Security protection method, security protection system and computer program product
By identifying the followers to be verified around the security protection object and determining the target followers based on their behavioral characteristics, the problem that traditional security measures are difficult to deal with complex security situations and misidentification is solved, and the reliability and accuracy of security protection are improved.
Patent Information
- Application Number
- CN202411746004.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-29
- Publication Date
- 2025-04-01
AI Technical Summary
Traditional security measures are difficult to deal with complex security situations in a comprehensive and timely manner, and portrait recognition methods are prone to misidentification problems, resulting in poor security protection reliability.
By identifying the followers to be checked around the security protection object, outputting action guidance information, and determining the target follower based on the first behavioral characteristics of the follower to be checked, accurate identification of the actual follower is achieved.
It improves the reliability of security protection, can accurately identify actual followers, including those that do not exist in the face library, and enhances the ability to respond to potential security threats.
Smart Images
Figure CN119741652A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of security technology, and in particular, relates to a security protection method, a security protection system and a computer program product. Background Art
[0002] Special occupations such as patrol officers, security personnel, and public figures often face various potential security threats. Traditional security measures are often limited to passive defense or human monitoring, which makes it difficult to respond to various complex situations in a comprehensive and timely manner. Some monitoring equipment uses portrait recognition for protection, but in some cases, there will be problems with misidentification. Summary of the invention
[0003] The embodiments of the present application provide a security protection method, a security protection system and a computer program product, which can solve the problem of poor security protection reliability in related technologies.
[0004] A first aspect of an embodiment of the present application provides a security protection method, comprising: if a follower to be verified is identified around a security protection object, outputting action guidance information; when the security protection object acts according to the action guidance information, monitoring a first behavior feature of the follower to be verified; and determining a target follower from among the followers to be verified based on the first behavior feature.
[0005] In some embodiments of the first aspect, the first behavioral feature includes a first motion parameter of the follower to be verified, and the first motion parameter includes position information and speed information; determining a target follower from the followers to be verified based on the first behavioral feature includes: determining a first distance between the follower to be verified and the safety protection object based on the position information; if the first distance remains within a preset distance range, detecting a degree of motion similarity between the follower to be verified and the safety protection object based on the speed information; if the degree of motion similarity is greater than a similarity threshold, confirming that the follower to be verified is a target follower.
[0006] In some embodiments of the first aspect, before outputting the action guidance information, the safety protection method further includes: detecting feature information of an object to be identified around the safety protection object, the feature information including facial features; and identifying the follower to be verified among the objects to be identified based on the facial features.
[0007] In some embodiments of the first aspect, identifying the follower to be verified among the objects to be identified based on the facial features includes: determining the gaze direction of the object to be identified at each sampling moment within a preset time length based on the facial features; determining the time proportion of each gaze direction within the preset time length; and confirming the object to be identified in which the time proportion of the target gaze direction has a peak as the follower to be verified, wherein the target gaze direction is the direction of the gaze at the security protection object.
[0008] In some embodiments of the first aspect, identifying the follower to be verified among the objects to be identified based on the facial features includes: obtaining position information of the object to be identified at each sampling moment; determining the facial integrity of the object to be identified when it is located in a preset area based on the position information and the sampling moment corresponding to the facial features; and confirming the object to be identified whose facial integrity is lower than a completeness threshold as the follower to be verified.
[0009] In some implementations of the first aspect, the feature information further includes a second behavior feature; and the security protection method further includes: identifying the follower to be verified from the object to be identified according to the second behavior feature.
[0010] In some embodiments of the first aspect, after determining the target follower from the followers to be verified, the method further includes: adding the facial information of the target follower to a face library; when the safety protection object is located in a target vehicle, detecting the cumulative appearance time of each vehicle to be identified behind the target vehicle; in the vehicle to be identified where the cumulative appearance time is greater than a duration threshold, comparing the facial information of the driver and passengers with the facial information in the face library; and determining a trailing vehicle from the vehicles to be identified based on the comparison result.
[0011] In some embodiments of the first aspect, the safety protection method further includes: obtaining heat source information behind the safety protection object, and / or a rear side image; and displaying the heat source information and / or the rear side image.
