Visitor identity automatic verification method and system based on intelligent access control

Abstract

The invention discloses a visitor identity automatic verification method and system based on intelligent access control, and belongs to the technical field of access control identity verification, and the method comprises the following steps: an access control monitoring camera senses whether a visitor appears in a scanning range in real time, obtains image information scanned by the camera at the moment when sensing that the visitor appears, and analyzes an image external interference execution scheme. And analyzing the stripe jitter characterization factor, and analyzing an image stripe jitter execution scheme. And performing fringe jitter adjustment, analyzing the fringe jitter characterization factor at the moment, analyzing fringe jitter adjustment effect information, and obtaining an image fringe jitter adjustment effect execution scheme. And analyzing the coupling interference characterization factor, analyzing a coupling interference execution scheme, and carrying out coupling interference adjustment. And performing visitor identity automatic verification based on a YOLOv5s target detection algorithm. According to the invention, the fringe jitter is analyzed and adjusted, so that the imaging quality of the camera is guaranteed, the recognition precision is improved, the coupling interference is analyzed and adjusted, the coupling interference is eliminated, and the image quality is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of access control identity verification, in particular to an automatic visitor identity verification method and system based on intelligent access control. Background Art

[0002] The existing automatic intelligent verification technologies for visitor identities mainly include multi-modal biometric technologies, intelligent hardware terminals, cloud and data management. First, face recognition and live detection are carried out through multi-modal biometric technologies. The visitors are identified through cameras for identity verification to ensure the judgment accuracy of the recognition. Through the intelligent visitor management terminal, self-service registration and mobile terminal collaborative management are carried out, and the visitor information data is synchronized to the platform in real time. Cloud and edge computing collaboration is carried out, and an AI risk decision engine is used to judge abnormal visitors. Multi-camera linkage scanning is used to analyze abnormal behaviors. A multi-dimensional and intelligent technical system is formed, combined with AI algorithms and cloud management, to achieve efficient, accurate and safe identity verification.

[0003] For example, a method and system for household security control in a smart community disclosed in a Chinese invention patent with the publication number of CN117273444B controls the risk behaviors of community households through the changed forms of risk attention items. Since the dissimilarity between the interval binary groups in the security hazard data to be analyzed and the corresponding potential security hazard data is large enough, it means that there are risk attention items in this interval binary group, and it is an interval binary group related to the risk attention item. Therefore, this interval binary group is determined as the target interval binary group, and according to the common knowledge field weight of the target interval binary group, the changed form of the risk attention item in the target interval binary group can be determined.

[0004] For example, an intelligent monitoring system for a community disclosed in a Chinese invention patent with the publication number of CN109711769B relates to the field of community monitoring, and specifically relates to an intelligent monitoring system for a community, including: a delivery information generation module for obtaining owner request information to generate a delivery information table, and the delivery information table includes: owner personal information, delivery address, delivery time, name, gender, contact information and affiliated company of the food delivery staff. A preferred route module for obtaining the community map information and the delivery address in the delivery information table to obtain a delivery route, and selecting the best delivery route from the delivery routes through the analysis of the delivery time and the delivery floor in the delivery address. A safety warning module, which determines abnormal delivery when the delivery duration exceeds the safety duration, sends a reminder signal to the food delivery staff, and at the same time sends a safety warning signal to the security personnel.

[0005] The above technologies have at least the following technical problems: Current visitor identity verification technologies used in smart access control systems primarily focus on analyzing visitor behavior and monitoring visitor routes through multiple monitoring devices. However, they neglect the potential impact of weather conditions on the monitoring and verification equipment's imaging. Incompatible frequencies can cause bright and dark stripes in the images, severely affecting the quality of the images captured by the camera and thus interfering with the accuracy of facial recognition visual algorithms. The coupling effect of multiple problems can lead to even greater interference, affecting camera imaging, image quality, and reducing the accuracy of verification and recognition. Summary of the Invention

[0006] To address the aforementioned technical problems in existing technologies, embodiments of the present invention provide a method and system for automatic visitor identity verification based on smart access control. The technical solution is as follows: On the one hand, a method for automatic visitor identity verification based on smart access control is provided, including the following steps: Access control monitoring cameras can detect whether visitors are present within their scanning range in real time. When a visitor is detected, the camera captures the image information, obtains the average value of the dark channel of the image, analyzes external interference in the image, and implements a solution to enhance the all-weather reliability of recognition in order to cope with complex scenarios.

[0007] When performing image information analysis, the external interference execution scheme analyzes the stripe jitter characterization factor and the image stripe jitter execution scheme to improve the image quality captured by the camera and increase recognition accuracy.

[0008] When performing image stripe jitter adjustment, the deviation value of the stripe jitter characterization factor is analyzed simultaneously, and stripe jitter adjustment is performed. After stripe jitter adjustment, the stripe jitter characterization factor is analyzed, and the stripe jitter adjustment effect information is analyzed. Thus, the image stripe jitter adjustment effect execution scheme is obtained to ensure the camera imaging quality and eliminate recognition interference.

[0009] When the image stripe jitter adjustment effect implementation scheme is to judge coupling interference, the coupling interference characterization factor is analyzed, the coupling interference implementation scheme is analyzed, coupling interference adjustment is performed, coupling interference is eliminated, and image quality is improved.

[0010] When the image is subjected to external interference, the solution is to continue visitor scanning and verification; when the image is subjected to stripe jitter, the solution is to continue visitor scanning and verification; or when the image is subjected to stripe jitter adjustment, the solution is to continue visitor scanning and verification, the visitor identity is automatically verified based on the YOLOv5s target detection algorithm.

[0011] On the other hand, it provides an automatic visitor identity verification system based on smart access control, including: The external interference judgment module uses the access control monitoring camera to sense whether a visitor is present within its scanning range in real time. When a visitor is detected, the module acquires the image information scanned by the camera at that time, obtains the average value of the dark channel of the image, analyzes the external interference of the image, and implements a solution to enhance the all-weather reliability of recognition in order to cope with complex scenarios.

[0012] The stripe jitter detection module analyzes stripe jitter characteristics and image stripe jitter detection schemes when performing image information analysis in the event of external interference, thereby improving the image quality captured by the camera and increasing recognition accuracy.

[0013] The stripe jitter adjustment module, when the image stripe jitter execution scheme is to perform stripe jitter adjustment, simultaneously analyzes the deviation value of the stripe jitter characterization factor and performs stripe jitter adjustment. After the stripe jitter adjustment, it analyzes the stripe jitter characterization factor at this time and analyzes the stripe jitter adjustment effect information, thereby obtaining the image stripe jitter adjustment effect execution scheme to ensure the camera imaging quality and eliminate recognition interference.

