An elevator access control security system and method based on image recognition

Abstract

The application provides an elevator access control security system and method based on image recognition, and belongs to the technical field of elevator access control safety and data protection. The method comprises the following steps: S100, predicting the number of passengers N1 in the next operation cycle of the elevator; S200, when N1 is less than a preset value Mt, preloading a first image acquisition process; S300, determining the actual number of passengers N2 in the next operation cycle of the elevator; when N2 is less than Mt, judging whether the elevator is normally started within a preset time length, if yes, returning to step S100; otherwise, entering step S400: S400, starting the first image acquisition process to issue an interactive instruction for entering image recognition, and based on the result of image recognition, executing elevator access control measures. The system is used for implementing the method. The application effectively balances the safety and convenience requirements and improves the system resource utilization efficiency by combining limited access control technology with security monitoring.

Description

Technical Field

[0001] This invention belongs to the field of elevator access control security and data protection technology, and particularly relates to an elevator access control security system and method based on image recognition. Background Technology

[0002] Traditional elevators only provide standard door opening, passenger pick-up, and closing operations, allowing anyone to enter and reach any floor. However, with the development of artificial intelligence and image recognition technologies, and the increasing prevalence of intelligent elevators, the automation and intelligence levels of elevators in high-rise residential and commercial office buildings are constantly improving.

[0003] In some strictly managed commercial office buildings, such as star-rated hotels, guests receive a hotel card or other form of identification (e.g., key ring, ID card) or identity verification (e.g., fingerprint, facial recognition, voice recognition, iris recognition, etc.) upon check-in. When using the elevator, guests must first verify their identity, such as by swiping a card or undergoing identity recognition, before the elevator can be opened and access can only be granted to designated floors (including designated floors and some public area floors). For example, Chinese invention patent publication CN114104888A discloses an automatic elevator with facial recognition. In public places like commercial office buildings, such strict identity management measures are necessary and comply with relevant laws and regulations. Some residential communities have also introduced similar elevator access control technologies, such as Chinese invention patent CN109502436B proposing an intelligent system safety elevator, and Chinese invention patent publication CN112017344A proposing an intelligent device that controls access and elevators using facial recognition technology.

[0004] However, residential communities differ from commercial office buildings. Residents' activities should not be limited to their own floors or some shared floors. To foster good neighborly relations, residents on different floors or even in different buildings frequently interact. Simply copying the elevator access control technology used in commercial office buildings—for example, restricting a resident to only access designated floors (including designated floors and some common areas)—would not only severely inconvenience normal communication among residents but also affect other essential needs (such as food delivery and courier services). While visitor access mechanisms can still facilitate interaction between residents on different floors or in different buildings, this requires active participation from both residents and visitors each time, making the process complex and necessitating modifications to the existing elevator access control system.

[0005] To balance public safety and the need for personal convenience, a compromise is to introduce limited access control technology into elevators while strengthening elevator access control and security video surveillance management. Limited access control technology means that once authorized residents (owners) enter the elevator, it can operate normally (reaching any floor). In this way, only one authorized passenger needs to be in the elevator at any time, which will not affect the normal operation of the elevator. At the same time, the relevant video surveillance security system can also ensure public safety.

[0006] However, the above approach still presents some challenges. First, elevator traffic in commercial office buildings exhibits a clear morning-noon-evening peak pattern, making it suitable for focused monitoring during peak hours. In contrast, elevator traffic in residential communities doesn't follow a clear morning-noon-evening peak pattern, operating continuously throughout the day. If elevator access control and security video surveillance are used indiscriminately around the clock, it will lead to resource waste. Second, for commercial office buildings, the security of public areas outweighs individual privacy. However, for residential communities, relevant laws and regulations require providing alternative methods besides facial (biometric) recognition for users to choose from. For example, some users may be unwilling to register their facial recognition data, but still have access to elevators. Regarding the right to use elevators, users can choose to obtain a physical card (or mobile QR code) to ride the elevator. However, the number of elevator passengers in residential communities is unevenly distributed, often resulting in a small number of passengers or even just one passenger using the elevator frequently. In such cases, if a passenger encounters a problem (e.g., forgetting their card or mobile phone), they may be unable to ride the elevator normally. Finally, although relevant laws and regulations allow elevator access control and security image monitoring to collect a large amount of personal data for the purpose of maintaining public safety, ensuring the security of this personal data and ensuring its reasonable use based on the principle of "minimum utilization" are also technical issues that need to be addressed by relevant technologies. Summary of the Invention

[0007] To address the aforementioned technical problems, this invention proposes an elevator access control security method based on image recognition, the method comprising the following steps:

[0008] S100: Predicts the number of passengers N1 in the next elevator operating cycle;

[0009] S200: When the number of passengers N1 is less than the preset value Mt, preload the first image acquisition process;

[0010] S300: Determine the actual number of passengers N2 carried by the elevator in the next operating cycle;

[0011] When the actual number of passengers N2 is less than the preset value Mt, determine whether the elevator starts normally within the preset time period. If so, return to step S100.