[0012] A second aspect of an embodiment of 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 implements the steps of the above-mentioned security protection method when executing the computer program.
[0013] A third aspect of an embodiment of the present application provides a security protection system, including: a wearable device, used to: output action guidance information if a follower to be verified is identified around a security protection object; monitor a first behavior feature of the follower to be verified when the security protection object acts according to the action guidance information; and determine a target follower from the followers to be verified based on the first behavior feature.
[0014] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned security protection method are implemented.
[0015] A fifth aspect of an embodiment of the present application provides a computer program product, and when the computer program is run, the security protection method is executed.
[0016] In the implementation manner of the present application, when a follower to be verified is identified around a security protection object, action guidance information is output, and when the security protection object acts according to the action guidance information, a target follower is determined among the followers to be verified based on the first behavior characteristics of the follower to be verified, so that the security protection object can be guided to perform special actions, the behavior of the follower to be verified is analyzed based on the behavior characteristics of the follower to be verified, the actual follower can be accurately identified, and the reliability of security protection is improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0018] Figure 1 This is a schematic diagram of an implementation flow of a security protection method provided in an embodiment of the present application;
[0019] Figure 2 This is a schematic diagram of a first specific implementation flow of identifying a follower to be verified provided by an embodiment of the present application;
[0020] Figure 3 This is a schematic diagram of a second specific implementation flow of identifying a follower to be verified provided by an embodiment of the present application;
[0021] Figure 4 This is a schematic diagram of a third specific implementation flow of identifying a follower to be verified provided by an embodiment of the present application;
[0022] Figure 5It is a schematic diagram of a specific implementation process of determining a target follower provided in an embodiment of the present application;
[0023] Figure 6 It is a structural schematic diagram of a safety protection system provided in an embodiment of the present application;
[0024] Figure 7 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0025] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are protected by the present application.
[0026] Special professionals such as patrol officers, security personnel, and public figures often face various potential security threats. Traditional security measures are often limited to passive defense or human monitoring, and it is difficult to respond to various complex situations in a comprehensive and timely manner. Some monitoring equipment uses portrait recognition for protection, but it is often difficult to identify and protect followers that do not exist in the face database.
[0027] In view of this, the present application proposes a security protection method, which can guide the security protection object to perform special actions, analyze the behavior of the follower to be verified based on the behavioral characteristics of the follower to be verified, accurately identify the actual follower, and have a good recognition effect for followers that do not exist in the face library, thereby improving the reliability of security protection.
[0028] In order to illustrate the technical solution of the present application, a specific embodiment is provided below for illustration.
[0029] Figure 1 A schematic diagram of the implementation process of a security protection method provided in an embodiment of the present application is shown, and the method can be applied to a security protection system.
[0030] Specifically, the above security protection method may include the following steps S101 to S103.
[0031] Step S101: if a follower to be verified is identified around the safety protection object, action guidance information is output.
[0032] The follower to be verified refers to a suspected follower around the security object, which may be a person, an animal, etc. In the implementation of the present application, the follower to be verified may be identified around the security object by existing recognition methods such as face recognition.
[0033] In order to ensure the reliability of the recognition results, the security protection system can output action guidance information. Action guidance information can be used to guide the security protection object to perform specific actions, such as guiding the security protection object to move to the target location along a specific path, guiding the security protection object to accelerate or decelerate, guiding the security protection object to stop moving periodically, etc. The target location can be a safe location such as a police station or a security booth, or a user-defined shelter or path. By outputting action guidance information, the behavior of the follower to be verified can be verified when the security protection object performs a specific action.
[0034] It is understandable that the output method of the action guidance information can be selected according to needs.
[0035] In some embodiments of the present application, the safety protection system may include a wearable device, which may be an augmented reality (AR) device. When the AR device identifies a follower to be verified around the safety protection object, it may display or output action guidance information through sound.
[0036] Step S102: When the security protection object acts according to the action guidance information, the first behavior feature of the follower to be verified is monitored.
[0037] In the implementation of the present application, the first behavior feature is used to describe the behavior characteristics of the follower to be verified, which may include but is not limited to the motion parameters of the security protection object such as the stop position and the moving speed. When the security protection object acts according to the action guidance information, the security protection system can monitor the first behavior feature of each follower to be verified.
