CN116886892A - Access control management method based on multi-source data - Google Patents
Access control management method based on multi-source data Download PDFInfo
- Publication number
- CN116886892A CN116886892A CN202311135517.7A CN202311135517A CN116886892A CN 116886892 A CN116886892 A CN 116886892A CN 202311135517 A CN202311135517 A CN 202311135517A CN 116886892 A CN116886892 A CN 116886892A
- Authority
- CN
- China
- Prior art keywords
- image
- index
- camera
- accuracy
- access control
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000007726 management method Methods 0.000 title claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 36
- 238000000034 method Methods 0.000 claims description 39
- 230000002159 abnormal effect Effects 0.000 claims description 27
- 238000004422 calculation algorithm Methods 0.000 claims description 19
- 230000006641 stabilisation Effects 0.000 claims description 13
- 238000011105 stabilization Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 12
- 238000012935 Averaging Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000007405 data analysis Methods 0.000 claims description 9
- 238000013480 data collection Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/002—Diagnosis, testing or measuring for television systems or their details for television cameras
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Closed-Circuit Television Systems (AREA)
- Studio Devices (AREA)
Abstract
The application discloses an access control management method based on multi-source data, which relates to the technical field of access control management and comprises the following steps: s101, acquiring information of a camera in the access control system during operation, wherein the information comprises camera data acquisition information and camera image processing information, and processing the acquired camera data acquisition information and the camera image processing information. According to the application, the running state of the camera in the access control management system is monitored, so that the access control management system intelligently senses the condition that the recognition accuracy of the camera is influenced, the condition that the recognition is wrong or misrefused is effectively prevented, the condition that a legal user is possibly mistakenly recognized as an illegal user and cannot enter a limited area is effectively prevented, the condition that the user is not full, work is interrupted or other inconvenience is possibly caused, and the practicability of the access control management system is improved.
Description
Technical Field
The application relates to the technical field of access control, in particular to an access control method based on multi-source data.
Background
The access control system can control the access of personnel, and can also control the behaviors of the personnel in the building and the sensitive area and accurately record and count the digital access control system of management data. The safety problem of important places such as enterprises and public institutions, schools, communities, offices and the like is mainly solved. Control devices such as access controllers, code keyboards, etc. are installed at the building doorways, elevators, etc. To enter a resident, the resident must have a card or enter the correct password or pass by a special biometric password. The access control system can effectively manage the opening and closing of the door, ensure the free access of authorized personnel and limit the access of unauthorized personnel.
Most of the prior art entrance guard management systems use face recognition, face images are acquired through cameras, users are usually required to stand at specific positions in the acquisition process, face orientation of the cameras is kept, then the acquired face features are compared and matched with the known face features, whether the matching is successful or not is determined, and identity authentication or recognition is carried out according to the matching result;
the prior art has the following defects: however, when the recognition accuracy of the camera in the access control system is affected, the access control system cannot sense intelligently, and as the recognition accuracy of the access control system is reduced, a situation of wrong recognition or wrong rejection may occur, which means that a legal user may be mistakenly recognized as an illegal user, so that the legal user cannot enter a limited area, which may cause dissatisfaction, work interruption or other inconvenience of the user, so that the practicability of the access control system becomes poor.
The above information disclosed in the background section is only for enhancement of understanding of the background of the disclosure and therefore it may include information that does not form the prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
The application aims to provide an access control management method based on multi-source data, which monitors the running state of a camera in an access control management system, so that the access control management system intelligently senses the condition that the recognition accuracy of the camera is influenced, the condition that the recognition is wrong or misrefused is effectively prevented, the condition that a legal user is possibly mistakenly recognized as an illegal user and cannot enter a limited area is effectively prevented, the condition that the user is not full, work is interrupted or other inconvenience is possibly caused, and the practicability of the access control management system is improved, so that the problems in the background technology are solved.
In order to achieve the above object, the present application provides the following technical solutions: an access control management method based on multi-source data comprises the following steps: s101, acquiring information of a camera in an access control system during operation, wherein the information comprises camera data acquisition information and camera image processing information, and processing the acquired camera data acquisition information and the camera image processing information;
s102, establishing a data analysis model of collected camera data collection information and camera image processing information, generating an accuracy influence index, and evaluating the identification accuracy of the camera through the accuracy influence index;
s103, comparing an accuracy influence index generated when the camera operates with an accuracy influence index reference threshold value to generate a high influence degree signal and a low influence degree signal;
and S104, when the camera runs and generates a high influence degree signal, continuously outputting a plurality of accuracy influence indexes generated when the camera runs to establish a data set, comprehensively analyzing the accuracy influence indexes in the data set to generate a risk signal, and sending or not sending an early warning prompt to the risk signal.
