Companion list processing method, abnormal travel event detection method and system

Abstract

The application relates to a companion list processing method, an abnormal travel event detection method, an abnormal travel event detection system, an electronic device and a storage medium. A video image is acquired, a first target object and a second target object accompanying the first target object are determined in the video image, and personnel features of the first target object and the second target object are extracted; personnel profile data is acquired, the personnel features of the first target object and the second target object are compared with personnel features in the personnel profile data respectively, and identity information of the first target object and the second target object is determined according to comparison results; a companion list corresponding to the first target object is acquired according to the identity information of the first target object, and the companion list is updated according to the identity information of the second target object, the companion list comprises identity information of at least one companion, and the maintenance real-time performance of guardian information is improved, and the manual maintenance cost is reduced.

Description

Technical Field

[0001] This application relates to the field of security technology, and in particular to methods for processing companion lists, methods for detecting abnormal travel events, systems for detecting abnormal travel events, electronic devices, and storage media. Background Technology

[0002] Related technologies offer a child behavior early warning system that uses the facial features of children and their associated guardians to determine whether a child is in a dangerous situation. It employs cameras to monitor the child's activity areas and collect facial features of all individuals who come into contact with the child. The system analyzes the surveillance video to determine the child's safety. However, this solution requires the proactive recording of facial features of both the child and guardian for monitoring, resulting in low real-time availability of guardian information.

[0003] There is currently no effective solution to the problem of low real-time maintenance of guardian information in related technologies. Summary of the Invention

[0004] This embodiment provides a method for processing a list of accompanying persons, a method for detecting abnormal travel events, an abnormal travel event detection system, an electronic device, and a storage medium to address the problem of low real-time performance in maintaining guardian information in related technologies.

[0005] Firstly, this embodiment provides a method for processing a list of companions, including:

[0006] Acquire video images, identify a first target object and a second target object accompanying the first target object in the video images, and extract the personnel features of the first target object and the second target object;

[0007] Obtain personnel cluster data, compare the personnel characteristics of the first target object and the second target object with the personnel characteristics in the personnel cluster data, and determine the identity information of the first target object and the second target object respectively based on the comparison results;

[0008] Based on the identity information of the first target object, a list of companions corresponding to the first target object is obtained, and the list of companions is updated based on the identity information of the second target object, wherein the list of companions includes the identity information of at least one companion.

[0009] In some embodiments, updating the entourage list based on the identity information of the second target object includes:

[0010] Determine whether the identity information of the second target object already exists in the list of companions;

[0011] If it is determined that the identity information of the second target object already exists in the companion list, the intimacy level corresponding to the second target object is incremented by one unit, and the companions in the companion list are sorted according to the intimacy level.

[0012] In some embodiments, the method further includes:

[0013] If it is determined that the identity information of the second target object does not exist in the list of companions, the identity information of the second target object is added to the list of companions.

[0014] In some embodiments, determining a second target object accompanying the first target object in the video image includes:

[0015] In the video image, at least one candidate whose distance from the first target object is within a preset range is identified;

[0016] Based on the distance between each candidate and the first target object, at least one second target object is determined from the at least one candidate that is closest to the first target object.

[0017] Secondly, this embodiment provides a method for detecting abnormal travel events, including:

[0018] In the event that a second target object carries a first target object through the security checkpoint, the identity information of the second target object is obtained, as well as the list of companions corresponding to the first target object, wherein the list of companions includes the list of companions obtained in the first aspect above.

[0019] The identity information of the second target object is compared with the identity information of the companions in the companion list, and the existence of an abnormal travel event is determined based on the comparison result.

[0020] In some embodiments, the identity information of the second target object is compared with the identity information of the companions in the companion list, and the existence of an abnormal travel event is determined based on the comparison result, including:

[0021] Determine whether the identity information of the second target object is ranked in the top N positions of the list of companions;

[0022] If it is determined that the identity information of the second target object is in the top N positions of the list of companions, it is determined that there is no abnormal travel event;

[0023] If it is determined that the identity information of the second target object is not ranked in the top N positions of the list of accompanying persons, an abnormal travel event is identified.

