Intelligent security method and system based on face recognition

Abstract

The application discloses an intelligent security method and system based on face recognition, which comprises the following steps: acquiring current parking data when receiving a parking operation, analyzing an optimal detection radius of an authorized person at a current parking site in combination with historical parking data, acquiring positioning information of the authorized person when detecting that the authorized person enters the optimal detection radius, identifying same-traveling persons with a high coincidence degree with a moving track of the authorized person according to the positioning information, analyzing a friendly value of the authorized person to the same-traveling persons and giving the same-traveling persons different identities according to the friendly value, and identifying whether the authorized person needs a car-searching navigation service according to a car-searching track of the authorized person when detecting that the authorized person searches for a car, and providing the car-searching navigation service for the authorized person if yes. The application has the characteristics of improving the intelligence of the system and optimizing the user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of face recognition, in particular to an intelligent security method and system based on face recognition. BACKGROUND

[0002] With the continuous progress of the intelligent automobile industry, since the face recognition lock control system is in an unattended unlocking state most of the time, and the parking environment is complex and changeable, it is necessary to use a 3D face recognition algorithm with a higher security level. With the help of double infrared camera technology, this algorithm can effectively adapt to various application scenarios under different environmental light conditions. At present, some new models of cars have realized the car face recognition anti-theft system through a 3D binocular face recognition algorithm board, which not only effectively reduces the inconvenience caused by factors such as the driver forgetting the car key or signal jammer interference, but also improves the convenience and security of car use. However, the existing face recognition lock control system prohibits unauthorized users from entering, resulting in the situation that the driver's friend needs to enter the car urgently, but the driver is not there, causing the driver's friend to be blocked outside the door, reducing the user experience. In addition, in the face of some complex spatial layout and dimly lit underground garages, the driver often loses direction and cannot find his own car when going back and forth, causing the driver to spend a long time looking for the car, reducing the intelligence of the system. Therefore, it is necessary to design an intelligent security method and system based on face recognition to improve the intelligence of the system and optimize the user experience. SUMMARY

[0003] The present application aims to provide an intelligent security method and system based on face recognition to solve the problems raised in the background.

[0004] In order to solve the above technical problems, the present application provides the following technical solution: an intelligent security method based on face recognition, the running steps of the method comprising:

[0005] Step S1: obtaining current parking data when receiving a parking operation, and analyzing the optimal detection radius of authorized personnel at the current parking location in combination with historical parking data, wherein the optimal detection radius is a range threshold for positioning the authorized personnel and triggering the car search navigation service;

[0006] Step S2: when detecting that the authorized personnel enters the optimal detection radius, obtaining the positioning information of the authorized personnel, identifying the same person as the authorized personnel whose moving track coincidence degree is higher than a threshold value according to the positioning information, analyzing the friendliness value of the authorized personnel to the same person, and assigning different identities to the same person according to the friendliness value, the identity including: authorized personnel and unauthorized personnel;

[0007] Step S3: When detecting that the authorized person is searching for the vehicle, determining whether the authorized person needs the vehicle search navigation service according to the vehicle search trajectory of the authorized person, and if so, providing the vehicle search navigation service for the authorized person.

[0008] Further, the step S1 further comprises the following steps:

[0009] Step S11: When detecting the parking operation, constructing a special historical parking feature vector according to historical parking data of different authorized persons using the vehicle search navigation;

[0010] Step S12: Constructing an optimal detection radius model of the vehicle search navigation for the authorized person according to the historical parking feature vector, extracting a parking feature vector of the current parking data, inputting the parking feature vector into the optimal detection radius model, and obtaining an optimal detection radius of the vehicle search navigation of the authorized person.

[0011] Further, the step S12 further comprises the following steps:

[0012] Step S121: Identifying whether there is a witness of the current parking location among the authorized persons, when there is the witness among the authorized persons, calculating a similarity between the current parking feature vector and a historical parking feature vector of the witness according to the historical parking feature vector, constructing an optimal detection radius model of the vehicle search navigation according to the similarity and the historical optimal detection radius, inputting the current parking feature vector into the optimal detection radius model to obtain the optimal detection radius, wherein the witness refers to an authorized person who has seen the vehicle parked at the current parking location;

[0013] Step S122: When there is no witness among the authorized persons, clustering historical parking data of the authorized persons to generate a scene category, matching the current parking data to obtain a scene category with the highest similarity, constructing an optimal detection radius model of the vehicle search navigation according to the scene category, inputting the current parking feature vector into the optimal detection radius model to obtain the optimal detection radius, wherein the scene category refers to a parking scene grouping with similar features formed after clustering analysis of the historical parking data of the authorized person.

