Identity authentication method based on image data processing and access control machine

Abstract

The application discloses an identity authentication method based on image data processing and a gate guard. In the method, after a tenant applies for moving online, the truck can be automatically matched as the truck recorded in the moving application when the truck enters the community. Whether the parking position of the truck matches the house position in the moving application can be determined through image recognition, and whether the personnel getting on and off the truck interact with the tenant submitting the application can be determined through video image analysis. When both are determined to be yes, the truck can be determined as a legal identity authentication target, and the truck is released at the exit. Through image data processing analysis, the safety and accuracy of identity authentication are ensured, and the efficiency of identity authentication of the truck entering the community is greatly improved.

Description

Technical Field

[0001] This application relates to the fields of image data processing and identity authentication, and in particular to identity authentication methods and access control machines based on image data processing. Background Technology

[0002] Most residential communities are equipped with access control gates at their entrances and exits to improve the security of residents and their property by verifying the identities of people and vehicles entering and exiting the community.

[0003] In modern urban residential communities, besides homeowners, many tenants also live there, and tenants move relatively frequently. To ensure the safety of property within the community, property management companies generally require tenants to contact the homeowner before moving out, and then the homeowner needs to obtain a pass from the property management company before allowing trucks with the pass to enter or leave the community.

[0004] However, in reality, this method of identity verification is far too inefficient: sometimes, because the landlord is out of town and cannot be contacted, or is too busy with work to go to the property management office in time to obtain the pass, the tenant may not be able to get the pass on time as expected. This could not only result in additional rental costs due to the delayed move, but also disrupt their normal work and life due to missing the planned move-in date. Summary of the Invention

[0005] This application provides an identity authentication method and access control machine based on image data processing, which improves the efficiency of identity authentication for trucks entering the community while ensuring the security and accuracy of identity authentication.

[0006] Firstly, this application provides an identity authentication method based on image data processing, comprising: receiving a moving application sent online by a tenant, including a tenant's facial image, vehicle license plate information, and house number information; after a truck matching the vehicle license plate information enters the community, obtaining the real-time location of the truck and a video image segment of an interaction to be confirmed through surveillance video; determining that the real-time location of the truck matches a preset parking area corresponding to the house number information; using a preset interaction recognition model to identify the video image segment of the interaction to be confirmed, determining that the tenant has interacted with a person getting off the truck; after determining that the real-time location of the truck matches the preset parking area corresponding to the house number information and that the tenant has interacted with a person getting off the truck, when the truck is identified at the exit, determining that the truck's identity authentication is successful, and opening the door to allow passage.

[0007] In conjunction with some embodiments of the first aspect, in some embodiments, after a truck matching the vehicle license plate information enters the residential area, the real-time location of the truck and the video image segment to be confirmed are obtained through surveillance video. Specifically, this includes: after the truck matching the vehicle license plate information enters the residential area, sending a trajectory tracking instruction including the vehicle license plate information and a vehicle photo to the control center server, the trajectory tracking instruction being used to instruct the control center server to identify and report the real-time location of the truck in the residential area at preset time intervals; receiving the real-time location of the truck in the residential area sent by the control center server at preset time intervals; sending an interaction recognition instruction including a vehicle photo of the truck and a tenant's facial image to the control center server, the interaction recognition instruction being used to instruct the control center server to extract images of the person getting off the truck and the tenant within a preset interaction distance from the surveillance video; and receiving the images of the person getting off the truck and the tenant within a preset interaction distance sent by the control center server as the video image segment to be confirmed.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, sending the interactive recognition instruction including a vehicle photo of the truck and a tenant's facial image to the control center server specifically includes: after determining that the real-time location of the truck matches the preset parking area corresponding to the house number information, sending the interactive recognition instruction including a vehicle photo of the truck and a tenant's facial image to the control center server.

[0009] In conjunction with some embodiments of the first aspect, in some embodiments, determining that the real-time location of the truck matches the preset parking area corresponding to the house number information specifically includes: when the truck is photographed in the preset parking area corresponding to the house number information, determining that the real-time location of the truck matches the preset parking area corresponding to the house number information.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, after receiving the moving application sent online by the tenant and before matching the vehicle license plate information with the truck, the method further includes: determining that the homeowner corresponding to the house number information has not performed an approval operation within a preset review period; acquiring video image segments including the tenant's image from the community surveillance video data; determining that the tenant's activity pattern conforms to preset residence rules based on the shooting time and shooting location information of each video image segment; and determining that the tenant is a lawful tenant if the tenant is determined to be a lawful tenant.