[0024] In some embodiments, after determining that an abnormal travel event has occurred when it is determined that the identity information of the second target object is not ranked in the top N positions of the accompanying persons list, the method further includes:

[0025] A warning message is triggered, which is used to indicate the existence of an abnormal travel event.

[0026] In some embodiments, obtaining the list of followers corresponding to the first target object includes:

[0027] Acquire video images, and extract personnel features of the first target object based on the video images;

[0028] Obtain personnel cluster data, compare the first target object with the personnel characteristics in the personnel cluster data, and determine the identity information of the first target object based on the comparison result;

[0029] Based on the identity information of the first target object, obtain the list of companions corresponding to the first target object.

[0030] Thirdly, this embodiment provides an abnormal travel event detection system, including: a first processing unit and a second processing unit, wherein the first processing unit is connected to the second processing unit; wherein the first processing unit is used to execute the companion list processing method described in the first aspect; and the second processing unit is used to execute the abnormal travel event detection method described in the second aspect.

[0031] In some embodiments, the system further includes: a first image acquisition unit connected to the first processing unit, the first image acquisition unit being used to acquire video images and send the acquired video images to the first processing unit.

[0032] In some embodiments, the system further includes a second image acquisition unit and an identity authentication unit, wherein the second processing unit is connected to the second image acquisition unit and the identity authentication unit respectively; wherein the second image acquisition unit is used to acquire video images and send the video images to the second processing unit; and the identity authentication unit is used to authenticate personnel identity information and send the personnel identity information to the second processing unit.

[0033] Fourthly, this embodiment provides an electronic device including a memory and a processor, wherein the memory stores a computer program; the processor is configured to run the computer program to perform the companion list processing method described in the first aspect above, or the processor is configured to run the computer program to perform the abnormal travel event detection method described in the second aspect above.

[0034] Fifthly, this embodiment provides a computer-readable storage medium having a computer program stored thereon, wherein when executed by a processor, the computer program implements the steps of the companion list processing method described in the first aspect above, or, when executed by a processor, the computer program implements the steps of the abnormal travel event detection method described in the second aspect above.

[0035] Compared with related technologies, the accompanying person list processing method, abnormal travel event detection method, abnormal travel event detection system, electronic device, and storage medium provided in this embodiment, by acquiring video images, identifying a first target object and a second target object accompanying the first target object in the video images, and extracting the personnel characteristics of the first and second target objects; acquiring personnel cluster data, comparing the personnel characteristics of the first and second target objects with the personnel characteristics in the personnel cluster data, and determining the identity information of the first and second target objects respectively based on the comparison results; obtaining an accompanying person list corresponding to the first target object based on the identity information of the first target object, and updating the accompanying person list based on the identity information of the second target object, wherein the accompanying person list includes the identity information of at least one accompanying person, solves the problem of low real-time maintenance of guardian information, improves the real-time maintenance of guardian information, and also reduces the cost of manual maintenance.

[0036] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0037] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0038] Figure 1 This is a hardware structure block diagram of a terminal using a method in one embodiment of this application;

[0039] Figure 2 This is a flowchart of a method for processing a list of companions in one embodiment of this application;

[0040] Figure 3This is a schematic diagram of a terminal identifying a target object in one embodiment of this application;

[0041] Figure 4 This is a flowchart of an abnormal travel event detection method in one embodiment of this application;

[0042] Figure 5 This is the structural framework of an abnormal travel event detection system in one embodiment of this application. Figure 1 ;

[0043] Figure 6 This is the structural framework of an abnormal travel event detection system in one embodiment of this application. Figure 2 ;

[0044] Figure 7 This is a topology diagram of an abnormal travel event detection system in one embodiment of this application;

[0045] Figure 8 This is a flowchart of the operation of an abnormal travel event detection system in one embodiment of this application. Detailed Implementation

[0046] To better understand the purpose, technical solution, and advantages of this application, the application is described and explained below in conjunction with the accompanying drawings and embodiments.