[0014] The coupling interference analysis module analyzes coupling interference characterization factors and coupling interference implementation schemes when the image stripe jitter adjustment effect execution scheme is to perform coupling interference judgment, adjust coupling interference, eliminate coupling interference, and improve image quality.

[0015] The visitor identity verification module automatically verifies visitor identity based on the YOLOv5s target detection algorithm when the image is affected by external interference, image stripe jitter, or image stripe jitter adjustment.

[0016] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: 1. The visitor identity automatic verification method and system based on smart access control provided by this invention analyzes the stripe jitter problem by judging the influence of the external environment and adjusts the stripe jitter to avoid image distortion and ensure smooth output image. Adjusting the jitter can eliminate misjudgment interference and improve the quality of the obtained image. Dynamic analysis and adjustment of stripe jitter can prevent equipment overload and dynamically adjust power consumption. Coupling problem analysis and adjustment can improve the recognition rate in the face of coupling interference, thus optimizing verification efficiency and improving verification accuracy.

[0017] 2. This invention addresses the problem of stripe jitter in images by adjusting the frequency and duty cycle based on the deviation value of the stripe jitter characterization factor, thereby improving the image quality captured by the camera, enhancing recognition accuracy, increasing robustness in different scenarios, optimizing image quality, and improving the accuracy of automatic verification of access control visitors.

[0018] 3. This invention analyzes the stripe jitter adjustment effect information to obtain an image stripe jitter adjustment effect execution scheme. Based on the first stripe jitter characterization factor and the stripe jitter characterization factor correction threshold, the stripe jitter adjustment effect information is judged. The adjustment effect is judged with stricter standards, which can more accurately measure the effectiveness of the adjustment operation. For effective stripe jitter adjustment, the consumption is minimized as much as possible to avoid introducing other interferences, and no further adjustment is made. Visitor scanning and verification continue. For invalid stripe jitter adjustment, coupling interference judgment is performed to solve the interference problem, so as to ensure the imaging quality of the camera and eliminate recognition interference.

[0019] 4. This invention adjusts the frequency and supplementary light intensity based on the deviation value of the coupling interference characterization factor to eliminate coupling interference, improve system reliability, reduce the false recognition rate, make recognition more accurate, improve image quality, effectively solve the coupling interference problem, precisely control signal timing, eliminate the periodic characteristics of interference signals, precisely destroy the physical interference mechanism, break resonance interference, use high frequency to suppress visible jitter, suppress the amplitude domain influence of scattering noise, and ensure the quality of the obtained image. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0021] Figure 1 This is a flowchart of the visitor identity automatic verification method based on smart access control provided in an embodiment of the present invention.

[0022] Figure 2 This is a schematic diagram of the visitor identity automatic verification system based on smart access control provided in an embodiment of the present invention.

[0023] Figure 3 This is a flowchart of the image stripe jitter analysis execution scheme involved in the embodiments of the present invention.

[0024] Figure 4 This is a flowchart illustrating the information on the adjustment effect of stripe jitter in an embodiment of the present invention. Detailed Implementation

[0025] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0026] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0027] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0028] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0029] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0030] This invention provides a method for automatic visitor identity verification based on smart access control, such as... Figure 1 The flowchart shown is for an automatic visitor identity verification method based on smart access control. The method includes: The smart access control systems involved in this embodiment may include, but are not limited to, community access control, school access control, hospital access control, and bank access control.

[0031] Access control monitoring cameras can detect whether visitors are present within their scanning range in real time. When a visitor is detected, the camera captures the image information, obtains the average value of the dark channel of the image, analyzes external interference in the image, and implements a solution to enhance the all-weather reliability of recognition in order to cope with complex scenarios.

[0032] The access control monitoring camera can detect whether a visitor is present within its scanning range in real time. It can use an infrared pyroelectric sensor to detect the infrared heat radiation emitted by the human body, thereby detecting whether a visitor is present within the scanning range.

[0033] When the infrared pyroelectric sensor detects infrared thermal radiation, it determines that a visitor has arrived.

[0034] In this embodiment, the dark channel mean of the image is obtained, and the external interference of the image is analyzed to implement a solution. The analysis process is as follows: Obtain the mean value of the dark channel of the image.

[0035] The dark channel mean is the arithmetic mean of all pixel values ​​in a dark channel image. The dark channel image is generated as follows: for each pixel in the input RGB image, the minimum value of its red, green, and blue channel intensity values ​​is first taken. Then, within a preset local window in the database, the local minimum value of these minimum values ​​is taken to form a single-channel image. This single channel is not a regular grayscale image, but rather a mapping reflecting the characteristics of the darkest pixels in a local area. The range of the dark channel mean depends on the image data type, commonly ranging from 0–255 or a normalized 0–1.

[0036] The dark channel mean of an image can be obtained using OpenCV + NumPy (NumericalPython, a numerical computation extension library).

[0037] Extract the dark channel mean threshold.

[0038] If the mean value of the dark channel of the image is greater than the threshold value of the dark channel, the method for handling external interference to the image is recorded as performing image information analysis.

[0039] It should be noted that if the dark channel mean of the image is greater than the dark channel mean threshold, it indicates that the dark pixel density in the image is insufficient, suggesting that the image deviates from the normal statistical pattern and is affected by external interference. Further analysis is needed to determine whether a problem has occurred and to make targeted adjustments. Therefore, the image external interference execution scheme is denoted as image information analysis.

[0040] If the dark channel mean of the image is less than or equal to the dark channel mean threshold, the external interference of the image is recorded as continuing to perform visitor scanning verification.

[0041] It should be noted that if the dark channel mean of the image is less than or equal to the dark channel mean threshold, it means that the external environment is not interfering with the monitoring camera's verification of visitor identity. In order to reduce the complexity of the algorithm, reduce system power consumption, and prevent the introduction of other interference, no further adjustments will be made, and the execution scheme for external image interference will be recorded as continuing to scan and verify visitors.

[0042] When performing image information analysis, the external interference execution scheme analyzes the stripe jitter characterization factor and the image stripe jitter execution scheme to improve the image quality captured by the camera and increase recognition accuracy.

