth type personnel, and the distance between the location information of any of the third type personnel and the location information of the fourth type personnel at the preset time point within the time interval is less than the preset distance threshold, then determine that the fourth type personnel and any of the third type personnel are the same third type personnel; determine the passenger flow in the preset area within the preset time period according to the number of the third type personnel.

[0103] In one possible implementation, the staff member is identified based on the clothing feature information, and the person corresponding to the non-biological object is identified based on the facial feature information and the body feature information to obtain the first type of person; the first type of person is deleted from the person to obtain the second type of person.

[0104] In one possible implementation, after the second-type persons with the same facial feature information and / or body feature information are determined as the same third-type persons based on the facial feature information and / or body feature information, a feature information database is established for the second-type persons belonging to the same third-type persons, wherein any of the feature information databases includes feature information corresponding to the second-type persons belonging to the same third-type persons.

[0105] In a possible implementation, after determining that the fourth type of person and any of the third type of persons are the same third type of person, the feature information of the fourth type of person is aggregated into a feature information database of any of the third type of persons.

[0106] In one possible implementation, the characteristic information also includes location information of the personnel. Based on the location information of the third type of personnel and the time point corresponding to the location information of the third type of personnel, if there are N third type personnel leaving the preset area and returning to the preset area within the preset time period and the time interval is greater than the preset time threshold, then the sum of N and the number of the third type of personnel is calculated, and the sum is determined as the passenger flow in the preset area within the preset time period.

[0107] In one possible implementation, based on the facial feature information and / or body feature information corresponding to the third type of person, the age group to which the third type of person belongs is determined, wherein the age groups include the elderly, adults, and children; and based on the third type of person corresponding to each age group, the passenger flow corresponding to each age group in a preset area within a preset time period is determined;

[0108] In one possible implementation, if the preset area is a shopping mall area, the residence time of the third type of personnel in the preset area is determined based on the movement trajectory information and location information of the third type of personnel; and the positions of the goods and store staff in the preset area are planned and configured based on the age group, movement trajectory and residence time corresponding to the third type of personnel.

[0109] The specific execution steps can refer to the various steps of the above-mentioned passenger flow statistics method embodiment, and can achieve the same technical effect. To avoid repetition, they will not be described here.

[0110] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0111] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0112] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0114] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0115] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0116] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0117] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0118] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0119] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A passenger flow statistics method, characterized in that: include: Acquire characteristic information of people in a preset area within a preset time period, the characteristic information including clothing characteristic information, facial characteristic information, body characteristic information and location information; screening, from the personnel, according to the characteristic information, a second type of personnel other than the first type of personnel, wherein the first type of personnel includes staff members and / or personnel corresponding to non-biological objects; Determining the second-type persons having the same facial feature information and / or body feature information as the same third-type persons; If there is a fourth type of person among the second type of persons whose corresponding third type of person cannot be determined based on the facial feature information and body feature information, determining the movement trajectory of the fourth type of person based on the location information of the fourth type of person, and determining the time interval corresponding to the movement trajectory of the fourth type of person based on the time point corresponding to the location information of the fourth type of person; determining, based on the location information corresponding to the third type of person, a movement trajectory of the third type of person within the time interval; if the movement trajectory of any of the third type of person within the time interval is the same as the movement trajectory of the fourth type of person, and the distance between the location information of any of the third type of person and the location information of the fourth type of person at a preset time point within the time interval is less than a preset distance threshold, then determining that the fourth type of person and any of the third type of person are the same third type of person; The passenger flow in the preset area within the preset time period is determined according to the number of the third type of people.

2. The statistical method according to claim 1, characterized in that The step of screening the personnel to obtain a second type of personnel other than the first type of personnel from the personnel according to the characteristic information includes: Identify the staff member according to the clothing feature information, and identify the person corresponding to the non-biological object according to the facial feature information and the body feature information to obtain the first type of person; The first type of personnel is deleted from the personnel to obtain the second type of personnel.

3. The statistical method according to claim 1, characterized in that After determining, based on the facial feature information and / or body feature information, the second-type persons having the same facial feature information and / or body feature information as the same third-type person, the method further includes: A feature information database is established for the second-type personnel who belong to the same third-type personnel, wherein any of the feature information databases includes feature information corresponding to the second-type personnel who belong to the same third-type personnel.

4. The statistical method according to claim 3, characterized in that: After determining that the fourth type of person and any of the third type of persons are the same third type of person, the method further includes: The characteristic information of the fourth type of personnel is aggregated into a characteristic information database of any of the third type of personnel.

5. The statistical method according to claim 1, characterized in that: The determining, based on the number of the third type of people, of the passenger flow in the preset area within the preset time period includes: According to the location information of the third type of personnel and the time point corresponding to the location information of the third type of personnel, if there are N third type of personnel leaving the preset area and returning to the preset area within the preset time period and the time interval is greater than the preset time threshold, then the sum of N and the number of the third type of personnel is calculated, and the sum is determined as the passenger flow in the preset area within the preset time period, wherein N is a non-negative integer.

6. The statistical method according to claim 1, characterized in that: The method further comprises: Determining the age group of the third type of person based on the facial feature information and / or body feature information corresponding to the third type of person, wherein the age group includes the elderly stage, the adult stage, and the childhood stage; Determining, based on the third type of people corresponding to each age group, the passenger flow corresponding to each age group in a preset area within a preset time period; Determine the movement trajectory of the third type of personnel according to the position information of the third type of personnel.

7. The statistical method according to claim 6, characterized in that: If the preset area is a shopping mall area, the method further includes: Determining the stay time of the third type of personnel in the preset area based on the movement trajectory information and location information of the third type of personnel; The positions of the merchandise and store staff within the preset area are planned and configured based on the age group, movement trajectory, and residence time corresponding to the third type of personnel.

8. A passenger flow statistics device, characterized in that: include: An acquisition module is used to acquire characteristic information of people in a preset area within a preset time period, wherein the characteristic information includes clothing characteristic information, facial characteristic information, body characteristic information and location information; a screening module, configured to screen, from the personnel, based on the characteristic information, a second type of personnel other than the first type of personnel, wherein the first type of personnel includes personnel and / or personnel corresponding to non-biological objects; a first determining module, configured to determine the second-type persons having the same facial feature information and / or body feature information as the same third-type persons; a second determining module configured to, if a fourth type of person exists among the second type of persons and whose corresponding third type of person cannot be determined based on the facial feature information and the body feature information, determine a movement trajectory of the fourth type of person based on the position information of the fourth type of person, and determine a time interval corresponding to the movement trajectory of the fourth type of person based on a time point corresponding to the position information of the fourth type of person; a third determining module, configured to determine, based on the location information corresponding to the third type of personnel, a movement trajectory of the third type of personnel within the time interval; if the movement trajectory of any of the third type of personnel within the time interval is the same as the movement trajectory of the fourth type of personnel, and the distance between the location information of any of the third type of personnel and the location information of the fourth type of personnel at a preset time point within the time interval is less than a preset distance threshold, then determining that the fourth type of personnel and any of the third type of personnel are the same third type of personnel; The fourth determining module is used to determine the passenger flow in the preset area within the preset time period according to the number of the third type of people.

9. An electronic device, characterized in that: The method comprises a processor, a memory and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the passenger flow statistics method as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the passenger flow statistics method according to any one of claims 1 to 7 are implemented.

Images