[0014] Further, the step S2 further comprises the following steps:

[0015] Step SA1: when detecting that the authorized personnel enters the corresponding optimal detection radius, matching the face data of the authorized personnel, identifying the identity of the authorized personnel, wherein the authorized personnel includes a first authorized personnel, a second authorized personnel, and a visitor authorized personnel, the first authorized personnel is a long-term usable personnel with the highest use permission, the second authorized personnel is a long-term usable personnel with lower use permission than the first authorized personnel, and the visitor authorized personnel is a temporary visitor of the vehicle and is switched to an unauthorized personnel after an authorized time period;

[0016] Step SA2: obtaining the positioning account of the same personnel, matching the positioning account with the historical authorized library, when identifying that the same personnel contains the unauthorized personnel, combining the monitoring video of the current parking place, giving the unauthorized personnel a visitor identity or still retaining the unauthorized personnel identity.

[0017] Further, the step SA2 further includes the following steps:

[0018] Step SA21: obtaining the face data of the associated personnel according to the positioning account, one-to-one matching the face data with the actual face data in the monitoring video, when the matching is unsuccessful, triggering an abnormal alarm and switching the authorization identity of the unmatched personnel, wherein the positioning accounts between the face data of the first authorized personnel and the second authorized personnel are associated;

[0019] Step SA22: when the same personnel contains the unauthorized personnel, extracting the face micro-expression and the body action of the same personnel and the authorized personnel from the monitoring video, inputting the face micro-expression and the body action into the body face comprehensive model of the authorized personnel and the unauthorized personnel, and obtaining the friendliness value of the authorized personnel to the unauthorized personnel;

[0020] Step SA23: comparing the friendliness value with a first threshold value, when the friendliness value is lower than the first threshold value, starting the in-vehicle video monitoring and the positioning function for the unauthorized personnel;

[0021] When the friendliness value is greater than a second threshold value, giving the unauthorized personnel the visitor authorized permission, wherein the first threshold value is less than the second threshold value.

[0022] Further, the step SA23 further includes the following steps:

[0023] Step SA231: when the first authorized personnel is in the vehicle and enters the unauthorized personnel, extracting the face micro-expression of the authorized personnel in the in-vehicle monitoring video to analyze the friendliness value of the personnel, and judging whether to give the unauthorized personnel the visitor authorized permission according to the friendliness value.

[0024] Step SA232: when there is no first authorized person in the car, the in-car monitoring and positioning function is started to send to the mobile phone of the car owner in real time, so that the car owner remotely authorizes the identity of the target person through the mobile phone.

[0025] Further, the system includes a parking navigation analysis module, an identity recognition verification module:

[0026] The parking navigation analysis module is configured to obtain current parking data when receiving a parking operation, and analyze an optimal detection radius of an authorized person at a current parking location in combination with historical parking data, wherein the optimal detection radius is a range threshold for positioning the authorized person and triggering a car search navigation service.

[0027] The identity recognition verification module is configured to obtain positioning information of the authorized person when detecting that the authorized person enters the optimal detection radius, identify a same-traveling person whose moving track coincides with the authorized person by more than a threshold value according to the positioning information, analyze a friendly value of the authorized person to the same-traveling person, and assign different identities to the same-traveling person according to the friendly value, the identities including authorized person and unauthorized person.

[0028] Further, the system further includes a behavior analysis response module:

[0029] The behavior analysis response module is configured to identify whether the authorized person needs the car search navigation service according to a car search track of the authorized person when detecting that the authorized person searches for a car, and provide the car search navigation service to the authorized person if so.

[0030] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to enable the electronic device to implement the method of the first aspect.

[0031] In a fourth aspect, the present application provides a computer readable storage medium for storing a computer program, wherein the computer program, when executed on a computer, enables the computer to execute the method of the first aspect.