[0038] Among them, the first behavior feature can be obtained through image recognition, temperature / heat source monitoring, etc.
[0039] For example, when the security object wears an AR device and enters the security control area, the AR device identifies the follower to be verified and outputs action guidance information, and the security object can act according to the action guidance information. At this time, the AR device can capture the image of the security object in real time to extract the first behavior feature of the follower to be verified from the image.
[0040] Step S103: determining a target follower from the followers to be verified according to the first behavior feature.
[0041] In the implementation of the present application, based on the first behavior feature, it is possible to analyze whether the behavior of each follower to be verified conforms to the actual characteristics of the follower, so as to determine the target follower among the followers to be verified. The target follower is the actual follower of the security protection object.
[0042] It is understandable that the followers to be verified are usually identified in the process of the security protection object performing routine actions, and their behaviors are likely to be consistent with those of non-followers, for example, they all move in a specific direction at a constant speed. The action guidance information can guide the security protection object to perform unconventional actions, thereby making the behaviors of actual followers and non-followers significantly different, which helps to identify the real followers among the followers to be verified.
[0043] In the implementation manner of the present application, when a follower to be verified is identified around a security protection object, action guidance information is output, and when the security protection object acts according to the action guidance information, a target follower is determined among the followers to be verified based on the first behavior characteristics of the follower to be verified, so that the security protection object can be guided to perform special actions, the behavior of the follower to be verified is analyzed based on the behavior characteristics of the follower to be verified, the actual follower can be accurately identified, and the reliability of security protection is improved.
[0044] In some embodiments of the present application, before outputting the action guidance information, the safety protection method may further include: detecting feature information of an object to be identified around the safety protection object, the feature information including facial features, and identifying a follower to be verified from the object to be identified based on the facial features.
[0045] The objects to be identified may be people, animals, and other objects that may follow the security object. Facial features are used to describe the facial conditions of the objects to be identified, and may include eye features, facial orientation, and the like. Based on the facial features, objects with suspicious facial movements can be identified from the objects to be identified as followers to be verified.
[0046] Specifically, in some embodiments of the present application, Figure 2 As shown, identifying a follower to be verified from among objects to be identified based on facial features may include: step S201 to step S203.
[0047] Step S201, determining the gaze direction of the object to be identified at each sampling time within a preset time period according to the facial features.
[0048] Specifically, the preset duration can be selected according to the recognition requirements, and the preset duration can include multiple sampling moments. For each sampling moment, the gaze direction of the eyes of the object to be recognized can be determined according to the eye features of the object to be recognized, such as the pupil position.
[0049] Step S202, determining the time proportion of each gaze direction within a preset time length.
[0050] Specifically, the gaze direction at each sampling moment can be classified, and the gaze directions of the same object can be divided into one category. For each gaze direction, the total duration of the sampling moment can be counted to determine the proportion of the total duration of each gaze direction within the preset duration.
[0051] For example, the preset duration is 20 seconds, each second is a sampling moment, and the direction of looking at the safety protection object is taken as a category. The total duration of looking in the direction of the safety protection object is 10 seconds, that is, there are 10 sampling moments when the gaze direction is the direction of looking at the safety protection object. At this time, it can be determined that the time proportion of looking in the direction of the safety protection object is 50%.
[0052] Step S203: The object to be identified whose time proportion in the target gaze direction reaches a peak is confirmed as a follower to be verified.
[0053] The target gaze direction is the direction in which the target is looking at the security protection object. For each object to be identified, if the time proportion of the target gaze direction has a peak, it means that the corresponding object to be identified is looking at the security protection object most of the time, and there is a possibility of following the security protection object. At this time, the corresponding object to be identified can be confirmed as a follower to be verified.
[0054] Correspondingly, if the time proportion of the target gaze direction does not peak, the object to be identified can be confirmed as a non-follower.
[0055] In other embodiments of the present application, Figure 3 As shown, identifying a follower to be verified from among objects to be identified based on facial features may include: step S301 to step S303.
[0056] Step S301, obtaining the position information of the object to be identified at each sampling time.