[0043] See Figure 3The diagram shows a flowchart of the image stripe jitter analysis execution scheme according to an embodiment of the present invention. The scheme involves collecting stripe jitter characterization parameters, analyzing stripe jitter characterization factors, extracting stripe jitter characterization factor thresholds, and if the stripe jitter characterization factor is greater than the stripe jitter characterization factor threshold, then the image stripe jitter execution scheme is recorded as stripe jitter adjustment. If the stripe jitter characterization factor is less than or equal to the stripe jitter characterization factor threshold, then the image stripe jitter execution scheme is recorded as continuing visitor scanning verification.

[0044] In this embodiment, the stripe jitter characterization factor is analyzed, and the analysis process is as follows: Collect fringe jitter characterization parameters, including fringe modulation depth, frequency domain main peak energy ratio, and fringe coverage of the current frame image.

[0045] The current frame image refers to the frame image that is being analyzed when the monitoring camera detects the presence of a visitor.

[0046] It should be noted that stripe modulation depth reflects the contrast intensity of the stripes, and is the extreme value of the maximum and minimum gray values ​​of a single row of pixels in the image. Specifically, it is the ratio of the maximum gray value minus the minimum gray value of a single row of pixels to the sum of the maximum and minimum gray values ​​of a single row of pixels. The frequency domain peak energy ratio quantifies the periodicity of the stripes; it is the ratio of the amplitude of the main peak in the Fourier spectrum to the average energy of the spectrum. Stripe coverage refers to the spatial distribution ratio of the stripes in the image, i.e., the ratio of the number of stripe pixels to the total number of pixels, where each stripe pixel represents the area occupied by a stripe row.

[0047] When the fringe modulation depth increases, i.e. the fringe contrast is enhanced, the amplitude of the main peak in the Fourier spectrum increases significantly, which enhances the main peak energy ratio in the frequency domain. The high fringe modulation depth and the main peak energy ratio in the high frequency domain will cause the fringe to spread in space, thereby increasing the fringe coverage.

[0048] It should be noted that the fringe modulation depth and fringe coverage can both be obtained using Python, and the frequency domain main peak energy ratio can be obtained using OpenCV.

[0049] Analysis of stripe jitter characterization factors based on stripe jitter characterization parameters.

[0050] The fringe modulation depth, frequency domain main peak energy ratio, and fringe coverage are compared with their corresponding reference values. The comparison results are then weighted and coupled with the corresponding metric coefficients to obtain the fringe jitter characterization factor.

[0051] The stripe jitter characterization factor is a quantitative representation of the stripe jitter state of the current frame image, which is jointly expressed by the stripe modulation depth, the frequency domain main peak energy ratio, and the stripe coverage.

[0052] It should be noted that the reference fringe modulation depth, reference frequency domain main peak energy ratio, and reference fringe coverage are extracted from the database.

[0053] Extract the preset fringe modulation depth metric coefficient, frequency domain main peak energy ratio metric coefficient, and fringe coverage metric coefficient from the database.

[0054] It should be further explained that, in this embodiment, in order to implement weighted coupling of fringe jitter characterization factors, multiple sets of parameter mapping relationships are pre-constructed in the database to associate different fringe modulation depths, frequency domain peak energy ratios, and fringe coverage with their corresponding metric coefficients. These mapping relationships are stored in the form of a structured configuration data table (e.g., a metric configuration table), which defines the metric coefficient values ​​corresponding to different fringe modulation depths, frequency domain peak energy ratios, and fringe coverage. This configuration table, through conditional matching combined with fringe jitter characterization parameters, dynamically adapts the fringe jitter characterization factors. Based on this configuration table, the system can automatically extract metric coefficients matching the fringe jitter characterization factors for subsequent weighted coupling calculations. The value range of each metric coefficient is limited to between 0 and 1, and the sum of the three is 1, to ensure that the multi-parameter fusion result has normalization properties and physical consistency, satisfying the weight constraints required for fringe jitter analysis.

[0055] In a specific embodiment, the stripe jitter characterization factor is represented as follows: , Where L is the fringe jitter characterization factor of the current frame image, T is the fringe modulation depth of the current frame image, P is the frequency domain main peak energy ratio of the current frame image, U is the fringe coverage of the current frame image, and T vef It is the reference fringe modulation depth, P vef It is the reference frequency domain main peak energy ratio, U vef T1 is the reference fringe coverage, P1 is the fringe modulation depth metric coefficient, and U1 is the frequency domain main peak energy ratio metric coefficient.

[0056] In this embodiment, the image stripe jitter execution scheme is analyzed, and the analysis process is as follows: Extract the threshold of the stripe jitter characterization factor.

[0057] If the stripe jitter characterization factor is greater than the stripe jitter characterization factor threshold, then the image stripe jitter execution scheme is recorded as stripe jitter adjustment.

[0058] It should be noted that if the stripe jitter characterization factor is greater than the stripe jitter characterization factor threshold, it means that the image obtained at this time has a stripe jitter problem, which will cause wavy interference or flickering in the image, reduce image quality, and easily cause visual fatigue for visitors. In order to eliminate misjudgment interference and avoid image distortion, the image stripe jitter implementation scheme is denoted as stripe jitter adjustment.

[0059] If the stripe jitter characterization factor is less than or equal to the stripe jitter characterization factor threshold, then the image stripe jitter execution scheme is recorded as continuing visitor scanning verification.

[0060] Continue visitor scanning and verification using the YOLOv5s object detection algorithm.

[0061] It should be noted that if the stripe jitter characterization factor is less than or equal to the stripe jitter characterization factor threshold, it indicates that the image does not have a stripe jitter problem. Although there may be external interference, it does not reduce the image quality or interfere with visual recognition. In order to reduce computing power consumption, the image stripe jitter execution scheme is recorded as continuing visitor scanning verification.

[0062] When performing image stripe jitter adjustment, the deviation value of the stripe jitter characterization factor is analyzed simultaneously, and stripe jitter adjustment is performed. After stripe jitter adjustment, the stripe jitter characterization factor is analyzed, and the stripe jitter adjustment effect information is analyzed. Thus, the image stripe jitter adjustment effect execution scheme is obtained to ensure the camera imaging quality and eliminate recognition interference.

