Metal locating methods, devices, storage media, and security gates for use in security inspection gates.

Abstract

This invention discloses a metal positioning method, device, storage medium, and security gate for use in security gates. The security gate includes a metal positioning system and a display module. The metal positioning system includes a main control unit, a height detection module, and a metal detection module. The method is applied to the main control unit and includes: receiving height data of the object to be measured from the height detection module; receiving current metal detection signal data corresponding to the object to be measured from the metal detection module; obtaining the metal detection result corresponding to the object to be measured based on the object's height data and the current metal detection signal data; and displaying the metal detection result through the display module. Thus, based on the user's object height data and metal detection signal data, the specific position of a metal object relative to the user is accurately located, and the metal detection result is displayed through the security gate's display module, allowing security personnel to re-inspect the user, thereby reducing false positives and false negatives, and improving security screening efficiency and accuracy.

Description

Technical Field

[0001] This invention relates to the field of intelligent security inspection technology, and in particular to a metal positioning method, device, storage medium, and security gate for use in security gates. Background Technology

[0002] Currently, when displaying alarm zones, smart security gates typically show the user's body parts containing metal on a human torso diagram on the gate's screen, allowing staff to conduct further checks. In related technologies, the smart security gate's induction coils are usually mapped one-to-one with the user's body parts. For example, if the top induction coil detects metal, the screen will display that the user's head contains metal.

[0003] However, the problem with this technology is that users' heights vary. When conducting security checks on users of non-standard heights, the displayed results may be incorrect. For example, if a 1.2-meter-tall user carries metal in their hat and passes through the security gate, the induction coil in the middle of the smart security gate will respond. However, the human torso image on the security gate screen may show that the user has metal hidden at their waist. In other words, the alarm location is inconsistent with the actual location, which can easily lead to misjudgment or missed detection. This results in low detection accuracy and affects the efficiency of security checks. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in related technologies. Therefore, the purpose of this invention is to provide a metal positioning method, device, storage medium, and security gate for use in security screening gates, achieving accurate positioning of metal objects relative to the user's specific location, and displaying the corresponding security screening results through the security gate, so that security personnel can re-inspect the user, thereby reducing misjudgments and omissions, and improving security screening efficiency and accuracy.

[0005] In a first aspect, embodiments of the present invention propose a metal positioning method for a security gate, the security gate including a metal positioning system and a display module; the metal positioning system including a main control unit, a height detection module, and a metal detection module; the method is applied to the main control unit and includes: receiving object height data of a target object sent by the height detection module; receiving current metal detection signal data corresponding to the target object sent by the metal detection module; obtaining a metal detection result corresponding to the target object based on the object height data and the current metal detection signal data; and displaying the metal detection result through the display module of the security gate.

[0006] In some embodiments of the present invention, obtaining the metal detection result corresponding to the object under test based on the object's height data and the current metal detection signal data includes: determining the target alarm area corresponding to the object under test based on the object's height data and the current metal detection signal data; and obtaining the metal detection result corresponding to the object under test based on the target alarm area.

[0007] In some embodiments of the present invention, determining the target alarm area corresponding to the object under test based on the object's height data and the current metal detection signal data includes: filtering out target metal positioning arrays that match the object under test from a pre-constructed metal positioning database based on the object's height data and the current metal detection signal data; the metal positioning database contains multiple metal positioning arrays; each metal positioning array contains at least three fields; the at least three fields include a height data field, a metal detection signal data field, and a target alarm area field; each metal positioning array is used to characterize the mapping relationship between the at least three fields; and determining the target alarm area corresponding to the object under test based on the target metal positioning arrays.

[0008] In some embodiments of the present invention, the height data field and the metal detection signal data field of each of the metal positioning arrays constitute a query vector; the step of filtering out the target metal positioning array that matches the test object in a pre-constructed metal positioning database based on the object's height data and the current metal detection signal data includes: obtaining the current query vector of the test object based on the object's height data and the current metal detection signal data; obtaining the correlation between the current query vector and each historical query vector contained in the metal positioning database; the correlation is used to characterize the similarity between the current query vector and each historical query vector; filtering out matching historical query vectors that match the current query vector in the pre-constructed metal positioning database based on the correlation; and determining the target metal positioning array that matches the test object based on the matching historical query vectors.

[0009] In some embodiments of the present invention, determining the target alarm area corresponding to the object under test based on the object's height data and the current metal detection signal data includes: using a pre-built metal positioning model, determining and outputting the target alarm area corresponding to the object under test based on the object's height data and the current metal detection signal data.

[0010] In some embodiments of the present invention, the step of determining and outputting the target alarm area corresponding to the object under test based on the object's height data and the current metal detection signal data using a pre-constructed metal positioning model includes: inputting the object's height data and the current metal detection signal data into the metal positioning model; having a feature extraction module included in the metal positioning model determine and output the metal positioning features of the object under test based on the object's height data and the current metal detection signal data; and having a classification module included in the metal positioning model determine and output the target alarm area corresponding to the object under test based on the metal positioning features output by the feature extraction module.

[0011] Secondly, embodiments of the present invention propose a metal positioning method for a security gate. The security gate includes a metal positioning system and a display module. The metal positioning system includes a main control unit, a height detection module, and a metal detection module. The height detection module includes a depth camera. The method is applied to the height detection module and includes: using the depth camera to acquire object height data of the object to be measured; sending the object height data to the main control unit; the main control unit is used to acquire the metal detection result corresponding to the object to be measured based on the object height data and the current metal detection signal data from the metal detection module, and displaying the metal detection result through the display module of the security gate.

[0012] In some embodiments of the present invention, the step of using the depth camera to obtain the object height data of the object to be tested includes: using the depth camera to obtain RGB video data and depth video data of the object to be tested; obtaining a target depth image of the object to be tested based on the RGB video data and depth video data; obtaining a target depth value corresponding to the object to be tested based on the target depth image; and obtaining the object height data of the object to be tested based on the device height value of the depth camera and the target depth value.

[0013] Thirdly, embodiments of the present invention provide a metal positioning device for a security gate, the security gate including a metal positioning system and a display module; the metal positioning system includes a main control unit, a height detection module, and a metal detection module, the device being applied to the main control unit, including: a first receiving module for receiving object height data of the object to be measured sent by the height detection module; a second receiving module for receiving current metal detection signal data corresponding to the object to be measured sent by the metal detection module; an acquisition module for acquiring the metal detection result corresponding to the object to be measured based on the object height data and the current metal detection signal data; and a result display module for displaying the metal detection result through the display module of the security gate.

[0014] Fourthly, this invention provides a metal positioning device for a security gate, the security gate including a metal positioning system; the metal positioning system including a main control unit, a height detection module, and a metal detection module; the height detection module including a depth camera, the device applied to the height detection module including: a calculation module for acquiring object height data of the object to be measured using the depth camera; a sending module for sending the object height data to the main control unit; the main control unit for acquiring the metal detection result corresponding to the object to be measured based on the object height data and the current metal detection signal data from the metal detection module, and displaying the metal detection result through the display module of the security gate.

[0015] Fifthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the metal positioning method for security gates described in the first and second aspect embodiments.

[0016] In a sixth aspect, embodiments of the present invention provide a security gate, the security gate including a metal positioning device for the security gate as described in the third and fourth aspect embodiments.

[0017] The metal positioning method, device, storage medium, and security gate of this application embodiment can be applied to the metal positioning system of a security gate. The metal positioning system may include a main control unit, a height detection module, and a metal detection module. The main control unit can receive the height data of the object to be measured from the height detection module and the current metal detection signal data corresponding to the object to be measured from the metal detection module. Furthermore, based on the user's height data and metal detection signal data, the specific position of the metal object relative to the user can be accurately located, and the metal detection result can be displayed through the display module of the security gate so that security personnel can re-inspect the user, thereby reducing misjudgments and omissions, and improving security passage efficiency and security accuracy.

[0018] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0019] Figure 1 This is a schematic flowchart of a metal positioning method for a security gate according to an embodiment of this application;

[0020] Figure 2 This is a block diagram of a security gate according to one embodiment of the present application; Figure 3This is a flowchart illustrating the process of obtaining metal detection results for an object under test according to an embodiment of this application; Figure 4 This is a schematic diagram of a process for determining a target alarm area using a metal location database according to an embodiment of this application; Figure 5 This is a flowchart illustrating the process of filtering a target metal location array that matches the object to be tested according to one embodiment of this application; Figure 6 This is a schematic diagram illustrating the process of determining a target alarm area using a metal positioning model according to an embodiment of this application; Figure 7 This is a schematic flowchart of a metal positioning method for a security gate according to another embodiment of this application; Figure 8 This is a block diagram of a security gate according to another embodiment of this application; Figure 9 This is a schematic diagram of the process for obtaining the height data of an object to be measured according to another embodiment of this application; Figure 10 This is a block diagram of a metal positioning device for a security gate according to an embodiment of this application; Figure 11 This is a block diagram of a metal positioning device for a security gate according to another embodiment of this application. Detailed Implementation

[0021] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0022] The following description, with reference to the accompanying drawings, outlines an embodiment of the metal positioning method, apparatus, storage medium, and security gate for a security gate according to the present invention.

[0023] Figure 1 This is a flowchart illustrating a metal positioning method for a security gate according to an embodiment of this application.

[0024] Specifically, in some embodiments of this application, the metal positioning method for security gates is applied to the main control unit of the security gate, with reference to... Figure 1 As shown, a metal locating method for a security gate is provided, which may include the following steps: S1 receives the height data of the object to be measured sent by the height detection module.

[0025] Specifically, such as Figure 2As shown, the security gate 1000 includes a metal positioning system 100 and a display module 200. The metal positioning system 100 includes a main control unit 110, a height detection module 120 and a metal detection module 130. The metal positioning method for the security gate in this embodiment of the application is applied to the main control unit 110.

[0026] More specifically, the height detection module 120 is located at the bottom of the lintel of the security gate 1000. An entrance sensor is also installed on the side of the entrance of the security gate 1000. When the entrance sensor detects that the object to be tested has entered the security gate 1000, the height detection module 120 will detect the height of the object to be tested, obtain the object's height data, and send it to the main control unit 110.

[0027] Optionally, in the actual design of the security gate, depending on the requirements for accuracy and economy in height detection, the height detection module 120 can use different sensors to acquire the height data of the object to be measured. For example, in one possible implementation, a 3D vision module can be configured in the height detection module 120 of the security gate, and then the height data can be acquired through the 3D vision module; in another possible implementation, the height data can also be acquired through an ultrasonic ranging module; in yet another possible implementation, the height data can also be acquired through an infrared ranging module.

[0028] S2 receives the current metal detection signal data corresponding to the object under test sent by the metal detection module.

[0029] Specifically, in this embodiment of the application, multiple induction coils built into the security gate 1000 are used to perform zoned metal detection on the object to be tested inside the security gate 1000, so as to obtain the current metal detection signal data corresponding to the object to be tested based on the detection results of the zoned metal detection and send it to the main control unit 110.

[0030] It is understood that metal detection signal data can include vertical position signal data and horizontal position signal data, wherein the vertical position signal data is used to indicate the vertical position of the metal object, and the horizontal position signal data is used to indicate the horizontal position of the metal object.

[0031] Specifically, in this embodiment of the application, the metal detection module 130 of the security gate 1000 includes multiple induction coils for detecting metal. The induction coils are arranged in sections from top to bottom on the side of the security gate 1000. When the object to be tested is carrying a metal object, the induction coils in different sections will generate induction signals of different intensities. The closer the induction coil is to the metal object, the stronger the induction signal it generates. Therefore, the position of the metal object in the vertical direction can be located based on the different induction signals generated by the induction coils in different sections. For example, in this embodiment of the application, the number of the induction coil that generates the strongest induction signal is used as the vertical position signal data of the metal detection signal.

[0032] Furthermore, when the object being tested is carrying a metal object, the induction coils in the same section may generate induction signals of different intensities in the horizontal direction. Therefore, the position of the metal object in the horizontal direction can also be located based on the induction signal intensity of the induction coils in the same section at different horizontal positions. For example, in this embodiment of the application, the induction coil is divided into two parts in the horizontal direction, namely the left side and the right side. If the induction signal intensity on the left side of the induction coil is greater, the horizontal position signal data is set to 0. If the induction signal intensity on the right side of the induction coil is greater, the horizontal position signal data is set to 1.

[0033] For example, if the signal strength is greatest on the left side of the second zone induction coil of the security gate, the metal detection signal data is represented as (2, 0). As another example, if the signal strength is greatest on the right side of the third zone induction coil of the security gate, the metal detection signal data is represented as (3, 1).

[0034] S3: Based on the object's height data and the current metal detection signal data, obtain the metal detection result corresponding to the object to be tested.

[0035] Specifically, in this embodiment of the application, the main control unit 110 of the security gate 1000 obtains the metal detection result corresponding to the object to be tested based on the object height data sent by the height detection module 120 and the current metal detection signal data corresponding to the object to be tested sent by the metal detection module 130, so as to accurately locate the specific position of the metal object relative to the object to be tested.

[0036] S4 displays the metal detection results through the display module of the security gate.

[0037] Specifically, in this embodiment of the application, the main control unit 110 of the security gate 1000 controls the display module 200 of the security gate 1000 to display the corresponding metal detection results, thereby realizing the visualization of the metal detection results so that security personnel can re-inspect users, thereby reducing misjudgments and omissions, and improving security passage efficiency and security accuracy.

[0038] Furthermore, in some embodiments of this application, reference is made to... Figure 3 As shown, based on the object's height data and the current metal detection signal data, the metal detection result corresponding to the object to be tested is obtained, including: S31, based on the object's height data and the current metal detection signal data, determine the target alarm area corresponding to the object to be tested.

[0039] Specifically, in this embodiment of the application, the specific position of the metal object relative to the object to be tested is accurately located based on the object's height data and the current metal detection signal data, and the specific position is determined as the target alarm area. For example, the target alarm area can be divided into ten areas, including the left head, right head, left shoulder, right shoulder, left waist, right waist, left leg, right leg, left foot, and right foot.

[0040] S32, based on the target alarm area, obtain the metal detection result corresponding to the object to be tested.

[0041] Specifically, in this embodiment of the application, based on the metal detection result corresponding to the object to be tested, the target alarm area is displayed on the display module 200 of the security gate 1000 (for example, the target alarm area can be displayed by means of text, color, pattern, etc.) so that security personnel can quickly view it and improve security inspection efficiency.

[0042] Furthermore, in some embodiments of this application, reference is made to... Figure 4 As shown, based on the object's height data and the current metal detection signal data, the target alarm area corresponding to the object to be tested is determined, including: S311, based on the object's height data and the current metal detection signal data, select a target metal positioning array that matches the object to be tested from a pre-built metal positioning database.

[0043] Specifically, in this embodiment of the application, a metal positioning database can be established in advance based on security inspection data samples collected during actual security inspections, from object height data and metal detection signal data to target alarm areas. This allows for the rapid determination of the target alarm area by querying the metal positioning database to see if matching security inspection data exists.

[0044] More specifically, in the above embodiments of this application, during the process of establishing the metal positioning database, the object height data and metal detection signal data of the object to be tested, as well as the corresponding target alarm area (which can be manually calibrated), are recorded as height data field, metal detection signal data field, and target alarm area field, respectively, to form a metal positioning array, which is then saved to the metal positioning database so as to represent the mapping relationship from object height data and metal detection signal data to target alarm area through each metal positioning array.

[0045] S312, determine the target alarm area corresponding to the object under test based on the target metal positioning array.

[0046] Specifically, in this embodiment of the application, the target alarm area corresponding to the object to be tested is determined by the mapping relationship between the object's height data and metal detection signal data and the target alarm area contained in the target metal positioning array.

[0047] Furthermore, in some embodiments of this application, reference is made to... Figure 5 As shown, based on the object's height data and the current metal detection signal data, a target metal location array matching the object to be tested is selected from a pre-built metal location database, including: S3111: Obtain the current query vector of the object to be tested based on the object's height data and the current metal detection signal data.

[0048] Specifically, in this embodiment of the application, the query vector is a tuple composed of the height data of the object to be tested and the metal detection signal data. Correspondingly, the height data field and the metal detection signal data field of each metal positioning array in the metal positioning database will also form a historical query vector.

[0049] S3112, obtain the correlation between the current query vector and each historical query vector contained in the metal positioning database.

[0050] Specifically, in this embodiment of the application, the correlation between the current query vector and each historical query vector contained in the metal location database is used to characterize the degree of similarity between the current query vector and each historical query vector contained in the metal location database. Then, by calculating the correlation between the current query vector and each historical query vector in the matching database through a similarity algorithm, the target metal location array that matches the object to be tested can be selected according to the magnitude of the correlation.

[0051] It should be noted that in the above embodiments of this application, different similarity algorithms, such as cosine similarity algorithm or Euclidean distance similarity algorithm, can be selected according to different requirements for the efficiency and accuracy of the target metal location array.

[0052] Furthermore, the Euclidean distance similarity algorithm works by calculating the geometric distance between two data points in a multidimensional space to obtain the similarity between them. The smaller the geometric distance between two data points, the greater their similarity. In some embodiments of this application, the Euclidean distance similarity algorithm can be used to calculate the geometric distance between the current query vector of the object under test and each historical query vector in the metal positioning database, thereby obtaining the similarity between them. The specific formula is as follows:

[0053] in, For the current query vector and the metal location database, the first... Geometric distance between historical query vectors This refers to the height data of the subject being tested. For the first in the metal location database Height data, This is the metal detection signal data of the current object under test. For the first in the metal location database Metal detection signal data.

[0054] It should be noted that the Euclidean distance similarity algorithm requires the vectors involved in the calculation to have the same dimension. However, the metal detection signal data is a two-dimensional vector containing horizontal and vertical position signal data, while the height data is a one-dimensional vector. Therefore, in this embodiment of the application, the metal detection signal data needs to be reduced to a one-dimensional vector to participate in the calculation of the Euclidean distance similarity algorithm. Specifically, in this embodiment of the application, the metal detection signal data is reduced to a one-dimensional vector using the formula... Obtain the one-dimensional vector corresponding to the metal detection signal data, where, This refers to the horizontal position signal data of the metal detection signal. This refers to the vertical position signal data of the metal detection signal. The number of induction coils is 5 in the embodiments of this application. For example, if the metal detection signal data is represented as (3, 1), then the one-dimensional vector corresponding to the metal detection signal data is 8.

[0055] Furthermore, in some embodiments of this application, before calculating the Euclidean distance similarity, the object height data and metal detection signal data of the object to be tested can be normalized using the following formula to limit the object height data and metal detection signal data of the object to be tested to the range [0, 1], thereby improving the calculation efficiency:

[0056]

[0057] in, The normalized height data of the object. This refers to the height data of the subject being tested. The minimum height value in the metal positioning database. The maximum value of the height data in the metal positioning database. This is the normalized metal detection signal data. This is the metal detection signal data of the current object under test. This is the minimum value among the metal detection signal data in the metal location database. This represents the maximum value of the metal detection signal data in the metal location database.

[0058] Furthermore, in some other embodiments of this application, the similarity between the current query vector and historical query vectors in the metal location database can also be calculated using a cosine similarity algorithm, as shown in the following formula:

[0059] in, For the current query vector and the metal location database, the first... The similarity between historical query vectors This refers to the height data of the subject being tested. For the first in the database The object's height data, This is the metal detection signal data of the current object under test. For the first in the metal location database Metal detection signal data.

[0060] Similarly, before performing cosine similarity calculation, the object height data and metal detection signal can be normalized to limit them to the range [0, 1], thereby improving calculation efficiency.

[0061] S3113, Based on relevance, filter out matching historical query vectors that match the current query vector from a pre-built metal location database.

[0062] Specifically, in this embodiment of the application, the historical query vector with the highest relevance is determined as the matching historical query vector that matches the current query vector.

[0063] S3114, Based on the matching historical query vector, determine the target metal location array that matches the object to be tested.

[0064] Specifically, in this embodiment of the application, the metal location array corresponding to the historical query vector is determined as the target metal location array that matches the object to be tested.

[0065] Furthermore, in some embodiments of this application, determining the target alarm area corresponding to the object to be tested based on the object's height data and the current metal detection signal data includes: using a pre-built metal positioning model, determining and outputting the target alarm area corresponding to the object to be tested based on the object's height data and the current metal detection signal data.

[0066] Specifically, in this embodiment of the application, based on security inspection data samples collected during actual security inspections, a metal positioning model is pre-established from object height data and metal detection signal data to the target alarm area. This allows the neural network to learn a more refined and complex correspondence, so that when encountering a combination of object height data and metal detection signal data that has never been seen before, it can reasonably output the target alarm area corresponding to the object under test through its generalization ability, thereby greatly improving the accuracy of alarm area display.

[0067] More specifically, in this embodiment of the application, the process of constructing the metal positioning model includes the following five steps: 1) Determine the input features and output features The height data of the object to be tested is obtained through the height detection module 120 and recorded as the input feature "object height". At the same time, the metal detection signal data of the object to be tested is obtained through the metal detection module 130 and recorded as the input feature "metal detection signal". Furthermore, the target alarm area corresponding to the object to be tested is obtained through manual calibration and recorded as the output feature "target alarm area".

[0068] 2) Data preprocessing First, all input feature data in the sample dataset are uniformly formatted, including but not limited to missing value completion and outlier removal, to improve the accuracy of metal location model prediction. Then, the input feature data are normalized or standardized (such as Min-Max normalization or Z-score standardization) to ensure that features of different dimensions are comparable during model training and to avoid numerical instability during gradient descent. Finally, the dataset is divided into training, validation, and test sets according to a certain ratio (such as 7:2:1) for model training, tuning, and final evaluation.

[0069] 3) Model Structure Construction Metal localization models can include feature extraction modules and classification modules: The feature extraction module includes an input layer that accepts a three-dimensional security inspection data vector (including a one-dimensional height data vector and a two-dimensional metal detection signal data vector); a hidden layer, which can be set up with one or more fully connected neural networks, each containing a number of neurons (e.g., 16–128), and uses activation functions such as ReLU, Sigmoid, or Tanh; an output layer that outputs a two-dimensional result vector representing the predicted relative position of the metal object on the body of the test subject; a loss function that uses mean squared error (MSE) as the regression loss; and an optimizer that uses a gradient descent-type optimizer (such as Adam, SGD, or RMSprop) to achieve iterative parameter updates.

[0070] The classification module is used to determine the corresponding target alarm area based on the two-dimensional result vector output by the feature extraction module's output layer.

[0071] 4) Model Training First, the training set is input into the constructed model to obtain predicted values ​​through forward propagation, and the loss between the predicted values ​​and the actual target alarm area is calculated. Then, the neural network parameters are updated based on the backpropagation algorithm to gradually converge the loss function. After each iteration, the validation set is used to calculate the validation error to determine whether the model is overfitting. If the validation loss no longer decreases in several consecutive iterations, an early stopping strategy is triggered to prevent overfitting. Finally, the model parameters with the best performance on the validation set are saved as the final metal location model.

[0072] 5) Model Evaluation First, the model is evaluated using a test set that was not used for training, and performance metrics such as MAE, MSE, and R² are calculated. Then, the model is optimized based on the evaluation metrics, including adjusting hyperparameters such as the number of neural network layers, number of neurons, activation function, and learning rate. Finally, the final model is confirmed based on the performance metrics, and the trained metal positioning model is saved for real-time prediction of target alarm areas during subsequent security checks.

[0073] Furthermore, in some embodiments of this application, reference is made to... Figure 6 As shown, using a pre-built metal positioning model, based on the object's height data and current metal detection signal data, the target alarm area corresponding to the object under test is determined and output, including: S313, input the object's height data and the current metal detection signal data into the metal positioning model.

[0074] Specifically, in this embodiment of the application, the height data of the object to be tested obtained by the height detection module 120 and the current metal detection signal data of the object to be tested obtained by the metal detection module 130 are used as input features and input to the metal positioning model to obtain the target alarm area corresponding to the object to be tested predicted by the metal positioning model.

[0075] S314, a feature extraction module included in the metal positioning model, determines and outputs the metal positioning features of the object to be tested based on the object's height data and the current metal detection signal data.

[0076] Specifically, in this embodiment of the application, the body of the subject is divided into five regions in the vertical direction (i.e., head, shoulders, waist, legs, and feet) and into two regions in the horizontal direction (i.e., left and right). Correspondingly, the metal positioning features (two-dimensional result vector) output by the feature extraction module of the metal positioning model include two categories: the first component is an integer from 1 to 5, representing the user's five body parts, and the second component is an integer from 0 to 1, representing the left and right positions of the user's body parts in the horizontal direction.

[0077] S315, a classification module included in the metal positioning model, determines and outputs the target alarm area corresponding to the object under test based on the metal positioning features output by the feature extraction module.

[0078] Specifically, if the metal location feature (two-dimensional result vector) output by the feature extraction module of the matching metal location model is (1, 0), then the target alarm area is determined to be the left head, which means that the detected metal object is located on the left head of the object to be tested; for example, if the two-dimensional result vector output by the matching neural network model is (3, 1), then the target alarm area is determined to be the right waist, which means that the detected metal object is located on the right waist of the object to be tested.

[0079] In summary, based on the user's height data and metal detection signal data, the system accurately locates the specific position of metal objects relative to the user and displays the metal detection results through the security gate's display module. This allows security personnel to re-inspect the user, thereby reducing misjudgments and omissions, and improving security screening efficiency and accuracy.

[0080] This application also proposes another metal positioning method for security gates, applied to the height detection module of the security gate.

[0081] Figure 7 This is a flowchart illustrating a metal positioning method for a security gate according to another embodiment of this application.

[0082] In some embodiments of this application, reference is made to Figure 7 As shown, the metal positioning method for security gates includes: The S5 uses a depth camera to acquire the height data of the object being measured.

[0083] Specifically, such as Figure 8 As shown, the security gate 1000 includes a metal positioning system 100 and a display module 200. The metal positioning system 100 includes a main control unit 110, a height detection module 120 and a metal detection module 130. The height detection module 110 also includes a depth camera (not shown in the figure). The metal positioning method for the security gate in this embodiment of the application is applied to the height detection module 120.

[0084] More specifically, in this embodiment of the application, a depth camera is used to acquire video data of the object to be tested, and the object height data of the object to be tested is obtained based on the video data.

[0085] S6, send the object's height data to the main control unit.

[0086] Specifically, after the height data of the object is sent to the main control unit 110, the main control unit 110 can obtain the metal detection result corresponding to the object to be tested based on the height data of the object and the current metal detection signal data from the metal detection module 130, and display the metal detection result through the display module 110 of the security gate 1000 so that security personnel can re-inspect the user, thereby reducing misjudgment and missed judgment, and improving the efficiency and accuracy of security checks.

[0087] In some embodiments of this application, reference is made to Figure 9 As shown, a depth camera is used to acquire the height data of the object being measured, including: The S51 uses a depth camera to acquire RGB video data and depth video data of the object under test.

[0088] Specifically, the height detection module is located at the bottom of the lintel housing of the security gate 1000. When the person to be tested enters the security gate, the depth camera will capture images of the person from top to bottom to obtain the top-view RGB video data and depth video data of the person to be tested. Since the depth camera captures images of the person to be tested from top to bottom, both the RGB video data and the depth video data are top-view video data of the person to be tested.

[0089] S52 acquires the target depth image of the object under test based on RGB video data and depth video data.

[0090] Specifically, RGB video data refers to color video data containing complete color information, while depth video data refers to grayscale video data that represents depth information (i.e., the distance of the scene relative to the camera) through grayscale values. Both display the same scene but contain different information. In this embodiment of the application, the outline and position of the object under test in the video are first analyzed using RGB video data to accurately identify the position of the object's head in the video and eliminate environmental interference. Subsequently, based on the position of the object's head in the video, the depth video data is cropped to obtain a target depth image of the object under test.

[0091] S53: Obtain the target depth value corresponding to the object under test based on the target depth image.

[0092] Specifically, there is a one-to-one correspondence between the grayscale values ​​of the target depth image and the depth values ​​(distance relative to the camera) of the object to be tested in the target depth image. In this embodiment of the application, the depth value corresponding to the minimum grayscale value of the target depth image is determined as the target depth value corresponding to the object to be tested, so as to represent the distance of the top of the object to be tested relative to the camera.

[0093] S54: Based on the device height value and target depth value of the depth camera, obtain the height data of the object to be measured.

[0094] Specifically, in this embodiment of the application, the height data of the object being measured can be accurately obtained by subtracting the target depth value (the distance between the top of the object's head and the camera) from the device height value of the depth camera.

[0095] In summary, by acquiring top-down RGB video data and depth video data of the object under test through a depth camera, and obtaining the object's height data based on the video data, the main control unit can obtain the corresponding metal detection result of the object under test based on the object's height data and the current metal detection signal data from the metal detection module after sending the object's height data to the main control unit. The metal detection result is then displayed on the display module of the security gate, allowing security personnel to re-inspect the user, thereby reducing false positives and false negatives, and improving security passage efficiency and accuracy.

[0096] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0097] Figure 10 This is a block diagram of a metal positioning device for a security gate according to an embodiment of this application.

[0098] In some embodiments of this application, reference is made to Figure 10 As shown, the metal positioning device 300 for the main control unit of the security gate includes: a first receiving module 310, a second receiving module 320, an acquisition module 330, and a result display module 340.

[0099] The system includes a first receiving module 310 for receiving height data of the object to be tested sent by the height detection module; a second receiving module 320 for receiving current metal detection signal data corresponding to the object to be tested sent by the metal detection module; an acquisition module 330 for acquiring the metal detection result corresponding to the object to be tested based on the object height data and the current metal detection signal data; and a result display module 340 for displaying the metal detection result through the display module of the security gate.

[0100] Furthermore, the acquisition module 330 is also used to determine the target alarm area corresponding to the object to be tested based on the object's height data and the current metal detection signal data; and to acquire the metal detection result corresponding to the object to be tested based on the target alarm area.

[0101] Furthermore, the acquisition module 330 is also used to filter out target metal positioning arrays that match the object to be tested from a pre-constructed metal positioning database based on the object's height data and the current metal detection signal data; the metal positioning database contains multiple metal positioning arrays; each metal positioning array contains at least three fields; the at least three fields include a height data field, a metal detection signal data field, and a target alarm area field; each metal positioning array is used to characterize the mapping relationship between the at least three fields; and the target alarm area corresponding to the object to be tested is determined based on the target metal positioning array.

[0102] Furthermore, the acquisition module 330 is also configured to acquire the current query vector of the object to be tested based on the object's height data and the current metal detection signal data; acquire the correlation between the current query vector and each historical query vector contained in the metal positioning database; the correlation is used to characterize the similarity between the current query vector and each of the historical query vectors; based on the correlation, filter out matching historical query vectors that match the current query vector in the pre-constructed metal positioning database; and determine the target metal positioning array that matches the object to be tested based on the matching historical query vectors.

[0103] Furthermore, the acquisition module 330 is also used to determine and output the target alarm area corresponding to the object under test based on the object's height data and the current metal detection signal data using a pre-built metal positioning model.

[0104] Furthermore, the acquisition module 330 is also used to input the object's height data and the current metal detection signal data into the metal positioning model; the feature extraction module included in the metal positioning model determines and outputs the metal positioning features of the object to be tested based on the object's height data and the current metal detection signal data; the classification module included in the metal positioning model determines and outputs the target alarm area corresponding to the object to be tested based on the metal positioning features output by the feature extraction module.

[0105] It should be understood that the specific implementation of the metal positioning device 300 for security gates in this application can be found in the specific implementation of the metal positioning method for security gates in one of the aforementioned embodiments of this application. To reduce redundancy, it will not be repeated here.

[0106] This application also proposes another metal positioning device for security gates, applied to the height detection module of the security gate.

[0107] Figure 11 This is a block diagram of a metal positioning device for a security gate according to another embodiment of this application.

[0108] In some embodiments of this application, reference is made to Figure 11 As shown, the metal positioning device 400 for the height detection module of the security gate includes: a calculation module 410 and a sending module 420.

[0109] The calculation module 410 is used to acquire the height data of the object to be tested using the depth camera; the sending module 420 is used to send the height data of the object to the main control unit; the main control unit is used to acquire the metal detection result corresponding to the object to be tested based on the height data of the object and the current metal detection signal data from the metal detection module, and display the metal detection result through the display module of the security gate.

[0110] Furthermore, the calculation module 410 is also used to acquire RGB video data and depth video data of the object under test using the depth camera; acquire a target depth image of the object under test based on the RGB video data and depth video data; acquire a target depth value corresponding to the object under test based on the target depth image; and acquire the object height data of the object under test based on the device height value of the depth camera and the target depth value.

[0111] It should be understood that the specific implementation of the metal positioning device 400 for security gates in this application can be found in the specific implementation of the metal positioning method for security gates in another embodiment of this application mentioned above. To reduce redundancy, it will not be described again here.

[0112] Based on the metal positioning method for security gates according to one embodiment of the present application or the metal positioning method for security gates according to another embodiment of the present application, the present application also proposes a computer-readable storage medium storing a metal positioning program for security gates, which, when executed by a processor, implements the metal positioning method for security gates according to one embodiment of the present application or the metal positioning method for security gates according to another embodiment of the present application.

[0113] It should be understood that specific embodiments of the computer-readable storage medium of this application can be found in the specific embodiments of the metal positioning method for security gates in one embodiment of this application or the metal positioning method for security gates in another embodiment of this application. To reduce redundancy, they will not be repeated here.

[0114] Based on the metal positioning device 300 for a security gate according to one embodiment of the present application or the metal positioning device 400 for a security gate according to another embodiment of the present application, the present application also proposes a security gate 1000.

[0115] In some embodiments of this application, reference is made to Figure 2 and Figure 8 As shown, the security gate 1000 includes a metal positioning device 300 for a security gate according to one embodiment of the present application or a metal positioning device 400 for a security gate according to another embodiment of the present application.

[0116] It should be understood that the specific implementation of the security gate 1000 of this application can be referred to the specific implementation of the metal positioning device 300 for security gate in one embodiment of this application or the metal positioning device 400 for security gate in another embodiment of this application. To reduce redundancy, it will not be described again here.

[0117] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0118] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0119] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0120] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0121] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0122] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "joining," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0123] In this application, unless otherwise expressly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "on top of," and "over" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0124] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A metal positioning method for security gates, characterized in that, The security gate includes a metal positioning system and a display module; the metal positioning system includes a main control unit, a height detection module, and a metal detection module; the method is applied to the main control unit, including: Receive the height data of the object to be measured sent by the height detection module; Receive the current metal detection signal data corresponding to the object under test sent by the metal detection module; Based on the object's height data and the current metal detection signal data, the metal detection result corresponding to the object to be tested is obtained; The metal detection results are displayed through the display module of the security gate.

2. The metal positioning method for security gates according to claim 1, characterized in that, The step of obtaining the metal detection result corresponding to the object to be tested based on the object's height data and the current metal detection signal data includes: Based on the object's height data and the current metal detection signal data, determine the target alarm area corresponding to the object to be tested; Based on the target alarm area, obtain the metal detection result corresponding to the object to be tested.

3. The metal positioning method for security gates according to claim 2, characterized in that, The step of determining the target alarm area corresponding to the object to be tested based on the object's height data and the current metal detection signal data includes: Based on the object's height data and the current metal detection signal data, a target metal location array matching the object to be tested is selected from a pre-constructed metal location database; the metal location database contains multiple metal location arrays; each metal location array contains at least three fields; the at least three fields include a height data field, a metal detection signal data field, and a target alarm area field; each metal location array is used to characterize the mapping relationship between the at least three fields; Based on the target metal location array, the target alarm area corresponding to the object under test is determined.

4. The metal positioning method for security gates according to claim 3, characterized in that, The height data field and metal detection signal data field of each of the metal positioning arrays form a query vector; the step of filtering out target metal positioning arrays that match the object to be tested from a pre-constructed metal positioning database based on the object's height data and the current metal detection signal data includes: Based on the object's height data and the current metal detection signal data, obtain the current query vector of the object to be tested; Obtain the relevance between the current query vector and each historical query vector contained in the metal location database; the relevance is used to characterize the degree of similarity between the current query vector and each of the historical query vectors; Based on the relevance, in the pre-built metal location database, matching historical query vectors that match the current query vector are filtered out; Based on the matching historical query vector, the target metal location array that matches the object to be tested is determined.

5. The metal positioning method for security gates according to claim 2, characterized in that, The step of determining the target alarm area corresponding to the object to be tested based on the object's height data and the current metal detection signal data includes: Using a pre-built metal positioning model, based on the object's height data and the current metal detection signal data, the target alarm area corresponding to the object under test is determined and output.

6. The metal positioning method for security gates according to claim 5, characterized in that, The step of using a pre-built metal positioning model to determine and output the target alarm area corresponding to the object under test based on the object's height data and the current metal detection signal data includes: The object's height data and the current metal detection signal data are input into the metal positioning model; The feature extraction module included in the metal positioning model determines and outputs the metal positioning features of the object to be tested based on the object's height data and the current metal detection signal data. The classification module included in the metal positioning model determines and outputs the target alarm area corresponding to the object under test based on the metal positioning features output by the feature extraction module.

7. A metal positioning method for security gates, characterized in that, The security gate includes a metal positioning system and a display module. The metal positioning system includes a main control unit, a height detection module, and a metal detection module. The height detection module includes a depth camera. The method is applied to the height detection module and includes: The depth camera is used to acquire the height data of the object to be measured; The object's height data is sent to the main control unit; the main control unit is used to obtain the metal detection result corresponding to the object to be tested based on the object's height data and the current metal detection signal data from the metal detection module, and to display the metal detection result through the display module of the security gate.

8. The metal positioning method for security gates according to claim 7, characterized in that, The step of using the depth camera to acquire the height data of the object to be measured includes: Using the depth camera, RGB video data and depth video data of the object under test are acquired; Based on the RGB video data and depth video data, obtain the target depth image of the object under test; Based on the target depth image, obtain the target depth value corresponding to the object to be tested; Based on the device height value of the depth camera and the target depth value, the height data of the object to be measured is obtained.

9. A metal positioning device for a security gate, characterized in that, The security gate includes a metal positioning system and a display module; the metal positioning system includes a main control unit, a height detection module, and a metal detection module, and the device is applied to the main control unit, including: The first receiving module is used to receive the height data of the object to be measured sent by the height detection module; The second receiving module is used to receive the current metal detection signal data corresponding to the object under test sent by the metal detection module; The acquisition module is used to acquire the metal detection result corresponding to the object to be tested based on the object's height data and the current metal detection signal data; The result display module is used to display the metal detection results through the display module of the security gate.

10. A metal positioning device for a security gate, characterized in that, The security gate includes a metal positioning system; the metal positioning system includes a main control unit, a height detection module, and a metal detection module; the height detection module includes a depth camera, and the device is applied to the height detection module, including: The calculation module is used to acquire the height data of the object to be measured using the depth camera; The sending module is used to send the height data of the object to the main control unit; the main control unit is used to obtain the metal detection result corresponding to the object to be tested based on the height data of the object and the current metal detection signal data from the metal detection module, and display the metal detection result through the display module of the security gate.

11. A computer-readable storage medium, characterized in that, It stores a metal positioning program for a security gate, which, when executed by a processor, implements the metal positioning method for a security gate as described in any one of claims 1-8.

12. A security gate, characterized in that, The security gate includes the metal positioning device for a security gate as described in claims 9-10.

Images