Preferably, the camera data acquisition information comprises an image acquisition frame rate stabilization index, and after acquisition, the image acquisition frame rate stabilization index is calibrated asThe camera image processing information comprises an image distortion degree index and an abnormal overexposure frequency index, and after acquisition, the image distortion degree index and the abnormal overexposure frequency index are respectively calibrated to be +.>And->. Preferably, the logic for obtaining the image acquisition frame rate stabilization index is as follows:
s1, acquiring image acquisition frame numbers of cameras in different time periods within T time, and calibrating the duration of the time period asLWill time periodLThe frame number of the internal image acquisition is marked as H, and the time period is calculatedLThe frame rate of the image acquisition in the system is calculated according to the following formula:wherein->Representing a frame rate; s2, acquiring image acquisition frame rates of the camera in different time periods within the T time, and calibrating the image acquisition frame rates to be +.>，bA number representing the image acquisition frame rate for different time periods within the T time,b=1、2、3、4、……、B，Bis a positive integer; s3, calculating standard deviation of image acquisition frame rates of the cameras in different time periods within the T time, and calibrating the standard deviation asRStandard deviationRThe calculation formula of (2) is as follows:
，
wherein, the liquid crystal display device comprises a liquid crystal display device,for the average value of image acquisition frame rates of the camera in different time periods within the T time, the acquired expression is as follows: />The method comprises the steps of carrying out a first treatment on the surface of the S4, calculating an image acquisition frame rate stability index, wherein the calculated expression is as follows: />。
Preferably, the logic for obtaining the image distortion degree index is as follows:
s1, acquiring an original shooting image and an image processed by a camera, and performing gray processing on the original shooting image and the image processed by the camera to convert the original shooting image and the image processed by the camera into a gray image;
s2, dividing pixels of pixel points on the original photographed image and the image processed by the cameraAre marked asAnd->，yRepresenting the numbers of pixels of the pixel points on the original photographed image and the image processed by the camera,y=1、2、3、4、……、c，cis a positive integer;
s3, calculating the mean square error of the image, and calibrating the mean square error asMSEThenThe method comprises the steps of carrying out a first treatment on the surface of the S4, acquiring the mean square error before and after all the image processing in the T time, and calibrating the mean square error as +.>，kMean square error +.>Is provided with the number of (a),k=1、2、3、4、……、P，Pis a positive integer;
s5, calculating an image distortion degree index, wherein a calculation formula is as follows:。
preferably, the logic for obtaining the abnormal overexposure frequency index is as follows:
s1, acquiring image data captured by a camera in T time, applying an image processing algorithm to the acquired image data to obtain processed images, counting the processed images, and recording the number of the images asN；
S2, converting the image into a gray image, and calculating a brightness value for each pixel of the gray image;
s3, calculating the average brightness value of each image, and calibrating the average brightness value as，xRepresenting each image in a time TAverage value of brightness->Is provided with the number of (a),x=1、2、3、4、……、N，Nis a positive integer; s4, averaging the brightness of each image +.>And a preset brightness reference threshold +.>Comparing and averaging the brightness +.>Greater than or equal to the luminance reference threshold->Counting the number of images of (a) and averaging the brightness +.>Greater than or equal to the luminance reference threshold->The number of images is calibrated asn；
S5, obtaining the number of images in the T timeNAnd average value of brightnessGreater than or equal to the luminance reference thresholdImage number of (a)nCalculating an abnormal overexposure frequency index, wherein the calculated expression is as follows: />。
Preferably, after obtaining the image acquisition frame rate stability index, the image distortion degree index and the abnormal overexposure frequency index, a data analysis model is established to generate an accuracy influence index according to the following formula:
，
in the method, in the process of the application,e1、e2、e3 minutes S4, average brightness of each imageAnd a preset brightness reference thresholdComparing and averaging the brightness +.>Greater than or equal to the luminance reference threshold->Counting the number of images of (a) and averaging the brightness +.>Greater than or equal to the luminance reference threshold->The number of images is calibrated asn；
S5, obtaining the number of images in the T timeNAnd average value of brightnessGreater than or equal to the luminance reference thresholdImage number of (a)nCalculating an abnormal overexposure frequency index, wherein the calculated expression is as follows: />。
Preferably, after obtaining the image acquisition frame rate stability index, the image distortion degree index and the abnormal overexposure frequency index, a data analysis model is established to generate an accuracy influence index according to the following formula:
，
in the method, in the process of the application,e1、e2、e3 are respectively image acquisition frame rate stabilization indexesImage distortion degree index->Abnormal overexposure frequency index->Is a preset proportionality coefficient of (1), ande1、e2、e3 are all greater than 0.
Preferably, the accuracy impact index generated when the camera operates is compared with an accuracy impact index reference threshold, if the accuracy impact index is greater than or equal to the accuracy impact index reference threshold, a high impact degree signal is generated, and if the accuracy impact index is less than the accuracy impact index reference threshold, a low impact degree signal is generated.