[0012] Otherwise, proceed to step S400:

[0013] S400: Start the first image acquisition process, the first image acquisition process issues an interactive command to enter image recognition, and based on the result of the image recognition, execute elevator access control measures, the elevator access control measures include normally starting the elevator or issuing a warning message.

[0014] Step S200 further includes:

[0015] When the number of passengers N1 is greater than the preset value Mt, the second image acquisition process is preloaded and a second memory is requested for the second image acquisition process.

[0016] N1, Mt, and M2 are all positive integers;

[0017] Step S300 further includes:

[0018] When the actual number of passengers N2 is greater than the preset value Mt, the second image acquisition process is started to acquire images within the current running cycle, and the acquired images are stored in the second memory;

[0019] Step S400 further includes:

[0020] Scene recognition is performed on the image stored in the second memory.

[0021] When the scene recognition results indicate an anomaly, elevator security measures are implemented.

[0022] In step S200, while preloading the first image acquisition process, a first memory is allocated to the first image acquisition process; the first memory is less than the second memory.

[0023] After each elevator operation cycle, the image data collected during that cycle is deleted. The second image acquisition process performs anonymous scene recognition, which anonymizes the identity data of passengers inside the elevator. The preset value Mt is determined based on the total number of residents within the elevator access control area and the number of floors the elevator operates on.

[0024] In a second aspect of the invention, an elevator access control security system based on image recognition is also proposed, the system comprising an elevator entrance image acquisition unit, an elevator interior access control sensing unit, an elevator interior image acquisition unit, and a central image processing unit.

[0025] The system also includes elevator access cards for at least some residents;

[0026] The elevator entrance image acquisition unit is used to acquire the number of target passengers located at the elevator entrance and send it to the central image processing unit;

[0027] The central image processing unit predicts the number of passengers N1 in the next operating cycle of the elevator based on the number of target passengers, the number of current passengers in the elevator, and the current operating parameters of the elevator.

[0028] When the number of passengers N1 is less than the preset value Mt, the central image processing unit preloads the first image acquisition process;

[0029] When the elevator door closes, and the elevator access control unit inside the elevator senses the elevator access card located inside the elevator, the elevator enters normal operation.

[0030] Otherwise, the central image processing unit determines the actual number of passengers N2 carried by the elevator in the next operating cycle;

[0031] When the actual number of passengers N2 is less than the preset value Mt, the central image processing unit determines whether the elevator has started normally within the preset time period. If not, the first image acquisition process is started, and the elevator image acquisition unit issues an interactive command to enter image recognition based on the first image acquisition process.

[0032] Based on the image recognition results, the central image processing unit executes elevator access control measures, including normally starting the elevator or issuing a warning message.

[0033] When the number of passengers N1 is greater than the preset value Mt, the central image processing unit preloads the second image acquisition process and requests second memory for the second image acquisition process.

[0034] The central image processing unit determines the actual number of passengers N2 carried by the elevator in the next operating cycle;

[0035] When the actual number of passengers N2 is greater than the preset value Mt, the second image acquisition process is started, the elevator image acquisition unit performs image acquisition within the current operating cycle, and stores the acquired images in the second memory;

[0036] The central image processing unit performs scene recognition on the images stored in the second memory; when the scene recognition result indicates that there is an anomaly, elevator security measures are implemented.

[0037] The central image processing unit deletes the image data collected during each elevator operation cycle after the cycle ends.

[0038] The second image acquisition process performs anonymous scene recognition, which anonymizes the identity data of passengers in the elevator.

[0039] While the central image processing unit preloads the first image acquisition process, it allocates first memory to the first image acquisition process; the first memory is smaller than the second memory.