[0032] Compared with the prior art, the present application has the beneficial effects that: the present application, through a multi-level dynamic permission management mechanism, combined with the fusion analysis of facial micro-expression, body movement and environmental data, significantly improves the intelligence and accuracy of vehicle safety protection. The system can not only quickly distinguish between authorized personnel and unauthorized personnel based on face recognition, but also dynamically adjust the visitor permission through real-time analysis of the emotional feedback of authorized personnel in the vehicle, effectively preventing security risks such as forced unlocking. At the same time, the innovative optimal detection radius model dynamically calculates the historical parking characteristics and environmental complexity, greatly improving the triggering accuracy and response efficiency of the car navigation, and reducing the interference of invalid navigation push. The depth trajectory analysis of personnel car search behavior, combined with the multi-dimensional verification mechanism of spatiotemporal characteristics, physiological data and environmental constraints. In addition, the cross-person navigation strategy optimization technology based on federated learning realizes the continuous evolution of the overall performance of the system under the premise of protecting privacy, solves the technical pain points of rigid path planning and poor environmental adaptability of traditional navigation systems in complex parking lot environments, and further improves the intelligence of the system and optimizes the user experience. BRIEF DESCRIPTION OF DRAWINGS

[0033] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, together with the embodiments of the present application, to explain the present application, and do not constitute a limitation on the present application. In the drawings:

[0034] Figure 1 A flowchart schematic diagram of an intelligent security method based on face recognition provided for the first embodiment of the present application.

[0035] Figure 2 A module composition schematic diagram of an intelligent security system based on face recognition provided for the second embodiment of the present application.

[0036] Figure 3 is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present application will be described in detail below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0038] The present embodiment can be applied to the scene of obtaining use permission by car face recognition, and the method can be executed by an intelligent security system based on face recognition provided by the present embodiment, Figure 1 A flowchart schematic diagram of an intelligent security method based on face recognition provided for the first embodiment of the present application, which specifically includes the following steps:

[0039] Step S1: obtaining current parking data when receiving a parking operation, analyzing the optimal detection radius of the authorized person at the current parking location in combination with historical parking data, wherein the optimal detection radius is a range threshold for positioning the authorized person and triggering the car search navigation service;

[0040] Step S2: when detecting that the authorized person enters the optimal detection radius, obtaining the positioning information of the authorized person, identifying the same person who has a high coincidence degree with the movement trajectory of the authorized person according to the positioning information, analyzing the friendly value of the authorized person to the same person and assigning different identities to the same person according to the friendly value, the identity includes: authorized person and unauthorized person;

[0041] Step S3: when detecting that the authorized person searches for the car, identifying whether the authorized person needs the car search navigation service according to the car search trajectory of the authorized person, if yes, providing the car search navigation service for the authorized person.

[0042] Specifically, through face recognition technology, the system can quickly and accurately identify the identity of the target person, whether authorized or unauthorized, which not only improves the security of vehicle access, but also simplifies the access process of personnel. Secondly, the system can intelligently analyze and determine the optimal detection radius in combination with historical data when receiving a parking operation, which helps to more accurately obtain the positioning information of the authorized person and provide more reliable data support for car search navigation. Finally, when the authorized person searches for the car, the system can intelligently judge whether the car search navigation is needed according to the movement trajectory, and timely send the navigation path when needed, which greatly improves the efficiency and accuracy of car search navigation, and reduces the time and trouble of personnel searching for the car in the parking lot. Overall, through intelligent face recognition, data analysis and behavior recognition technology, the system realizes the automation and refinement of vehicle access and car search navigation, and provides a more secure, convenient and efficient vehicle use experience for personnel.

[0043] In some preferred embodiments, the step S1 further comprises the following steps:

[0044] Step S11: when detecting the parking operation, constructing a special historical parking feature vector according to the historical parking data of different authorized personnel using the car search navigation;

[0045] Step S12: constructing an optimal detection radius model of the car search navigation for the authorized person according to the historical parking feature vector, extracting a parking feature vector of the current parking data, inputting the parking feature vector into the optimal detection radius model, and obtaining the optimal detection radius of the car search navigation for the authorized person.

[0046] Specifically, the optimization of the parking search process of authorized personnel in the parking lot is realized, and the accuracy and efficiency of the parking search navigation are significantly improved. The historical parking feature vector is constructed by using the historical parking data of authorized personnel, which provides important reference information for analyzing and predicting the current parking location. The optimal detection radius model is constructed according to the historical parking feature vector, which can calculate the optimal detection radius according to the current parking location and the parking feature vector, thereby providing more accurate positioning information for the parking search navigation. The optimal detection radius is associated with the mobile positioning account of the authorized personnel, and the movement trajectory of the authorized personnel within the optimal detection radius is monitored in real time, so as to ensure that the parking search navigation service can timely and accurately respond to the needs of the authorized personnel. This process not only improves the efficiency of the parking search navigation and reduces the time of personnel searching for vehicles in the parking lot, but also enhances the personnel experience, making the entire parking search process more convenient and intelligent.

