Security inspection warning method and device, storage medium and electronic equipment

Abstract

The present invention discloses a security inspection warning method and device, a storage medium, and an electronic device. The method comprises: obtaining first image information of a security inspection object currently captured by a first image acquisition device; wherein the first image acquisition device is used for video capture during the security inspection process; obtaining second image information of the security inspection object captured by a second image acquisition device from a non-security inspection database; comparing the security inspection object identified from the first image information with the security inspection object identified from the second image information; and when the comparison result indicates that the feature difference between the first limb movement feature of the security inspection object in the first image information and the second limb movement feature of the security inspection object in the second image information is greater than a preset threshold, indicating that the security inspection object is an abnormal object. The present invention solves the technical problem of low security inspection warning efficiency caused by inaccurate recognition of dangerous actions and delayed dangerous warning in related technologies.

Description

Technical Field

[0001] The present invention relates to the field of image recognition technology, and in particular to a security inspection early warning method and device, a storage medium, and an electronic device. Background Art

[0002] In places where security checks are required, such as airports, train stations, and subways, it is usually necessary to identify people in the security check area in advance for dangerous actions. Related technologies use facial recognition to compare facial data to see if there are any people on record; motion recognition is used to detect whether the person currently being checked has any dangerous actions. In this case, it can only be detected when the danger is about to occur or is occurring. Facial expression recognition is used to analyze facial expressions for danger and screen out people with dangerous expressions. This is limited by factors such as wearing masks and disguised expressions. Overall, related technologies for security inspection and early warning of people in security check areas have technical problems such as inaccurate recognition of dangerous actions and delayed warning of dangers.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] The embodiments of the present invention provide a security inspection warning method and device, a storage medium and an electronic device to at least solve the technical problem of low security inspection warning efficiency caused by inaccurate recognition of dangerous actions and delayed danger warning in related technologies.

[0005] According to one aspect of an embodiment of the present invention, a security inspection warning method is provided, comprising: obtaining first image information of a security inspection object currently captured by a first image acquisition device; wherein the first image acquisition device is used for video acquisition during a security inspection process; obtaining second image information of the security inspection object captured by a second image acquisition device from a non-security inspection database, wherein the second image acquisition device is used for video acquisition during a non-security inspection process; comparing the security inspection object identified from the first image information with the security inspection object identified from the second image information; when a result of the comparison indicates that a feature difference between a first limb movement feature of the security inspection object in the first image information and a second limb movement feature of the security inspection object in the second image information is greater than a preset threshold, prompting the security inspection object as an abnormal object.

[0006] According to another aspect of an embodiment of the present invention, a security inspection warning device is further provided, including: a first acquisition unit, used to acquire first image information of the security inspection object currently captured by a first image acquisition device; wherein the above-mentioned first image acquisition device is used for video acquisition during the security inspection process; a second acquisition unit, used to acquire second image information of the above-mentioned security inspection object captured by a second image acquisition device from a non-security inspection database, wherein the above-mentioned second image acquisition device is used for video acquisition during the non-security inspection process; a comparison unit, used to compare the above-mentioned security inspection object identified from the above-mentioned first image information with the above-mentioned security inspection object identified from the above-mentioned second image information; and a prompt unit, used to prompt that the above-mentioned security inspection object is an abnormal object when the comparison result indicates that the feature difference between the first limb movement feature of the above-mentioned security inspection object in the above-mentioned first image information and the second limb movement feature of the above-mentioned security inspection object in the above-mentioned second image information is greater than a preset threshold.

[0007] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the above-mentioned security inspection warning method when running.

[0008] According to another aspect of an embodiment of the present invention, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the security warning method through the computer program.

[0009] In an embodiment of the present invention, a method is adopted in which first image information of a security inspection object currently captured by a first image capture device is obtained; wherein the first image capture device is used for video capture during the security inspection process; second image information of the security inspection object captured by a second image capture device is obtained from a non-security inspection database, wherein the second image capture device is used for video capture during the non-security inspection process; the security inspection object identified from the first image information is compared with the security inspection object identified from the second image information; when the result of the comparison indicates that the feature difference between the first limb movement feature of the security inspection object in the first image information and the second limb movement feature of the security inspection object in the second image information is greater than a preset threshold, the security inspection object is prompted to be an abnormal object. This method achieves the purpose of accurately and timely identifying dangerous actions during the security inspection process, thereby realizing the technical effect of improving the accuracy and timeliness of judging dangerous actions of personnel in security inspection places, and further solves the technical problem of low security inspection warning efficiency caused by inaccurate dangerous action recognition and delayed dangerous warning in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0011] Figure 1 is a schematic diagram of an application environment of an optional security inspection warning method according to an embodiment of the present invention;

[0012] Figure 2 is a schematic diagram of an application environment of another optional security inspection and early warning method according to an embodiment of the present invention;

[0013] Figure 3 is a flow chart of an optional security inspection warning method according to an embodiment of the present invention;

[0014] Figure 4 is a schematic diagram of a limb model of an optional security inspection warning method according to an embodiment of the present invention;

[0015] Figure 5 is a schematic diagram of a body movement change curve of an optional security inspection warning method according to an embodiment of the present invention;

[0016] Figure 6 1 is a schematic diagram of the system architecture of an optional security inspection and early warning method according to an embodiment of the present invention;

[0017] Figure 7 is a flowchart of another optional security inspection warning method according to an embodiment of the present invention;

[0018] Figure 8 is a schematic structural diagram of an optional security inspection and early warning device according to an embodiment of the present invention;

[0019] Figure 9 FIG. 4 is a schematic structural diagram of an optional electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] According to one aspect of an embodiment of the present invention, a security inspection warning method is provided. Optionally, as an optional implementation, the security inspection warning method can be applied to, but is not limited to, Figure 1 in the environment shown.

[0023] Figure 1 In the example, terminal device 104 is responsible for human-computer interaction with user 102. Terminal device 104 includes memory 106, processor 108, and display 110. Terminal device 104 can interact with server 114 via network 112. Server 114 includes database 116 and processing engine 118. First image acquisition device 120 and second image acquisition device 122 interact with terminal device 104 via network 112. Both first and second image acquisition devices 120 and 122 can be connected to network 112 via wired or wireless modules. Terminal device 104 can display videos or images captured by first and second image acquisition devices 120 and 122 via display 110. Server 114 acquires the images or videos captured by first and second image acquisition devices 120 and 122 and stores them in database 116. Processing engine 118 can compare the images or videos captured by first and second image acquisition devices 120 and 122.