[0011] In conjunction with some embodiments of the first aspect, in some embodiments, the acquisition of video image segments including the tenant's image from the community surveillance video data specifically includes: sending a resident identification instruction including the tenant's facial image to the control center server, the resident identification instruction being used to instruct the control center server to extract video image segments including the tenant's image within a preset time period from the stored surveillance video data; and receiving the video image segments including the tenant's image sent by the control center server.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, before the step of obtaining the real-time location of the truck and the interactive video image segment to be confirmed through monitoring video, the method further includes: determining that the license plate of the currently identified truck matches the vehicle license plate information in the moving application; generating a route guidance map based on the current location of the truck and the house number information in the moving application; displaying the route guidance map and opening the door to allow passage.

[0013] In some embodiments, in conjunction with the first aspect, the method further includes: generating guidance information when it is determined that the real-time location of the truck is not on a specified route in the route guidance map; and broadcasting the guidance information to cells within a preset broadcast distance range around the real-time location of the truck.

[0014] In a second aspect, embodiments of this application provide an access control machine, including: a camera, a display, an electric door, one or more processors, and a memory; the camera is used to capture images of objects entering or exiting through the access control machine; the display is used to display data based on data sent by the processor; the electric door is used to open or close based on instructions sent by the processor; the memory is coupled to the one or more processors, and the memory is used to store computer program code, the computer program code including computer instructions, and the one or more processors call the computer instructions to execute the method described in the first aspect and any possible implementation thereof.

[0015] Thirdly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on an access control machine, cause the access control machine to perform the method described in the first aspect and any possible implementation thereof.

[0016] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0017] 1. By using image recognition from surveillance videos within the community, the real-time location of the truck was determined to match the preset parking area corresponding to the house number information in the moving application. Furthermore, by analyzing the video image segments of the interaction to be confirmed, it was determined that the tenant interacted with the person getting off the truck. Therefore, it can be determined that the truck is a vehicle that meets the identity authentication criteria. This effectively solves the problem of low efficiency in using pass-based truck identity authentication. By directly processing image data, the security and accuracy of identity authentication can be guaranteed, and trucks can pass through identity authentication seamlessly if they meet the preset conditions identified by image recognition. This improves the efficiency of identity authentication for trucks entering the community.

[0018] 2. By extracting and analyzing video image segments from historical surveillance video data of the community and the facial information of tenants who submit moving applications, the system can automatically approve moving applications even if the homeowner corresponding to the house number has not performed an approval operation within the preset review period, but the tenant who submitted the moving application is determined to be a compliant tenant. This effectively solves the problem of low approval efficiency for compliant tenants' moving applications when the homeowner's review operation status is abnormal, and greatly improves the approval efficiency of online moving applications while ensuring the safety of people and property in the community.

[0019] 3. Upon identifying a truck whose license plate information matches the moving application, a route map can be directly generated and displayed, facilitating the truck's rapid arrival at the target location within the community. The system can also monitor the truck's location in real time. If its route deviates from the expected path, route guidance information can be generated and broadcast from nearby loudspeakers. This effectively solves the problem of unfamiliar trucks struggling to determine their routes, preventing them from taking detours, wasting their own time, and inconveniencing other residents, thus significantly improving the efficiency of trucks reaching their destination. Attached Figure Description

[0020] Figure 1 This is a schematic diagram of a system architecture for which the identity authentication method based on image data processing can be applied in the embodiments of this application;

[0021] Figure 2 This is an exemplary scenario diagram illustrating the identity authentication method based on image data processing as described in the embodiments of this application;

[0022] Figure 3 This is an exemplary hardware structure block diagram of the access control machine 100 in the embodiments of this application;

[0023] Figure 4 This is a flowchart illustrating an identity authentication method based on image data processing in an embodiment of this application;

[0024] Figure 5This is a flowchart illustrating the relocation application stage in the identity authentication method based on image data processing according to an embodiment of this application.

[0025] Figure 6 This is a flowchart illustrating the matching truck guidance stage in the identity authentication method based on image data processing according to an embodiment of this application.

[0026] Figure 7 This is a flowchart illustrating the truck identity authentication stage in the image data processing-based identity authentication method of this application. Detailed Implementation

[0027] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0028] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0029] Figure 1 This is a schematic diagram of a system architecture for which the identity authentication method based on image data processing can be applied in the embodiments of this application.