[0063] See Figure 4 The diagram shows a flowchart of the analysis of stripe jitter adjustment effect information in an embodiment of the present invention. The process involves obtaining the stripe jitter characterization factor at this time, denoted as the first stripe jitter characterization factor; extracting the stripe jitter characterization factor threshold correction coefficient; obtaining the stripe jitter characterization factor correction threshold based on the threshold correction coefficient and the stripe jitter characterization factor threshold; if the first stripe jitter characterization factor is greater than the stripe jitter characterization factor correction threshold, the stripe jitter adjustment effect information is considered invalid, and the image stripe jitter adjustment effect execution scheme is denoted as performing coupling interference judgment; if the first stripe jitter characterization factor is less than or equal to the stripe jitter characterization factor correction threshold, the stripe jitter adjustment effect information is considered valid, and the image stripe jitter adjustment effect execution scheme is denoted as continuing visitor scanning verification.

[0064] In this embodiment, stripe jitter adjustment is performed, and the specific process is as follows: The difference between the stripe jitter characterization factor and the stripe jitter characterization factor threshold is used to obtain the stripe jitter characterization factor deviation value.

[0065] It should be noted that the deviation value of the stripe jitter characterization factor is obtained by subtracting the stripe jitter characterization factor threshold from the stripe jitter characterization factor.

[0066] Frequency adjustment value and duty cycle adjustment value are extracted based on the deviation value of the stripe jitter characterization factor.

[0067] It should be noted that both the frequency adjustment value and the duty cycle adjustment value are numerical data and have no positive or negative meaning.

[0068] In this embodiment, the system pre-constructs a mapping relationship between stripe jitter characterization factor deviation values ​​and corresponding frequency adjustment values ​​and duty cycle adjustment values ​​in the database. This mapping relationship is managed in the form of a structured configuration table (e.g., a stripe jitter parameter configuration table). During the matching process, the system uses the stripe jitter characterization factor deviation value as a query key to retrieve the corresponding frequency adjustment value and duty cycle adjustment value from the configuration table. By finding the frequency adjustment value and duty cycle adjustment value that match the stripe jitter characterization factor deviation value, the system can dynamically adjust the stripe jitter to ensure the quality of the obtained image.

[0069] It should be noted that the larger the deviation value of the stripe jitter characterization factor, the more serious the stripe jitter problem is. This can lead to the loss of key content during scanning, resulting in an increased recognition error rate. Severe stripe jitter can reduce user comfort and easily overload and damage the device. In order to obtain complete image information and improve the accuracy of visual recognition, the corresponding frequency adjustment value and duty cycle adjustment value should be larger to adjust the stripe jitter, improve the image quality captured by the camera, and improve recognition accuracy.

[0070] Adjusting the frequency and duty cycle can effectively solve the stripe jitter problem and optimize image quality. The core of this approach lies in precisely controlling signal timing and energy distribution to eliminate the periodic characteristics of interfering signals. Frequency adjustment breaks resonant interference, using high frequencies to suppress visible jitter. Duty cycle adjustment evens out energy distribution, eliminating sharp-edge stripes. Therefore, adjusting the frequency and duty cycle can solve the stripe jitter problem and ensure the quality of the obtained image.

[0071] Obtain the rolling shutter cycle of the camera.

[0072] It should be noted that the rolling shutter cycle of the camera is a cycle inherent to the camera device itself, and is obtained directly from the database when in use.

[0073] The dimming frequency is supplemented and adjusted based on the camera's rolling shutter cycle and frequency adjustment value.

[0074] It should be noted that the supplementary adjustment of the dimming frequency refers to multiplying the frequency adjustment value by the camera's rolling shutter period to obtain an integer multiple of the camera's rolling shutter period. In a specific embodiment, assuming the camera's rolling shutter period is 10μs and the frequency adjustment value is 1, then the execution value of the supplementary adjustment of the dimming frequency is 100kHz.

[0075] Multiplying the frequency adjustment value by the camera's rolling shutter cycle yields an integer multiple of the rolling shutter cycle. The camera sensor exposes line by line from top to bottom, with the exposure start time of each line differing by one line cycle. If the frequency and line cycle are not synchronized, the signals captured within the integration time of each line will have different phases, leading to inconsistent brightness across lines. This results in bright and dark stripes in the image, causing stripe jitter. The integer multiple relationship is for phase alignment, ensuring that the exposure window of each line covers the same number of complete cycles, maximizing stripe suppression and eliminating inter-line brightness differences.

[0076] Obtain the duty cycle of the dimming light source at this time.

[0077] It should be noted that the duty cycle of a dimming light source refers to the proportion of the time the light source is powered on within a complete cycle, which directly determines the visual brightness and flicker characteristics of the light source.

[0078] The duty cycle of a dimming light source can be obtained directly using Arduino.

[0079] The duty cycle is adjusted by supplementing the duty cycle based on the duty cycle adjustment value and the duty cycle of the dimming light source at this time.

[0080] It should be noted that the value obtained by adding the duty cycle adjustment value to the duty cycle of the dimming light source at this time is used as the execution value for the supplementary adjustment of the duty cycle.

[0081] In this embodiment, the stripe jitter adjustment effect information is analyzed to obtain the image stripe jitter adjustment effect implementation scheme. The analysis process is as follows: Obtain the fringe jitter characterization factor at this time, and denote it as the first fringe jitter characterization factor.

[0082] The threshold correction coefficient for stripe jitter characterization factors is extracted based on the frequency adjustment value.

[0083] It should be noted that the system pre-establishes a correspondence between frequency adjustment values ​​and corresponding stripe jitter characterization factor threshold correction coefficients in the database. This correspondence is managed by the system through structured data tables (such as the stripe jitter correction coefficient table). During the matching process, the system uses the frequency adjustment value as the search key to query the corresponding stripe jitter characterization factor threshold correction coefficient. This correction coefficient is used to dynamically adjust stripe jitter, thereby optimizing the application of the stripe jitter threshold and improving the accuracy and stability of the acquired image.

[0084] It should be noted that the larger the frequency adjustment value, the more severe the stripe jitter problem, the worse the image quality, and the greater the degree of stripe jitter adjustment. In order to ensure the imaging quality of the camera and eliminate recognition interference, the threshold of the stripe jitter characterization factor is strictly corrected, so the corresponding extracted stripe jitter characterization factor threshold correction coefficient is larger.

[0085] The stripe jitter characterization factor correction threshold is obtained based on the stripe jitter characterization factor threshold and the stripe jitter characterization factor threshold correction coefficient.

[0086] It should be noted that the stripe jitter characterization factor correction threshold is obtained by multiplying the stripe jitter characterization factor threshold by the stripe jitter characterization factor correction coefficient.

[0087] It should be noted that the above-mentioned correction coefficient for the stripe jitter characterization factor reading value is only a slight correction to the stripe jitter characterization factor reading value.