[0047] In some preferred embodiments, the step S12 further comprises the following steps:

[0048] Step S121: identifying whether there is a witness of the current parking location among the authorized personnel, when there is the witness among the authorized personnel, calculating the similarity s between the current parking feature vector and the historical parking feature vector according to the historical parking feature vector of the witness sim , constructing the optimal detection radius model of the parking search navigation according to the similarity and the historical optimal detection radius, inputting the current parking feature vector into the optimal detection radius model to obtain the optimal detection radius, wherein the witness refers to the authorized personnel who has seen the vehicle parked at the current parking location:

[0049]

[0050] In the formula, w k represents dynamic weight distribution, n represents the number of times the witness uses the parking search navigation, R witness represents the optimal detection radius of the witness to the current parking location, R hist (k) represents the historical optimal detection radius of the witness, γ witness and λ represent environmental and signal attenuation adjustment coefficients respectively, C complex represents the complexity of the parking lot structure, S signal represents the signal strength of the positioning information;

[0051] Step S122: When the witness is not in the authorized personnel, the historical parking data of the authorized personnel is clustered to generate a scene category, the current parking data is matched to obtain a scene category with the highest similarity, the optimal detection radius model of the car searching navigation is constructed according to the scene category, and the current parking feature vector is input into the optimal detection radius model to obtain the optimal detection radius, wherein the scene category refers to a parking scene grouping with similar features formed after clustering analysis of the historical parking data of the authorized personnel:

[0052]

[0053] In the formula, R witness represents the optimal detection radius of the authorized personnel to the current parking location, μ j represents the mean of the optimal detection radius in the scene category, and γ cluster represents an environmental adjustment coefficient.

[0054] Specifically, according to the complexity of the historical parking location environment, the optimal detection radius of different authorized personnel is analyzed for different authorized personnel with different car searching abilities, and the car searching intention of the authorized personnel is accurately judged, which can reduce unnecessary calculation and data processing, thereby reducing the energy consumption of the system, and the accuracy of the optimal detection radius is more accurate.

[0055] In some preferred embodiments, the step S2 further comprises the following steps:

[0056] Step SA1: When it is detected that the authorized personnel enters the corresponding optimal detection radius, the face data of the authorized personnel is matched, and the identity of the authorized personnel is identified, wherein the authorized personnel includes a first authorized personnel, a second authorized personnel, and a visitor authorized personnel, the first authorized personnel is a long-term usable personnel with the highest use permission, the second authorized personnel is a long-term usable personnel with lower use permission than the first authorized personnel, and the visitor authorized personnel is a temporary visitor of the vehicle and is switched to an unauthorized personnel after an authorized time period.

[0057] Step SA2: Obtain the positioning account of the same person, match the positioning account with the historical authorized library, and when it is identified that the unauthorized personnel is included in the same person, combine the monitoring video of the current parking location to give the unauthorized personnel a visitor identity or still retain the unauthorized personnel identity.

[0058] Specifically, through precise facial recognition technology and detailed behavioral analysis, the system enables rapid and accurate classification and identification of target personnel entering the monitoring range. This covers the identification of first-authorized personnel, second-authorized personnel, and authorized visitors, and extends to the analysis of facial micro-expressions and body movements of unauthorized personnel, thereby achieving more refined identity segmentation. This improves the security and intelligence level of vehicle access control, while optimizing the user experience and ensuring that only verified and authorized personnel can obtain access.

[0059] In some preferred embodiments, step SA2 further includes the following steps:

[0060] Step SA21: Obtain the facial data of the associated personnel according to the location account, and match the facial data with the actual facial data in the surveillance video one by one. When the match fails, trigger an abnormal alarm and switch the authorized identity of the mismatched personnel. The location accounts of the facial data of the first authorized personnel and the second authorized personnel are associated.

[0061] Step SA22: When there is an unauthorized person among the companions, extract the facial micro-expressions and body movements of the companions and the authorized person from the surveillance video, input the facial micro-expressions and body movements into the body and facial composite model of the authorized person and the unauthorized person, and obtain the current friendliness value of the authorized person to the unauthorized person;

[0062] Step SA23: Compare the friendliness value with a first threshold. When the friendliness value is lower than the first threshold, enable the in-vehicle video monitoring and the positioning function for the unauthorized personnel.