[0047] Unless otherwise defined, the technical or scientific terms used in this application shall have the general meaning understood by one of ordinary skill in the art to which this application pertains. Words such as “a,” “an,” “an,” “the,” “the,” and “these,” used in this application, do not indicate quantitative limitation and may be singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include steps or modules (units) not listed, or may include other steps or modules (units) inherent to such processes, methods, products, or devices. The terms “connected,” “linked,” and “coupled,” used in this application, are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. The term “multiple” used in this application refers to two or more. The "and / or" operator describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: A alone, A and B simultaneously, and B alone. Typically, the character " / " indicates that the objects before and after it are in an "or" relationship. The terms "first," "second," and "third," etc., used in this application are merely for distinguishing similar objects and do not represent a specific ordering of the objects.

[0048] The method embodiments provided in this example can be executed on a terminal, computer, or similar computing device. For example, it can run on a terminal. Figure 1 This is a hardware structure block diagram of a terminal using a method according to an embodiment of this application. For example... Figure 1 As shown, a terminal may include one or more ( Figure 1 Only one processor and a memory for storing data are shown in the diagram. The processor may include, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA). The terminal may also include transmission devices for communication functions and input / output devices. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown are illustrated.

[0049] The memory can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the method in this embodiment. The processor executes various functional applications and data processing by running the computer program stored in the memory, thereby implementing the above-described method. The memory may include high-speed random access memory (RAM) and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks (LANs), mobile communication networks, and combinations thereof.

[0050] The transmission device is used to receive or send data via a network. This network includes a wireless network provided by the terminal's communication provider. In one example, the transmission device includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0051] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. The acquisition, storage, use, and processing of data involved in the embodiments of this application all comply with the relevant provisions of national laws and regulations.

[0052] The following examples are not only applicable to the maintenance of guardianship information for children, but also to the maintenance of guardianship information for other individuals, such as the elderly, patients, or other persons without full civil capacity or lacking self-care ability, who typically require guardianship. Unless otherwise specified, the following examples will use the maintenance of guardianship information for children as an example.

[0053] In one embodiment, such as Figure 2 As shown, a method for processing a follower list is provided, which can be applied to... Figure 1 Taking the terminal in the example, the following steps are included:

[0054] Step S201: Acquire video images, identify a first target object and a second target object accompanying the first target object in the video images, and extract the personnel features of the first target object and the second target object.

[0055] The video images include those captured by networked cameras deployed in public places to capture pedestrian images. These networked cameras are authorized by relevant service systems and can access, store, and process the captured video images. Terminals can acquire video images either by directly connecting to the cameras or by connecting to the relevant service systems.

[0056] The first target group refers to individuals lacking full civil capacity or self-care ability, such as children, the elderly, and patients, who typically require guardianship. The second target group refers to individuals suspected of being guardians of the first target group, such as adults who usually possess full civil capacity.

[0057] Personnel characteristics refer to one or more of the following: facial features, body features, and head and shoulder features. Based on personnel characteristics, the age of a target object can be determined, and it can be identified as a first target object, a second target object, or another. For example, the first target object could be a child, and the second target object could be an adult. Optionally, if the facial image in the video is relatively clear, facial features can be prioritized to accurately identify the target object's age; based on body features, the age of the target object can be preliminarily identified even when a clear face is not yet visible in the acquired video image; in situations with dense crowds and limited access to body features, head and shoulder features can be used to identify the target object's age. Furthermore, personnel characteristics can also be used to identify the target object's gender, clothing, backpack, hat, and other related attributes.

[0058] Step S202: Obtain personnel cluster data, compare the personnel characteristics of the first target object and the second target object with the personnel characteristics in the personnel cluster data, and determine the identity information of the first target object and the second target object respectively based on the comparison results.