[0088] It should be further explained that the stripe jitter characterization factor threshold is corrected by the stripe jitter characterization factor threshold correction coefficient, and the stripe jitter characterization factor correction threshold is used to judge the stripe jitter adjustment effect. Compared with judging by the stripe jitter characterization factor threshold, a more stringent standard is used to judge the adjustment effect, which can accurately measure the effectiveness of the stripe jitter adjustment operation.

[0089] If the first fringe jitter characterization factor is greater than the fringe jitter characterization factor correction threshold, then the fringe jitter adjustment effect information is invalid adjustment, and the image fringe jitter adjustment effect execution scheme is recorded as performing coupling interference judgment.

[0090] It should be noted that if the first stripe jitter characterization factor is greater than the stripe jitter characterization factor correction threshold, it means that the camera stripe jitter problem has not been solved after stripe jitter adjustment, and the image stripe jitter is severe. Therefore, the stripe jitter adjustment effect information is considered invalid adjustment. In order to ensure the camera imaging quality and eliminate recognition interference, the image stripe jitter adjustment effect execution scheme is recorded as performing coupling interference judgment.

[0091] If the first stripe jitter characterization factor is less than or equal to the stripe jitter characterization factor correction threshold, then the stripe jitter adjustment effect information is considered effective, and the image stripe jitter adjustment effect execution plan is recorded as continuing visitor scanning verification.

[0092] It should be noted that if the first stripe jitter characterization factor is less than or equal to the stripe jitter characterization factor correction threshold, it means that the image stripe jitter problem has been solved after adjustment. The stripe jitter adjustment effect information is effective adjustment, which improves the image quality captured by the camera and enhances the accuracy of scanning and recognition. In order to reduce the power consumption of the system and reduce the complexity of the algorithm, the image stripe jitter adjustment effect execution scheme is recorded as continuing to perform visitor scanning verification.

[0093] When the image stripe jitter adjustment effect implementation scheme is to judge coupling interference, the coupling interference characterization factor is analyzed, the coupling interference implementation scheme is analyzed, coupling interference adjustment is performed, coupling interference is eliminated, and image quality is improved.

[0094] In this embodiment, the coupling interference characterization factor is analyzed, and the specific analysis process is as follows: Collect coupling interference characterization parameters, including the composite modulation depth, coupling frequency domain feature ratio, and spatiotemporal coupling interference index of the current frame image.

[0095] It should be noted that the composite modulation depth refers to the degree of superimposed distortion reflecting both fringe contrast and rain / fog scattering effects. This is achieved by multiplying the fringe modulation depth and the rain / fog scattering coefficient by their respective weighting coefficients, and then summing the results. The rain / fog scattering coefficient refers to the dark channel mean. The coupling frequency domain characteristic ratio quantifies the proportion of coupling energy between flicker and raindrop dynamic noise in the frequency domain. This is achieved by adding the fundamental frequency and its harmonic energy, the raindrop motion frequency band energy, and the cross-modulation energy, and then dividing by the total frequency band energy. The coupling frequency domain characteristic ratio parameter is collected in rainy weather because rain causes water droplets to adhere to the lens, forming irregular lenses that cause multi-directional scattering of light and affect the camera's image quality. The spatiotemporal coupling interference index assesses the degree of spatiotemporal overlap between the fringe edges and the raindrop motion area. It is the ratio of the overlap area between the fringe edge region and the raindrop motion area to the fringe edge region. The spatiotemporal coupling interference index parameter is collected in rainy weather because rain causes water droplet lens distortion, with water droplets forming aspherical lenses that affect the camera's image quality.

[0096] It should be noted that, except for rainy days, the coupled frequency domain eigenvalue ratio and the spatiotemporal coupling interference index are set to zero. The weather conditions excluding rainy days include, but are not limited to, sunny days and cloudy days.

[0097] When the coupling frequency domain eigenvalue increases, the cross-modulation energy increases, which in turn increases the spatiotemporal coupling interference index. The increase in both the coupling frequency domain eigenvalue and the spatiotemporal coupling interference index indicates strong coupling, and therefore the composite modulation depth also increases accordingly.

[0098] It should be noted that the composite modulation depth can be obtained using Python + OpenCV, the coupling frequency domain eigenvalue ratio can be obtained using OpenCV + NumPy, and the spatiotemporal coupling interference index can be obtained using Python.

[0099] Analysis of coupling interference characterization factors based on coupling interference characterization parameters.

[0100] Extract the preset reference composite modulation depth, reference coupling frequency domain eigenvalue ratio, and reference spatiotemporal coupling interference index from the database.

[0101] The composite modulation depth is compared with a reference composite modulation depth to obtain a composite modulation depth scaling factor; that is, the composite modulation depth is divided by the reference composite modulation depth. Similarly, the coupling frequency domain characteristic ratio is compared with a reference coupling frequency domain characteristic ratio to obtain a coupling frequency domain characteristic ratio scaling factor; that is, the coupling frequency domain characteristic ratio is divided by the reference coupling frequency domain characteristic ratio. Finally, the spatiotemporal coupling interference index is compared with a reference spatiotemporal coupling interference index to obtain a spatiotemporal coupling interference index scaling factor; that is, the spatiotemporal coupling interference index is divided by the reference spatiotemporal coupling interference index.

[0102] The composite modulation depth scaling factor, the coupling frequency domain feature ratio scaling factor, and the spatiotemporal coupling interference index scaling factor are combined with their corresponding metric coefficients for weighted coupling processing to obtain the coupling interference characterization factor.

[0103] The coupling interference characterization factor is a quantitative representation of coupling interference by the composite modulation depth, coupling frequency domain feature ratio, and spatiotemporal coupling interference index of the current frame image.

[0104] It should be noted that the preset composite modulation depth metric coefficient, coupled frequency domain feature ratio metric coefficient, and spatiotemporal coupling interference index metric coefficient are extracted from the database.

[0105] In this embodiment, to achieve weighted coupling of the coupling interference characterization factors, multiple sets of parameter mapping relationships are pre-constructed in the database to associate different composite modulation depths, coupling frequency domain eigenvalue ratios, and spatiotemporal coupling interference indices with their corresponding metric coefficients. These mapping relationships are stored in the form of a structured configuration data table (e.g., a metric configuration table). The configuration table defines the metric coefficient values ​​corresponding to different composite modulation depths, coupling frequency domain eigenvalue ratios, and spatiotemporal coupling interference indices. This configuration table, through conditional matching combined with the coupling interference characterization parameters, achieves dynamic adaptation of the coupling interference characterization factors. Based on this configuration table, the system can automatically extract metric coefficients that match the coupling interference characterization parameters for subsequent weighted coupling calculations. The value range of each metric coefficient is limited to between 0 and 1, and the sum of the three is 1, to ensure that the multi-feature fusion results possess normalization properties and physical consistency, satisfying the weight constraints required for coupling interference analysis.