[0030] Please see Figure 1 Access control systems can be used at each entrance and exit of the residential community, and cameras can monitor various areas within the community in real time. All access control systems and cameras can be connected to a control center server, enabling data transmission between devices and allowing captured video images to be stored on the server.

[0031] It should be noted that since both the access control machine and the control center server have certain data processing capabilities, and with the popularization and development of high-performance chips, the data processing capabilities of the access control machine itself are also constantly improving, some steps in the identity authentication method based on image data processing in this application embodiment can be executed by the control center server or by the access control machine, and no limitation is made here.

[0032] For ease of description and understanding, the following embodiments of this application use an access control machine to perform most of the steps as an example. However, it is understood that some steps can also be performed directly by the control center server, or the relevant data can be sent to the control center server, which will then perform the relevant steps and send the processing results back to the access control machine. This is not limited here.

[0033] In practical applications, access control systems can take many different forms, such as roller shutters, glass doors, and double-sided opening mechanisms. For ease of understanding and description, the embodiments in this application use... Figure 1 The common vehicle gate configuration shown is described as an example of an access control system. An access control system typically includes an access camera for capturing images and an electric gate for controlling the opening and closing of entrances and exits.

[0034] In related technologies, the process of verifying the identity of a truck in a residential community when a tenant wants to move is too cumbersome. It requires the landlord to issue a release slip. If the landlord is unreachable or delayed by something, the identity verification cannot be completed. Since the truck cannot enter or leave, the tenant cannot move, which leads to a waste of time and rental costs.

[0035] The image data processing-based identity authentication method used in this embodiment allows tenants to submit online moving applications. When a truck enters the community, the system automatically matches the truck with the information recorded in the application. Image recognition can determine if the truck's parking location matches the house location in the moving application, and video image analysis can determine if people getting on and off the truck interact with the tenant who submitted the application. If both are confirmed, the truck is deemed a legitimate target for identity authentication and allowed to pass through the exit. Through image data processing and analysis, the system significantly improves the efficiency of authenticating trucks entering the community while ensuring the security and accuracy of identity authentication.

[0036] Figure 2 This is an exemplary scenario diagram illustrating the identity authentication method based on image data processing in the embodiments of this application.

[0037] like Figure 2 In (a) of the example, a tenant in a room in the community submitted a moving application online.

[0038] like Figure 2 In (b), when a truck with a license plate matching the information in the moving application appears in front of the access control machine, the access control machine determines that the license plate matches and can directly allow the truck to pass.

[0039] like Figure 2In step (c), when the truck is parking and unloading goods, the community's security cameras can monitor the process. Image analysis of the video images can determine if the truck's parking location matches the housing information in the moving application, and if the tenant who submitted the application interacted with the person entering the truck. Based on these findings, it can be determined that the truck exhibited no abnormal behavior and is a legitimate vehicle.

[0040] like Figure 2 In (d), when the truck appears in front of the access control machine's exit, it does not need to issue a release slip; the access control machine can directly open the door and allow it to leave.

[0041] As can be seen, by adopting the identity authentication method based on image data processing in this application embodiment, it is no longer necessary for landlords, property management, tenants and other parties to coordinate and issue a pass in order to authenticate the identity of trucks entering the community. By directly processing image data, the security and accuracy of identity authentication can be guaranteed, and trucks can pass through identity authentication seamlessly if they meet the preset conditions of image recognition, thereby improving the efficiency of identity authentication for trucks entering the community.

[0042] To facilitate understanding of the image data processing-based identity authentication method in the embodiments of this application, the exemplary access control machine 100 provided in the embodiments of this application will be introduced first.

[0043] Please refer to Figure 3 This is an exemplary hardware structure block diagram of the access control machine 100 in this application embodiment.

[0044] In some embodiments, the access control device 100 includes a processor, a memory, a camera, a display, and an electric door connected via a system bus.

[0045] The camera is used to capture images of objects entering and exiting through the access control machine 100; the display is used to show information; and the electric door is used to receive instructions to open or close.

[0046] The processor provides computational and control capabilities. It may include one or more processing units, such as an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), and / or a neural network processing unit (NPU). These different processing units may be independent devices or integrated into one or more processors.