Preferably, when the camera is in operation to generate a high influence degree signal, continuously outputting a plurality of accuracy influence indexes generated during operation of the camera to establish a data set, and calibrating the data set asEThen, the first and second data are obtained,ha number representing an accuracy impact index within the data set,h=1、2、3、4、……、i，icalculating the average value and the discrete degree value of a plurality of accuracy influence indexes in the data set for positive integers, and respectively calibrating the average value and the discrete degree value of the accuracy influence indexes asAndFthen:
the method comprises the steps of carrying out a first treatment on the surface of the Then: />. Preferably, the accuracy impact index average is compared to an accuracy impact index reference thresholdComparing the discrete degree value of the accuracy influence index with a reference threshold value of the discrete degree value, wherein the comparison and the division are as follows:
if the accuracy influence index average value is smaller than the accuracy influence index reference threshold value and the accuracy influence index discrete degree value is smaller than the discrete degree value reference threshold value, the low risk signal is sent out, and an early warning prompt is not sent out to the low risk signal;
and if the accuracy influence index average value is larger than or equal to the accuracy influence index reference threshold value or the accuracy influence index average value is smaller than the accuracy influence index reference threshold value and the accuracy influence index discrete degree value is larger than or equal to the discrete degree value reference threshold value, the high risk signal is sent out to give an early warning prompt.
In the technical scheme, the application has the technical effects and advantages that:
according to the application, the running state of the camera in the access control management system is monitored, so that the condition that the recognition accuracy of the camera is influenced by the access control management system is intelligently perceived, the condition that recognition errors or misrefuses occur is effectively prevented, the condition that legal users possibly are mistakenly recognized as illegal users and cannot enter a limited area is effectively prevented, the condition that users are not full, work is interrupted or other inconvenience is possibly caused, and the practicability of the access control management system is improved;
when the camera in the access control system generates a high-influence degree signal during operation, the application continuously outputs a plurality of accuracy influence indexes generated during operation of the camera to establish a data set, and comprehensively analyzes the accuracy influence indexes in the data set instead of only single analysis, thereby effectively preventing accidental situations of single analysis, ensuring the accuracy of data analysis, further improving the accuracy of monitoring the operation state of the camera in the access control system and ensuring the efficient operation of the camera in the access control system.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings for those skilled in the art.
Fig. 1 is a flow chart of a method of access control management method based on multi-source data.
Description of the embodiments
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.
The application provides an access control management method based on multi-source data as shown in fig. 1, which comprises the following steps:
s101, acquiring information of a camera in an access control system during operation, wherein the information comprises camera data acquisition information and camera image processing information, and processing the acquired camera data acquisition information and the camera image processing information;
the camera information acquisition information comprises an image acquisition frame rate stabilization index, and after acquisition, the image acquisition frame rate stabilization index is calibrated into；
Poor frame rate stability of the camera can have serious influence on the camera identification accuracy of the access control system, and the following is possible:
dynamic object blurring: the unstable frame rate may cause a blurring effect of the dynamic object in the image, and when the frame rate is lower than the motion speed of the target object, a larger time interval may exist between the continuous image frames, so that the motion track of the object cannot be captured clearly, thereby causing the blurring effect;
delay and loss of frames: the unstable frame rate may cause delay and loss of image frames, the delay represents time difference between display of images and actual scenes, and the lost frame represents loss of some image frames in transmission or processing, which may cause reduction of instantaneity and loss of image information, thereby affecting accuracy and instantaneity of an identification algorithm;
motion blur: the unstable frame rate may cause a motion blur effect of a fast moving object in an image, when the frame rate is lower than the motion speed of the object, the time interval between successive image frames is too large, and the position change of the object between adjacent frames cannot be captured clearly, so that the object presents a blur effect;
the recognition accuracy declines: the instability of the frame rate may cause the accuracy of the recognition algorithm to be reduced, the recognition algorithm usually extracts the face features or performs target tracking based on continuous image frames, and when the frame rate is unstable, the interval between the image frames is inconsistent, which may cause the inaccuracy of feature extraction or loss of key information, thereby affecting the recognition accuracy;
the real-time performance is reduced: the instability of the frame rate may cause the real-time performance of the system to be reduced, and if the frame rate of the camera cannot meet the requirements of real-time application, such as rapid identification or tracking of a target, the response time and processing speed of the system may be affected, thereby affecting the accuracy and practicality of identification;
therefore, the abnormal problem that the stability of the image acquisition frame rate of the camera is poor can be known in time by monitoring the image acquisition frame rate of the camera in the access control management system;
the logic for obtaining the image acquisition frame rate stabilization index is as follows:
s1, acquiring image acquisition frame numbers of cameras in different time periods within T time, and calibrating the duration of the time period asLWill time periodLThe frame number of the internal image acquisition is marked as H, and the time period is calculatedLThe frame rate of the image acquisition in the system is calculated according to the following formula:wherein->Representing a frame rate;