[0024] As another optional implementation, the above security warning method of the present application can be applied to Figure 2 In. Figure 2 As shown, human-computer interaction can be performed between user 202 and user device 204. User device 204 includes memory 206 and processor 208. In this embodiment, user device 204 can, but is not limited to, perform the operations performed by the terminal device 104 described above to identify and warn of dangerous actions of the security inspection object.

[0025] Optionally, in this embodiment, the terminal device 104 and user device 204 may be terminal devices configured with a target client, which may include, but are not limited to, at least one of the following: a mobile phone (such as an Android phone, an iOS phone, etc.), a laptop computer, a tablet computer, a PDA, an MID (Mobile Internet Device), a PAD, a desktop computer, a smart TV, etc. The target client may be a video client, an instant messaging client, a browser client, an educational client, etc. The first image acquisition device 120 and the second image acquisition device 122 may be cameras configured with wired or wireless modules. The network 112 may include, but is not limited to, a wired network and a wireless network, wherein the wired network includes a local area network, a metropolitan area network, and a wide area network, and the wireless network includes Bluetooth, Wi-Fi, and other networks that enable wireless communication. The server 114 may be a single server, a server cluster consisting of multiple servers, or a cloud server. The above is merely an example and is not limited in this embodiment.

[0026] Alternatively, as an optional implementation, as Figure 3 As shown, the above-mentioned security inspection warning method includes:

[0027] S302, obtaining first image information of the security inspection object currently captured by a first image capture device; wherein the first image capture device is used for video capture during the security inspection process;

[0028] S304, obtaining second image information of the inspection object captured by a second image capture device from a non-security inspection database, wherein the second image capture device is used for video capture during the non-security inspection process;

[0029] S306, comparing the security inspection object identified from the first image information with the security inspection object identified from the second image information;

[0030] S308 , when the comparison result indicates that the feature difference between the first limb movement feature of the security inspection object in the first image information and the second limb movement feature of the security inspection object in the second image information is greater than a preset threshold, it is indicated that the security inspection object is an abnormal object.

[0031] Optionally, in this embodiment, the above-described security inspection and warning method can be applied, but is not limited to, to the process of binding household devices in the Internet of Things. That is, multiple household devices to be bound can be managed on a management platform. These household devices may include, but are not limited to, humidifiers, air conditioners, robot vacuums, and the like. This is merely an example and is not intended to be limiting in this embodiment.

[0032] In step S302, in actual application, the first image acquisition device can be a camera connected via a wired or wireless module. The first image information can include multiple frames of pictures or videos of the current security inspection object. The video acquisition during the security inspection process can include the acquisition of images or videos of security personnel when passing through security inspection equipment such as security inspection doors or security inspection gates, which is not limited here.

[0033] In step S304, in actual application, the second image acquisition device can be a camera connected via a wired or wireless module, and the second image information can include multiple frames of pictures or videos of the current security inspection object. Video acquisition during non-security inspection processes can include but is not limited to capturing images or videos of security personnel before entering the security inspection door or security gate, which is not limited here.

[0034] In step S306, in actual application, the security inspection object identified from the first image information is compared with the above security inspection object identified from the second image information. That is, the image information of the current security inspection object is identified from the security inspection database, and the image information of the security inspection object is identified from the non-security inspection database, and the two are compared.

[0035] In step S308, in actual application, the first limb movement feature and the second limb movement feature may include but are not limited to movement features of the head, hands, elbows, shoulders, hips, knees, feet and other parts of the current security inspection object. When the comparison result indicates that the feature difference between the first limb movement feature of the security inspection object in the first image information and the second limb movement feature of the security inspection object in the second image information is greater than a preset threshold, that is, when the image information of the current security inspection object in the non-security inspection database and the image information in the security inspection database show a difference greater than a preset value, it can be judged that the current security inspection object is an abnormal object and may perform dangerous actions, which requires special attention.

[0036] In an embodiment of the present invention, a method is adopted in which first image information of a security inspection object currently captured by a first image capture device is obtained; wherein the first image capture device is used for video capture during the security inspection process; second image information of the security inspection object captured by a second image capture device is obtained from a non-security inspection database, wherein the second image capture device is used for video capture during the non-security inspection process; the security inspection object identified from the first image information is compared with the security inspection object identified from the second image information; when the result of the comparison indicates that the feature difference between the first limb movement feature of the security inspection object in the first image information and the second limb movement feature of the security inspection object in the second image information is greater than a preset threshold, the security inspection object is prompted to be an abnormal object. This method achieves the purpose of accurately and timely identifying dangerous actions during the security inspection process, thereby realizing the technical effect of improving the accuracy and timeliness of judging dangerous actions of personnel in security inspection places, and further solves the technical problem of low security inspection warning efficiency caused by inaccurate dangerous action recognition and delayed dangerous warning in related technologies.

[0037] In one embodiment, step S306 may include at least one of the following: determining a first elbow movement feature of the security inspection subject in the first image information and a second elbow movement feature of the security inspection subject in the second image information, wherein the first limb movement feature includes the first elbow movement feature of the security inspection subject, and the second limb movement feature includes the second elbow movement feature of the security inspection subject; and comparing the first elbow movement feature with the second elbow movement feature; wherein the first elbow movement feature and the second elbow movement feature both include an elbow movement amplitude and an elbow change angle; in this embodiment, by comparing the elbow movement amplitude and elbow change angle of the security inspection subject in the first image information with the elbow movement amplitude and elbow change angle in the second image information to determine the behavioral difference of the security inspection subject, a behavioral judgment basis can be provided for security inspection warning.

[0038] Determine a first knee motion feature of the security subject in the first image information and a second knee motion feature of the security subject in the second image information, wherein the first limb motion feature includes the first knee motion feature of the security subject and the second limb motion feature includes the second knee motion feature of the security subject; and compare the first knee motion feature with the second knee motion feature; wherein both the first knee motion feature and the second knee motion feature include knee motion amplitude and knee change angle. In this embodiment, by comparing the knee motion amplitude and knee change angle of the security subject in the first image information with the knee motion amplitude and knee change angle of the security subject in the second image information, behavioral differences of the security subject are determined, which can provide a behavioral judgment basis for security warning.