[0047] If the processor includes an NPU (Neural Processing Unit), it can help improve the efficiency of deep learning processing. An NPU is a neural network (NN) computing processor that, by borrowing from the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, can quickly process input information and continuously learn on its own. An NPU can be used to implement intelligent cognitive applications in the access control machine 100, such as image recognition, facial recognition, speech recognition, and text understanding.

[0048] The access control machine 100's memory includes a non-volatile storage medium. This non-volatile storage medium stores the operating system, computer programs, and a database. The database of the access control machine 100 is used to store data.

[0049] When the computer program is executed by the processor, it implements the image data processing-based identity authentication method in the embodiments of this application.

[0050] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the solution of this application and does not constitute a limitation on the access control machine 100 to which the solution of this application is applied. The specific access control machine 100 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0051] In some embodiments of this application, a computer-readable storage medium is also provided, including instructions that, when executed on the access control machine 100, cause the access control machine 100 to perform the identity authentication method based on image data processing as described in this application.

[0052] The following section combines the hardware structure diagram of the exemplary access control machine 100 described above with... Figure 2The schematic diagram shown illustrates a scenario using an image data processing-based authentication method. This description illustrates the image data processing-based authentication method used in this embodiment of the application.

[0053] Please see Figure 4 This is a flowchart illustrating an identity authentication method based on image data processing in an embodiment of this application.

[0054] S401. Receive moving requests sent online by tenants, including tenant facial images, vehicle license plate information, and house number information;

[0055] Tenants can submit moving requests on their mobile phones, uploading and filling in their facial images, vehicle license plate information, and house number information. Access control machines or control center servers can receive moving requests sent online by tenants.

[0056] The vehicle license plate information refers to the license plate number of the truck that the tenant scheduled to move in; the house number information refers to the house number where the tenant lives. This house number is unique within the community. This house number can be a number identified by the community itself or a unique house number assigned by the Housing and Construction Bureau. No restrictions are imposed here.

[0057] In some embodiments, the moving request may also include information such as the moving date and vehicle size, which is not limited here.

[0058] S402. After a truck matching the vehicle license plate information enters the community, the real-time location of the truck and the video image segments to be confirmed are obtained through the monitoring video.

[0059] When the access control machine recognizes that the license plate number of the truck waiting to enter matches the vehicle photo information in the moving application, the truck can be allowed to pass directly.

[0060] Furthermore, the access control machine can send instructions to the control center server to activate the cameras within the community to capture images of the truck's movement, thereby obtaining the truck's real-time location.

[0061] In addition, it is also possible to acquire interactive video image clips to be confirmed, which include images of the person getting off the truck and the tenant within a preset interactive distance.

[0062] S403. Determine that the real-time location of the truck matches the preset parking area corresponding to the house number information;

[0063] Each house in the community can be pre-set with a corresponding parking area, which can be stored as a correspondence between house number information and pre-set parking area.

[0064] There are many ways to determine whether the real-time location of the truck matches the preset parking area corresponding to the house number information. For example, a match can be determined when the truck is captured in the preset parking area corresponding to the house number information; a match can also be determined when the truck is captured in the preset parking area corresponding to the house number information for a continuous preset parking time; or a match can be determined when the distance between the truck and the camera at the preset parking area corresponding to the house number information is within a preset distance threshold based on the captured images. There are also other similar methods that can quickly and accurately determine the match between the real-time location of the truck and the preset parking area corresponding to the house number information without GPS or other positioning technologies, which are not limited here.

[0065] If a moving truck is parked in the correct, pre-designated parking area, then its actions are reasonable; however, if a moving truck is parked in the wrong, it suggests that the person in control of the truck may have other intentions.

[0066] Therefore, the access control machine or control center server can determine whether the real-time location of the truck matches the preset parking area corresponding to the house number information;

[0067] If a match is found, then S404 can be executed.

[0068] If there is no match, it indicates that the truck is behaving abnormally. A security alert can be issued to notify property management personnel (such as security guards) to check. Alternatively, the truck can be added to the restricted list first, and then removed from the restricted list after its safety has been confirmed.

[0069] S404. Use a preset interaction recognition model to identify the video image segment of the interaction to be confirmed, and determine that the tenant has interacted with the person getting off the truck;

[0070] The video image segment to be confirmed includes images of people getting off the truck and the tenant within a preset interaction distance. However, the fact that the people getting off the truck and the tenant are within the preset interaction distance does not necessarily mean that there is interaction between them. Therefore, a pre-trained preset interaction recognition model will be used to identify the video image segment to be confirmed in order to determine whether there is interaction.