[0040] The technical solution of this invention dynamically preloads image acquisition processes (first / second processes) of different levels and allocates differentiated memory resources (first memory < second memory) based on the predicted passenger volume (N1), achieving precise matching of computing resources. During high passenger flow, a more powerful second process and larger memory are activated to ensure image processing efficiency in complex scenarios; during low passenger flow, a lightweight configuration is switched to reduce system load and energy consumption. Simultaneously, this invention employs a dual-mode verification mechanism of "access card priority + image recognition backup": swiping the access card allows direct entry, while failure to swipe the card results in secondary verification via image recognition. This design ensures basic security while using image recognition to compensate for lost or forgotten cards, improving ease of use. Furthermore, by comparing the predicted passenger volume (N1) with the actual passenger volume (N2) and combining this with elevator start-up status monitoring, the system quickly identifies abnormal situations (such as no one swiping their card but the elevator not starting for an extended period) and immediately triggers image recognition for identity verification or scene analysis, achieving real-time interception of security risks. Finally, the technical solution of this invention automatically deletes the collected image data after each operating cycle, adhering to the "minimum necessary" principle; it differentiates the processing methods for different passenger flow scenarios (strengthening security but anonymizing during high passenger flow, and ensuring passage while retaining necessary verification during low passenger flow), balancing security and privacy requirements.

[0041] Further specific advantages and implementation principles of the present invention will be further detailed in the specific embodiments section in conjunction with the accompanying drawings. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a flowchart of an embodiment of the elevator access control security method based on image recognition of the present invention in a scenario with a small number of actual passengers;

[0044] Figure 2 This is a flowchart of an embodiment of the elevator access control security method based on image recognition of the present invention in a scenario with a large number of passengers.

[0045] Figure 3 This is a schematic diagram of the hardware unit composition of an elevator access control and security system based on image recognition, according to an embodiment of the present invention.

[0046] Figure 4 yes Figure 3A schematic diagram illustrating a practical application scenario of an elevator access control and security system based on image recognition. Detailed Implementation

[0047] In the specific embodiments of this application, if the embodiments of the relevant technical solutions involve user-related data, then when the embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0048] The embodiments in this section include method embodiments and system embodiments, which are mutually corresponding. The implementation principles of the method embodiments are similar to those of the system embodiments. Therefore, the description in this section is based on the method embodiments, including the corresponding computer flow implementation of the method. Subsequent system embodiments will not repeat the same parts; the system embodiments themselves are used to implement the method or the corresponding computer flow.

[0049] First see Figure 1 , Figure 1 The flowchart illustrates an embodiment of the elevator access control security method based on image recognition of the present invention in a scenario with a small number of actual passengers.

[0050] exist Figure 1 The method includes the following steps:

[0051] S100: Predicts the number of passengers N1 in the next elevator operating cycle;

[0052] S200: When the number of passengers N1 is less than the preset value Mt, preload the first image acquisition process;

[0053] S300: Determine the actual number of passengers N2 carried by the elevator in the next operating cycle;

[0054] When the actual number of passengers N2 is less than the preset value Mt, determine whether the elevator starts normally within the preset time period. If so, return to step S100.

[0055] Otherwise, proceed to step S400:

[0056] S400: Start the first image acquisition process, the first image acquisition process issues an interactive command to enter image recognition, and based on the result of the image recognition, execute elevator access control measures, the elevator access control measures include normally starting the elevator or issuing a warning message.

[0057] Since elevators typically operate continuously, in various examples of this invention, the elevator's operating state can be divided into a cyclical process: starting (beginning to ascend or descend), running, stopping / pausing (reaching a certain floor), elevator doors opening, (after waiting for a preset time) elevator doors closing, and (after the target floor button is illuminated) starting (beginning to ascend or descend).

[0058] For ease of description, the time when the elevator is in operation (i.e., after starting and running) is considered as one operating cycle.

[0059] Step S100 predicts the number of passengers N1 in the next operating cycle of the elevator. Specifically, when the elevator is in the current operating cycle (for example, the elevator starts after the door is closed and before reaching the next target floor / the next time the door is closed and opened), the elevator starts to predict the number of passengers N1 in the next operating cycle, that is, the possible number of passengers N1 in the elevator after the door is closed and started again after the next time the door is closed and opened.

[0060] When implementing the method, the number of passengers in the elevator in the next operating cycle can be predicted as N1 = A1 - A2 + A3, based on the number of people A1 in the elevator during the current operating cycle, the number of people A2 who will exit the elevator after the next cycle (which can be estimated based on the lighting data of the target floor, historical statistics of the same period, etc.), and the number of people A3 who will enter the elevator after the next cycle (which can be estimated based on the number of people waiting to enter the elevator on the target floor obtained from the elevator entrance image acquisition data, historical statistics of the same period, etc.).