[0063] When the friendliness value is greater than the second threshold, the unauthorized person is granted visitor authorization, wherein the first threshold is less than the second threshold.

[0064] Specifically, through high-precision facial recognition technology and detailed behavioral analysis, the system achieves intelligent identification and friendliness assessment of unauthorized individuals among those traveling together. When the facial data associated with the location account does not match the actual facial data in the surveillance video, the system can quickly trigger an alarm and revoke the authorization of the mismatched individual, effectively improving the security of vehicle access. Simultaneously, the system can accurately assess the friendliness level between authorized personnel and unauthorized personnel based on a comprehensive analysis of their facial micro-expressions and body language, and decide whether to grant unauthorized visitor access accordingly.

[0065] In some optional embodiments, step SA22 further includes: the combined limb and facial model of the authorized person and the unauthorized person is:

[0066]

[0067] In the formula, T face represents the facial emotion value of the authorized person, ω i represents the weight coefficient of the i-th authorized person emotion, E i represents the facial emotion value of the i-th authorized person, E base represents the daily expression baseline of the i-th authorized person, S threat represents the current friendly value of the authorized person to the unauthorized person, α, β and γ represent weight coefficients, A k represents the body movement detection value of the person in the k-th video frame, ω k represents the body weight coefficient of the person in the k-th video frame, N alert represents the historical body movement of the authorized person, t represents a time variable, and N represents the number of times the unauthorized person is given the temporary access right.

[0068] In some preferred embodiments, the step SA23 further comprises the following steps:

[0069] Step SA231: When the first authorized person is in the vehicle, the unauthorized person enters, the facial micro-expression analysis of the authorized person in the in-vehicle monitoring video is extracted to obtain the friendly value of the person, and it is judged whether to give the visitor authorization permission to the unauthorized person according to the friendly value;

[0070] Step SA232: When the first authorized person is not in the vehicle, the in-vehicle monitoring and positioning function is started to send real-time information to the mobile phone of the vehicle owner, so that the vehicle owner can remotely authorize the identity of the target person through the mobile phone.

[0071] Specifically, the vehicle access control strategy is more flexible and personalized. When the first authorized person is in the vehicle and the unauthorized person appears, the system can capture and analyze the facial micro-expression of the authorized person by using the in-vehicle monitoring video, so as to accurately evaluate the friendly degree of the authorized person to the unauthorized person, and decide whether to grant the visitor permission accordingly. This not only improves the intelligent level of vehicle access, but also ensures the harmony and safety of the in-vehicle environment. In the case that the first authorized person is not in the vehicle, the system automatically starts the in-vehicle monitoring and positioning function, and sends real-time information to the mobile phone of the vehicle owner, so that the vehicle owner can remotely authorize the identity of the target person. This function greatly enhances the convenience and safety of vehicle use, so that the vehicle owner can master and control the access permission of the vehicle at any time and anywhere, and realizes the intelligent and personalized vehicle management.

[0072] Based on the same inventive concept as the above method embodiment, the embodiments of the present application also provide an intelligent security system based on face recognition,Figure 2 A module composition schematic diagram of an intelligent security and protection system based on face recognition provided for an embodiment of the present application is shown in Figure 2 The system includes a parking navigation analysis module, an identity recognition verification module, and a behavior analysis response module.

[0073] The parking navigation analysis module is configured to acquire current parking data when receiving a parking operation, and analyze an optimal detection radius of a current parking location for authorized personnel in combination with historical parking data, wherein the optimal detection radius is a range threshold for positioning the authorized personnel and triggering a car search navigation service.

[0074] The identity recognition verification module is configured to acquire positioning information of the authorized personnel when detecting that the authorized personnel enters the optimal detection radius, identify same-traveling personnel with a high coincidence degree with a movement track of the authorized personnel according to the positioning information, analyze a friendly value of the authorized personnel for the same-traveling personnel, and assign different identities to the same-traveling personnel according to the friendly value, wherein the identities include authorized personnel and unauthorized personnel.

[0075] The behavior analysis response module is configured to identify whether the authorized personnel needs the car search navigation service according to a car search track of the authorized personnel when detecting that the authorized personnel searches for a car, and provide the car search navigation service for the authorized personnel if yes.