[0059] Personnel profile data refers to data provided by relevant service systems, which at least includes personnel characteristics and identity information, with personnel characteristics and identity information stored together. In addition, personnel profile data may also include age, gender, place of origin, and address, all of which are also stored together with identity information. The terminal can extract personnel characteristics from video images and compare them with the personnel characteristics in the personnel profile data. Based on the comparison results, the identity information of a first target object and a second target object are determined. For example, the terminal compares facial features extracted from a video image with facial features in the personnel profile data, and determines the identity information of the first target object and the second target object based on the comparison results.

[0060] Step S203: Based on the identity information of the first target object, obtain the list of companions corresponding to the first target object, and update the list of companions based on the identity information of the second target object, wherein the list of companions includes the identity information of at least one companion.

[0061] The companion list is stored in association with the identity information of the first target object. The companion list can be stored in a relevant service system or on a terminal. The terminal's storage and processing of the companion list is authorized by the relevant service system. For example, if the first target object is a child, the companions included in the companion list can be the child's direct blood relatives and / or collateral blood relatives, such as parents, grandparents, and siblings. If the child adds a new guardian, the new guardian's information needs to be added. In this case, this embodiment can compare the identity information of the second target object with the identity information already existing in the companion list to update the companion list in real time.

[0062] Through the above steps S201 to S203, when there is a change in guardianship, it is not necessary to actively enter the personnel characteristics of children and guardians for monitoring. This solves the problem of low real-time maintenance of guardian information, improves the real-time maintenance of guardian information, and at the same time reduces the cost of manual maintenance.

[0063] In one embodiment, the companion list can be updated as follows: determining whether the identity information of the second target object already exists in the companion list; if it is determined that the identity information of the second target object already exists in the companion list, incrementing the intimacy level corresponding to the second target object by one unit, and sorting the companions in the companion list according to the intimacy level; if it is determined that the identity information of the second target object does not exist in the companion list, adding the identity information of the second target object to the companion list.

[0064] For example, if the terminal detects that the identity information of the child's companion is not in the companion list, it will add the companion's information to the companion list to update it, such as adding identity information or name. Optionally, an initial intimacy value can be set for the companion. If the terminal detects that the identity information of the child's companion already exists in the companion list, it will increment the companion's intimacy value by 1 and sort the companion information recorded in the companion list in reverse order according to the intimacy value to update the companion list.

[0065] The initial creation of the accompanying person list can be achieved through manual input of the ward's and actual guardian's information. This includes inputting the child's and parents' identity information, and setting an initial affinity value for each guardian. Affinity value represents the probability that an accompanying person in the list is the child's actual guardian. The terminal updates the accompanying person list in real time based on captured video images. The more frequently certain individuals are seen accompanying a child in video images, the higher their affinity value will be, increasing the probability that they are the actual guardian. Accompanying persons with the lowest affinity values ​​may have been originally listed as actual guardians but are unable to fulfill their guardianship duties for some reason, or they may be temporary non-actual guardians. This setup allows for tracking the frequency of accompanying persons appearing near the child, accurately determining the legitimacy of the guardianship.

[0066] In one embodiment, the terminal determines a second target object accompanying a first target object in a video image by: determining at least one candidate object in the video image whose distance from the first target object is within a preset range; and determining at least one second target object that is closest to the first target object from among the at least one candidate object based on the distance between each candidate object and the first target object.

[0067] For example, such as Figure 3As shown, the terminal extracts body shape features from the video image and initially identifies children and adults based on these features. The child is designated as the first target object. Then, one or more adults within a 2-meter radius of the child are located, and the three adults closest to the child are selected as the second target objects. Further, the terminal extracts the facial features of the child and the three adults and compares them with personnel data. This setup enables automatic tracking of both the first and second target objects.