[0039] In one embodiment, determining a first elbow motion feature of the security inspection subject in the first image information and a second elbow motion feature of the security inspection subject in the second image information includes:

[0040] In a three-dimensional coordinate system constructed based on the body of the security inspection subject, the distance between the coordinates of the point where the security inspection subject's elbow is located in the first image information and the coordinate origin of the three-dimensional coordinate system is determined as the elbow motion amplitude in the first elbow motion feature, and the distance between the coordinates of the point where the security inspection subject's elbow is located in the second image information and the coordinate origin of the three-dimensional coordinate system is determined as the elbow motion amplitude in the second elbow motion feature; Figure 4 As shown, the range of motion of the elbow can be determined by calculating the distance between the elbow and the coordinate origin.

[0041] The angle between the vector corresponding to the first arm of the security inspection object in the first image information and the vector corresponding to the second arm is determined as the elbow change angle in the first elbow motion feature, and the angle between the vector corresponding to the first arm of the security inspection object in the second image information and the vector corresponding to the second arm is determined as the elbow change angle in the second elbow motion feature; in this embodiment, the first arm can be the upper arm of the human body, and the second arm can be the forearm of the human body; or the first arm can be the forearm of the human body, and the second arm can be the upper arm of the human body, such as Figure 4 As shown, the change angle of the elbow can be determined by the angle between the upper arm and the forearm of the human body.

[0042] In one embodiment, determining a first knee motion feature of the security inspection subject in the first image information and a second knee motion feature of the security inspection subject in the second image information includes:

[0043] In a three-dimensional coordinate system constructed based on the body of the security inspection subject, the distance between the coordinates of the point where the security inspection subject's knee is located in the first image information and the coordinate origin of the three-dimensional coordinate system is used as the knee motion amplitude in the first knee motion feature, and the distance between the coordinates of the point where the security inspection subject's knee is located in the second image information and the coordinate origin of the three-dimensional coordinate system is used as the knee motion amplitude in the second knee motion feature; Figure 4 As shown, the range of motion of the knee can be determined by calculating the distance between the knee and the coordinate origin.

[0044] The angle between the vector corresponding to the first leg of the security subject in the first image information and the vector corresponding to the second leg is used as the knee change angle in the first knee motion feature, and the angle between the vector corresponding to the first leg of the security subject in the second image information and the vector corresponding to the second leg is used as the knee change angle in the second knee motion feature. Figure 4 As shown, the change in the knee angle can be determined by the angle between the upper arm and the forearm of the human body.

[0045] In one embodiment, comparing the first elbow motion feature with the second elbow motion feature includes at least one of the following:

[0046] The curvature of a first curve formed by the left elbow movement amplitude and the left elbow angle of the security subject in the first image information in the first plane coordinate system is obtained respectively, and the curvature of a second curve formed by the left elbow movement amplitude and the left elbow angle of the security subject in the first image information in the first plane coordinate system is obtained, and the curvature of the first curve is compared with the curvature of the second curve; in this example, Figure 5 As shown, a first plane coordinate system can be established with the movement amplitude of the left elbow as the horizontal coordinate and the movement angle of the left elbow as the vertical coordinate. In the first image information, the movement amplitude and angle of the left elbow of the security subject at different times form a first curve; in the second image information, the movement amplitude and angle of the left elbow of the security subject at different times form a second curve; and then the curvatures of the first curve and the second curve are compared.

[0047] The curvature of a third curve formed by the right elbow movement amplitude and the right elbow angle of the security subject in the first image information in the second plane coordinate system is obtained respectively, and the curvature of a fourth curve formed by the right elbow movement amplitude and the right elbow angle of the security subject in the second image information in the second plane coordinate system is obtained, and the curvature of the third curve is compared with the curvature of the fourth curve; in this example, Figure 5 As shown, a first plane coordinate system can be established with the movement amplitude of the right elbow as the horizontal coordinate and the movement angle of the right elbow as the vertical coordinate. In the first image information, the movement amplitude and the angle of the right elbow of the security subject at different times form a third curve; in the second image information, the movement amplitude and the angle of the right elbow of the security subject at different times form a fourth curve; and then the curvatures of the third curve and the fourth curve are compared.

[0048] In one embodiment, comparing the first elbow motion feature with the second elbow motion feature includes at least one of the following:

[0049] The curvature of a fifth curve formed by the left knee motion amplitude and the left knee angle of the security subject in the first image information in the third plane coordinate system is obtained respectively, and the curvature of a sixth curve formed by the left knee motion amplitude and the left knee angle of the security subject in the second image information in the third plane coordinate system is obtained; the curvature of the fifth curve is compared with the curvature of the sixth curve; in this example, Figure 5As shown, a first plane coordinate system can be established with the movement amplitude of the left knee as the horizontal coordinate and the movement angle of the left knee as the vertical coordinate. In the first image information, the movement amplitude and angle of the left knee of the security subject at different times form a fifth curve; in the second image information, the movement amplitude and angle of the left knee of the security subject at different times form a sixth curve; and then the curvature of the fifth curve is compared with the curvature of the sixth curve.

[0050] The curvature of the seventh curve formed by the right knee motion amplitude and right knee angle of the right knee of the security subject in the first image information in the fourth plane coordinate system is obtained respectively, and the curvature of the eighth curve formed by the right knee motion amplitude and right knee angle of the right knee of the security subject in the second image information in the fourth plane coordinate system is obtained respectively; the curvature of the third curve is compared with the curvature of the fourth curve. In this example, if Figure 5 As shown, a first plane coordinate system can be established with the movement amplitude of the right knee as the horizontal coordinate and the movement angle of the right knee as the vertical coordinate. In the first image information, the movement amplitude and the right knee angle of the right knee of the security subject at different times form a seventh curve; in the second image information, the movement amplitude and the right knee angle of the right knee of the security subject at different times form an eighth curve; and then the curvatures of the seventh curve and the eighth curve are compared.

[0051] In one embodiment, step S308 includes at least one of the following:

[0052] When the comparison result indicates that the difference between the curvature of the first curve and the curvature of the second curve is greater than a preset threshold, it is indicated that the security inspection object is an abnormal object;

[0053] When the comparison result indicates that the difference between the curvature of the third curve and the curvature of the fourth curve is greater than a preset threshold, it is indicated that the security inspection object is an abnormal object;

[0054] When the comparison result indicates that the difference between the curvature of the fifth curve and the curvature of the sixth curve is greater than a preset threshold, it is indicated that the security inspection object is an abnormal object;

[0055] When the comparison result indicates that the difference between the curvature of the seventh curve and the curvature of the eighth curve is greater than a preset threshold, it is suggested that the security inspection object is an abnormal object.

[0056] In this embodiment, that is, when there is an obvious difference between the first image information and the second image information in either the elbow or the knee of the security inspection object, it can be determined that the current security inspection object is an abnormal object.