[0071] If there is interaction, it indicates that the tenant's behavior with the truck is reasonable. Combined with the real-time location of the truck and the preset parking area corresponding to the house number information, it can be determined that the truck is the one that came to move the house. There is no abnormal behavior, and step S405 can be executed.

[0072] If there is no interaction, it is possible that the truck has a fake license plate, or that the tenant applied for the truck to come to the community for other purposes. In this case, it is impossible to directly determine that the truck is trustworthy, and automatic identity authentication cannot be completed for the truck. Manual verification is required in the conventional way.

[0073] S405. When the truck is detected at the exit, the door shall be opened to allow it to pass.

[0074] If the real-time location of the truck matches the preset parking area corresponding to the house number, and if there is interaction between the tenant and the person getting off the truck, the truck can be identified as a trustworthy truck with reasonable behavior. The access control machine or control center server can automatically authenticate the truck. When the truck is detected at the exit, the door can be opened directly without issuing a pass.

[0075] In this embodiment, image recognition of the surveillance video within the community is used to determine the real-time location of the truck and match it with the preset parking area corresponding to the house number information in the moving application. Furthermore, by analyzing the interactive video image segments to be confirmed, it is determined that the tenant interacted with the person getting off the truck. Therefore, the truck can be identified as a vehicle that meets the identity authentication criteria. This effectively solves the problem of low efficiency in using pass-through methods for truck identity authentication. By directly processing image data, the security and accuracy of identity authentication can be guaranteed, while allowing trucks to pass through identity authentication seamlessly if they meet the preset conditions identified by image recognition. This improves the efficiency of identity authentication for trucks entering the community.

[0076] In the above embodiment, a preset interaction recognition model can be used to identify the video image segment of the interaction to be confirmed, and to determine that the tenant has an interaction with the person getting off the truck. The preset interaction recognition model is a pre-trained deep learning model.

[0077] The basic architecture of this deep learning model can be, for example, the BERT classification model, the recurrent neural network (RNN) model, or other classification prediction model frameworks, which are not limited here.

[0078] The training data for this deep learning can be: a large number of surveillance video images in the community, including trucks and people getting off the trucks. In some moving scenarios, the images in which the tenants and people getting off the trucks interact are manually labeled with the vehicle location, the people getting off the trucks, the tenants, and the label "interaction exists". In other scenarios, the images in which people getting off the trucks do not interact with others are manually labeled with the vehicle location, the people getting off the trucks, and the label "no interaction exists".

[0079] By using this training data to train a deep learning model that has undergone pre-training for video recognition, a pre-trained interaction recognition model can be obtained. When given the target truck image, the target tenant image, and the video image to be analyzed as input, this model can determine whether the video image contains an interaction between "the person getting off the target truck and the target tenant," and output the analysis result: interaction exists, or no interaction exists.

[0080] In practical applications, to further ensure the security of automatic truck identification through image recognition, the trustworthiness of the tenant and any abnormalities in the truck can be assessed first.

[0081] The following are different optional stages, combined with Figure 5 , Figure 6 and Figure 7 The flowcharts of some stages of the image data processing-based identity authentication method are shown respectively. Figure 1 The system architecture diagram shown below provides a detailed description of the image data processing-based identity authentication method in this application embodiment:

[0082] like Figure 5 The diagram shown is a flowchart of the moving application stage in the identity authentication method based on image data processing according to an embodiment of this application.

[0083] S501: The cameras in the community transmit daily monitoring video data to the control center server in real time.

[0084] Cameras are distributed throughout the community, and these cameras can transmit daily monitoring video data to the control center server in real time.

[0085] S502, the control center server stores daily monitoring video data;

[0086] After receiving the surveillance video data transmitted from each camera in the community, the control center server can store it according to different identifiers for different areas.

[0087] S503: The access control machine receives a moving application sent online by the tenant, which includes the tenant's facial image, vehicle license plate information and house number information;

[0088] Please refer to step S401, which will not be repeated here.

[0089] S504. The access control machine has determined that the homeowner corresponding to the house number information has not performed the approval operation within the preset review period.

[0090] After a tenant submits a moving application online, if the homeowner corresponding to the property number confirms and approves the move within the preset review period, the access control machine or control center server can receive the approval instruction and begin execution directly. Figure 6 and Figure 7 The subsequent stages are shown.