[0061] Next, proceed to step S200: when the number of passengers N1 is less than the preset value Mt, preload the first image acquisition process.

[0062] Figure 1 The focus of the embodiment branch is to introduce the case where "the number of passengers N1 is less than the preset value Mt", that is, the elevator has a small number of passengers (another case will be introduced in the subsequent embodiments).

[0063] When the number of passengers N1 is less than the preset value Mt, the first image acquisition process is preloaded.

[0064] As an explanation, the preset value Mt is determined based on the total number of residents within the elevator access control range and the number of floors the elevator operates on.

[0065] Preferably, the preset value Mt can be determined based on the total number of residents within the elevator access control range, the number of floors the elevator operates on, and historical relevant statistical data of the elevator access control security system.

[0066] One technical problem that this invention aims to solve is "when the number of passengers in the elevator is small and the target passengers inside the elevator cannot start the elevator normally".

[0067] As described in the background section, some elevators currently have identity recognition capabilities, which can identify passengers entering the elevator in real time based on biometrics such as facial recognition, fingerprint recognition, and iris recognition. In residential communities with compromise-based limited access control systems, as long as the passenger's identity can be identified as a pre-authorized user of the community, the elevator can operate normally (e.g., the current passenger can press any floor button).

[0068] However, due to concerns about the leakage of personal privacy data, some users are still unwilling to relinquish their personal identity data in exchange for the aforementioned conveniences. For these users, relevant laws explicitly require service providers to offer alternative methods beyond personal identification authentication, such as hardware media like access cards or mobile access control (NFC) devices (collectively referred to as access cards).

[0069] For this type of user, in order to ride the elevator normally, they must carry the aforementioned hardware medium (such as an elevator access card). When such a user enters the elevator alone without carrying the hardware medium, or when multiple such users enter the elevator simultaneously without carrying the hardware medium (all passengers in the elevator include such users), it will lead to a situation where the elevator cannot be used normally.

[0070] Of course, according to the principles of large numbers and probability, the probability of multiple people simultaneously entering the elevator, multiple people belonging to the aforementioned users, and multiple people not carrying any hardware devices will decrease rapidly as the specific number of "multiple people" increases. In short, the more people who enter the elevator simultaneously, the greater the probability that the elevator can start normally immediately. Conversely, if fewer people enter the elevator simultaneously, the probability that the elevator can start normally immediately will decrease.

[0071] That's why it was proposed Figure 1 The example solution branch, namely step S2, when the number of passengers N1 is less than the preset value Mt, preloads the first image acquisition process; then continues to step S3 for confirmation: determine the actual number of passengers N2 of the elevator in the next operating cycle.

[0072] Preferably, the preset value Mt is no greater than 3. That is, long-term statistical data shows that when three people enter an elevator simultaneously, the probability that multiple people are simultaneously unauthorized users plus multiple people without any hardware device is very low. Preferably, Mt can be set to 1, 2, or 3. Mt is an integer not less than 1.

[0073] Figure 1The branch described above can be described as handling a small number of passengers. That is, when the predicted number of passengers N1 is less than Mt, the first image acquisition process is preloaded. After confirming that the actual number of passengers N2 is less than the preset value Mt, it is determined whether the elevator has started normally within the preset time. This step is to confirm that "multiple people enter the elevator at the same time + multiple people belong to the above-mentioned users + multiple people do not carry hardware media" has indeed occurred. Therefore, the first image acquisition process is started. The first image acquisition process issues an interactive command to enter image recognition. Based on the result of the image recognition, elevator access control measures are executed. The elevator access control measures include starting the elevator normally or issuing a warning message.

[0074] When the following conditions are met: "multiple people simultaneously enter the elevator + multiple people simultaneously belong to the aforementioned users + multiple people do not carry any hardware media," the method includes:

[0075] The first image acquisition process is initiated, and the first image acquisition process issues an interactive command to enter image recognition. For example, it may issue a voice prompt through the interactive unit (voice module) in the elevator or provide a text prompt simultaneously through the visual human-computer interaction unit.

[0076] "Please swipe your card or verify your identity."

[0077] "If you do not have a card, please face the camera for identity verification."

[0078] "Please exit the elevator and seek assistance."

[0079] "Please press the help button for assistance. Your identity verification image will still need to be collected at this time."

[0080] Clearly, in the above embodiments of the present invention, the current user is given full freedom to collect and update personal data.

[0081] At this point, users can choose to exit the elevator (even if it is inconvenient and they do not want to have their image captured), or temporarily undergo identity verification before using the elevator normally.