[0106] In the specific implementation process, the coupling interference characterization factor is represented as follows: , Where M is the coupling interference characterization factor, a is the composite modulation depth scaling factor, b is the coupling frequency domain characteristic ratio scaling factor, c is the spatiotemporal coupling interference exponential scaling factor, E1 is the composite modulation depth measurement factor, E2 is the coupling frequency domain characteristic ratio measurement factor, and E3 is the spatiotemporal coupling interference exponential measurement factor.

[0107] In this embodiment, the coupling interference execution scheme is analyzed. The specific analysis process is as follows: Extract the threshold of the coupling interference characterization factor.

[0108] The threshold correction coefficient for the coupling interference characterization factor is extracted based on the first fringe jitter characterization factor.

[0109] It should be noted that the system pre-establishes a correspondence between the first fringe jitter characterization factor and the corresponding coupling interference characterization factor threshold correction coefficient in the database. This correspondence is managed by the system through structured data tables (such as the coupling interference correction coefficient table). During the matching process, the system uses the first fringe jitter characterization factor as the search key to query the corresponding coupling interference characterization factor threshold correction coefficient. This correction coefficient is used to dynamically adjust the coupling interference, thereby optimizing the application of the coupling interference threshold, improving the image quality captured by the camera, and increasing recognition accuracy.

[0110] It should be noted that the larger the jitter characterization factor of the first fringe, the more serious the coupling interference problem is, and the worse the image quality captured by the camera. In order to ensure the imaging quality of the camera and eliminate recognition interference, the threshold of the coupling interference characterization factor is strictly corrected. Therefore, the larger the corresponding extracted coupling interference characterization factor threshold correction coefficient is.

[0111] The correction threshold for the coupling interference characterization factor is obtained based on the correction coefficient for the coupling interference characterization factor threshold and the threshold for the coupling interference characterization factor.

[0112] It should be noted that the coupling interference characterization factor threshold correction threshold is obtained by multiplying the coupling interference characterization factor threshold correction coefficient by the coupling interference characterization factor threshold.

[0113] It should be noted that the above-mentioned coupling interference characterization factor threshold correction coefficient is only a slight correction to the coupling interference characterization factor threshold.

[0114] It should be further explained that by correcting the threshold of the coupling interference characterization factor through the threshold correction coefficient, and then using the obtained corrected threshold to judge the coupling interference characterization factor, the judgment standard is corrected more strictly than that of judging by the threshold. This allows for a more accurate judgment of the coupling interference execution scheme, making the execution scheme more targeted, solving the problems caused by the image, eliminating coupling interference, and improving image quality.

[0115] If the coupling interference characterization factor is greater than or equal to the coupling interference characterization factor correction threshold, then the coupling interference execution scheme is recorded as performing coupling interference adjustment.

[0116] It should be noted that judging the coupling interference problem can improve the accuracy of governance, enhance system reliability, reduce the false judgment rate of identification, and make the identification more accurate. At this time, if the coupling interference characterization factor is greater than or equal to the coupling interference characterization factor correction threshold, it indicates that the coupling interference is serious. In order to eliminate coupling interference and improve image quality, the coupling interference implementation scheme is denoted as coupling interference adjustment.

[0117] If the coupling interference characterization factor is less than the coupling interference characterization factor correction threshold, then the coupling interference execution scheme is recorded as sending early warning information.

[0118] It should be noted that if the coupling interference characterization factor is less than the coupling interference characterization factor correction threshold, it means that the coupling problem is not serious at this time. However, this is a judgment of coupling interference after the stripe jitter adjustment is ineffective. In order to ensure the operation of the system and not continue to generate erroneous scanning results, the coupling interference execution scheme is recorded as sending a warning message.

[0119] In this embodiment, coupling interference is adjusted, and the specific process is as follows: The deviation value of the coupling interference characterization factor is obtained by performing a difference processing on the coupling interference characterization factor and the correction threshold of the coupling interference characterization factor.

[0120] It should be noted that the deviation value of the coupling interference characterization factor is obtained by subtracting the correction threshold of the coupling interference characterization factor from the coupling interference characterization factor.

[0121] The frequency adjustment value and the supplementary light intensity adjustment value are obtained based on the deviation value of the coupling interference characterization factor.

[0122] It should be noted that both the frequency adjustment value and the supplementary light intensity adjustment value are numerical data and have no positive or negative meaning.

[0123] In this embodiment, the system pre-constructs a mapping relationship between the coupling interference characterization factor deviation value and the corresponding frequency adjustment value and supplementary light intensity adjustment value in the database. This mapping relationship is managed in the form of a structured configuration table (e.g., a coupling interference parameter configuration table). During the matching process, the system uses the coupling interference characterization factor deviation value as the query key to retrieve the corresponding frequency adjustment value and supplementary light intensity adjustment value in the configuration table. By finding the frequency adjustment value and supplementary light intensity adjustment value that match the coupling interference characterization factor deviation value, the system can dynamically adjust the coupling interference to ensure the quality of the obtained image.

[0124] It should be noted that the larger the deviation value of the coupling interference characterization factor, the more serious the coupling interference problem is. This will cause the algorithm indicators to deteriorate, increase the false detection rate of camera verification, cause equipment recognition failure, and cover key scanning features. In order to obtain complete image information and improve recognition accuracy, the corresponding frequency adjustment value and supplementary light intensity adjustment value should be larger to adjust the coupling interference, improve the image quality captured by the camera, and improve recognition accuracy.

[0125] Adjusting the frequency and supplementary light intensity can effectively solve coupling interference problems and improve the quality of the acquired image. The core of this approach lies in precisely controlling signal timing to eliminate the periodic characteristics of interfering signals and accurately disrupt the physical interference mechanism. Frequency adjustment can break resonance interference and suppress visible jitter using high frequencies. Adjusting the supplementary light intensity can suppress the amplitude domain influence of scattering noise. Therefore, adjusting the frequency and supplementary light intensity can solve coupling interference problems and ensure the quality of the acquired image.

[0126] The dimming frequency is supplemented and adjusted based on the camera's rolling shutter cycle and frequency adjustment value.

[0127] It should be noted that the supplementary adjustment of the dimming frequency refers to multiplying the frequency adjustment value by the camera's rolling shutter period to obtain an integer multiple of the camera's rolling shutter period. In a specific embodiment, assuming the camera's rolling shutter period is 10μs and the frequency adjustment value is 1, then the execution value of the supplementary dimming frequency adjustment is 100kHz. Obtain the infrared illumination intensity at this time.

[0128] It should be noted that the infrared illumination intensity at this time refers to the infrared radiation power received per unit area.

[0129] The intensity of the infrared supplementary light at this time can be obtained through an integrated optical sensor.

[0130] The supplementary light intensity is adjusted based on the supplementary light intensity adjustment value and the infrared supplementary light intensity at this time.

[0131] It should be noted that the value obtained by adding the supplementary light intensity adjustment value to the infrared supplementary light intensity at this time is used as the execution value for the supplementary adjustment of the supplementary light intensity.

[0132] When the image is subjected to external interference, the solution is to continue visitor scanning and verification; when the image is subjected to stripe jitter, the solution is to continue visitor scanning and verification; or when the image is subjected to stripe jitter adjustment, the solution is to continue visitor scanning and verification, the visitor identity is automatically verified based on the YOLOv5s target detection algorithm.

[0133] It should be noted that the automatic visitor identity verification is performed based on the YOLOv5s object detection algorithm. First, target face detection and liveness detection are performed, then facial features are extracted, and the facial features are compared with the database to obtain the final verification result. If the verification result is successful, the door is opened; if the verification result is unsuccessful, a prompt or alarm is issued.

[0134] like Figure 2 The diagram shown illustrates the structure of an automatic visitor identity verification system based on smart access control. This system includes: The external interference judgment module uses the access control monitoring camera to sense whether a visitor is present within its scanning range in real time. When a visitor is detected, the module acquires the image information scanned by the camera at that time, obtains the average value of the dark channel of the image, analyzes the external interference of the image, and implements a solution to enhance the all-weather reliability of recognition in order to cope with complex scenarios.

[0135] The stripe jitter detection module analyzes stripe jitter characteristics and image stripe jitter detection schemes when performing image information analysis in the event of external interference, thereby improving the image quality captured by the camera and increasing recognition accuracy.

[0136] The stripe jitter adjustment module, when the image stripe jitter execution scheme is to perform stripe jitter adjustment, simultaneously analyzes the deviation value of the stripe jitter characterization factor and performs stripe jitter adjustment. After the stripe jitter adjustment, it analyzes the stripe jitter characterization factor at this time and analyzes the stripe jitter adjustment effect information, thereby obtaining the image stripe jitter adjustment effect execution scheme to ensure the camera imaging quality and eliminate recognition interference.

[0137] The coupling interference analysis module analyzes coupling interference characterization factors and coupling interference implementation schemes when the image stripe jitter adjustment effect execution scheme is to perform coupling interference judgment, adjust coupling interference, eliminate coupling interference, and improve image quality.

[0138] The visitor identity verification module automatically verifies visitor identity based on the YOLOv5s target detection algorithm when the image is affected by external interference, image stripe jitter, or image stripe jitter adjustment.

[0139] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, 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., infrared, wireless, microwave, etc.) means. A 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 includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0140] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0141] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0142] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0143] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0144] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0145] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0146] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0147] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for automatic visitor identity verification based on smart access control, characterized in that, Includes the following steps: Access control monitoring cameras can detect whether visitors are present within their scanning range in real time. When a visitor is detected, the camera captures the image information and obtains the average value of the dark channel of the image. It also analyzes external interference in the image to implement a solution, thereby enhancing the all-weather reliability of the recognition and coping with complex scenarios. When performing image information analysis, the external interference execution scheme analyzes the stripe jitter characterization factor and the image stripe jitter execution scheme to improve the image quality captured by the camera and increase the recognition accuracy. When the image stripe jitter removal scheme is to adjust the stripe jitter, the deviation value of the stripe jitter characterization factor is analyzed simultaneously, and stripe jitter adjustment is performed. After the stripe jitter adjustment is performed, the stripe jitter characterization factor is analyzed at this time, and the stripe jitter adjustment effect information is analyzed. Thus, the image stripe jitter adjustment effect implementation scheme is obtained to ensure the imaging quality of the camera and eliminate recognition interference. When the image stripe jitter adjustment effect implementation scheme is to judge coupling interference, the coupling interference characterization factor is analyzed, the coupling interference implementation scheme is analyzed, the coupling interference is adjusted, the coupling interference is eliminated, and the image quality is improved. When the image is subjected to external interference, the solution is to continue visitor scanning and verification; when the image is subjected to stripe jitter, the solution is to continue visitor scanning and verification; or when the image is subjected to stripe jitter adjustment, the solution is to continue visitor scanning and verification, the visitor identity is automatically verified based on the YOLOv5s target detection algorithm.

2. The method for automatic visitor identity verification based on smart access control according to claim 1, characterized in that, The process of obtaining the dark channel mean of the image and analyzing external interference is as follows: Obtain the mean value of the dark channel of the image; Extract the dark channel mean threshold; If the mean value of the dark channel of the image is greater than the threshold value of the dark channel mean value, the external interference of the image is recorded as performing image information analysis. If the dark channel mean of the image is less than or equal to the dark channel mean threshold, the external interference of the image is recorded as continuing to perform visitor scanning verification.

3. The method for automatic visitor identity verification based on smart access control according to claim 1, characterized in that, The analysis process for the stripe jitter characterization factor is as follows: Collect fringe jitter characterization parameters, including fringe modulation depth, frequency domain main peak energy ratio, and fringe coverage of the current frame image; Analysis of stripe jitter characterization factors based on stripe jitter characterization parameters; The fringe modulation depth, frequency domain main peak energy ratio, and fringe coverage are compared with their corresponding reference values. The comparison results are then weighted and coupled with the corresponding metric coefficients to obtain the fringe jitter characterization factor. The stripe jitter characterization factor is a quantitative representation of the stripe jitter state of the current frame image, which is jointly expressed by the stripe modulation depth, the frequency domain main peak energy ratio, and the stripe coverage.