[0057] The position information may refer to the absolute position of the object to be identified, or the position of the object to be identified relative to the security protection object. The position information may be determined by image recognition or other methods, which is not limited in this application.
[0058] Step S302, determining the facial integrity of the object to be identified when it is located in a preset area according to the location information and the sampling time corresponding to the facial features.
[0059] At each sampling moment, the position information and facial features of the object to be identified can be obtained. Based on the position information, it can be determined whether the object to be identified is located in a preset area. Based on the facial features, the facial integrity of the object to be identified can be determined.
[0060] The preset area may refer to an open area, for example, an area where the density of people is lower than a density threshold, or an area where the number of visual obstacles is lower than the number of obstacles. The facial integrity indicates whether a complete face can be recognized, which can be obtained based on the number of facial feature points recognized at the corresponding sampling moment. The more facial feature points there are, the higher the facial integrity.
[0061] Step S303: The object to be identified whose facial integrity is lower than the integrity threshold is confirmed as a follower to be verified.
[0062] In an embodiment of the present application, when the facial integrity of the object to be identified is located in a preset area, it is lower than the integrity threshold, indicating that the exposure of the front of the object to be identified in the preset area is reduced, and there is a possibility of following a security protection object. At this time, the corresponding object to be identified can be confirmed as a follower to be verified.
[0063] Correspondingly, if the facial integrity is greater than or equal to the integrity threshold, the object to be identified may be confirmed as a non-follower.
[0064] In some other embodiments of the present application, the feature information of the object to be identified may further include a second behavior feature. In this case, the security protection method further includes: identifying a follower to be verified from the object to be identified according to the second behavior feature.
[0065] Specifically, the second behavior feature includes a second motion parameter of the follower to be verified, and the second motion parameter includes position information and speed information of the object to be identified. Figure 4 As shown, according to the second behavior feature, identifying a follower to be verified from the object to be identified may include: step S401 to step S403.
[0066] Step S401: determining a second distance between any object to be identified and a security protection object according to the position information of the object to be identified.
[0067] Step S402: If the second distance remains within the preset distance range, the motion similarity between the object to be identified and the safety protection object is detected based on the speed information.
[0068] Specifically, if the second distance remains within the preset distance range within the preset time, it means that the object to be identified always maintains a relatively fixed distance from the safety protection object. At this time, the degree of motion similarity between the object to be identified and the safety protection object can be detected according to the speed information of the object to be identified and the speed information of the safety protection object.
[0069] Specifically, it is possible to detect whether the speed information between the object to be identified and the safety protection object is consistent at each sampling moment, and to fuse the consistency results at different sampling moments to obtain the degree of motion similarity between the object to be identified and the safety protection object.
[0070] Step S403: taking the objects to be identified whose motion similarity is greater than the similarity threshold as followers to be verified.
[0071] If the motion similarity is greater than the similarity threshold, it means that there is a certain correlation between the walking, stopping, acceleration and deceleration of the object to be identified and the safety protection object. At this time, it can be confirmed that the object to be identified is a follower to be verified.
[0072] Correspondingly, if the motion similarity is less than or equal to the similarity threshold, the object to be identified may be confirmed as a non-follower.
[0073] Preferably, in order to ensure the accuracy of the followers to be verified, Figures 2 to 4 That is, the object to be identified is confirmed as the follower to be verified if the time proportion of the target gaze direction has a peak, the facial integrity when located in the preset area is lower than the integrity threshold, and the motion similarity between the object to be identified and the security protection object is greater than the similarity threshold.
[0074] After identifying the follower to be verified, the security protection system can output prompt information, such as display and sound prompts through AR devices, so that the security protection object can be more vigilant. Specifically, the above prompt information can be the real-time location of the follower to be verified, the current distance, the suspected tracking time, the clearest facial photo taken, and whether it is a known dangerous person (compared with the face library, if a match is shown, the corresponding identity is displayed). At the same time, the security protection object can be advised to share the information with emergency contacts.
[0075] When the security protection object acts according to the action guidance information, the first behavior characteristics of the followers to be verified may be monitored to determine the target follower from the followers to be verified according to the first behavior characteristics.