[0082] It is understandable that temporary identity verification here does not necessarily mean that the user agrees to continue using the identity entered this time for elevator access control. The user can also be given the option to choose whether it is valid for a single time or continuously.

[0083] In this situation, if the user does not have a card, they can obtain temporary access to the elevator for one time by performing temporary identity recognition by facing the camera, and then the elevator can be started normally in step S400.

[0084] Alternatively, if the user is unwilling to temporarily authenticate or identify themselves (unwilling to temporarily enter identity information), does not exit the elevator, or takes other abnormal actions (such as obstructing the elevator door from opening / closing), then step S400 will issue a warning message.

[0085] Under one security mechanism, users can obtain elevator access simply by registering their real names (e.g., by entering facial recognition information). Under another security mechanism, after a user temporarily enters their real-name authentication information (e.g., by entering facial recognition information), the backend may need to perform information comparison before determining whether to grant access (in this case, the database used for comparison can be the user's identity information entered through other means (other than the elevator identity recognition database)). Of course, other methods can also be adopted, and this invention does not specifically limit them. It should be understood that when a user agrees to temporarily enter data, it usually indicates that the user agrees to the necessary subsequent identification and data processing processes, as long as the relevant processes comply with relevant laws.

[0086] Compared to Figure 1 The "minority cases" branch, see below. Figure 2 . Figure 2 The flowchart illustrates an embodiment of the elevator access control security method based on image recognition of the present invention in a scenario with a large number of passengers.

[0087] exist Figure 2 In step S200, the method further includes:

[0088] When the number of passengers N1 is greater than the preset value Mt, the second image acquisition process is preloaded and a second memory is requested for the second image acquisition process.

[0089] Step S300 further includes:

[0090] When the actual number of passengers N2 is greater than the preset value Mt, the second image acquisition process is started to acquire images within the current running cycle, and the acquired images are stored in the second memory;

[0091] Step S400 further includes:

[0092] Scene recognition is performed on the image stored in the second memory.

[0093] When the scene recognition results indicate an anomaly, elevator security measures are implemented.

[0094] exist Figure 2 The scenario handled is where "the predicted number of passengers N1 in the next elevator operating cycle is greater than the preset value Mt" (predicted value) and "the actual number of passengers N2 is greater than the preset value Mt" (actual value).

[0095] In this situation, as described above, when multiple people enter the elevator at the same time, the probability of "multiple people entering the elevator at the same time + multiple people belonging to the aforementioned users + multiple people not carrying hardware media" is extremely low. Therefore, the method of this embodiment skips the step of "determining whether the elevator starts normally within a preset time period", and assumes that the elevator can start normally (because it is highly likely that at least one person carries hardware media, or at least one person has pre-registered identity information that can automatically open the elevator door).

[0096] At this point, during the prediction phase, the second image acquisition process is preloaded and a second memory is requested for the second image acquisition process; during the determination phase, the second image acquisition process is started to acquire images within the current running cycle and the acquired images are stored in the second memory; scene recognition is performed on the images stored in the second memory; when the scene recognition result indicates that there is an anomaly, elevator security measures are executed.

[0097] Of course, those skilled in the art will understand that although there may be some very extreme situations, such as the elevator not starting normally within the preset time after 10 people have entered, that is, all 10 people are simultaneously users (i.e., no elevator access control identification information has been pre-entered) and many people do not carry or have no hardware medium, the technical solution of the present invention can still solve such extreme problems.

[0098] At this time, it is possible Figure 2 Step S200 in the embodiment is further defined as follows:

[0099] When the actual number of passengers N2 is greater than the preset value Mt, determine whether the elevator starts normally within the preset time period. If so, return to step S100.

[0100] Otherwise, the second image acquisition process is started to acquire images within the current running cycle, and the acquired images are stored in the second memory.

[0101] Furthermore, the predicted value (the predicted number of passengers N1 in the next elevator cycle) and the determined value (the actual number of passengers N2 in the next elevator cycle) may also be inconsistent. For example, N1 might be predicted to be small, but a sudden increase in the number of people entering the elevator after the doors open (these people may not be in the queuing area at the elevator entrance, but simply arrive after the doors open) could cause N2 to increase. In this case, it is also possible to... Figure 2 The solution was found in the embodiment branch "When the number of passengers N1 is greater than the preset value Mt, preload the second image acquisition process and request second memory for the second image acquisition process".

[0102] Of course, in order to avoid unnecessary interference with the description of the key improvements to the technical solution of the present invention, it is neither appropriate nor necessary to elaborate on such cases.

[0103] Key improvements of this invention Figure 1 and Figure 2 The processing of two different branches, the process pre-start mechanism under corresponding conditions, and the resource scheduling mechanism for different image acquisition processes.

[0104] Preferably, the first image acquisition process can be a single-target or P-target (P less than 3) acquisition process, which can run a maximum of P threads;

[0105] The second image acquisition process can be a single-target or Q-target (Q not less than 3) acquisition process, which can run up to Q threads;

[0106] Meanwhile, the second image acquisition process performs anonymous scene recognition, which anonymizes the identity data of passengers in the elevator.

[0107] Preferably, the second image acquisition process acquires image information of the body movements of Q target individuals that is irrelevant to identity recognition.

[0108] As can be seen, the second image acquisition process requires more resources than the first image acquisition process. In step S200, while preloading the first image acquisition process, a first memory is allocated to the first image acquisition process; the first memory is less than the second memory.

[0109] Preferably, to ensure the principle of minimum utilization, the image data collected during each elevator operation cycle is deleted after the cycle ends.

[0110] As another advantage, based on different process resource scheduling mechanisms, the above embodiments all adopt a process preloading mechanism.

[0111] The process preloading mechanism in the aforementioned image recognition-based elevator access control security system preloads relevant image acquisition processes based on elevator passenger capacity predictions, thereby improving system response speed and resource utilization efficiency. Its implementation mechanism and related advantages include:

[0112] Preloading judgment criteria: The central image processing unit predicts the passenger capacity N1 for the next elevator operating cycle based on the number of passengers at the elevator entrance image acquisition unit, the current number of passengers inside the elevator fed back by the elevator access control sensor unit, and the current operating parameters of the elevator. If N1 is less than the preset value Mt, the first image acquisition process is preloaded; if N1 is greater than the preset value Mt, the second image acquisition process is preloaded and second memory is allocated for it.

[0113] The preloading process works as follows: When the elevator doors close, if the elevator access control unit does not detect the elevator access card, the central image processing unit will determine the actual passenger load N2 for the next operating cycle. If N2 is less than the preset value Mt and the elevator does not start normally within the preset time, the first image acquisition process is initiated. Based on the image recognition results, elevator access control measures are implemented, such as starting the elevator normally or issuing an alarm message. If N2 is greater than the preset value Mt, the second image acquisition process is initiated to acquire images for the current operating cycle and store the images in a second memory. Scene recognition can also be performed on the stored images, and elevator security measures are implemented based on the results.

[0114] Memory allocation strategy: When preloading the first image acquisition process, it is allocated first memory, which is less than the second memory. Simultaneously, after each elevator operation cycle, the central image processing unit deletes the image data acquired during that cycle. The second image acquisition process performs anonymous scene recognition, anonymizing passenger identity data to ensure data security and user privacy.

[0115] This preloading mechanism can allocate resources reasonably according to the elevator passenger load. When the passenger load is low, it can prioritize ensuring that passengers can ride the elevator normally. When the passenger load is high, it can strengthen security monitoring. At the same time, it can focus on data security and the rational use of resources.

[0116] exist Figures 1-2 Based on the method implementation examples, the corresponding system implementation examples will be briefly introduced below. See also Figure 3 This paper presents an elevator access control security system based on image recognition. The system includes an elevator entrance image acquisition unit, an elevator interior access control sensing unit, an elevator interior image acquisition unit, and a central image processing unit.

[0117] See further Figure 4 , Figure 4 yes Figure 3 A schematic diagram illustrating a practical application scenario of an elevator access control and security system based on image recognition.

[0118] In practical applications, the system also includes elevator access cards configured for at least some residents;

[0119] The elevator entrance image acquisition unit is used to acquire the number of target passengers located at the elevator entrance and send it to the central image processing unit;

[0120] The central image processing unit predicts the number of passengers N1 in the next operating cycle of the elevator based on the number of target passengers, the number of current passengers in the elevator, and the current operating parameters of the elevator.

[0121] When the number of passengers N1 is less than the preset value Mt, the central image processing unit preloads the first image acquisition process;

[0122] When the elevator door closes, and the elevator access control unit inside the elevator senses the elevator access card located inside the elevator, the elevator enters normal operation.

[0123] Otherwise, the central image processing unit determines the actual number of passengers N2 carried by the elevator in the next operating cycle;

[0124] When the actual number of passengers N2 is less than the preset value Mt, the central image processing unit determines whether the elevator has started normally within the preset time period. If not, the first image acquisition process is started, and the elevator image acquisition unit issues an interactive command to enter image recognition based on the first image acquisition process.

[0125] Based on the image recognition results, the central image processing unit executes elevator access control measures, including normally starting the elevator or issuing a warning message.

[0126] When the number of passengers N1 is greater than the preset value Mt, the central image processing unit preloads the second image acquisition process and requests second memory for the second image acquisition process.

[0127] The central image processing unit determines the actual number of passengers N2 carried by the elevator in the next operating cycle;

[0128] When the actual number of passengers N2 is greater than the preset value Mt, the second image acquisition process is started, the elevator image acquisition unit performs image acquisition within the current operating cycle, and stores the acquired images in the second memory;

[0129] The central image processing unit performs scene recognition on the images stored in the second memory; when the scene recognition result indicates that there is an anomaly, it executes elevator security measures, such as promptly notifying security personnel if a violent incident or dispute occurs in the elevator.

[0130] The central image processing unit deletes the image data collected during each elevator operation cycle after the cycle ends.

[0131] The second image acquisition process performs anonymous scene recognition, which anonymizes the identity data of passengers in the elevator.

[0132] While the central image processing unit preloads the first image acquisition process, it allocates first memory to the first image acquisition process; the first memory is smaller than the second memory.

[0133] In summary, the present invention provides targeted technical solutions to address the relevant technical issues raised in the background section. Compared with the prior art, its advantages include at least the following:

[0134] (1) Existing technologies typically employ a fixed resource allocation model, while this solution dynamically preloads image acquisition processes (first / second processes) at different levels and allocates differentiated memory (first memory < second memory) based on predicted passenger volume (N1). During periods of high passenger flow, a more powerful second process and larger memory are enabled to ensure image processing efficiency in complex scenarios; during periods of low passenger flow, a lightweight configuration is switched to reduce system load and energy consumption. Compared to traditional solutions, this dynamic adaptation strategy can reduce the consumption of ineffective computing resources by more than 30% while improving high-concurrency response speed by 50%.

[0135] (2) Traditional elevator access control systems often rely on a single verification method (such as card swiping or facial recognition), while this solution constructs a dual-modal verification system of "access card priority + image recognition backup". When no access card is detected, the system automatically triggers image recognition for secondary verification, which not only ensures basic security, but also makes up for the vulnerability of lost or forgotten cards through image recognition. Compared with traditional solutions, this design can reduce elevator access obstacles caused by forgotten documents by 80%, and at the same time enhances the monitoring capability of safety hazards such as carrying dangerous items and abnormal behavior through scene recognition function.

[0136] (3) Existing technologies often rely on manual inspections or post-event analysis, while this solution achieves real-time automatic identification of abnormal situations by comparing the predicted passenger volume (N1) with the actual passenger volume (N2) and combining it with elevator start-up status monitoring. For example, when an abnormal state of no one swiping their card but not starting for a long time is detected, the system immediately triggers image recognition for identity verification. The entire response process can be completed within 3 seconds, which shortens the response time by 95% compared with the traditional manual intervention method, significantly improving the efficiency of safety hazard interception.

[0137] (4) Traditional security systems often cause privacy disputes due to excessive collection of user data, while this solution constructs a multi-layered privacy protection mechanism: in high-passenger-flow scenarios, the second image acquisition process performs anonymous scene recognition and blurs the passenger identity data; the collected image data is automatically deleted after each operation cycle, following the principle of "data minimization"; at the same time, it provides a variety of non-biometric verification methods (such as IC cards and QR codes) for users to choose from. These designs enable the system to meet security requirements while shortening the personal data retention time to 1 / 10 of traditional solutions, significantly reducing the risk of data leakage.

[0138] Although not shown in the accompanying drawings, a preferred and further embodiment of the product may also be an electronic device comprising: a memory and one or more processors. The memory stores one or more application programs adapted to be executed by the one or more processors, as described above, of an image recognition-based elevator access control security method.

[0139] Although not shown in the accompanying drawings, further embodiments also include a computer-readable storage medium storing a computer program that, when executed, implements the steps of the aforementioned image recognition-based elevator access control security method.

[0140] It is understood that the system, product, equipment, and media implementations correspond to each other and can be referenced by each other, and their principles are similar or the same, so they will not be elaborated on again.

[0141] Other technologies, principles, algorithms, or models not elaborated in detail in this application can be found in the prior art.