[0057] In one embodiment, a first area formed by a first curve and a first plane coordinate system is obtained; and a second area formed by a second curve and the first plane coordinate system is obtained;

[0058] Obtaining a third area formed by the third curve and the second plane coordinate system; and a fourth area formed by the fourth curve and the second plane coordinate system;

[0059] Obtaining a fifth area formed by the fifth curve and the third plane coordinate system; and a sixth area formed by the sixth curve and the third plane coordinate system;

[0060] Obtain a seventh area formed by the seventh curve and the fourth plane coordinate system; and an eighth area formed by the eighth curve and the fourth plane coordinate system;

[0061] When the comparison result indicates that the difference between the first limb movement feature of the security inspection object in the first image information and the second limb movement feature of the security inspection object in the second image information is greater than a preset threshold, it is indicated that the security inspection object is an abnormal object, and at least one of the following is also included:

[0062] When the comparison result indicates that the difference between the first area and the second area is greater than a preset threshold, it is prompted that the security inspection object is an abnormal object;

[0063] When the comparison result indicates that the difference between the third area and the fourth area is greater than a preset threshold, it is prompted that the security inspection object is an abnormal object;

[0064] When the comparison result indicates that the difference between the fifth area and the sixth area is greater than a preset threshold, it is indicated that the security inspection object is an abnormal object;

[0065] When the comparison result indicates that the difference between the seventh area and the eighth area is greater than a preset threshold, it is suggested that the security inspection object is an abnormal object.

[0066] Through the above technical means, it is possible to timely and accurately determine whether the security inspection object is an abnormal object and whether an early warning prompt is required.

[0067] In one embodiment, after step S308, at least one of the following is further included:

[0068] When the comparison result indicates that the difference between the curvature of the first curve and the curvature of the second curve is greater than a preset threshold, it is prompted that the left elbow of the security inspected person is in an abnormal position;

[0069] When the comparison result indicates that the difference between the curvature of the third curve and the curvature of the fourth curve is greater than a preset threshold, it is indicated that the right elbow of the subject is in an abnormal position;

[0070] When the comparison result indicates that the difference between the curvature of the fifth curve and the curvature of the sixth curve is greater than a preset threshold, it is indicated that the left knee of the subject is in an abnormal position;

[0071] When the comparison result indicates that the difference between the curvature of the seventh curve and the curvature of the eighth curve is greater than a preset threshold, it is suggested that the right knee of the security inspection subject is in an abnormal position.

[0072] Through the above technical means, the abnormal positions corresponding to security inspection objects with dangerous behaviors can be warned and displayed in a timely and accurate manner.

[0073] In one embodiment, step S304 includes comparing the head portrait information of the security subject with the head portrait information stored in the non-security database; and determining the corresponding second image information of the security subject in the non-security database based on the comparison result. In this embodiment, the current security subject is identified from the non-security database through head portrait recognition, and the video or image information of the current security subject in the non-security database can be obtained.

[0074] In one embodiment, the security inspection warning method further includes: if the inspected object is determined to be an abnormal object, storing the first image information of the inspected object in a security inspection verification database; if the inspected object is determined to be normal, deleting the first and second image information corresponding to the inspected object. In other words, if the inspected object is determined to be an abnormal object, the image information of the inspected object during the inspection process is stored in the security inspection verification database, which can be further verified with the current inspected object in the non-inspection database.

[0075] In one embodiment, a three-dimensional coordinate system is constructed based on the body of the security inspection object, such as Figure 4 As shown, it includes: constructing a three-dimensional coordinate system with the head of the security inspection object as the coordinate origin, the direction parallel to the security inspection object's body as the x-axis, the direction perpendicular to the security inspection object's body as the y-axis, and the forward direction of the security inspection object's body as the z-axis.

[0076] In an embodiment of the present invention, a method is adopted in which first image information of a security inspection object currently captured by a first image capture device is obtained; wherein the first image capture device is used for video capture during the security inspection process; second image information of the security inspection object captured by a second image capture device is obtained from a non-security inspection database, wherein the second image capture device is used for video capture during the non-security inspection process; the security inspection object identified from the first image information is compared with the security inspection object identified from the second image information; when the result of the comparison indicates that the feature difference between the first limb movement feature of the security inspection object in the first image information and the second limb movement feature of the security inspection object in the second image information is greater than a preset threshold, the security inspection object is prompted to be an abnormal object. This method achieves the purpose of accurately and timely identifying dangerous actions during the security inspection process, thereby realizing the technical effect of improving the accuracy and timeliness of judging dangerous actions of personnel in security inspection places, and further solves the technical problem of low security inspection warning efficiency caused by inaccurate dangerous action recognition and delayed dangerous warning in related technologies.

[0077] Based on the above embodiments, in one embodiment, in the security early warning method described above, a monitoring system is installed in locations requiring security checks, such as stations and airports. This monitoring system is networked with all cameras and can obtain all monitoring data in real time. Cameras are divided into two categories: security cameras and non-security cameras. Non-security cameras are installed on the main thoroughfares that people need to pass through to enter the station building. They are primarily used for facial recognition, body movement analysis, and other personnel data modeling before security checks. Security cameras are installed in front of security gates or turnstiles to collect and analyze the body movement data of people being checked during security checks.

[0078] The monitoring system is equipped with a body movement analysis algorithm module, which can exist at the front end (camera end) or the back end (i.e., server end).

[0079] In one embodiment, when the body movement analysis algorithm module is in the front-end, the camera first generates a person model for each person detected in the video. The model data includes facial data and body movement data. This model data is then transmitted to the back-end in real time and inserted into the model database. As the person (security inspection subject) passes through other non-security inspection cameras, the camera continuously analyzes the person's movements and updates the model data in the database in real time. The longer the monitoring time, the more accurate the body movement data.

[0080] Finally, as people begin lining up for security checks, security cameras analyze their current body movement data and upload it to the security system. The system's suspicion analysis module analyzes the differences between the body movement data before and during the checkpoint, further analyzing the changes in the range of motion models of major joints—the elbow, shoulder, hip, and knee. This data is then reported to the security personnel in real time. The greater the overall body movement differences, the more suspicious the person is. This data is also reported, along with changes in the motion models of individual joints, alerting security personnel to key areas of the person's body and providing a warning of danger.

[0081] In one embodiment, if Figure 6 As shown, when the body movement model analysis algorithm module is on the backend (i.e., server), the camera is solely responsible for video data acquisition, while the backend server processes the video data, including facial and body movement data. The backend server categorizes the body movement model data into two categories, depending on whether it is security inspection data or not, and inserts the data into different model databases based on the different categories. The Suspicion Analysis Module analyzes the differences in the model data for the same person in the two databases and pushes the analysis results to security personnel in real time. Upon completion of the personnel inspection, if the inspection process was normal, the relevant model data is deleted; if it was abnormal, the relevant monitoring analysis data is archived.

[0082] Figure 6 The limb motion analysis algorithm model is at the back end (i.e., the server end). When the limb motion analysis algorithm model is at the front end, that is, each camera has a limb motion analysis algorithm model, but there is no such model in the monitoring system.

[0083] In one embodiment, the above-mentioned security inspection warning method may include the following steps: step S702, a non-security inspection camera collects video data; step S704, performs facial analysis and body movement analysis on the person in the video; step S706, inserts or updates the non-security inspection database; step S708, a security inspection camera collects video data; step S710, performs facial analysis and body movement analysis on the person in the video; step S712, inserts or updates the security inspection database; step S714, a suspicious analysis module compares the non-security inspection database and the security inspection database for the same person, and analyzes to obtain the difference of body movement model data and specific joint motion amplitude model data; then proceeds to step S716, reports to the security inspection personnel, step S718, determines whether the current data is normal; step S720, if the security inspection is suspicious, archives the specific person analysis information, and step S722, if the security inspection is normal, deletes the specific person analysis information.

[0084] In one embodiment, the limb difference calculation method of the above-mentioned security inspection warning method can be implemented by the following method:

[0085] The calculation process is based on a deep learning model of limb movements, which can provide the coordinate values ​​of the human body's shoulders, elbows, hands, hips, knees, and feet in three-dimensional coordinates with the head as the zero point during movement.

[0086] like Figure 4 As shown, the vertical direction is the y-axis, the forward direction is the z-axis, and the direction parallel to the human body is the x-axis. The limb movement deep learning model gives the following during the movement:

[0087] Right shoulder coordinates sR (x, y, z), left shoulder coordinates sL (x, y, z)

[0088] Right elbow coordinates eR (x, y, z), left elbow coordinates eL (x, y, z)

[0089] Right hand coordinates haR (x, y, z), left hand coordinates haL (x, y, z)

[0090] Right hip coordinates hiR (x, y, z), left hip coordinates hiL (x, y, z)

[0091] Right knee coordinates kR (x, y, z), left knee coordinates kL (x, y, z)

[0092] Right foot coordinates fR (x, y, z), left foot coordinates fL (x, y, z)

[0093] Based on these coordinate data, we can calculate the linear relationship between the limb movement amplitude and the joint (elbow, knee) bending angle during human movement.

[0094] first step:

[0095] The relationship between the elbow angle and the range of motion: Re-L (left elbow) can be identified as Angle-eL or Length-eL; Re-R (right elbow) can be identified as Angle-eR or Length-eR;

[0096] The relationship between the knee angle and the range of motion of the knee: Rk-L (left knee) can be identified as Angle-kL or Length-kL; Rk-R (right knee) can be identified as Angle-kR or Length-kR;

[0097] The calculation process for the four relationships above, namely left elbow, right elbow, left knee, and right knee, is similar, as shown below:

[0098] (1) First, the range of motion in the relationship:

[0099]

[0100]

[0101]

[0102]

[0103] Where: Length-eL: left elbow range of motion;

[0104] Length-eR: right elbow range of motion;

[0105] Length-kL: left knee range of motion;

[0106] Length-kR: right knee range of motion;

[0107] x and z are coordinate values, such as eL represents the coordinate of the left elbow.

[0108] (2) Recalculate the angle value in the relationship

[0109] The elbow angle is the angle between the forearm and upper arm, and the knee angle is the angle between the calf and thigh.

[0110] The calculation process takes the left elbow angle as an example, as shown below:

[0111] First calculate the vectors on both sides:

[0112] Upper arm vector: sL-eL=(x eL -x sL ,y eL -y sL ,z eL -z sL )

[0113] Lower arm vector: haL-eL=(x eL -x haL ,y eL -y haL ,z eL -z haL )

[0114] Calculate the vector angle again and you can get the left elbow angle:

[0115]

[0116] Similarly, the right elbow angle can be calculated:

[0117]

[0118] Left knee angle:

[0119]

[0120] Right knee angle:

[0121]

[0122] Step 2:

[0123] In this way, during the character's movement, the deep body movement learning model will output the data corresponding to Angle-eL and Length-eL throughout the entire process.

[0124] The Length-eL value ranges from Length-eL(min) to L(max) (i.e., the range from the minimum value to the maximum value); the Angle-eL value ranges from Angle-eL(min) to Angle-eL(max) (i.e., the range from the minimum value to the maximum value);

[0125] Step 3:

[0126] Plot the above data as Figure 5 Schematic diagram of the coordinate axes and curves shown.

[0127] The horizontal axis is the specific movement of the left elbow, and the vertical axis is the angle of the left elbow. In the example, the movement distance is 0-20cm.

[0128] The angle range is 90-180°.

[0129] Curve Q1 is obtained by analyzing and calculating the data collected by non-security cameras.

[0130] Curve Q2 is obtained by analyzing and calculating the data collected by the security camera.

[0131] Define the area formed by the relationship curve collected by the non-security inspection camera and the coordinate system as S1; the area formed by the relationship curve collected by the security inspection camera and the coordinate system as S2;

[0132] The area can be approximately equal to the sum of Angle-eL(min) to Angle-eL(max) corresponding to each interval unit Length-eL.

[0133] S=Angle-eL(1)+Angle-eL(2)+……+Angle-eL(N);

[0134] Left elbow difference

[0135] This way, we can find the difference in the left elbow's movement. Similarly, we can find the difference in the right elbow's DeR, left knee's DkL, and right knee's DkR.

[0136] Step 4: The normal difference value of the person D = DeL + DeR + DkL + DkR; when D is greater than a certain value, an alarm is generated.

[0137] Similarly, if a single value of DeL, DeR, DkL, or DkR is greater than a certain value, an alarm will be generated to pay attention to a certain part of the body.

[0138] The embodiment of the present invention utilizes the principle that people's body movements change in different environments or with different mental states. When people are nervous or about to make any movement, local muscles will tense up, causing changes in movement when walking, such as a smaller swing amplitude of the upper limbs, stiffness of the elbow and shoulder joints, etc. By using a monitoring system, the movement postures of people are collected in different environments, and the body movement calculation module is used to calculate the difference in body movements of people in the situations of no security check and during security check. The higher the difference, the higher the suspicion. At the same time, the security personnel are provided with the difference in the range of motion of the main joints of the people being checked, which provides a reference for security checks.

[0139] Using a networked monitoring system, we compare and analyze changes in a person's body movements before and during entry, in sparsely populated and densely populated areas, and before and during security checks to assess whether they are suspicious. This information provides security personnel with the difference between the inspected and uninspected states of each key joint, providing a reference for targeted inspections and providing a certain degree of risk prevention.

[0140] By analyzing changes in body movements, the present invention can provide early warnings before security checks are conducted. This overcomes the lag inherent in previous systems, where warnings are only triggered when dangerous movements occur. It also overcomes the limitation of masks that cannot detect dangerous expressions. Furthermore, the present invention provides security personnel with detailed data on changes in body joint movement in real time, providing a reference for these personnel and speeding up security checks. Furthermore, the warnings provide them with a clear message, improving their safety.

[0141] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that the present invention is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0142] According to another aspect of the embodiments of the present invention, a security inspection warning device for implementing the above security inspection warning method is also provided. Figure 8 As shown, the device includes:

[0143] The first acquisition unit 802 is configured to acquire first image information of the security inspection object currently acquired by a first image acquisition device; wherein the first image acquisition device is used for video acquisition during the security inspection process;

[0144] A second acquiring unit 804 is configured to acquire, from a non-security inspection database, second image information of the inspection object captured by a second image acquisition device, wherein the second image acquisition device is used for video capture during the non-security inspection process;

[0145] a comparison unit 806, configured to compare the security inspection object identified from the first image information with the security inspection object identified from the second image information;

[0146] The prompting unit 808 is used to prompt that the security inspection object is an abnormal object when the comparison result indicates that the feature difference between the first limb movement feature of the security inspection object in the first image information and the second limb movement feature of the security inspection object in the second image information is greater than a preset threshold.

[0147] In an embodiment of the present invention, the first image acquisition device may be a camera connected via a wired or wireless module. The first image information may include multiple frames of pictures or videos of the current security inspection object. Video acquisition during the security inspection process may include capturing images or videos of security personnel when passing through security inspection equipment such as security inspection doors or security inspection gates, which is not limited here.

[0148] In an embodiment of the present invention, in actual application, the second image acquisition device can be a camera connected via a wired or wireless module, and the second image information can include multiple frames of pictures or videos of the current security inspection object. Video acquisition during non-security inspection processes can include but is not limited to the acquisition of images or videos of security personnel before entering the security inspection door or security inspection gate, which is not limited here.

[0149] In an embodiment of the present invention, in actual application, the security inspection object identified from the first image information is compared with the above-mentioned security inspection object identified from the second image information. That is, the image information of the current security inspection object is identified from the security inspection database, and the image information of the security inspection object is identified from the non-security inspection database, and the two are compared.

[0150] In an embodiment of the present invention, in actual application, the first limb movement feature and the second limb movement feature may include but are not limited to movement features of the head, hands, elbows, shoulders, hips, knees, feet and other parts of the current security inspection object. When the comparison result indicates that the feature difference between the first limb movement feature of the security inspection object in the first image information and the second limb movement feature of the security inspection object in the second image information is greater than a preset threshold, that is, when the image information of the current security inspection object in the non-security inspection database and the image information in the security inspection database show a difference greater than a preset value, it can be judged that the current security inspection object is an abnormal object and may perform dangerous actions, which requires special attention.

[0151] In an embodiment of the present invention, a method is adopted in which first image information of a security inspection object currently captured by a first image capture device is obtained; wherein the first image capture device is used for video capture during the security inspection process; second image information of the security inspection object captured by a second image capture device is obtained from a non-security inspection database, wherein the second image capture device is used for video capture during the non-security inspection process; the security inspection object identified from the first image information is compared with the security inspection object identified from the second image information; when the result of the comparison indicates that the feature difference between the first limb movement feature of the security inspection object in the first image information and the second limb movement feature of the security inspection object in the second image information is greater than a preset threshold, the security inspection object is prompted to be an abnormal object, thereby achieving the purpose of accurately and timely identifying dangerous actions during the security inspection process, thereby realizing the technical effect of improving the accuracy and timeliness of judging dangerous actions of personnel in security inspection places, and further solving the technical problem of low security inspection warning efficiency caused by inaccurate dangerous action recognition and delayed dangerous warning in related technologies.

[0152] According to another aspect of the embodiment of the present invention, an electronic device for implementing the above-mentioned security inspection warning method is also provided. The electronic device can be Figure 1 The terminal device or server shown. Figure 9 As shown, the electronic device includes a memory 902 and a processor 904. The memory 902 stores a computer program, and the processor 904 is configured to execute the steps in any of the above method embodiments through the computer program.

[0153] Optionally, in this embodiment, the electronic device may be located in at least one network device among a plurality of network devices of a computer network.

[0154] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0155] S1, obtaining first image information of the security inspection object currently captured by a first image acquisition device; wherein the first image acquisition device is used for video capture during the security inspection process;

[0156] S2, obtaining second image information of the inspection object captured by a second image acquisition device from a non-security inspection database, wherein the second image acquisition device is used for video acquisition during the non-security inspection process;

[0157] S3, comparing the security inspection object identified from the first image information with the security inspection object identified from the second image information;

[0158] S4. When the comparison result indicates that the difference between the first limb movement feature of the security inspection object in the first image information and the second limb movement feature of the security inspection object in the second image information is greater than a preset threshold, it is indicated that the security inspection object is an abnormal object.

[0159] Alternatively, those skilled in the art will appreciate that Figure 9 The structure shown is for illustration only, and the electronic device or electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (MID), a PAD, or other electronic devices. Figure 9 It does not limit the structure of the electronic device. For example, the electronic device may also include Figure 9 More or fewer components (such as network interfaces, etc.) as shown in, or with Figure 9 Different configurations shown.

[0160] Among them, the memory 902 can be used to store software programs and modules, such as the program instructions / modules corresponding to the security warning method and device in the embodiment of the present invention. The processor 904 executes various functional applications and data processing by running the software programs and modules stored in the memory 902, that is, realizing the above-mentioned security warning method. The memory 902 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 902 may further include a memory remotely located relative to the processor 904, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned networks include but are not limited to the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Among them, the memory 902 can be used specifically, but not limited to, to store information such as videos or images of virtual security inspection objects. As an example, if Figure 9 As shown, the memory 902 may include, but is not limited to, the first acquisition unit 802, the second acquisition unit 804, the comparison unit 806, and the prompt unit 808 of the security inspection and early warning device. In addition, it may also include, but is not limited to, other module units of the security inspection and early warning device, which will not be repeated in this example.

[0161] Optionally, the transmission device 909 is used to receive or send data via a network. Specific examples of the network may include wired networks and wireless networks. In one embodiment, the transmission device 909 includes a network interface controller (NIC), which can be connected to other network devices and a router via a network cable to communicate with the Internet or a local area network. In one embodiment, the transmission device 909 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0162] In addition, the electronic device further includes: a display 908 for displaying the video or image information of the security inspection object; and a connection bus 910 for connecting various module components in the electronic device.

[0163] In other embodiments, the terminal device or server may be a node in a distributed system, wherein the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting multiple nodes through network communication. The nodes may form a peer-to-peer (P2P) network, and any computing device, such as a server, terminal, or other electronic device, may become a node in the blockchain system by joining the peer-to-peer network.

[0164] According to another aspect of the embodiments of the present invention, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the steps of any of the above method embodiments when run.

[0165] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0166] S1, obtaining first image information of the security inspection object currently captured by a first image acquisition device; wherein the first image acquisition device is used for video capture during the security inspection process;

[0167] S2, obtaining second image information of the inspection object captured by a second image acquisition device from a non-security inspection database, wherein the second image acquisition device is used for video acquisition during the non-security inspection process;

[0168] S3, comparing the security inspection object identified from the first image information with the security inspection object identified from the second image information;

[0169] S4. When the comparison result indicates that the difference between the first limb movement feature of the security inspection object in the first image information and the second limb movement feature of the security inspection object in the second image information is greater than a preset threshold, it is indicated that the security inspection object is an abnormal object.

[0170] Optionally, in this embodiment, a person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing the hardware related to the terminal device through a program, and the program may be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0171] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0172] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above-mentioned computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing one or more computer devices (such as personal computers, servers, or network devices) to execute all or part of the steps of the methods of various embodiments of the present invention.

[0173] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0174] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is merely a logical functional division. In actual implementation, there may be other division methods, such as combining or integrating multiple units or components into another system, or ignoring or not implementing some features. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interface, indirect coupling or communication connection of units or modules, and may be electrical or other forms.

[0175] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0176] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0177] The above are only preferred embodiments of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A security inspection early warning method, characterized in that: include: Acquire first image information of a current security inspection object captured by a first image capture device deployed in a target location during a security inspection process; obtaining, from a non-security inspection database, second image information captured by a second image acquisition device on the current security inspection object, the second image acquisition device being used to capture video of multiple security inspection objects during a non-security inspection process in the target location, the multiple security inspection objects including the current security inspection object; If the difference between the motion characteristics of the limb of the current security inspection object in the first image information and the motion characteristics of the limb of the current security inspection object in the second image information is greater than a preset threshold, prompting the current security inspection object as an abnormal object and storing the first image information of the current security inspection object in the security inspection verification database; If a comparison result between the current security inspection object identified in the first image information and the current security inspection object identified from the second image information does not meet a target condition, deleting the first image information and the second image information; The object's limbs include knees and elbows, the motion features include motion amplitude and change angle, the feature difference includes area difference, the area difference is determined based on the feature description area corresponding to the first image information and the feature description area corresponding to the second image information, the feature description area is determined based on a motion description curve and a plane coordinate system, the motion amplitude and the change angle form the motion description curve in the plane coordinate system, and the motion amplitude and the change angle are determined based on a three-dimensional coordinate system constructed by the body of the current security inspection object.

2. The method according to claim 1, characterized in that After obtaining the second image information of the current security inspection object captured by the second image capture device from the non-security inspection database, the method further includes: determining a first elbow motion feature of the current security inspection subject in the first image information and a second elbow motion feature of the current security inspection subject in the second image information; and comparing the first elbow motion feature with the second elbow motion feature; Determine a first knee motion feature of the current security inspection subject in the first image information and a second knee motion feature of the current security inspection subject in the second image information; and compare the first knee motion feature with the second knee motion feature.

3. The method according to claim 2, characterized in that Determining the first elbow motion feature of the current security inspection subject in the first image information and the second elbow motion feature of the current security inspection subject in the second image information includes: In the three-dimensional coordinate system constructed based on the body of the current security inspection subject, determining the distance between the coordinates of the point where the elbow of the current security inspection subject is located in the first image information and the coordinate origin of the three-dimensional coordinate system as the elbow motion amplitude in the first elbow motion feature, and determining the distance between the coordinates of the point where the elbow of the current security inspection subject is located in the second image information and the coordinate origin of the three-dimensional coordinate system as the elbow motion amplitude in the second elbow motion feature; determining the angle between the vector corresponding to the first arm and the vector corresponding to the second arm of the current security inspection subject in the first image information as the elbow change angle in the first elbow motion feature, and determining the angle between the vector corresponding to the first arm and the vector corresponding to the second arm of the current security inspection subject in the second image information as the elbow change angle in the second elbow motion feature; Determining a first knee motion feature of the current security inspection subject in the first image information and a second knee motion feature of the current security inspection subject in the second image information includes: In a three-dimensional coordinate system constructed based on the body of the current security inspection subject, the distance between the coordinates of the current security inspection subject's knee in the first image information and the coordinate origin of the three-dimensional coordinate system is used as the knee motion amplitude in the first knee motion feature, and the distance between the coordinates of the current security inspection subject's knee in the second image information and the coordinate origin of the three-dimensional coordinate system is used as the knee motion amplitude in the second knee motion feature; The angle between the vector corresponding to the first leg and the vector corresponding to the second leg of the current security inspection subject in the first image information is used as the knee change angle in the first knee motion feature, and the angle between the vector corresponding to the first leg and the vector corresponding to the second leg of the current security inspection subject in the second image information is used as the knee change angle in the second knee motion feature.

4. The method according to claim 2, characterized in that The comparing the first elbow motion feature with the second elbow motion feature comprises at least one of the following: respectively obtaining a curvature of a first curve formed by the left elbow motion amplitude and the left elbow angle of the current security inspection subject in the first image information in a first plane coordinate system, and a curvature of a second curve formed by the left elbow motion amplitude and the left elbow angle of the current security inspection subject in the first image information in the first plane coordinate system, and comparing the curvatures of the first curve and the second curve; respectively obtaining a curvature of a third curve formed by the right elbow motion amplitude and the right elbow angle of the current security inspection subject in the first image information in the second plane coordinate system, and a curvature of a fourth curve formed by the right elbow motion amplitude and the right elbow angle of the current security inspection subject in the second image information in the second plane coordinate system, and comparing the curvature of the third curve with the curvature of the fourth curve; The comparing the first elbow motion feature with the second elbow motion feature comprises at least one of the following: respectively obtaining the curvature of a fifth curve formed by the left knee motion amplitude and the left knee angle of the current security inspection subject in the first image information in a third plane coordinate system, and obtaining the curvature of a sixth curve formed by the left knee motion amplitude and the left knee angle of the current security inspection subject in the second image information in the third plane coordinate system; and comparing the curvature of the fifth curve with the curvature of the sixth curve; Obtain the curvature of a seventh curve formed by the right knee motion amplitude and the right knee angle of the right knee of the current security inspection subject in the first image information in a fourth plane coordinate system, and obtain the curvature of an eighth curve formed by the right knee motion amplitude and the right knee angle of the right knee of the current security inspection subject in the second image information in the fourth plane coordinate system; and compare the curvature of the third curve with the curvature of the fourth curve.

5. The method according to claim 4, characterized in that When a comparison result between the current security inspection object identified in the first image information and the current security inspection object identified from the second image information meets a target condition, prompting that the current security inspection object is an abnormal object includes at least one of the following: When the comparison result indicates that the difference between the curvature of the first curve and the curvature of the second curve is greater than a preset threshold, it is prompted that the current security inspection object is an abnormal object; When the comparison result indicates that the difference between the curvature of the third curve and the curvature of the fourth curve is greater than a preset threshold, it is prompted that the current security inspection object is an abnormal object; When the comparison result indicates that the difference between the curvature of the fifth curve and the curvature of the sixth curve is greater than a preset threshold, it is prompted that the current security inspection object is an abnormal object; When the comparison result indicates that the difference between the curvature of the seventh curve and the curvature of the eighth curve is greater than a preset threshold, it is suggested that the current security inspection object is an abnormal object.

6. The method according to claim 4, characterized in that The method further comprises: Obtaining a first area formed by the first curve and the first plane coordinate system; and a second area formed by the second curve and the first plane coordinate system; obtaining a third area formed by the third curve and the second plane coordinate system; and a fourth area formed by the fourth curve and the second plane coordinate system; obtaining a fifth area formed by the fifth curve and the third plane coordinate system; and a sixth area formed by the sixth curve and the third plane coordinate system; obtaining a seventh area formed by the seventh curve and the fourth plane coordinate system; and an eighth area formed by the eighth curve and the fourth plane coordinate system; When a comparison result between the current security inspection object identified in the first image information and the current security inspection object identified from the second image information meets a target condition, prompting that the current security inspection object is an abnormal object further includes at least one of the following: When the comparison result indicates that the difference between the first area and the second area is greater than a preset threshold, it is prompted that the current security inspection object is an abnormal object; When the comparison result indicates that the difference between the third area and the fourth area is greater than a preset threshold, it is prompted that the current security inspection object is an abnormal object; When the comparison result indicates that the difference between the fifth area and the sixth area is greater than a preset threshold, it is prompted that the current security inspection object is an abnormal object; When the comparison result indicates that the difference between the seventh area and the eighth area is greater than a preset threshold, it is suggested that the current security inspection object is an abnormal object.

7. The method according to any one of claims 4 to 5, characterized in that After the prompting that the current security inspection object is an abnormal object, the method further includes at least one of the following: When the comparison result indicates that the difference between the curvature of the first curve and the curvature of the second curve is greater than a preset threshold, it is prompted that the left elbow of the current security inspection subject is in an abnormal position; When the comparison result indicates that the difference between the curvature of the third curve and the curvature of the fourth curve is greater than a preset threshold, it is prompted that the right elbow of the current security inspection object is in an abnormal position; When the comparison result indicates that the difference between the curvature of the fifth curve and the curvature of the sixth curve is greater than a preset threshold, it is indicated that the left knee of the current security inspection subject is in an abnormal position; When the comparison result indicates that the difference between the curvature of the seventh curve and the curvature of the eighth curve is greater than a preset threshold, it is suggested that the right knee of the current security inspection object is in an abnormal position.

8. The method according to claim 1, characterized in that The acquiring, from the non-security inspection database, second image information captured by the second image acquisition device on the current security inspection object includes: Comparing the head portrait information of the current security inspection object with the head portrait information stored in the non-security inspection database; Based on the comparison result, the corresponding second image information of the current security inspection object in the non-security inspection database is determined.

9. The method according to claim 3, characterized in that The three-dimensional coordinate system constructed based on the body of the current security inspection object includes: The three-dimensional coordinate system is constructed with the head of the current security inspection object as the coordinate origin, the direction parallel to the body of the current security inspection object as the x-axis, the direction perpendicular to the body of the current security inspection object as the y-axis, and the forward direction of the body of the current security inspection object as the z-axis.

10. A security inspection early warning device, characterized in that: include: A first acquisition unit is configured to acquire first image information captured by a first image acquisition device disposed in a target location on a current security inspection object during a security inspection process; a second acquiring unit, configured to acquire, from a non-security inspection database, second image information captured by a second image acquisition device on the current security inspection subject, the second image acquisition device being configured to capture video of a plurality of security inspection subjects during a non-security inspection process in the target location, the plurality of security inspection subjects including the current security inspection subject; a prompting unit, configured to, if a difference between a motion feature of a limb of the current security inspection object in the first image information and a motion feature of the limb of the current security inspection object in the second image information is greater than a preset threshold, prompt the current security inspection object as an abnormal object, and store the first image information of the current security inspection object in a security inspection verification database; If a comparison result between the current security inspection object identified in the first image information and the current security inspection object identified from the second image information does not meet a target condition, deleting the first image information and the second image information; The object's limbs include knees and elbows, the motion features include motion amplitude and change angle, the feature difference includes area difference, the area difference is determined based on the feature description area corresponding to the first image information and the feature description area corresponding to the second image information, the feature description area is determined based on a motion description curve and a plane coordinate system, the motion amplitude and the change angle form the motion description curve in the plane coordinate system, and the motion amplitude and the change angle are determined based on a three-dimensional coordinate system constructed by the body of the current security inspection object.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 9 when executed.

12. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 9 through the computer program.

Images