it should be noted that, using an image processing library, such as OpenCV, FFmpeg, the camera device can be accessed and the image stream read, theseLibraries typically provide functions or methods to obtain information on the number of frames of a real-time image; s2, acquiring image acquisition frame rates of the cameras in different time periods within the T time, and calibrating the image acquisition frame rates as，bA number representing the image acquisition frame rate for different time periods within the T time,b=1、2、3、4、……、B，Bis a positive integer;
s3, calculating standard deviation of image acquisition frame rates of the cameras in different time periods within the T time, and calibrating the standard deviation asRStandard deviationRThe calculation formula of (2) is as follows:
，
wherein, the liquid crystal display device comprises a liquid crystal display device,for the average value of image acquisition frame rates of the camera in different time periods within the T time, the acquired expression is as follows: />；
Standard deviation of image acquisition frame rate of different time periods in T time by cameraRIt can be seen that the standard deviationRThe larger the expression value of the camera is, the larger the fluctuation condition of the image acquisition frame rate of the camera in different time periods in the T time is, and the standard deviation is shownRThe smaller the expression value of the camera is, the smaller the fluctuation condition of the image acquisition frame rate of the camera in different time periods in the T time is; s4, calculating an image acquisition frame rate stability index, wherein the calculated expression is as follows:；
the calculation expression of the image acquisition frame rate stability index shows that the larger the expression value of the image acquisition frame rate stability index of the camera in the time T is, the larger the influence on the identification accuracy of the camera is, otherwise, the smaller the influence on the identification accuracy of the camera is;
the camera image processing information comprises an image distortion degree index and an abnormal overexposure frequency index, and after acquisition, the image distortion degree index and the abnormal overexposure frequency index are respectively calibrated as followsAnd->；
When the image distortion degree of the camera to the image processing in the access control management system is high, the following serious influence may be caused on the recognition accuracy of the camera:
the feature extraction is difficult: the image distortion can cause blurring, deformation or loss of details in the face image, which makes it difficult for a face recognition algorithm to accurately extract the face features, thereby reducing the recognition accuracy;
the recognition error rate increases: the image distortion may cause the position deviation, deformation or inconspicuous of the feature points in the face image, so that the recognition algorithm generates errors when matching and comparing the face features, the recognition error rate is increased, and the accuracy and reliability of the access control system are reduced;
false positive recognition increases: the false characteristic points or textures may be caused to appear in the non-face area by image distortion, so that the recognition algorithm can erroneously recognize the non-face area as a face, the false positive recognition is increased, and the false recognition rate of the system to unauthorized personnel is increased;
the recognition success rate is reduced: due to image distortion, the matching and specific alignment accuracy of the recognition algorithm on the face image is reduced, so that the recognition success rate is reduced, the recognition failure of legal users can be caused, and the efficiency and the usability of the access control system are reduced;
the false alarm rate rises: the image distortion can cause misjudgment and false alarm, and the recognition algorithm can generate false matching results on the distorted image, so that the false alarm rate is increased, and the false recognition rate of the system to unauthorized personnel is increased;
therefore, the abnormal problem of the image distortion of the camera can be known in time by monitoring the image processing distortion condition of the camera in the access control management system;
the logic for image distortion index acquisition is as follows:
s1, acquiring an original shooting image and an image processed by a camera, and performing gray processing on the original shooting image and the image processed by the camera to convert the original shooting image and the image processed by the camera into a gray image;
s2, respectively calibrating pixels of pixel points on the original photographed image and the image processed by the camera asAnd->，yRepresenting the numbers of pixels of the pixel points on the original photographed image and the image processed by the camera,y=1、2、3、4、……、c，cis a positive integer;
it should be noted that, the pixel points on the original photographed image and the image processed by the camera are in one-to-one correspondence, that is, the pixel numbers of the original photographed image and the image processed by the camera on the same pixel point are the same, secondly, each pixel point has a unique coordinate index on the image, the pixel value of the designated coordinate position can be obtained by using a function provided by an image processing library or a programming language, and the pixel value of the pixel point can be directly obtained by providing the row and column indexes of the pixel, so as to obtain the pixel values of the pixel points on the original photographed image and the image processed by the camera;
s3, calculating the mean square error of the image, and calibrating the mean square error asMSEThenThe method comprises the steps of carrying out a first treatment on the surface of the S4, acquiring the mean square error before and after all the image processing in the T time, and calibrating the mean square error as +.>，kMean square error +.>Is provided with the number of (a),k=1、2、3、4、……、P，Pis a positive integer;
s5, calculating an image distortion degree index, wherein a calculation formula is as follows:；
the calculation expression of the image distortion degree index shows that the larger the expression value of the image distortion degree index of the camera in the time T is, the larger the influence on the recognition accuracy of the camera is, otherwise, the smaller the influence on the recognition accuracy of the camera is; when the overexposure frequency of the camera to image processing in the access control system is high, the following serious influence may be caused on the recognition accuracy of the camera:
loss of detail information: the overexposure causes loss of details of a bright part in the image, including details of a face area, which causes a face feature extraction algorithm to be unable to accurately capture detail information, thereby reducing recognition accuracy;
characteristic distortion: overexposure can cause over-high brightness in the image, and color and texture information of a face area can be distorted, so that errors occur in the process of matching and comparing face features in a recognition algorithm, and the recognition accuracy and reliability are reduced;
false positive recognition increases: overexposure may cause false bright features, so that the recognition algorithm erroneously recognizes the non-face region as a face, which may result in increased false positive recognition and reduced accuracy and reliability of the system;
identifying a false positive rate rise: because the details of the bright part are lost and the characteristics are distorted due to overexposure, misjudgment and misinformation can occur in an identification algorithm, and the misinformation rate of identification can be increased, so that the misidentification rate of a system to unauthorized personnel is increased;
the recognition success rate is reduced: the influence of overexposure on the image can reduce the success rate of the system for identifying the human face, which may cause the identification failure of legal users and reduce the efficiency and the availability of the access control system;
therefore, the problem of abnormal overexposure frequency of the camera can be known in time by monitoring the overexposure condition of the camera in the access control management system;
the logic for obtaining the abnormal overexposure frequency index is as follows:
s1, acquiring image data captured by a camera in T time, applying an image processing algorithm to the acquired image data to obtain processed images, counting the processed images, and recording the number of the images asN；
It should be noted that, the image data may be real-time data or stored image data, and the applied image processing algorithm may be an automatic exposure control (Auto Exposure Control, AEC) algorithm or a brightness contrast adjustment algorithm;
s2, converting the image into a gray image, and calculating a brightness value for each pixel of the gray image;
it should be noted that, the processed color image is converted into a gray image so as to analyze the brightness, and the pixel value in the gray image is used to represent the brightness, because in the gray image, the brightness and the pixel value are in one-to-one correspondence; s3, calculating the average brightness value of each image, and calibrating the average brightness value as，xRepresenting the average value of the brightness of each image in time T +.>Is provided with the number of (a),x=1、2、3、4、……、N，Nis a positive integer;
s4, averaging the brightness of each imageAnd a preset brightness reference threshold +.>Comparing and averaging the brightness +.>Greater than or equal to the luminance reference threshold->Number of images of (a)The amount was counted and the luminance was averaged +.>Greater than or equal to the luminance reference threshold->The number of images is calibrated asn；
It should be noted that, the threshold may be set according to the dynamic range and the expected brightness range of the image, which is not limited herein, and may be adjusted according to the scene and the expected brightness;
s5, obtaining the number of images in the T timeNAnd average value of brightnessGreater than or equal to the luminance reference threshold->Image number of (a)nCalculating an abnormal overexposure frequency index, wherein the calculated expression is as follows: />；
The calculation expression of the abnormal overexposure frequency index shows that the larger the expression value of the abnormal overexposure frequency index of the camera in the T time is, the larger the influence on the identification accuracy of the camera is, and otherwise, the smaller the influence on the identification accuracy of the camera is;
s102, establishing a data analysis model of collected camera data collection information and camera image processing information, generating an accuracy influence index, and evaluating the identification accuracy of the camera through the accuracy influence index;
after obtaining an image acquisition frame rate stability index, an image distortion degree index and an abnormal overexposure frequency index, establishing a data analysis model to generate an accuracy influence index according to the following formula:in which, in the process,e1、e2、e3 are respectively the image acquisition frame rate stabilization indexes +.>Image distortion degree index->Abnormal overexposure frequency index->Is a preset proportionality coefficient of (1), ande1、e2、e3 are all greater than 0;
as can be seen from the formula, the larger the image acquisition frame rate stability index, the larger the image distortion degree index and the larger the abnormal overexposure frequency index generated when the camera operates in the T time, namely the accuracy influence indexThe larger the expression value of the camera is, the larger the influence on the identification accuracy of the camera is, the smaller the image acquisition frame rate stability index generated when the camera operates in the T time is, the smaller the image distortion degree index is, the smaller the abnormal overexposure frequency index is, namely the accuracy influence index is->The smaller the expression value of (2) is, the smaller the influence on the identification accuracy of the camera is; s103, comparing an accuracy influence index generated when the camera operates with an accuracy influence index reference threshold value to generate a high influence degree signal and a low influence degree signal;
comparing an accuracy influence index generated when the camera operates with an accuracy influence index reference threshold, generating a high influence degree signal if the accuracy influence index is larger than or equal to the accuracy influence index reference threshold, and generating a low influence degree signal if the accuracy influence index is smaller than the accuracy influence index reference threshold;
s104, when a high influence degree signal is generated when the camera operates, continuously outputting a plurality of accuracy influence indexes generated when the camera operates to establish a data set, comprehensively analyzing the accuracy influence indexes in the data set to generate a risk signal, and sending or not sending an early warning prompt to the risk signal;