[0091] If the homeowner corresponding to the house number does not approve the application within the preset review period, the subsequent stages in this application embodiment will not be executed. The tenant will need to communicate with the homeowner and initiate the online moving application process again or abandon the online application.

[0092] If the homeowner corresponding to the house number does not complete the approval process within the preset review period, it indicates that the homeowner may be unreachable or busy in the near future. In this case, the subsequent steps of the moving application stage can be executed. The credibility of the tenant can be confirmed by identifying historical monitoring image data, thereby automatically determining whether to approve the moving application and improving the efficiency of application processing.

[0093] S505: The access control machine sends a resident identification command to the control center server, which includes the tenant's facial image;

[0094] If the homeowner corresponding to the property number fails to complete the approval process within the preset review period, the access control system sends a resident identification command to the control center server, which includes the tenant's facial image. This resident identification command instructs the control center server to extract video clips containing the tenant's image from stored surveillance video data within a preset time period (e.g., within 3 months), thereby facilitating the analysis of the tenant's behavior.

[0095] S506. The control center server identifies and extracts video image segments containing the tenant within a preset time period from daily monitoring video data.

[0096] After receiving the resident identification command from the access control machine, the control center server compares the tenant's face image in the resident identification command with the face images in the regular monitoring video data. This allows it to extract video image segments that include the tenant within a preset time period from the daily monitoring video data.

[0097] S507, The control center server sends video image clips, including those of the tenant, to the access control machine;

[0098] It is understandable that each video image clip may include not only image information, but also information such as the shooting time and shooting location.

[0099] S508: If the access control machine determines that the tenant's activity pattern conforms to the preset residence rules based on the shooting time and shooting location information of each video image segment, then the tenant is identified as a lawful tenant.

[0100] In some embodiments, the control center server may directly execute step S508 and then send the execution result to the access control machine; this is not limited here.

[0101] The preset residency rules are a set of pre-defined rules that define a tenant as a regular resident, reflecting their living patterns. For example, these rules might include: over 70% of weekday arrival times within the building fall within a preset timeframe (e.g., 6:00-8:00), and entry times within the building also fall within a preset timeframe (e.g., 18:00-20:00); over 60% of the footage shows the tenant's location along a regular route from the building to the access control machine, etc., rules that confirm the tenant as a regular working professional. Understandably, these preset residency rules can also include other rules to enhance the tenant's credibility; this is not limited here.

[0102] If the access control machine determines that the tenant's activity pattern conforms to the preset residence rules based on the shooting time and location information of each video image segment, the tenant is identified as a lawful tenant. That is, the tenant can be considered a normal and compliant tenant, who is likely to be trustworthy and whose behavior is unlikely to pose a safety risk to the people or property in the community. The tenant's moving application can be approved directly and automatically.

[0103] If it is determined that the tenant's activity pattern does not conform to the preset residency rules, the tenant can be identified as a non-compliant tenant, and automatic approval can be skipped, continuing to wait for the landlord's approval.

[0104] S509, The relocation application for the access control system has been approved;

[0105] If the homeowner corresponding to the house number does not approve the move within the preset review period, and the tenant who submitted the move application is confirmed to be a compliant tenant, the access control machine or control center server can automatically determine that the move application is approved.

[0106] In the moving application stage described in this application embodiment, by extracting and analyzing video image segments from historical surveillance video data of the community and the facial information of the tenant submitting the moving application, the moving application can be automatically approved even if the homeowner corresponding to the house number information has not performed the approval operation within the preset review period, but it is determined that the tenant submitting the moving application is a compliant tenant. This effectively solves the problem of low approval efficiency for compliant tenants' moving applications when the homeowner's review operation status is abnormal, and greatly improves the approval efficiency of online moving applications while ensuring the safety of people and property in the community.

[0107] In some embodiments, after a moving application is approved, the truck matching the moving application can be guided within the community.

[0108] Please see Figure 6 This is a flowchart illustrating the matching truck guidance stage in the identity authentication method based on image data processing according to an embodiment of this application.

[0109] S601, The access control machine determines that the license plate of the currently identified truck matches the vehicle license plate information in the moving application;

[0110] When the truck arrives at the access control machine, the machine can identify the truck's license plate. The identified license plate is compared with the vehicle photo information in the moving application. If they match, step S602 can be executed; if they do not match, no operation can be performed or a preset routine operation can be executed.

[0111] S602, The access control machine generates and displays a route map based on the truck's current location and the house number information in the moving application;

[0112] If the license plate of the currently identified truck matches the vehicle license plate information in the moving application, the access control machine can generate a route map based on the truck's current location and the house number information in the moving application, and display the route map on the access control machine's display screen facing the truck to indicate the truck's driving route within the community.

[0113] It is understandable that in step S602, the current location of the truck is consistent with the location of the access control machine that identifies the truck's license plate information. Therefore, as long as the location information of each access control machine and the location information of each house in the community are preset, the route guidance map can be accurately generated without GPS or other positioning processing technologies.

[0114] S603, Access control machine opens door to allow passage;

[0115] After confirming that the license plate of the currently identified truck matches the vehicle license plate information in the moving application and displaying a route map, the access control machine can open the door to allow passage.

[0116] S604, the access control machine sends a trajectory tracking instruction to the control center server, which includes the truck's license plate information and vehicle photo;

[0117] The trajectory tracking indicator is used to instruct the control center server to identify and report the real-time location of the truck in the community at preset time intervals.

[0118] S605. The control center server determines the real-time location of the truck by acquiring the monitoring video data.

[0119] The control center server can perform image matching between real-time monitoring data and the truck's license plate information and vehicle photos, thereby determining the truck's real-time location based on the location and shooting distance of the community camera that captured the truck.

[0120] Understandably, since the location information of each camera in the community can be preset, determining the real-time location of the truck in this step does not require GPS or other positioning processing technologies. The real-time location of the truck in the community can be obtained simply by calculating the location and shooting distance of the community camera that captured the truck.

[0121] S606, The control center server sends the real-time location of the truck to the access control machine;

[0122] S607. When the access control machine determines that the real-time location of the truck is not on the designated route in the route guidance map, it generates guidance information.

[0123] S608, The access control machine broadcasts the directional guidance information to the community within a preset broadcast distance range around the real-time location of the truck;

[0124] In some embodiments, steps S606 to S608 may also be executed directly by the control center server, or some actions, calculations, or information transmissions may be executed by the control center server; this is not limited here.

[0125] If the truck's real-time location is not on the designated route in the route guidance map, the truck may have taken the wrong route. In this case, guidance information can be sent to the community broadcast within a preset broadcast distance range around the truck's real-time location, so that the community broadcast can play the correct route guidance to drive the truck to the parking area corresponding to the house number information.

[0126] In some embodiments, if it is determined that the truck has failed to follow the broadcast directional guidance information more than a preset number of times, it indicates that the truck may have entered the community for other purposes than moving. In this case, the access control machine or control center server can send an alarm message to the property management personnel, which includes a picture of the truck, its license plate information, and its real-time location information. In some embodiments, the truck can also be added to a prohibited entry list first, and then removed from the prohibited entry list after the property management personnel confirm its safety.

[0127] In the truck matching and guidance stage described in this embodiment, when a truck matching the license plate information in the moving application is identified, a route guidance map can be directly generated and displayed, facilitating the truck's rapid arrival at the target location within the community. The truck's location within the community can be monitored in real time; if its route is abnormal, route guidance information can be generated and nearby broadcasts can be invoked to provide guidance. This effectively solves the problem of external trucks having difficulty determining their routes due to unfamiliarity with the community environment, preventing trucks from taking detours, wasting their own time, and affecting other residents, thus greatly improving the efficiency of trucks reaching their target locations.

[0128] After the truck stops moving, the identity verification of the truck can be determined by the area where the truck was parked and whether the people in the truck interacted with the tenant who submitted the moving application.

[0129] Please see Figure 7 This is a flowchart illustrating the truck identity authentication stage in the image data processing-based identity authentication method of this application.

[0130] S701, The access control machine determines the real-time location of the truck and matches it with the preset parking area corresponding to the house number information;

[0131] S702, the access control machine sends an interactive identification command to the control center server, which includes a photo of the truck and a facial image of the tenant;

[0132] The interaction recognition instruction is used to instruct the control center server to extract images of the person getting off the truck and the tenant within a preset interaction distance, as video image segments of the interaction to be confirmed.

[0133] S703. The control center server extracts images of the person getting off the truck and the tenant within a preset interaction distance, as video image segments of the interaction to be confirmed.

[0134] S704. The control center server sends the video image segment to be confirmed to the access control machine.

[0135] S705 The access control machine uses a preset interaction recognition model to identify the video image segment of the interaction to be confirmed, and determines that the tenant has interacted with the person getting off the truck;

[0136] S706. When the access control machine recognizes the truck at the exit, it opens the door to allow passage.

