Door lock control method and device based on palm vein technology, storage medium and electronic device

Abstract

The invention discloses a palm vein technology-based door lock control method and device, a storage medium and an electronic device, and relates to the technical field of smart home, the method comprises the following steps: carrying out contour recognition on a target object located in an induction range of an intelligent door lock to obtain a contour type; according to the contour type, adjusting a current optical zoom focal length to a target optical zoom focal length when the intelligent door lock performs image acquisition on the target object, and obtaining an object image obtained by performing image acquisition by using the target optical zoom focal length; the object type of the target object is determined according to the comparison result of the object image and the preset image, and the intelligent door lock is controlled to be unlocked based on the object type, and by adopting the technical scheme, the technical problem of how to quickly and accurately recognize the user identity and unlock the lock for the user is solved.

Description

Technical Field

[0001] The present application relates to the field of smart home technology, and more specifically, to a door lock control method, device, storage medium and electronic device based on palm vein technology. Background Art

[0002] With the continuous development of smart home technology, smart door locks have become an important part of home security. Traditional smart door locks are usually powered off when the door is not opened to reduce energy consumption and extend the life of the device. However, this design has some limitations in actual use. When the user approaches the door lock and triggers the unlocking mechanism, the smart door lock needs to quickly switch from the power-off state to the working state to capture the user's biometric information, such as facial images or palm vein data. This process usually involves powering on and starting up, followed by capturing image data. However, it often takes several seconds for existing smart door locks to go from the power-off state to capturing the first frame of image data. If the user walks fast, the user may have moved to a position that is not conducive to image capture during this period, thereby affecting the clarity of the captured image. The unclear image will directly lead to errors or delays in the subsequent image recognition process, which in turn affects the identification of the user's identity and the smoothness of the unlocking process.

[0003] Therefore, smart door locks face challenges in quickly identifying user identities and improving unlocking efficiency. In related technologies, there are technical issues on how to quickly and accurately identify user identities and unlock the door for users.

[0004] In the related art, there is no effective solution to the technical problem of how to quickly and accurately identify the identity of the user and unlock the door for the user. Summary of the invention

[0005] The embodiments of the present application provide a door lock control method, device, storage medium and electronic device based on palm vein technology to at least solve the technical problem of how to quickly and accurately identify the identity of a user and unlock the door for the user in the related art.

[0006] According to one embodiment of the embodiments of the present application, a door lock control method based on palm vein technology is provided, including: performing contour recognition on a target object located within the sensing range of the smart door lock to obtain a contour type; adjusting the current optical zoom focal length of the smart door lock when performing image acquisition on the target object to a target optical zoom focal length according to the contour type, and obtaining an object image obtained by image acquisition using the target optical zoom focal length; determining the object type of the target object according to a comparison result between the object image and a preset image, and controlling the smart door lock to open based on the object type.

[0007] In an exemplary embodiment, before performing contour recognition on a target object within the sensing range of the smart door lock to obtain a contour type, the method further includes: when it is determined that the smart door lock is in a sleep mode, using an external sensing device of the smart door lock to monitor whether there is an active object within the sensing range; when it is determined that the external sensing device of the smart door lock detects the presence of an active object within the sensing range, capturing a first image of the active object; obtaining a recognition result of the first image, and determining the target object based on the recognition result.

[0008] In an exemplary embodiment, the current optical zoom focal length of the smart door lock when capturing an image of the target object is adjusted to the target optical zoom focal length according to the contour type, including: when it is determined that the contour type is a human contour, determining the telephoto focal length corresponding to the human contour; determining the target optical zoom focal length according to the telephoto focal length, and adjusting the current optical zoom focal length to the target optical zoom focal length.

[0009] In an exemplary embodiment, the current optical zoom focal length of the smart door lock when capturing an image of the target object is adjusted to a target optical zoom focal length according to the contour type, including: when it is determined that the contour type is a palm-shaped contour, determining a near focus focal length corresponding to the palm-shaped contour; determining the target optical zoom focal length according to the near focus focal length, and adjusting the current optical zoom focal length to the target optical zoom focal length.

[0010] In an exemplary embodiment, determining the object type of the target object based on a comparison result between the object image and a preset image includes: determining an image selected from a face database as the preset image, and calculating the image similarity between the object image and the preset image; when it is determined that the image similarity is higher than the preset similarity, determining the face object to which the preset image is bound from the face database, and determining the object type indicated by the face object as the object type of the target object.

[0011] In an exemplary embodiment, calculating the image similarity between the object image and the preset image includes: using a face detection algorithm to detect a first face in the object image and a second face in the preset image, and aligning the first face and the second face; extracting a first feature vector of the first face, and extracting a second feature vector of the second face; calculating the cosine similarity between the first feature vector and the second feature vector, and determining the cosine similarity as the image similarity.

[0012] In an exemplary embodiment, controlling the opening of the smart door lock based on the object type includes: obtaining all control permissions bound to the object type; when it is determined that the face object belongs to a preset object and all control permissions include unlocking permissions for controlling the opening of the smart door lock, controlling the opening of the smart door lock, wherein information of the preset object has been entered into the smart door lock; when it is determined that all control permissions do not include unlocking permissions for controlling the opening of the smart door lock, generating a prompt message of unlocking failure, and sending the prompt message to other objects, and controlling the opening of the smart door lock based on the unlocking instructions of the other objects, wherein the other objects have unlocking permissions for controlling the opening of the smart door lock.

[0013] According to another aspect of the embodiment of the present application, a door lock control device based on palm vein technology is also provided, including: an identification module, used to perform contour recognition on a target object located within the sensing range of the smart door lock to obtain a contour type; an adjustment module, used to adjust the current optical zoom focal length of the smart door lock when performing image acquisition on the target object to the target optical zoom focal length according to the contour type, and obtain the object image obtained by using the target optical zoom focal length for image acquisition; a control module, used to determine the object type of the target object based on a comparison result between the object image and a preset image, and control the smart door lock to open based on the object type. According to another aspect of the embodiment of the present application, a computer-readable storage medium is also provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned door lock control method based on palm vein technology when it is run.

[0014] According to another aspect of an embodiment of the present application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the door lock control method based on palm vein technology through the computer program.

[0015] In an embodiment of the present application, the target object located within the sensing range of the smart door lock is subjected to contour recognition to obtain a contour type; the current optical zoom focal length when the smart door lock performs image acquisition on the target object is adjusted to the target optical zoom focal length according to the contour type, and an object image obtained by using the target optical zoom focal length for image acquisition is obtained; the object type of the target object is determined according to the comparison result between the object image and the preset image, and the smart door lock is controlled to open based on the object type. Through contour recognition and intelligent adjustment of the optical zoom focal length, the present application is compatible with the face recognition means at far focus and the palm vein recognition means at near focus in the smart door lock, which can more accurately capture the image of the target object, and then determine the object type through image comparison, which not only improves the security of the door lock, but also improves the recognition speed and accuracy of the user in the door entry scene, optimizes the user experience, especially in the recognition of human contours and palm contours, can automatically adjust the focal length according to different object types, improve the clarity of image acquisition, and thus improve the accuracy of subsequent recognition. It can be seen that the adoption of the above technical solution solves the technical problem of how to quickly and accurately identify the user's identity and unlock the door for the user. It can quickly identify the user's identity, realize precise control of the smart door lock, and improve the unlocking efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 Schematic diagram of the hardware environment of a door lock control method based on palm vein technology in an embodiment of the present application;

[0019] Figure 2 is a flow chart of a door lock control method based on palm vein technology according to an embodiment of the present application;

[0020] Figure 3 is a flow chart of a door lock control method based on palm vein technology according to an embodiment of the present application;

[0021] Figure 4 This is a structural block diagram of a door lock control device based on palm vein technology according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] According to one aspect of an embodiment of the present application, a door lock control method based on palm vein technology is provided. The door lock control method based on palm vein technology is widely used in smart home (Smart Home), smart home, smart home device ecology, smart residential (Intelligence House) ecology and other whole-house intelligent digital control application scenarios. Optionally, in this embodiment, the above-mentioned door lock control method based on palm vein technology can be applied to Figure 1 In the hardware environment composed of the terminal device 102 and the server 104 shown in FIG. Figure 1 As shown, the server 104 is connected to the terminal device 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. A database can be set on the server or independently of the server to provide data storage services for the server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data computing services for the server 104.

[0025] The network may include but is not limited to at least one of the following: wired network, wireless network. The wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network, and the wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal device 102 may be but is not limited to a PC, a mobile phone, a tablet computer, a smart air conditioner, a smart range hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing device, a smart dishwasher, a smart projection device, a smart TV, a smart clothes drying rack, a smart curtain, a smart audio and video, a smart socket, a smart speaker, a smart fresh air device, a smart kitchen and bathroom device, a smart bathroom device, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purification device, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, a smart door lock, etc.

[0026] Among them, smart door locks, as an important part of the smart security system, have higher security and convenience compared with traditional mechanical door locks. Smart door locks include push-button door locks, fingerprint door locks, face recognition door locks, palm vein recognition door locks, iris recognition door locks and other types. Among them, fingerprint door locks and face recognition door locks use biometric recognition technology to realize the biometric identification of the target object, and then control the unlocking action of the smart door lock. It is worth noting that palm vein recognition technology, as a new type of biometric identification method, can collect the user's palm vein information, identify the unique identity information of the target object, and realize the control of the smart door lock.