[0068] It is understood that population transfer mainly relies on manual analysis of surveillance video to trace the movements of people. This method is difficult and inefficient, and by the time the transferred individuals are identified, they have likely already left the area. Related technologies offer a missing child search system that uploads reference photos and related identity information of children identified as missing to a remote management center. A mobile client displays real-time reference photos of currently missing children to users. Users can take photos of suspected missing children using the mobile client and upload them to the remote management center for matching with reference photos of missing children stored there. Once a match is found, the result is uploaded to the relevant service system. However, this solution has poor timeliness. By the time a child is confirmed as missing, they may have already moved beyond the current monitoring range. This solution requires other users to actively upload information about suspected missing children, making the search system relatively passive. Even after confirming the accuracy of the uploaded information, dispatching police to rescue the child takes time, and the individuals may have moved again.

[0069] To address this problem, and in conjunction with the companion list processing method described in the above embodiments, in one embodiment, such as Figure 4 As shown, an abnormal travel event detection method is provided, which can be applied to... Figure 1 Taking the terminal in the example, the following steps are included:

[0070] Step S401: When a second target object carries a first target object through the security checkpoint, the identity information of the second target object is obtained, and a list of companions corresponding to the first target object is obtained, wherein the list of companions includes the list of companions obtained through any of the above embodiments.

[0071] Security checkpoints are channels established to ensure the safety of public places and to check whether pedestrians and their luggage are carrying dangerous items, such as security checkpoints for cars, subways, high-speed trains, and airports.

[0072] Abnormal travel incidents refer to situations where a ward is accompanied by an unauthorized guardian, such as during transit. Taking the detection of child transit incidents as an example, the child is the primary target, and the adult is the secondary target. When an adult is seen carrying a child through a security checkpoint, staff will request the adult's identity information and the child's image. Specifically, the identity authentication system verifies the adult's identity on-site, and the terminal obtains the adult's identity information based on the identity authentication system; networked cameras are deployed in public places to capture pedestrian images, and the terminal can access these networked cameras to obtain the child's facial image, identify the child's identity information, and thus obtain a list of accompanying persons corresponding to the child. This list of accompanying persons has been described in the above embodiments and will not be repeated here.

[0073] Step S402: Compare the identity information of the second target object with the identity information of the accompanying persons in the accompanying persons list, and determine whether there is an abnormal travel event based on the comparison result.

[0074] If the child is accompanied by three adults, the identity information of the three adults is compared with the identity information in the list of companions. Based on the comparison results, it is determined whether the three adults are the actual guardians of the child, thereby determining whether a child transfer incident has occurred.

[0075] Through the steps S401 to S402 described above, on the one hand, considering that the ward is being transferred to another location, there is a high probability that they will need to travel by public transportation such as long-distance buses, trains, or airplanes. If they are intercepted in time at these key checkpoints, the safety of children will be greatly improved and the occurrence of children's transfer incidents will be reduced. On the other hand, by using the real-time updated list of accompanying persons, guardians can be automatically tracked, avoiding misjudgments caused by changes in guardians and improving the accuracy of incident detection.

[0076] It should be noted that while the above embodiments only list solutions for detecting children's transit events, this does not limit the application of the method provided in this application to the detection of other abnormal travel events, such as those involving the elderly, patients, or other persons without full civil capacity or lacking self-care ability, who typically require supervision by a guardian. Unless otherwise specified, the following embodiments will be described using the detection of children's transit events as an example.

[0077] In one embodiment, the identity information of the second target object is compared with the identity information of the companions in the companion list, and the existence of an abnormal travel event is determined based on the comparison result. This includes: determining whether the identity information of the second target object is ranked in the top N positions in the companion list; if the identity information of the second target object is ranked in the top N positions in the companion list, it is determined that there is no abnormal travel event; if the identity information of the second target object is not ranked in the top N positions in the companion list, it is determined that there is an abnormal travel event.