[0137] Steps S701~S706 and Figure 4 The steps S401 to S405 in the illustrated embodiment are similar, and can be referred to the descriptions in steps S401 to S405, which will not be repeated here.

[0138] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0139] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0140] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.

[0141] 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. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. An identity authentication method based on image data processing, characterized in that, include: Receive moving requests sent online by tenants, including tenant facial images, vehicle license plate information, and house number information; After receiving the tenant's online moving application and before matching the vehicle license plate information with the truck, the method further includes: determining that the homeowner corresponding to the house number information has not performed an approval operation within a preset review period; acquiring video image segments from the community surveillance video data that include the tenant's image; determining that the tenant's activity pattern conforms to preset residence rules based on the shooting time and shooting location information of each video image segment; and determining that the tenant is a lawful tenant if the tenant is determined to be a lawful tenant. After a truck matching the vehicle license plate information enters the community, the real-time location of the truck and the video image segment to be confirmed are obtained through surveillance video; the video image segment to be confirmed is an image extracted from the surveillance video of a person getting off the truck and the tenant within a preset interaction distance; When the truck is photographed in the preset parking area corresponding to the house number information, the real-time location of the truck is determined to match the preset parking area corresponding to the house number information. The preset interaction recognition model is used to identify the video image segment to be confirmed, and it is determined that the tenant interacted with the person getting off the truck. Once the real-time location of the truck matches the preset parking area corresponding to the house number information and the tenant interacts with the person getting off the truck, the truck is identified at the exit, the truck's identity is confirmed to be valid, and the door is opened to allow passage.

2. The method according to claim 1, characterized in that, After a truck matching the vehicle license plate information enters the residential area, the real-time location of the truck and the video image segments to be confirmed are obtained through surveillance video, specifically including: After a truck matching the vehicle license plate information enters the community, a trajectory tracking instruction including the vehicle license plate information and vehicle photo of the truck is sent to the control center server. The trajectory tracking instruction is used to instruct the control center server to identify and report the real-time location of the truck in the community at preset time intervals. Receive the real-time location of the truck in the community from the control center server at preset time intervals; Send an interactive recognition instruction, including a photo of the truck and a facial image of the tenant, to the control center server. The interactive recognition instruction is used to instruct the control center server to extract images of the person getting off the truck and the tenant within a preset interaction distance from the surveillance video. The system receives images sent by the control center server showing the person getting off the truck and the tenant within a preset interaction distance, which are used as the video image segments of the interaction to be confirmed.

3. The method according to claim 2, characterized in that, Sending the interactive recognition command, which includes a photo of the truck and a facial image of the tenant, to the control center server specifically includes: After determining that the real-time location of the truck matches the preset parking area corresponding to the house number information, an interactive recognition command including a photo of the truck and a facial image of the tenant is sent to the control center server.

4. The method according to claim 1, characterized in that, The acquisition of video image segments, including images of the tenant, from the community surveillance video data specifically includes: Send a residence recognition instruction including the tenant's facial image to the control center server. The residence recognition instruction is used to instruct the control center server to extract video image segments including the tenant's image from the stored surveillance video data within a preset time period. Receive video image segments, including images of the tenant, sent by the control center server.

5. The method according to any one of claims 1 to 3, characterized in that, Before the step of obtaining the real-time location of the truck and the interactive video image segment to be confirmed through monitoring video, the method further includes: Determine if the license plate of the currently identified truck matches the vehicle license plate information in the moving application; Based on the current location of the truck and the house number information in the moving application, a route guidance map is generated; Display the route map and open the gate to allow passage.

6. The method according to claim 5, characterized in that, The method further includes: If it is determined that the real-time location of the truck is not on the specified route in the route guidance map, directional guidance information is generated; The guidance information is broadcast to communities within a preset broadcast distance range around the real-time location of the truck.

7. An access control machine, characterized in that, include: Camera, display, electric door, one or more processors and memory; The camera is used to capture images of objects entering and exiting through the access control machine; The display is used to display data based on the received data sent by the processor; The electric door is used to open or close based on instructions received from the processor; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the access control machine to perform the method as described in any one of claims 1-6.

8. A computer-readable storage medium comprising instructions, characterized in that, When the instruction is executed on the access control machine, the access control machine performs the method as described in any one of claims 1-6.

Images