when a high influence degree signal is generated during camera operation, continuously outputting a plurality of accuracy influence indexes generated during camera operation to establish a data set, and calibrating the data set asEThen，hA number representing an accuracy impact index within the data set,h=1、2、3、4、……、i，iis a positive integer; calculating the average value and the discrete degree value of a plurality of accuracy influence indexes in the data set, and respectively calibrating the average value and the discrete degree value of the accuracy influence indexes as +.>AndFthen:
the method comprises the steps of carrying out a first treatment on the surface of the Then: />；
Setting an accuracy influence index reference threshold value according to the accuracy influence index, if the accuracy influence index is larger than or equal to the accuracy influence index reference threshold value, indicating that the identification accuracy of the camera is greatly influenced, and if the accuracy influence index is smaller than the accuracy influence index reference threshold value, indicating that the identification accuracy of the camera is less influenced;
comparing the average value of the accuracy impact index with the reference threshold value of the accuracy impact index, and comparing the discrete degree value of the accuracy impact index with the reference threshold value of the discrete degree value, wherein the comparison and the division are as follows:
if the average value of the accuracy impact indexes is smaller than the reference threshold value of the accuracy impact indexes and the discrete degree value of the accuracy impact indexes is smaller than the reference threshold value of the discrete degree value, the accuracy impact indexes in the data set are indicated to be generally smaller than the reference threshold value of the accuracy impact indexes, the low risk signals are sent out, and early warning prompt is not sent out to the low risk signals;
it should be noted that, the accuracy impact index in the data set is generally smaller than the accuracy impact index reference threshold, and the accuracy impact index is indicated to be larger than or equal to the accuracy impact index reference threshold, which is an accidental condition;
if the average value of the accuracy impact indexes is larger than or equal to the reference threshold value of the accuracy impact indexes, or the average value of the accuracy impact indexes is smaller than the reference threshold value of the accuracy impact indexes and the discrete degree value of the accuracy impact indexes is larger than or equal to the reference threshold value of the discrete degree value, the accuracy impact indexes in the data set are not generally smaller than the reference threshold value of the accuracy impact indexes, a high risk signal is sent out, an early warning prompt is given out to the high risk signal, the manager is prompted that the recognition accuracy of a camera in the access control system is influenced, the access control system intelligently perceives the situation that the recognition accuracy of the camera is influenced, the situation that the access control system is wrong or misly refused is effectively prevented, legal users are effectively prevented from being possibly mistakenly recognized as illegal users, the situation that the users are not full, work interruption or other inconvenience is possibly caused, and the practicability of the access control system is improved;
according to the application, the running state of the camera in the access control management system is monitored, so that the condition that the recognition accuracy of the camera is influenced by the access control management system is intelligently perceived, the condition that recognition errors or misrefuses occur is effectively prevented, the condition that legal users possibly are mistakenly recognized as illegal users and cannot enter a limited area is effectively prevented, the condition that users are not full, work is interrupted or other inconvenience is possibly caused, and the practicability of the access control management system is improved;
when the camera in the access control system generates a high-influence degree signal during operation, the application continuously outputs a plurality of accuracy influence indexes generated during operation of the camera to establish a data set, and comprehensively analyzes the accuracy influence indexes in the data set instead of only single analysis, thereby effectively preventing accidental situations of single analysis, ensuring the accuracy of data analysis, further improving the accuracy of monitoring the operation state of the camera in the access control system and ensuring the efficient operation of the camera in the access control system.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
While certain exemplary embodiments of the present application have been described above by way of illustration only, it will be apparent to those of ordinary skill in the art that modifications may be made to the described embodiments in various different ways without departing from the spirit and scope of the application. Accordingly, the drawings and description are to be regarded as illustrative in nature and not as restrictive of the scope of the application, which is defined by the appended claims.
It is noted that relational terms such as first and second, and the like, if any, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present application, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (9)
1. The access control management method based on the multi-source data is characterized by comprising the following steps of:
s101, acquiring information of a camera in an access control system during operation, wherein the information comprises camera data acquisition information and camera image processing information, and processing the acquired camera data acquisition information and the camera image processing information;
s102, establishing a data analysis model of collected camera data collection information and camera image processing information, generating an accuracy influence index, and evaluating the identification accuracy of the camera through the accuracy influence index;
s103, comparing an accuracy influence index generated when the camera operates with an accuracy influence index reference threshold value to generate a high influence degree signal and a low influence degree signal;
and S104, when the camera runs and generates a high influence degree signal, continuously outputting a plurality of accuracy influence indexes generated when the camera runs to establish a data set, comprehensively analyzing the accuracy influence indexes in the data set to generate a risk signal, and sending or not sending an early warning prompt to the risk signal.