[0076] It should be noted that although several units or sub-units of the apparatus are mentioned in the foregoing detailed description, such a division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into units embodied by multiple units.

[0077] Based on the same inventive concept as the method embodiments described above, an electronic device is also provided in the embodiments of the present application, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to enable the electronic device to implement the control method in the above embodiments.

[0078] In an embodiment, the electronic device can be a server, and in this embodiment, the structure of the electronic device can be as shown in Figure 3 The electronic device includes a memory 2001, a communication module 2003, and one or more processors 2002.

[0079] The memory 2001 is used to store computer programs executed by the processor 2002. The memory 2001 may mainly include a program storage area and a data storage area. The program storage area may store the operating system and programs required to run instant messaging functions, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0080] Memory 2001 may be volatile memory, such as random-access memory (RAM); memory 2001 may also be non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or memory 2001 may be any other medium capable of carrying or storing a desired computer program having the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory 2001 may be a combination of the above-mentioned memories.

[0081] Processor 2002 may include one or more central processing units (CPUs) or digital processing units, etc. Processor 2002 is used to implement the above-mentioned audio data processing method when calling computer programs stored in memory 2001.

[0082] The communication module 2003 is used to communicate with terminal devices and other servers.

[0083] This application embodiment does not limit the specific connection medium between the memory 2001, communication module 2003, and processor 2002. This application embodiment... Figure 3 The memory 2001 and the processor 2002 are connected via a bus 2004, which is in... Figure 3 The connections between other components are illustrated with arrows and are for illustrative purposes only, not as limiting information. The Bus 2004 can be divided into address bus, data bus, control bus, etc. For ease of description, Figure 3 The text uses only one arrow to describe it, but does not indicate that there is only one bus or one type of bus.

[0084] With the same inventive concept as the above method embodiments, the embodiments of the present application also provide a computer readable storage medium for storing a computer program, which, when executed on a computer, causes the electronic device to implement the control method in the above embodiments. The computer readable storage medium can be a readable signal medium or a readable storage medium. The readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0085] With the same inventive concept as the above method embodiments, the embodiments of the present application also provide a computer program product, which includes a computer program, when the program product is executed on an electronic device, the computer program is used to cause the electronic device to perform the steps in the control method according to various exemplary embodiments of the present application described in the specification. The program product can adopt any combination of one or more readable media. These computer program commands can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the commands executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in the flowchart Figure 1 one flowchart or multiple flowcharts and / or blocks Figure 1 one block or multiple blocks.

[0086] Although the preferred embodiments of the present application have been described, those skilled in the art who understand the basic inventive concept can make additional changes and modifications to the embodiments once they get the basic inventive concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

Claims

1. An intelligent security method based on face recognition, characterized in that: when receiving a parking operation, obtaining current parking data, combining historical parking data to analyze the optimal detection radius of the authorized personnel at the current parking location, wherein the optimal detection radius is a range threshold for positioning the authorized personnel and triggering the car search navigation service; when detecting that the authorized personnel enter the optimal detection radius, obtaining the positioning information of the authorized personnel, identifying the same personnel with a high coincidence degree with the moving track of the authorized personnel according to the positioning information, analyzing the friendly value of the authorized personnel to the same personnel and assigning different identities to the same personnel according to the friendly value, the identity including: authorized personnel and unauthorized personnel; when detecting that the authorized personnel searches for a car, identifying whether the authorized personnel needs the car search navigation service according to the car search track of the authorized personnel, and if so, providing the car search navigation service for the authorized personnel; when receiving a parking operation, obtaining current parking data, combining historical parking data to analyze the optimal detection radius of the authorized personnel at the current parking location, including: when detecting the parking operation, constructing a special historical parking feature vector according to the historical parking data of different authorized personnel using the car search navigation; constructing an optimal detection radius model of the car search navigation for the authorized personnel according to the historical parking feature vector, extracting a parking feature vector of the current parking data, inputting the parking feature vector into the optimal detection radius model, and obtaining the optimal detection radius of the car search navigation for the authorized personnel; constructing an optimal detection radius model of the car search navigation for the authorized personnel according to the historical parking feature vector, extracting a parking feature vector of the current parking data, inputting the parking feature vector into the optimal detection radius model, and obtaining the optimal detection radius of the car search navigation for the authorized personnel, including: identifying whether there is a witness of the current parking location among the authorized personnel, when there is a witness among the authorized personnel, calculating the similarity between the current parking feature vector and the historical parking feature vector according to the historical parking feature vector of the witness, constructing an optimal detection radius model of the car search navigation according to the similarity and the historical optimal detection radius, inputting the current parking feature vector into the optimal detection radius model to obtain the optimal detection radius, wherein the witness refers to the authorized personnel who has seen the car parked at the current parking location; when there is no witness among the authorized personnel, clustering the historical parking data of the authorized personnel to generate a scene category, matching the current parking data to obtain the scene category with the highest similarity, constructing an optimal detection radius model of the car search navigation according to the scene category, inputting the current parking feature vector into the optimal detection radius model to obtain the optimal detection radius, wherein the scene category refers to a parking scene grouping with similar features formed by clustering and analyzing the historical parking data of the authorized personnel. ​ ​ ​ ​ ​ ​ ​ ​ 2.The intelligent security method based on face recognition of claim 1, characterized in that: ​ 3.The intelligent security method based on face recognition of claim 2, characterized in that: The method comprises the following steps: When it is detected that the authorized personnel enters the optimal detection radius, the positioning information of the authorized personnel is acquired, the same personnel with high coincidence degree with the moving track of the authorized personnel is identified according to the positioning information, the friendly value of the authorized personnel to the same personnel is analyzed, and the identity of the same personnel is given, comprising: When it is detected that the authorized personnel enters the corresponding optimal detection radius, the face data of the authorized personnel is matched, and the identity of the authorized personnel is identified, wherein the authorized personnel includes a first authorized personnel, a second authorized personnel and a visitor authorized personnel, the first authorized personnel is a long-term usable personnel with the highest use permission, the second authorized personnel is a long-term usable personnel with lower use permission than the first authorized personnel, and the visitor authorized personnel is a temporary visitor of the vehicle and is switched to an unauthorized personnel after an authorized time period. 4.The intelligent security method based on face recognition of claim 3, characterized in that: The positioning account of the same personnel is acquired, the positioning account is matched with the positioning account in the historical authorized library, when the unauthorized personnel is identified in the same personnel, the visitor identity of the unauthorized personnel is given or the identity of the unauthorized personnel is still reserved in combination with the monitoring video of the current parking place. The positioning account of the same personnel is acquired, the positioning account is matched with the positioning account in the historical authorized library, when the unauthorized personnel is identified in the same personnel, the identity of the unauthorized personnel is divided in combination with the monitoring video of the current parking place, comprising: The face data of the associated personnel is acquired according to the positioning account, the face data is matched with the actual face data in the monitoring video one by one, when the matching is unsuccessful, an abnormal alarm is triggered and the authorized identity of the unmatched personnel is switched, wherein the positioning accounts between the face data of the first authorized personnel and the second authorized personnel are associated; When the unauthorized personnel is in the same personnel, the face micro-expression and the body action of the same personnel and the authorized personnel are extracted from the monitoring video, the face micro-expression and the body action are input into the body face comprehensive model of the authorized personnel and the unauthorized personnel, and the friendly value of the current authorized personnel to the unauthorized personnel is acquired; The friendly value is compared with a first threshold value, when the friendly value is lower than the first threshold value, the in-vehicle video monitoring and the positioning function of the unauthorized personnel are started; 5.The intelligent security method based on face recognition of claim 4, characterized in that: When the friendly value is greater than a second threshold value, the visitor authorized permission is given to the unauthorized personnel, wherein the first threshold value is smaller than the second threshold value. The friendly value is compared with a first threshold value, when the friendly value is lower than the first threshold value, the in-vehicle video monitoring and the positioning function of the unauthorized personnel are started; when the friendly value is higher than the first threshold value and lower than a second threshold value, the visitor authorized permission is not given to the unauthorized personnel; when the friendly value is greater than the second threshold value, the visitor authorized permission is given to the unauthorized personnel, comprising: When the first authorized person is in the vehicle, the un-authorized person enters, the facial micro-expression analysis of the authorized person in the vehicle monitoring video extracts the friendly value of the person, and judges whether to give the visitor authorization permission to the un-authorized person according to the friendly value; When the first authorized person is not in the vehicle, the vehicle monitoring and positioning function is started to send to the mobile phone of the vehicle owner in real time, so that the vehicle owner remotely authorizes the identity of the un-authorized person through the mobile phone.

Images