[0078] Where N is a positive integer. There can be one or more second target objects. When there are multiple second target objects, the ranking of their identity information in the accompanying person list must be within the top N positions. This can mean that at least one second target object's identity information ranks within the top N positions, or that all second target objects' identity information ranks within the top N positions. For example, the terminal compares the identity information of three adults with the accompanying person list. If at least one of these three adults has a closeness ranking within the top three, it indicates that the child is likely being traveled by a non-guardian (relative) and a non-guardian (friend of a relative), which is considered a safe situation, meaning there is no abnormal travel event. If none of these three adults has a closeness ranking within the top three, it indicates that all three are non-guardians traveling with the child, which is considered an unsafe situation, meaning there is an abnormal travel event. To improve security, the strictness of the judgment condition can be further increased. That is, only when all three adults have a closeness ranking within the top three is it determined that there is no abnormal travel event; otherwise, an abnormal travel event is determined to exist.

[0079] Furthermore, after determining that the identity information of the second target object is not ranked in the top N positions in the list of accompanying persons, and confirming the existence of an abnormal travel event, the method also includes: triggering a warning message, which is used to indicate the existence of an abnormal travel event.

[0080] In one embodiment, the terminal obtains the list of companions corresponding to the first target object in the following manner: acquiring video images and extracting personnel features of the first target object from the video images; acquiring personnel cluster data and comparing the first target object with the personnel features in the personnel cluster data, determining the identity information of the first target object based on the comparison result; and obtaining the list of companions corresponding to the first target object based on the identity information of the first target object.

[0081] In this embodiment, the terminal acquires video images of the child through a networked camera, extracts facial features, and obtains personnel cluster data. The child's facial features are compared with those in the personnel cluster data to determine the child's identity information. Based on this identity information, a list of accompanying persons corresponding to the child is obtained. The personnel cluster data has been described in the previous embodiment and will not be repeated here.

[0082] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0083] In one embodiment, an abnormal travel event detection system is also provided to implement the above embodiments and preferred embodiments; details already described will not be repeated. The terms "module," "unit," "subunit," etc., used below refer to combinations of software and / or hardware that perform a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated. Figure 5 As shown, the abnormal travel event detection system includes: a first processing unit and a second processing unit, the first processing unit being connected to the second processing unit; wherein, the first processing unit is used to execute the companion list processing method of any of the above embodiments; the second processing unit is used to execute the abnormal travel event detection method of any of the above embodiments.

[0084] In one embodiment, see Figure 6 The abnormal travel event detection system also includes: a first image acquisition unit connected to the first processing unit, which is used to acquire video images and send the acquired video images to the first processing unit.

[0085] In one embodiment, please continue reading Figure 6 The abnormal travel event detection system also includes: a second image acquisition unit and an identity authentication unit, with the second processing unit connected to both the second image acquisition unit and the identity authentication unit; wherein, the second image acquisition unit is used to acquire video images and send the video images to the second processing unit; the identity authentication unit is used to authenticate personnel identity information and send the personnel identity information to the second processing unit.

[0086] The modules mentioned above can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented in hardware, the modules can reside in the same processor; or the modules can be located in different processors in any combination.

[0087] It should be noted that the abnormal travel event detection system provided in this application can detect not only children's transit events, but also other abnormal travel events, such as those involving the elderly, patients, or other persons without full civil capacity or lacking self-care ability. These individuals typically require supervision by a guardian. Unless otherwise specified, the following embodiments will be described using children's transit event detection as an example.

[0088] In one embodiment, Figure 7 A topology diagram of an abnormal travel event detection system is provided. Please refer to [link / reference]. Figure 7The topology includes: multiple front-end cameras, a cloud platform, security checkpoint cameras, and an identity authentication system. The cloud platform is communicatively connected to the multiple front-end cameras, security checkpoint cameras, and identity authentication system. The multiple front-end cameras serve as the first image acquisition unit, used to collect information about children and their companions. The security checkpoint cameras serve as the second image acquisition unit, used to collect information about children. The identity authentication system includes an identity authentication unit used to authenticate the identities of the children's companions. The cloud platform includes a first processing unit and a second processing unit, used to perform cluster analysis on the children and their companions, create or update a list of companions for each child, and analyze the child information and companion identity authentication data transmitted from the security checkpoint. If it is determined that the companion is not among the top N individuals in the companion list, an alert is triggered.