[0142] The foregoing has shown and described the method embodiments and systems of the present invention, but it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An elevator access control security method based on image recognition, characterized in that, The method includes the following steps: S100: Predicts the number of passengers N1 in the next elevator operating cycle; S200: When the number of passengers N1 is less than the preset value Mt, preload the first image acquisition process; When the elevator door closes, the elevator enters normal operation when the access control unit inside the elevator detects the elevator access card located inside the elevator. Otherwise, proceed to step S300; S300: Determine the actual number of passengers N2 carried by the elevator in the next operating cycle; N1, Mt, and M2 are all positive integers; When the actual number of passengers N2 is less than the preset value Mt, determine whether the elevator starts normally within the preset time period. If so, return to step S100. Otherwise, proceed to step S400: S400: Start the first image acquisition process, the first image acquisition process issues an interactive command to enter image recognition, and based on the result of the image recognition, execute elevator access control measures, the elevator access control measures include normally starting the elevator or issuing a warning message.

2. The elevator access control security method based on image recognition as described in claim 1, characterized in that, Step S200 further includes: When the number of passengers N1 is greater than the preset value Mt, the second image acquisition process is preloaded and a second memory is requested for the second image acquisition process. Step S300 further includes: When the actual number of passengers N2 is greater than the preset value Mt, the second image acquisition process is started to acquire images within the current running cycle, and the acquired images are stored in the second memory; Step S400 further includes: Scene recognition is performed on the image stored in the second memory. When the scene recognition results indicate an anomaly, elevator security measures are implemented.

3. The elevator access control security method based on image recognition as described in claim 2, characterized in that, In step S200, while preloading the first image acquisition process, a first memory is allocated to the first image acquisition process; the first memory is less than the second memory.

4. The elevator access control security method based on image recognition as described in claim 2, characterized in that, After each elevator operation cycle ends, the image data collected during that cycle is deleted.

5. The elevator access control security method based on image recognition as described in claim 2, characterized in that, The second image acquisition process performs anonymous scene recognition, which anonymizes the identity data of passengers in the elevator.

6. The elevator access control security method based on image recognition as described in claim 1, characterized in that, The preset value Mt is determined based on the total number of residents within the elevator access control range and the number of floors the elevator operates on.

7. An elevator access control security system based on image recognition, the system comprising an elevator entrance image acquisition unit, an elevator interior access control sensing unit, an elevator interior image acquisition unit, and a central image processing unit; Its features are, The system also includes elevator access cards for at least some residents; The elevator entrance image acquisition unit is used to acquire the number of target passengers located at the elevator entrance and send it to the central image processing unit; The central image processing unit predicts the number of passengers N1 in the next operating cycle of the elevator based on the number of target passengers, the number of current passengers in the elevator, and the current operating parameters of the elevator. When the number of passengers N1 is less than the preset value Mt, the central image processing unit preloads the first image acquisition process; When the elevator door closes, and the elevator access control unit inside the elevator senses the elevator access card located inside the elevator, the elevator enters normal operation. Otherwise, the central image processing unit determines the actual number of passengers N2 carried by the elevator in the next operating cycle; When the actual number of passengers N2 is less than the preset value Mt, the central image processing unit determines whether the elevator has started normally within the preset time period. If not, the first image acquisition process is started, and the in-elevator image acquisition unit issues an interactive command to enter image recognition based on the first image acquisition process; N1, Mt, and M2 are all positive integers. Based on the image recognition results, the central image processing unit executes elevator access control measures, including normally starting the elevator or issuing a warning message.

8. The elevator access control and security system based on image recognition as described in claim 7, characterized in that: When the number of passengers N1 is greater than the preset value Mt, the central image processing unit preloads the second image acquisition process and requests second memory for the second image acquisition process. The central image processing unit determines the actual number of passengers N2 carried by the elevator in the next operating cycle; When the actual number of passengers N2 is greater than the preset value Mt, the second image acquisition process is started, the elevator image acquisition unit performs image acquisition within the current operating cycle, and stores the acquired images in the second memory; The central image processing unit performs scene recognition on the images stored in the second memory; When the scene recognition results indicate an anomaly, elevator security measures are implemented.

9. The elevator access control and security system based on image recognition as described in claim 8, characterized in that: The central image processing unit deletes the image data collected during each elevator operation cycle after the cycle ends. The second image acquisition process performs anonymous scene recognition, which anonymizes the identity data of passengers in the elevator.

10. The elevator access control and security system based on image recognition as described in claim 8, characterized in that: While the central image processing unit preloads the first image acquisition process, it allocates first memory to the first image acquisition process; the first memory is smaller than the second memory.

Images