2. The access control method based on multi-source data according to claim 1, wherein the camera data acquisition information includes an image acquisition frame rate stabilization index, and after acquisition, the image acquisition frame rate stabilization index is calibrated asThe camera image processing information comprises an image distortion degree index and an abnormal overexposure frequency index, and after acquisition, the image distortion degree index and the abnormal overexposure frequency index are respectively calibrated to be +.>And->。
3. The access control method based on multi-source data according to claim 2, wherein the logic for obtaining the image acquisition frame rate stabilization index is as follows:
s1, acquiring image acquisition frame numbers of cameras in different time periods within T time, and calibrating the duration of the time period asLWill time periodLThe frame number of the internal image acquisition is marked as H, and the time period is calculatedLThe frame rate of the image acquisition in the system is calculated according to the following formula:wherein->Representing a frame rate;
s2, acquiring image acquisition frame rates of the cameras in different time periods within the T time, and calibrating the image acquisition frame rates as，bA number representing the image acquisition frame rate for different time periods within the T time,b=1、2、3、4、……、B，Bis a positive integer;
s3, calculating standard deviation of image acquisition frame rates of the cameras in different time periods within the T time, and calibrating the standard deviation asRStandard deviationRThe calculation formula of (2) is as follows:wherein->For the average value of image acquisition frame rates of the camera in different time periods within the T time, the acquired expression is as follows: />；
S4, calculating an image acquisition frame rate stability index, wherein the calculated expression is as follows:。
4. the access control method based on multi-source data according to claim 3, wherein the logic for obtaining the image distortion degree index is as follows:
s1, acquiring an original shooting image and an image processed by a camera, and performing gray processing on the original shooting image and the image processed by the camera to convert the original shooting image and the image processed by the camera into a gray image;
s2, respectively calibrating pixels of pixel points on the original photographed image and the image processed by the camera asAnd，yrepresenting the numbers of pixels of the pixel points on the original photographed image and the image processed by the camera,y=1、2、3、4、……、c，cis a positive integer;
s3, calculating the mean square error of the image, and calibrating the mean square error asMSEThenThe method comprises the steps of carrying out a first treatment on the surface of the S4, acquiring the mean square error before and after all the image processing in the T time, and calibrating the mean square error as +.>，kMean square error +.>Is provided with the number of (a),k=1、2、3、4、……、P，Pis a positive integer;
s5, calculating an image distortion degree index, wherein a calculation formula is as follows:。
5. the access control method based on multi-source data according to claim 4, wherein the logic for obtaining the abnormal overexposure frequency index is as follows:
s1, acquiring image data captured by a camera in T time, applying an image processing algorithm to the acquired image data to obtain processed images, counting the processed images, and recording the number of the images asNThe method comprises the steps of carrying out a first treatment on the surface of the S2, converting the image into a gray image, and calculating a brightness value for each pixel of the gray image;
s3, calculating the average brightness value of each image, and calibrating the average brightness value as，xRepresenting the average value of the brightness of each image in time T +.>Is provided with the number of (a),x=1、2、3、4、……、N，Nis a positive integer;
s4, averaging the brightness of each imageAnd a preset brightness reference threshold +.>Comparing and averaging the brightness +.>Greater than or equal to the luminance reference threshold->Is carried out by the number of imagesStatistics, mean luminance->Greater than or equal to the luminance reference threshold->The number of images is calibrated asn；
S5, obtaining the number of images in the T timeNAnd average value of brightnessGreater than or equal to the luminance reference threshold->Image number of (a)nCalculating an abnormal overexposure frequency index, wherein the calculated expression is as follows: />。
6. The access control method based on multi-source data according to claim 5, wherein the image acquisition frame rate stabilization index is obtainedImage distortion degree index->Abnormal overexposure frequency index->Then, a data analysis model is built, and an accuracy influence index is generated>The formula according to is:
in which, in the process,e1、e2、e3 are respectively the image acquisition frame rate stabilization indexes +.>Image distortion degree index->Abnormal overexposure frequency index->Is a preset proportionality coefficient of (1), ande1、e2、e3 are all greater than 0.
7. The access control method based on multi-source data according to claim 6, wherein an accuracy impact index generated when the camera is operated is compared with an accuracy impact index reference threshold, a high impact degree signal is generated if the accuracy impact index is greater than or equal to the accuracy impact index reference threshold, and a low impact degree signal is generated if the accuracy impact index is less than the accuracy impact index reference threshold.