[0089] Further, please refer to Figure 8 The following is a flowchart of the operation of the abnormal travel event detection system, which includes the following steps:

[0090] Step S801: Multiple front-end cameras acquire the first video image and upload it to the cloud platform;

[0091] Step S802: The cloud platform extracts the features of the person in the first video image and determines whether they are a child; if yes, proceed to step S803; if no, end the process.

[0092] In step S803, the cloud platform determines whether there is a follower in the first video image; if yes, proceed to step S804; otherwise, end the process.

[0093] Step S804: The cloud platform determines whether the identity information of the accompanying person exists in the accompanying person list; if yes, proceed to step S805; if no, proceed to step S806.

[0094] Step S807: The security checkpoint camera captures a second video image and uploads the second video image to the cloud platform;

[0095] Step S808: The identity authentication system authenticates the identity of the accompanying adult and uploads the identity authentication information to the cloud platform.

[0096] Step S809: The cloud platform obtains the list of accompanying persons corresponding to the child and compares the identity information of the adults with the identity information in the list of accompanying persons;

[0097] In step S810, the cloud platform determines whether the adult's identity information is among the first N positions; if yes, the process ends; otherwise, step S811 is executed.

[0098] Step S811: The cloud platform triggers an alert.

[0099] The abnormal travel event detection system in this application embodiment has the following advantages:

[0100] (1) It is convenient. The information of children and their companions can be generated automatically through clustering platform without user input.

[0101] (2) It has high real-time performance. When people with children are going through security checks, it can automatically determine whether there is a child transit incident in real time. If an incident occurs, the on-site staff can intervene immediately and handle it in a timely manner.

[0102] (3) It has an automatic information maintenance function. Based on the daily social monitoring information, it can update personnel data in a timely manner, and one child can support multiple companions to avoid false alarms caused by changes in guardians.

[0103] (4) It has a wide coverage area and focuses on key areas. It is not affected by the field of view of a single camera. As long as the target appears under any networked camera, the child's information can be recorded. The security checkpoint can make an early warning judgment without the need for additional manpower.

[0104] In one embodiment, an electronic device is also provided, including a memory and a processor, wherein a computer program is stored in the memory; the processor is configured to run the computer program to perform the companion list processing method of any of the above embodiments, or the processor is configured to run the computer program to perform the abnormal travel event detection method of any of the above embodiments. It should be noted that specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated in this embodiment.

[0105] In one embodiment, a computer-readable storage medium is also provided, on which a computer program is stored. When executed by a processor, the computer program implements the steps of the companion list processing method of any of the above embodiments, or, when executed by a processor, the computer program implements the steps of the abnormal travel event detection method of any of the above embodiments. It should be noted that specific examples in this embodiment can be found in the examples described in the above embodiments and optional implementations, and will not be repeated in this embodiment.

[0106] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0107] Obviously, the accompanying drawings are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar situations based on these drawings without any creative effort. Furthermore, it is understood that although the work done in this development process may be complex and lengthy, for those skilled in the art, certain design, manufacturing, or production modifications made based on the technical content disclosed in this application are merely conventional technical means and should not be considered as insufficient disclosure of this application.

[0108] The term "embodiment" in this application refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily imply the same embodiment, nor does it imply that it is mutually exclusive with or independent of other embodiments. It will be clearly or implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0109] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims

1. A method of processing a list of followers, characterized by, include: Acquire video images, identify a first target object and a second target object accompanying the first target object in the video images, and extract the personnel features of the first target object and the second target object; Obtain personnel cluster data, compare the personnel characteristics of the first target object and the second target object with the personnel characteristics in the personnel cluster data, and determine the identity information of the first target object and the second target object respectively based on the comparison results; Based on the identity information of the first target object, obtain a list of companions corresponding to the first target object, and update the list of companions based on the identity information of the second target object, wherein the list of companions includes the identity information of at least one companion; The step of updating the companion list based on the identity information of the second target object includes: determining whether the identity information of the second target object already exists in the companion list; if it is determined that the identity information of the second target object already exists in the companion list, incrementing the intimacy level corresponding to the second target object by one count unit, and sorting the companions in the companion list according to the intimacy level.