[0076] Specifically, Figure 5 As shown, determining a target follower from followers to be verified according to the first behavior feature may include: step S501 to step S503.
[0077] Step S501: determining a first distance between a follower to be verified and a safety protection object according to the position information.
[0078] Step S502: If the first distance is maintained within the preset distance range, the degree of motion similarity between the follower to be verified and the safety protection object is detected according to the speed information.
[0079] Step S503: if the motion similarity is greater than the similarity threshold, the follower to be verified is confirmed to be the target follower.
[0080] The specific implementation of steps S501 to S503 can be referred to Figure 4 That is to say, if the first distance is maintained within the preset distance range within the preset time length, it means that the follower to be verified always maintains a relatively fixed distance with the safety protection object. At this time, the motion similarity between the follower to be verified and the safety protection object can be detected according to the speed information of the follower to be verified and the speed information of the safety protection object. If the motion similarity is greater than the similarity threshold, it means that there is a certain correlation between the walking, stopping, acceleration and deceleration of the follower to be verified and the safety protection object. At this time, the follower to be verified can be confirmed as the target follower. Correspondingly, if the motion similarity is less than or equal to the similarity threshold, the follower to be verified can be confirmed as a non-follower.
[0081] It is understandable that the action guidance information can guide the safety protection object to perform unconventional actions, thereby making the actual follower and the non-follower have obvious differences in behavior. By re-verifying the first distance between the follower to be verified and the safety protection object and the degree of motion similarity between the follower to be verified and the safety protection object, it can be confirmed whether the follower to be verified still maintains a fixed distance when the safety protection object performs unconventional actions, and is correlated with the walking, stopping, accelerating and decelerating of the safety protection object. If the follower to be verified still maintains a fixed distance and is correlated with the walking, stopping, accelerating and decelerating of the safety protection object, it can be confirmed that it is the target follower.
[0082] Correspondingly, if the motion similarity is less than or equal to the similarity threshold, the follower to be verified is confirmed to be a non-follower.
[0083] In some implementations of the present application, after the target follower is determined among the followers to be verified, the method may further include: adding the face information of the target follower to a face library.
[0084] Specifically, the user may be asked through a display interface whether to add the target follower as a dangerous person to the face library. The face library may be shared among various devices of the security protection system to improve security.
[0085] In some embodiments of the present application, after the target follower is determined among the followers to be verified, the method further includes: adding the face information of the target follower to the face library. When the security protection object is located in the target vehicle, the cumulative appearance time of each vehicle to be identified behind the target vehicle is detected, and in the vehicle to be identified whose cumulative appearance time is greater than the time threshold, the face information of the driver and passenger is compared with the face information in the face library, and the trailing vehicle is determined among the vehicles to be identified based on the comparison result.
[0086] Specifically, for vehicle-mounted tailgating behavior, the safety protection system can detect the license plate information of the vehicle behind in real time through the on-board camera. If a license plate appears in the rear field of view multiple times and the cumulative appearance time exceeds the set time threshold, the safety protection system will issue a warning to remind the driver that there may be a tailgating vehicle. It will also detect the facial information of the driver and passengers of the vehicle behind in real time through the camera, and compare it with the shared face library of tailgating recognition to determine the tailing vehicle among the vehicles to be identified, avoiding the impact caused by the target follower changing the tracking method or means of transportation.
[0087] It should be noted that, in addition to target followers, the above-mentioned face database can also include dangerous persons such as wanted criminals, so that the security protection system can be used in public safety scenarios.
[0088] In some embodiments of the present application, the safety protection method may further include: obtaining heat source information and / or a rear side image behind the safety protection object, and displaying the heat source information and / or the rear side image.
[0089] Specifically, the AR device of the safety protection system can be provided with visible light sensors and infrared sensors to achieve all-weather environmental perception. The visible light sensor can be one or more, including at least one visible light sensor installed backwards, which is used to obtain the rear image to make up for the blind spot of human vision. The infrared sensor can monitor the heat source conditions around the user in real time, distinguish different types of heat sources (such as human body, animals, mechanical equipment, etc.), especially the heat source information that may exist behind the user. In other implementations, the AR device can also obtain heat source information through an external infrared imager. The AR device can display the heat source information and / or the rear image in the interface to form a virtual "rearview mirror" effect, so that the user can clearly perceive the movements behind him and guard against potential sneak attacks from behind.
[0090] In some embodiments of the present application, the security protection method further includes: detecting whether the objects to be identified around the security protection object are armed, and for the objects to be identified armed, detecting whether they are approaching the security protection object. If the objects to be identified armed are approaching the security protection object, an alarm signal is output to remind the security protection object to defend itself.
[0091] It should be noted that, for the sake of simplicity of description, the aforementioned method embodiments are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders.
[0092] like Figure 6 Shown is a schematic structural diagram of a safety protection system provided in an embodiment of the present application.
[0093] Specifically, the security protection system may include: a wearable device 61, which is used to: output action guidance information if a follower to be verified is identified around the security protection object; monitor the first behavioral characteristics of the follower to be verified when the security protection object acts according to the action guidance information; and determine the target follower among the followers to be verified based on the first behavioral characteristics.
[0094] In some embodiments of the present application, the first behavioral feature includes a first motion parameter of the follower to be verified, and the first motion parameter includes position information and speed information; the wearable device 61 is also used to: determine a first distance between the follower to be verified and the safety protection object based on the position information; if the first distance remains within a preset distance range, then detect the degree of motion similarity between the follower to be verified and the safety protection object based on the speed information; if the degree of motion similarity is greater than a similarity threshold, confirm that the follower to be verified is a target follower.
[0095] In some embodiments of the present application, the wearable device 61 is further used to: detect feature information of objects to be identified around the security protection object, the feature information including facial features; and identify the follower to be verified among the objects to be identified based on the facial features.
[0096] In some embodiments of the present application, the wearable device 61 is also used to: determine the gaze direction of the object to be identified at each sampling moment within a preset time length based on the facial features; determine the time proportion of each gaze direction within the preset time length; and confirm the object to be identified in which the time proportion of the target gaze direction has a peak as the follower to be verified, wherein the target gaze direction is the direction of the gaze at the security protection object.
[0097] In some embodiments of the present application, the wearable device 61 is also used to: obtain the position information of the object to be identified at each sampling time; determine the facial integrity of the object to be identified when it is located in a preset area based on the sampling time corresponding to the position information and the facial features; and confirm the object to be identified whose facial integrity is lower than the integrity threshold as the follower to be verified.
[0098] In some implementations of the present application, the feature information further includes a second behavior feature; and the wearable device 61 is further configured to: identify the follower to be verified from among the objects to be identified according to the second behavior feature.
[0099] In some implementations of the present application, the wearable device 61 is further used to: add the facial information of the target follower to a facial library.
[0100] In some embodiments of the present application, the safety protection system may further include: a vehicle-mounted device 62, which is used to detect the cumulative appearance time of each vehicle to be identified behind the target vehicle when the safety protection object is located in the target vehicle; in the vehicle to be identified where the cumulative appearance time is greater than a duration threshold, the facial information of the driver and passengers is compared with the facial information in the face library; and based on the comparison result, the following vehicle is determined in the vehicle to be identified.
[0101] In some embodiments of the present application, the wearable device 61 is also used to: obtain the heat source information behind the safety protection object, and / or the rear side image; and display the heat source information and / or the rear side image.
[0102] In some embodiments of the present application, the safety protection system may further include: an infrared imaging monitoring module 63, including one or more infrared imagers, for acquiring heat source information.
[0103] It should be noted that for the convenience and simplicity of description, the specific working process of the above safety protection system can be referred to Figures 1 to 5 The corresponding process of the method will not be repeated here.
[0104] like Figure 7 , which is a schematic diagram of an electronic device provided in an embodiment of the present application. The electronic device may refer to the aforementioned wearable device 61, vehicle-mounted device 62 or infrared imaging monitoring module 63.
[0105] Specifically, the electronic device 7 may include: a processor 70, a memory 71, and a computer program 72 stored in the memory 71 and executable on the processor 70, such as a security protection program. When the processor 70 executes the computer program 72, the steps in the above-mentioned security protection method embodiments are implemented, such as Figure 1 Steps S101 to S103 are shown.
[0106] The computer program may be divided into one or more modules / units, which are stored in the memory 71 and executed by the processor 70 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the electronic device.
[0107] The electronic device may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art will appreciate that Figure 7These are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.
[0108] The processor 70 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0109] The memory 71 may be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device. The memory 71 may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Furthermore, the memory 71 may also include both an internal storage unit of the electronic device and an external storage device. The memory 71 is used to store the computer program and other programs and data required by the electronic device. The memory 71 may also be used to temporarily store data that has been output or is to be output.
[0110] It should be noted that, for the convenience and brevity of description, the structure of the above electronic device can also refer to the specific description of the structure in the method embodiment, which will not be repeated here.
[0111] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0112] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0113] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0114] In the embodiments provided in the present application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0115] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple 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.
[0116] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0117] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.
[0118] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A safety protection method, characterized in that: include: If a follower to be verified is identified around the security protection object, action guidance information is output; When the security protection object acts according to the action guidance information, monitoring the first behavior characteristic of the follower to be verified; According to the first behavior feature, a target follower is determined from the followers to be verified.
2. The safety protection method according to claim 1, characterized in that: The first behavior feature includes a first motion parameter of the follower to be verified, and the first motion parameter includes position information and speed information; The step of determining a target follower from the followers to be verified according to the first behavior feature includes: Determine a first distance between any of the followers to be verified and the safety protection object according to the position information; If the first distance remains within a preset distance range, detecting the degree of motion similarity between the follower to be verified and the safety protection object according to the speed information; If the motion similarity is greater than the similarity threshold, the follower to be verified is confirmed to be the target follower.
3. The safety protection method according to claim 1, characterized in that: Before outputting the action guidance information, the safety protection method further includes: Detecting feature information of an object to be identified around the security protection object, wherein the feature information includes facial features; The follower to be verified is identified from among the objects to be identified according to the facial features.
4. The safety protection method according to claim 3, characterized in that: The step of identifying the follower to be verified from the object to be identified according to the facial features includes: Determining the gaze direction of the object to be identified at each sampling moment within a preset time period according to the facial features; Determine the time proportion of each gaze direction within the preset time length; The object to be identified whose time proportion in the target gaze direction reaches a peak is confirmed as the follower to be verified, wherein the target gaze direction is the direction in which the security protection object is gazed.
5. The safety protection method according to claim 3, characterized in that: The step of identifying the follower to be verified from the object to be identified according to the facial features includes: Obtaining the position information of the object to be identified at each sampling time; Determining the facial integrity of the object to be identified when it is located in a preset area according to the location information and the sampling time corresponding to the facial features; The object to be identified whose facial integrity is lower than the integrity threshold is confirmed as the follower to be verified.
6. The safety protection method according to claim 3, characterized in that: The characteristic information also includes a second behavior characteristic; Safety protection methods also include: The follower to be verified is identified from the objects to be identified according to the second behavior feature.
7. The safety protection method according to any one of claims 1 to 6, characterized in that: After determining the target follower among the followers to be verified, the method further includes: Adding the face information of the target follower to the face library; When the safety protection object is located in the target vehicle, detecting the cumulative appearance time of each vehicle to be identified behind the target vehicle; In the vehicle to be identified whose cumulative appearance time is greater than the duration threshold, comparing the facial information of the driver and passenger with the facial information in the face database; According to the comparison result, the trailing vehicle is determined among the vehicles to be identified.
8. The safety protection method according to any one of claims 1 to 6, characterized in that: The safety protection method also includes: Acquiring heat source information behind the safety protection object and / or a rear side image; The heat source information and / or the rear side image are displayed.
9. A safety protection system, characterized in that: include: The wearable device is used to: if a follower to be verified is identified around the safety protection object, output action guidance information; When the security protection object acts according to the action guidance information, the first behavior feature of the followers to be verified is monitored; and according to the first behavior feature, a target follower is determined from the followers to be verified.
10. A computer program product, characterized in that It comprises a computer program, which, when executed, enables the security protection method according to any one of claims 1 to 8 to be executed.