4. The method for automatic visitor identity verification based on smart access control as described in claim 3, characterized in that, The analysis of image stripe jitter execution scheme and the judgment process are as follows: Extract the threshold of the stripe jitter characterization factor; If the stripe jitter characterization factor is greater than the stripe jitter characterization factor threshold, then the image stripe jitter execution scheme is recorded as stripe jitter adjustment. If the stripe jitter characterization factor is less than or equal to the stripe jitter characterization factor threshold, then the image stripe jitter execution scheme is recorded as continuing visitor scanning verification.

5. The method for automatic visitor identity verification based on smart access control according to claim 4, characterized in that, The specific process for adjusting the stripe jitter is as follows: The difference between the stripe jitter characterization factor and the stripe jitter characterization factor threshold is used to obtain the stripe jitter characterization factor deviation value. Frequency adjustment value and duty cycle adjustment value are extracted based on the deviation value of the stripe jitter characterization factor. Obtain the rolling shutter cycle of the camera; The dimming frequency is supplemented and adjusted based on the camera's rolling shutter cycle and frequency adjustment value. Obtain the duty cycle of the dimming light source at this time; The duty cycle is adjusted by supplementing the duty cycle based on the duty cycle adjustment value and the duty cycle of the dimming light source at this time.

6. The method for automatic visitor identity verification based on smart access control according to claim 1, characterized in that, The analysis of the stripe jitter adjustment effect information yields the image stripe jitter adjustment effect implementation scheme. The analysis process is as follows: Obtain the fringe jitter characterization factor at this time, and denote it as the first fringe jitter characterization factor; Extract the threshold correction coefficient for stripe jitter characterization factors based on frequency adjustment values; The stripe jitter characterization factor correction threshold is obtained based on the stripe jitter characterization factor threshold and the stripe jitter characterization factor threshold correction coefficient; If the first fringe jitter characterization factor is greater than the fringe jitter characterization factor correction threshold, then the fringe jitter adjustment effect information is invalid adjustment, and the image fringe jitter adjustment effect execution scheme is recorded as performing coupling interference judgment. If the first stripe jitter characterization factor is less than or equal to the stripe jitter characterization factor correction threshold, then the stripe jitter adjustment effect information is considered effective, and the image stripe jitter adjustment effect execution plan is recorded as continuing visitor scanning verification.

7. The method for automatic visitor identity verification based on smart access control according to claim 1, characterized in that, The analysis of coupling interference characterization factors is as follows: Collect coupling interference characterization parameters, including the composite modulation depth, coupling frequency domain feature ratio, and spatiotemporal coupling interference index of the current frame image; Analysis of coupling interference characterization factors based on coupling interference characterization parameters; Extract the preset reference composite modulation depth, reference coupling frequency domain eigenvalue ratio, and reference spatiotemporal coupling interference index from the database; The composite modulation depth is compared with the reference composite modulation depth to obtain the composite modulation depth ratio coefficient; the coupled frequency domain feature ratio is compared with the reference coupled frequency domain feature ratio to obtain the coupled frequency domain feature ratio ratio coefficient; and the spatiotemporal coupling interference index is compared with the reference spatiotemporal coupling interference index to obtain the spatiotemporal coupling interference index ratio coefficient. The composite modulation depth scaling factor, the coupled frequency domain feature ratio scaling factor, and the spatiotemporal coupled interference index scaling factor are combined with the corresponding metric coefficients for weighted coupling processing to obtain the coupled interference characterization factor. The coupling interference characterization factor is a quantitative representation of coupling interference by the composite modulation depth, coupling frequency domain feature ratio, and spatiotemporal coupling interference index of the current frame image.

8. The method for automatic visitor identity verification based on smart access control according to claim 1, characterized in that, The analysis of the coupling interference execution scheme is as follows: Extract the threshold for coupling interference characterization factors; The threshold correction coefficient for the coupling interference characterization factor is extracted based on the first fringe jitter characterization factor. The correction threshold for the coupling interference characterization factor is obtained based on the correction coefficient for the coupling interference characterization factor threshold and the threshold for the coupling interference characterization factor. If the coupling interference characterization factor is greater than or equal to the coupling interference characterization factor correction threshold, then the coupling interference execution scheme is recorded as performing coupling interference judgment. If the coupling interference characterization factor is less than the coupling interference characterization factor correction threshold, then the coupling interference execution scheme is recorded as sending early warning information.

9. The method for automatic visitor identity verification based on smart access control according to claim 1, characterized in that, The specific process for adjusting coupling interference is as follows: The difference between the coupling interference characterization factor and the correction threshold of the coupling interference characterization factor is processed to obtain the deviation value of the coupling interference characterization factor. The frequency adjustment value and the supplementary light intensity adjustment value are obtained based on the deviation value of the coupling interference characterization factor. The dimming frequency is supplemented and adjusted based on the camera's rolling shutter cycle and frequency adjustment value. Obtain the infrared illumination intensity at this time; The supplementary light intensity is adjusted based on the supplementary light intensity adjustment value and the infrared supplementary light intensity at this time.

10. An automatic visitor identity verification system based on smart access control, employing the automatic visitor identity verification method based on smart access control as described in any one of claims 1-9, characterized in that, The system includes: The external interference judgment module uses the access control monitoring camera to sense whether a visitor is present within its scanning range in real time. When a visitor is detected, the module acquires the image information scanned by the camera at that time, obtains the average value of the dark channel of the image, analyzes the external interference of the image, and implements a solution to enhance the all-weather reliability of recognition in order to cope with complex scenarios. The stripe jitter judgment module analyzes stripe jitter characterization factors and image stripe jitter execution schemes when the image is subjected to external interference and the image information analysis is not performed, thereby improving the image quality captured by the camera and increasing recognition accuracy. The stripe jitter adjustment module, when the image stripe jitter execution scheme is to perform stripe jitter adjustment, simultaneously analyzes the deviation value of the stripe jitter characterization factor and performs stripe jitter adjustment. After the stripe jitter adjustment is performed, it analyzes the stripe jitter characterization factor at this time and analyzes the stripe jitter adjustment effect information, thereby obtaining the image stripe jitter adjustment effect execution scheme to ensure the camera imaging quality and eliminate recognition interference. The coupling interference analysis module analyzes coupling interference characterization factors and coupling interference execution schemes when the image stripe jitter adjustment effect is implemented, performs coupling interference adjustment, eliminates coupling interference, and improves image quality. The visitor identity verification module automatically verifies visitor identity based on the YOLOv5s target detection algorithm when the image is affected by external interference, image stripe jitter, or image stripe jitter adjustment.

Images