2. The retinue list processing method according to claim 1, characterized by, The method further includes: If it is determined that the identity information of the second target object does not exist in the list of companions, the identity information of the second target object is added to the list of companions.

3. The method for processing the companion list according to claim 1, characterized in that, Determining a second target object accompanying the first target object in the video image includes: In the video image, at least one candidate whose distance from the first target object is within a preset range is identified; Based on the distance between each candidate and the first target object, at least one second target object is determined from the at least one candidate that is closest to the first target object.

4. An abnormal travel event detection method characterized by comprising: include: In the event that a second target object carries a first target object through the security checkpoint, the identity information of the second target object is obtained, as well as the list of companions corresponding to the first target object, wherein the list of companions includes the list of companions obtained by the method of any one of claims 1 to 3. The identity information of the second target object is compared with the identity information of the companions in the companion list, and the existence of an abnormal travel event is determined based on the comparison result.

5. The abnormal travel event detection method according to claim 4, characterized by, The identity information of the second target object is compared with the identity information of the accompanying persons in the accompanying persons list, and the existence of abnormal travel events is determined based on the comparison results, including: Determine whether the identity information of the second target object is ranked in the top N positions of the list of companions; If it is determined that the identity information of the second target object is in the top N positions of the list of companions, it is determined that there is no abnormal travel event; If it is determined that the identity information of the second target object is not ranked in the top N positions of the list of accompanying persons, an abnormal travel event is identified.

6. The abnormal travel event detection method according to claim 5, characterized by, After determining that the identity information of the second target object is not among the top N items in the list of accompanying persons, and confirming the existence of an abnormal travel event, the method further includes: A warning message is triggered, which is used to indicate the existence of an abnormal travel event.

7. The abnormal travel event detection method according to claim 4, characterized by, Obtain the list of followers corresponding to the first target object, including: Acquire video images, and extract personnel features of the first target object based on the video images; Obtain personnel cluster data, compare the first target object with the personnel characteristics in the personnel cluster data, and determine the identity information of the first target object based on the comparison result; Based on the identity information of the first target object, obtain the list of companions corresponding to the first target object.

8. An abnormal travel event detection system, characterized in that, include: A first processing unit and a second processing unit are connected; wherein the first processing unit is used to execute the companion list processing method according to any one of claims 1 to 3; and the second processing unit is used to execute the abnormal travel event detection method according to any one of claims 4 to 7.

9. The anomalous travel event detection system of claim 8, wherein, Also includes: A first image acquisition unit is connected to the first processing unit. The first image acquisition unit is used to acquire video images and send the acquired video images to the first processing unit.

10. The anomalous travel event detection system of claim 8, wherein, Also includes: The second image acquisition unit and the identity authentication unit are respectively connected to the second image acquisition unit and the identity authentication unit; wherein, the second image acquisition unit is used to acquire video images and send the video images to the second processing unit; the identity authentication unit is used to authenticate personnel identity information and send the personnel identity information to the second processing unit. 11.An electronic device comprising a memory and a processor, the electronic device characterized by, The memory stores a computer program; the processor is configured to run the computer program to perform the companion list processing method according to any one of claims 1 to 3, or the processor is configured to run the computer program to perform the abnormal travel event detection method according to any one of claims 4 to 7.

12. A computer readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the companion list processing method according to any one of claims 1 to 3, or, when the computer program is executed by the processor, it implements the steps of the abnormal travel event detection method according to any one of claims 4 to 7.

Images