8. The access control method based on multi-source data according to claim 7, wherein when the camera is operated to generate a high influence degree signal, a plurality of accuracy influence indexes generated by the camera is continuously output to build a data set, and the data set is calibrated asEThen，hA number representing an accuracy impact index within the data set,h=1、2、3、4、……、i，iis a positive integer;
calculating the average value and the discrete degree value of a plurality of accuracy impact indexes in the data set, and respectively calibrating the average value and the discrete degree value of the accuracy impact indexes asAndFthen:
the method comprises the steps of carrying out a first treatment on the surface of the Then: />。
9. The access control management method based on multi-source data according to claim 8, wherein the accuracy impact index average value and the accuracy impact index reference threshold value are compared, and the accuracy impact index discrete degree value and the discrete degree value reference threshold value are compared, wherein the comparison is as follows:
if the accuracy influence index average value is smaller than the accuracy influence index reference threshold value and the accuracy influence index discrete degree value is smaller than the discrete degree value reference threshold value, the low risk signal is sent out, and an early warning prompt is not sent out to the low risk signal;
and if the accuracy influence index average value is larger than or equal to the accuracy influence index reference threshold value or the accuracy influence index average value is smaller than the accuracy influence index reference threshold value and the accuracy influence index discrete degree value is larger than or equal to the discrete degree value reference threshold value, the high risk signal is sent out to give an early warning prompt.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311135517.7A CN116886892B (en) | 2023-09-05 | 2023-09-05 | Access control management method based on multi-source data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311135517.7A CN116886892B (en) | 2023-09-05 | 2023-09-05 | Access control management method based on multi-source data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116886892A true CN116886892A (en) | 2023-10-13 |
| CN116886892B CN116886892B (en) | 2023-12-29 |
Family
ID=88271797
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311135517.7A Active CN116886892B (en) | 2023-09-05 | 2023-09-05 | Access control management method based on multi-source data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116886892B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015114958A (en) * | 2013-12-13 | 2015-06-22 | 東芝テック株式会社 | Face recognition gate system and face recognition gate system program |
| CN104851140A (en) * | 2014-12-12 | 2015-08-19 | 重庆凯泽科技有限公司 | Face recognition-based attendance access control system |
| CN105516716A (en) * | 2016-01-27 | 2016-04-20 | 华东师范大学 | Site test method of video image quality of a closed-loop security and protection system |
| CN112351272A (en) * | 2020-10-29 | 2021-02-09 | 福建新大陆通信科技股份有限公司 | CTID access control equipment detection method and system |
| CN115278209A (en) * | 2022-06-13 | 2022-11-01 | 上海研鼎信息技术有限公司 | Camera test system based on intelligent walking robot |
| CN116600104A (en) * | 2023-07-17 | 2023-08-15 | 微网优联科技(成都)有限公司 | Phase acquisition quality analysis method and system for IPC network camera |
-
2023
- 2023-09-05 CN CN202311135517.7A patent/CN116886892B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015114958A (en) * | 2013-12-13 | 2015-06-22 | 東芝テック株式会社 | Face recognition gate system and face recognition gate system program |
| CN104851140A (en) * | 2014-12-12 | 2015-08-19 | 重庆凯泽科技有限公司 | Face recognition-based attendance access control system |
| CN105516716A (en) * | 2016-01-27 | 2016-04-20 | 华东师范大学 | Site test method of video image quality of a closed-loop security and protection system |
| CN112351272A (en) * | 2020-10-29 | 2021-02-09 | 福建新大陆通信科技股份有限公司 | CTID access control equipment detection method and system |
| CN115278209A (en) * | 2022-06-13 | 2022-11-01 | 上海研鼎信息技术有限公司 | Camera test system based on intelligent walking robot |
| CN116600104A (en) * | 2023-07-17 | 2023-08-15 | 微网优联科技(成都)有限公司 | Phase acquisition quality analysis method and system for IPC network camera |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116886892B (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jung | Efficient background subtraction and shadow removal for monochromatic video sequences | |
| US7751647B2 (en) | System and method for detecting an invalid camera in video surveillance | |
| CN101281595B (en) | Apparatus and method for face recognition | |
| WO2019134346A1 (en) | Face recognition method, application server, and computer-readable storage medium | |
| JP4156430B2 (en) | Face verification method and system using automatic database update method | |
| KR20200006987A (en) | Access control method, access control device, system and storage medium | |
| US20080049985A1 (en) | Identification method | |
| JP5669082B2 (en) | Verification device | |
| WO2020259128A1 (en) | Liveness detection method and apparatus, electronic device, and computer readable storage medium | |
| CN104966266B (en) | The method and system of automatic fuzzy physical feeling | |
| JP2016012752A (en) | Video monitoring device, video monitoring system, and video monitoring method | |
| CN110490126B (en) | Safe deposit box safety control system based on artificial intelligence | |
| Ravi et al. | A novel method for touch-less finger print authentication | |
| JP2002304651A (en) | Device and method for managing entering/leaving room, program for executing the same method and recording medium with the same execution program recorded thereon | |
| CN114898443A (en) | Face data acquisition method and device | |
| CN116886892B (en) | Access control management method based on multi-source data | |
| CN115984973B (en) | Human body abnormal behavior monitoring method for peeping-preventing screen | |
| CN114529962A (en) | Image feature processing method and device, electronic equipment and storage medium | |
| CN112804519A (en) | Camera shielding detection method and device, electronic equipment and channel gate | |
| CN114863337A (en) | Novel screen anti-photographing recognition method | |
| CN116188937A (en) | Camera anomaly detection method, system, device and storage medium | |
| WO2018179723A1 (en) | Facial authentication processing apparatus, facial authentication processing method, and facial authentication processing system | |
| CN114973135A (en) | Head-shoulder-based sequential video sleep post identification method and system and electronic equipment | |
| WO1996038820A1 (en) | Security control system | |
| CN111274899B (en) | Face matching method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |