Access control method, device, computer equipment and storage medium

By obtaining and matching the gait and face features of the access control object, and using the decision tree model for classification, the problem of time-consuming identification of access control systems in the existing technology under a large database is solved, and the recognition efficiency is improved.

CN113743270BActive Publication Date: 2024-11-26ZHEJIANG DAHUA TECH CO LTD
View PDF 10 Cites 0 Cited by

Patent Information

Application Number
CN202110988372.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-08-26
Publication Date
2024-11-26
Estimated Expiration
2041-08-26

AI Technical Summary

Technical Problem

The existing access control system based on face recognition is difficult to quickly recognize under a large number of databases, resulting in a time-consuming problem.

Method used

By obtaining the gait features and face features of the access control object, classifying the objects that are allowed to pass based on the decision tree model, and matching the gait features of the object to be identified with the face features of the category to be belonged to, to control the access control device's Turn on, reducing matching with all database features.

Benefits of technology

It reduces data computing and matching time, improves recognition efficiency, and achieves rapid access control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113743270B_ABST
    Figure CN113743270B_ABST
Patent Text Reader

Abstract

This application relates to the field of control, and in particular to an access control method, apparatus, computer device, and storage medium. The method includes: acquiring a video to be processed, the video containing objects to be counted; based on the video to be processed, acquiring a first gait feature and a first facial feature of an object allowed to pass through the access control; classifying the allowed objects based on the first gait feature; acquiring a second gait feature and a second facial feature of an object to be identified; determining the category to which the object to be identified belongs based on the second gait feature; matching the second facial feature with a first facial feature corresponding to the category to which the object to be identified belongs, and controlling the access control device according to the matching result. This invention matches the second facial feature with the first facial feature corresponding to the category to which the object to be identified belongs, instead of matching with all first facial features in a database, reducing data processing and matching time.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of control, and in particular to a door access control method, device, computer equipment and storage medium. Background Art

[0002] Access control devices are constantly innovating and incorporating various intelligent technologies. The commonly used access control system based on face recognition uses a high-definition camera to capture facial images, sends the images to the face recognition module, extracts the features of the facial images, and uses an algorithm to compare and analyze the extracted features with the face database. When the comparison is successful, the access control system opens the door, forming a face recognition access control device.

[0003] Existing access control devices based on face recognition contain a large face database of face data. Traditional pattern recognition algorithms are difficult to perform rapid recognition based on a large database and have the disadvantage of being time-consuming. Summary of the invention

[0004] Based on this, it is necessary to provide a door access control method, device, computer equipment and storage medium to address the above technical problems.

[0005] In a first aspect, an embodiment of the present invention provides a door access control method, which is applied to a door access device. The method includes:

[0006] Obtain the first gesture feature and the first face feature of the object allowed to pass through the access control;

[0007] Classifying objects allowed to pass through the access control based on the first posture feature;

[0008] Acquire a second gait feature and a second facial feature of the object to be identified;

[0009] determining the category to which the object to be identified belongs based on the second gait feature;

[0010] The second facial feature is matched with the first facial feature corresponding to the category to which the object to be identified belongs, and the access control device is controlled according to the matching result.

[0011] In one embodiment, the step of obtaining the first posture feature of the object allowed to pass through the access control includes:

[0012] Obtaining a video stream to be processed, wherein the video stream to be processed includes the object allowed to pass through the access control system;

[0013] Based on the video stream to be processed, the first gait feature of the object allowed to pass through the gate is obtained by using the trained gait feature extraction model.

[0014] In one embodiment, the classifying of objects allowed to pass through the door based on the first posture feature includes:

[0015] Establishing a decision tree model based on the first step characteristics of the object allowed to pass through the access control;

[0016] Based on the decision tree model, objects allowed to pass through the access control are classified.

[0017] In one embodiment, establishing a decision tree model based on the first step feature of the object allowed to pass through the access control includes:

[0018] Obtaining the gain rate of each information contained in the first step feature;

[0019] Determining the node order of each information based on the gain rate of each information;

[0020] A decision tree model is established based on the node order of each information.

[0021] In one embodiment, the gain rate of each information satisfies the following formula:

[0022]

[0023]

[0024] Where D represents a data set; a represents a data list; D N Indicates that the Nth branch node contains the value a in the data set D on the data list a n samples; Gain(D, a) represents information gain; IV(a) represents the intrinsic value of attribute a.

[0025] In one embodiment, matching the second facial feature with the first facial feature corresponding to the category to which the object to be identified belongs, and controlling the access control device according to the matching result includes:

[0026] If the second facial feature matches any first facial feature corresponding to the category to which the object to be identified belongs, controlling the access control device to open;

[0027] If the second facial feature does not match the first facial feature corresponding to the category to which the object to be identified belongs, the access control device is not controlled to open.

[0028] In one embodiment, the method further comprises:

[0029] Obtaining the travel speed of the object to be identified and the distance between the object to be identified and the access control device;

[0030] The time for controlling the access control device to be opened is determined based on the travel speed of the object to be identified and the distance between the object to be identified and the access control device.

[0031] In a second aspect, an embodiment of the present invention provides an access control device, the device comprising:

[0032] A first acquisition module, used to acquire a first gesture feature and a first face feature of an object allowed to pass through the access control system;

[0033] A classification module, used for classifying objects allowed to pass through the access control based on the first posture feature;

[0034] A second acquisition module, used to acquire a second gait feature and a second face feature of the object to be identified;

[0035] a determination module, configured to determine the category to which the object to be identified belongs based on the second gait feature;

[0036] A matching module is used to match the second facial feature with the first facial feature corresponding to the category to which the object to be identified belongs, and control the access control device according to the matching result.

[0037] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0038] Obtain the first gesture feature and the first face feature of the object allowed to pass through the access control;

[0039] Classifying objects allowed to pass through the access control based on the first posture feature;

[0040] Acquire a second gait feature and a second facial feature of the object to be identified;

[0041] determining the category to which the object to be identified belongs based on the second gait feature;

[0042] The second facial feature is matched with the first facial feature corresponding to the category to which the object to be identified belongs, and the access control device is controlled according to the matching result.

[0043] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the processor executes the computer program, the following steps are implemented:

[0044] Obtain the first gesture feature and the first face feature of the object allowed to pass through the access control;

[0045] Classifying objects allowed to pass through the access control based on the first posture feature;

[0046] Acquire a second gait feature and a second facial feature of the object to be identified;

[0047] determining the category to which the object to be identified belongs based on the second gait feature;

[0048] The second facial feature is matched with the first facial feature corresponding to the category to which the object to be identified belongs, and the access control device is controlled according to the matching result.

[0049] The above method, device, computer equipment and storage medium obtain the first gait feature and the first facial feature of the object allowed to pass through the door; classify the object allowed to pass through the door based on the first gait feature; obtain the second gait feature and the second facial feature of the object to be identified; determine the category of the object to be identified based on the second gait feature; match the second facial feature with the first facial feature corresponding to the category of the object to be identified, and control the door access device according to the matching result. The present invention matches the second facial feature with the first facial feature corresponding to the category of the object to be identified, rather than matching with all the first facial features in the database, which reduces data calculation and matching time. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A diagram showing an application environment of a door access control method in an embodiment;

[0051] Figure 2 A schematic diagram of a flow chart of a door access control method in an embodiment;

[0052] Figure 3 is a schematic diagram of a flow chart of a gait feature acquisition method in one embodiment;

[0053] Figure 4 A schematic diagram of a classification method in one embodiment;

[0054] Figure 5 A schematic diagram of a flow chart of a method for controlling access control equipment in one embodiment;

[0055] Figure 6 A schematic diagram of a flow chart of a method for controlling the opening time of a door access device in one embodiment;

[0056] Figure 7 is a schematic diagram of the structure of an access control device in one embodiment;

[0057] Figure 8 The figure is a diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] The access control method provided by the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The terminal 102 first obtains the first gait feature and the first facial feature of the object allowed to pass through the door, classifies the object allowed to pass through the door based on the first gait feature, obtains the second gait feature and the second facial feature of the object to be identified, determines the category of the object to be identified based on the second gait feature, matches the second facial feature with the first facial feature corresponding to the category of the object to be identified, and controls the door control device according to the matching result, and the terminal 102 sends the door control result to the server 104. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0060] In one embodiment, if Figure 2 As shown, a door access control method is provided, which is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0061] S202: Acquire a first gesture feature and a first facial feature of a subject allowed to pass through the access control system.

[0062] Gait features include static features and dynamic features. Static features include height, body shape, leg bones, joints, muscles, clothing and other features. Dynamic features include walking posture, movement and other features, such as arm swing, walking speed, step frequency and other features.

[0063] In this embodiment, all objects are divided into objects that are allowed to pass through the access control and objects to be identified. Objects that are allowed to pass through the access control can pass through the access control by identification, such as students in a dormitory building. Objects to be identified refer to objects that need to be identified, and can only pass through the access control after successful identification.

[0064] The first facial feature can be extracted using a facial feature extraction model. The facial feature extraction model is an existing technology and will not be described in detail.

[0065] S204: Classify objects allowed to pass through the gate based on the first gesture feature.

[0066] It is understandable that each object allowed to pass through the gate has a corresponding first gesture feature, some of which are similar. In this embodiment, similar first gesture features are taken as a category to obtain multiple categories, thereby achieving classification of objects allowed to pass through the gate.

[0067] S206: Acquire a second gait feature and a second facial feature of the object to be identified.

[0068] S208: Determine the category to which the object to be identified belongs based on the second gait feature.

[0069] In step S204, the objects allowed to pass through the gate have been classified. In this step, the category to which the second gait feature is similar is determined, thereby determining the category to which the object to be identified belongs.

[0070] S210: Match the second facial feature with the first facial feature corresponding to the category to which the object to be identified belongs, and control the access control device according to the matching result.

[0071] After the objects allowed to pass through the gate are classified, the corresponding first facial features are also stored according to the classification. In this embodiment, the second facial features are matched with the first facial features corresponding to the category of the object to be identified, rather than with all the first facial features in the database, which reduces data calculation and matching time.

[0072] In one embodiment, if Figure 3 As shown, obtaining the first step feature of the object allowed to pass through the access control includes the following steps:

[0073] S302: Acquire a video stream to be processed, wherein the video stream to be processed includes the object allowed to pass through the access control system.

[0074] It is understandable that the access control equipment is equipped with a camera device, and the video stream to be processed including the objects allowed to pass through the access control is obtained through the camera device.

[0075] S304: Based on the video stream to be processed, using the trained gait feature extraction model, obtain the first gait feature of the object allowed to pass through the gate.

[0076] The gait feature extraction model is used to extract the first gait feature of the object allowed to pass through the door. First, the image sequence of the object is obtained from the sample video stream, and the gait feature extraction model is obtained by training the image sequence. Then, the image sequence of the object extracted from the video stream to be processed is input into the gait feature extraction model to obtain the first gait feature of the object allowed to pass through the door.

[0077] It is understandable that, in step S206, the same method may also be used to obtain the second gait feature of the object to be identified.

[0078] In one embodiment, if Figure 4 As shown, classifying objects allowed to pass through the access control based on the first step feature includes the following steps:

[0079] S402: Building a decision tree model based on the first step characteristics of the object allowed to pass through the gate, arranging the information of each person into a data list, and re-acquiring the information if the list is empty.

[0080] First, the gain rate of each information contained in the first step feature is obtained; then, based on the gain rate of each information, the node order of each information is determined; finally, based on the node order of each information, a decision tree model is established.

[0081] Specifically, we first need to construct a root node, select an optimal feature according to the gain rate, and divide the first step feature into subsets according to the optimal feature; if the subset can be correctly classified, we will construct a leaf node and divide the subset into each leaf node; otherwise, if the subset cannot be correctly classified, the subset needs to select a new optimal feature to continue dividing and constructing nodes until all subsets in the first step feature are correctly classified, thus forming a decision tree.

[0082] Information gain refers to the difference in information before and after the data set is split. The first step feature of the split is to arrange the disordered data into an ordered data list. To calculate the information gain rate, all the first step features need to form a data set, take a part of the data set as the training set D, and set the proportion of the i-th class samples in the training set D to p. i , the information entropy of the training set D is:

[0083]

[0084] The greater the information entropy, the greater the uncertainty of the information and the lower the purity.

[0085] In an example embodiment, the data list of travel speed is set to a, and there are N values ​​in data list a. Using a to divide the data set D, N branch nodes are generated. The Nth branch node contains the values ​​in data set D that are a in data list a. n The sample is denoted as D N The information entropy calculation formula is used to calculate the data set D and the segmented D N The information entropy of is divided into several subsets according to the travel speed attribute, and the entropy of each subset is weighted to obtain the information gain:

[0086]

[0087] A small information entropy after division can ensure high data purity and low information uncertainty. If a feature has many values, the information entropy of the feature is low, and the information gain obtained will be high. Therefore, the information gain is affected by the number of feature values, and dividing the data set by information gain lacks generalization ability.

[0088] In order to reduce unfavorable factors, this method will use the information gain rate algorithm:

[0089]

[0090]

[0091] The information gain rate of other information such as height and clothing is calculated in the same way. The information gain rate of travel speed, the information gain rate of height data and the information gain rate of clothing in the data list are compared. The travel speed, height and clothing data are divided into data nodes in the order of information gain rate from large to small to generate a complete decision tree model.

[0092] S404: Classify objects allowed to pass through the access control based on the decision tree model.

[0093] Based on the generated complete decision tree model, objects allowed to pass through the access control are classified.

[0094] In one embodiment, if Figure 5 As shown, matching the second facial feature with the first facial feature corresponding to the category to which the object to be identified belongs, and controlling the access control device according to the matching result includes the following steps:

[0095] S502: If the second facial feature matches any first facial feature corresponding to the category to which the object to be identified belongs, controlling the access control device to open;

[0096] S504: If the second facial feature does not match the first facial feature corresponding to the category to which the object to be identified belongs, the access control device is not controlled to open.

[0097] If the second facial feature matches any first facial feature corresponding to the category to which the object to be identified belongs, it means that the recognition is successful, and the access control device is controlled to open; if the second facial feature does not match the first facial feature corresponding to the category to which the object to be identified belongs, it means that the recognition is unsuccessful, and the access control device is not controlled to open.

[0098] In this embodiment, the second facial feature only needs to be matched with the first facial feature corresponding to the category to which the object to be identified belongs, without having to be matched with all first facial features in the database, thereby reducing data calculations, reducing matching time, and improving recognition efficiency.

[0099] In one embodiment, if Figure 6 As shown, the method also includes:

[0100] S602: Acquire the travel speed of the object to be identified and the distance between the object to be identified and the access control device;

[0101] S604: Determine the time to control the opening of the access control device based on the travel speed of the object to be identified and the distance between the object to be identified and the access control device.

[0102] The camera device obtains the speed of the object to be identified through video stream analysis, and then calculates the time when the object to be identified reaches the access control device according to the speed of the object to be identified and the distance between the object to be identified and the access control device. If the object to be identified is successfully identified, the door will be opened immediately when it arrives at the access control. When the speed of the object to be identified changes, the arrival time is recalculated to open the door.

[0103] In this embodiment, by controlling the opening time of the access control device, the door can be opened immediately when the object to be identified arrives, and the object to be identified can pass quickly, saving the time of the object to be identified waiting for the door to open in front of the access control and improving the speed of passing the access control.

[0104] It should be understood that although Figure 1-6 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1-6 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0105] In one embodiment, if Figure 7 As shown, the present invention provides a door access control device, the device comprising:

[0106] A first acquisition module 702, used to acquire a first gesture feature and a first facial feature of an object allowed to pass through the door control;

[0107] A classification module 704, configured to classify objects allowed to pass through the gate based on the first posture feature;

[0108] A second acquisition module 706, used to acquire a second gait feature and a second face feature of the object to be identified;

[0109] A determination module 708, configured to determine the category to which the object to be identified belongs based on the second gait feature;

[0110] The matching module 710 is used to match the second facial feature with the first facial feature corresponding to the category to which the object to be identified belongs, and control the access control device according to the matching result.

[0111] In one embodiment, the first acquisition module includes:

[0112] A video stream acquisition module, used to acquire a video stream to be processed, wherein the video stream to be processed contains the object allowed to pass through the access control;

[0113] The gait feature acquisition module is used to obtain the first gait feature of the object allowed to pass through the gate based on the video stream to be processed and using the trained gait feature extraction model.

[0114] In one embodiment, the classification module includes:

[0115] A model building module, used to build a decision tree model based on the first step feature of the object allowed to pass through the access control;

[0116] The classification submodule is used to classify objects allowed to pass through the access control based on the decision tree model.

[0117] In one embodiment, the model building module is specifically used to:

[0118] Obtaining the gain rate of each information contained in the first step feature;

[0119] Determining the node order of each information based on the gain rate of each information;

[0120] A decision tree model is established based on the node order of each information.

[0121] In one embodiment, the gain rate of each information satisfies the following formula:

[0122]

[0123]

[0124] In one embodiment, the matching module is specifically used for:

[0125] If the second facial feature matches any first facial feature corresponding to the category to which the object to be identified belongs, controlling the access control device to open;

[0126] If the second facial feature does not match the first facial feature corresponding to the category to which the object to be identified belongs, the access control device is not controlled to open.

[0127] In one embodiment, the device further comprises:

[0128] A third acquisition module is used to acquire the travel speed of the object to be identified and the distance between the object to be identified and the access control device;

[0129] The control module is used to determine the time to control the access control device to open based on the travel speed of the object to be identified and the distance between the object to be identified and the access control device.

[0130] For the specific definition of the access control device, please refer to the definition of the access control method above, which will not be repeated here. Each module in the above-mentioned access control device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0131] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store motion detection data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the steps in any of the above-mentioned access control method embodiments are implemented.

[0132] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0133] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in any one of the above-mentioned access control method embodiments are implemented.

[0134] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in any of the above-mentioned access control method embodiments are implemented.

[0135] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0136] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0137] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A door access control method, which is applied to a door access device, characterized in that: The method comprises: Obtain the first gesture feature and the first face feature of the object allowed to pass through the access control; Classifying objects allowed to pass through the access control based on the first posture feature; Acquire a second gait feature and a second facial feature of the object to be identified; determining the category to which the object to be identified belongs based on the second gait feature; Matching the second facial feature with the first facial feature corresponding to the category to which the object to be identified belongs, and controlling the access control device according to the matching result; The classification of objects allowed to pass through the gate based on the first posture feature includes: Establishing a decision tree model based on the first step characteristics of the object allowed to pass through the access control; Based on the decision tree model, classify objects allowed to pass through the access control; The step of establishing a decision tree model based on the first step feature of the object allowed to pass through the access control comprises: Obtaining the gain rate of each information contained in the first step feature; Determining the node order of each information based on the gain rate of each information; A decision tree model is established based on the node order of each information.

2. The method according to claim 1, characterized in that The first step of obtaining the posture feature of the object allowed to pass through the access control includes: Obtaining a video stream to be processed, wherein the video stream to be processed includes the object allowed to pass through the access control system; Based on the video stream to be processed, the first gait feature of the object allowed to pass through the gate is obtained by using the trained gait feature extraction model.

3. The method according to claim 1, characterized in that The gain rate of each information satisfies the following formula: Wherein, D represents a data set; a represents a data list, which is obtained by arranging the information of the first step characteristics of the object allowed to pass through the access control; D N Indicates that the Nth branch node contains the value a in the data set D on the data list a n samples; Gain(D, a) represents information gain; IV(a) represents the intrinsic value of attribute a.

4. The method according to claim 1, characterized in that: The step of matching the second facial feature with the first facial feature corresponding to the category to which the object to be identified belongs, and controlling the access control device according to the matching result includes: If the second facial feature matches any first facial feature corresponding to the category to which the object to be identified belongs, controlling the access control device to open; If the second facial feature does not match the first facial feature corresponding to the category to which the object to be identified belongs, the access control device is not controlled to open.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Obtaining the travel speed of the object to be identified and the distance between the object to be identified and the access control device; The time for controlling the access control device to be opened is determined based on the travel speed of the object to be identified and the distance between the object to be identified and the access control device.

6. An access control device, characterized in that: The device comprises: A first acquisition module, used to acquire a first gesture feature and a first face feature of an object allowed to pass through the access control system; A classification module, used for classifying objects allowed to pass through the access control based on the first posture feature; A second acquisition module, used to acquire a second gait feature and a second face feature of the object to be identified; a determination module, configured to determine the category to which the object to be identified belongs based on the second gait feature; A matching module, used for matching the second facial feature with the first facial feature corresponding to the category to which the object to be identified belongs, and controlling the access control device according to the matching result; The classification module comprises: A model building module, used to build a decision tree model based on the first step feature of the object allowed to pass through the access control; A classification submodule, used for classifying objects allowed to pass through the access control based on the decision tree model; The model building module is specifically used to: obtain the gain rate of each information contained in the first step feature; determine the node order of each information based on the gain rate of each information; and build a decision tree model based on the node order of each information.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Citation Information

Patent Citations

  • Security protection management method and system based on face features and gait features

    CN105787440A

  • Entrance guard control device, system and method for identification through gait information

    CN105844746A

  • Access control method and apparatus

    CN109544751A

  • Access control system with integration of face recognition and gait recognition

    CN109920111A

  • Gait feature collection system and method and target object recognition method and device

    CN110110703A