[0027] Among them, palm vein recognition technology has the following characteristics:

[0028] 1) Uniqueness: The unique vascular structure of palm veins determines the uniqueness of palm vein recognition technology. The palm vein feature information obtained through palm veins can effectively avoid misrecognition caused by facial similarity.

[0029] 2) Security: Palm vein recognition technology uses a non-contact palm vein information collection method, which can effectively prevent the forgery of fingerprint information, facial information, etc.

[0030] 3) High recognition rate: Compared with traditional fingerprint recognition and face recognition, palm vein recognition technology has a higher recognition rate.

[0031] 4) Long recognition distance: Palm vein recognition technology has a long recognition distance, which can effectively avoid the situation where the recognition device cannot recognize the target object in a crowded state in front of the door lock.

[0032] 5) Fast recognition speed: The recognition time of palm vein recognition technology is short, which can effectively avoid the user waiting time in front of the door lock and improve the efficiency of door lock use.

[0033] In this embodiment, a door lock control method based on palm vein technology is provided, which is applied to the above terminal device. Figure 2 : is a flow chart of a door lock control method based on palm vein technology according to an embodiment of the present application, and the flow includes the following steps:

[0034] Step S202, performing contour recognition on a target object within the sensing range of the smart door lock to obtain a contour type;

[0035] Step S204, adjusting the current optical zoom focal length when the smart door lock performs image acquisition on the target object to the target optical zoom focal length according to the contour type, and acquiring the object image obtained by performing image acquisition using the target optical zoom focal length;

[0036] It should be noted that the present application uses the same image acquisition device (such as a camera) for image acquisition, and determines whether the outline of the object is a human shape or a palm shape through the rough screening step of contour recognition, and then switches the camera to the corresponding optical focal length to collect facial data or palm vein (or palm print) data, and then performs comparison.

[0037] The human contour represents the outer contour of the human body, and the palm contour represents the palm contour of the human hand.

[0038] Step S206, determining the object type of the target object according to the comparison result between the object image and the preset image, and controlling the smart door lock to open based on the object type.

[0039] Through the above steps, the target object within the sensing range of the smart door lock is identified by contour recognition to obtain the contour type; the current optical zoom focal length when the smart door lock performs image acquisition on the target object is adjusted to the target optical zoom focal length according to the contour type, and the object image obtained by using the target optical zoom focal length for image acquisition is obtained; the object type of the target object is determined according to the comparison result between the object image and the preset image, and the smart door lock is controlled to open based on the object type. This application uses contour recognition and intelligent adjustment of the optical zoom focal length to make the smart door lock compatible with the face recognition means at far focus and the palm vein recognition means at near focus, so that the image of the target object can be acquired more accurately, and then the object type can be determined by image comparison, which not only improves the security of the door lock, but also improves the recognition speed and accuracy of the user in the door entry scene, optimizes the user experience, especially in the recognition of human contours and palm contours, can automatically adjust the focal length according to different object types, improve the clarity of image acquisition, and thus improve the accuracy of subsequent recognition. It can be seen that the adoption of the above technical solution solves the technical problem of how to quickly and accurately identify the user's identity and unlock the door for the user. It can quickly identify the user's identity, realize precise control of the smart door lock, and improve the unlocking efficiency.

[0040] In an exemplary embodiment, before performing contour recognition on a target object within the sensing range of the smart door lock to obtain a contour type, further, when it is determined that the smart door lock is in sleep mode, the external sensing device of the smart door lock can be used to monitor whether there is an active object within the sensing range; when it is determined that the external sensing device of the smart door lock detects the presence of an active object within the sensing range, a first image of the active object is captured; a recognition result of the first image is obtained, and the target object is determined based on the recognition result. This embodiment can effectively save the power consumption of the smart door lock through intelligent awakening from sleep mode, while quickly responding to the appearance of active objects. It is also suitable for access control in outdoor or large places that require long-term monitoring and have limited power supply.

[0041] In this embodiment, when the door lock is in sleep mode, a dry cell or lithium battery can be used for power supply to save power. If the low power trigger source (equivalent to the external sensing device) is triggered, it is determined whether to wake up the door lock. If so, the subsequent contour recognition process is started.

[0042] Among them, the external sensing device, such as an infrared tube, ultrasonic radar, high-frequency centimeter-wave radar or millimeter-wave radar, etc., wakes up the door lock when it senses someone at the door. It is understandable that the above-mentioned sensing device can also be built into the smart door lock, and this application does not limit the installation location and installation method of the sensing device.

[0043] Optionally, in this embodiment, before the first image is recognized, it is necessary to determine whether the active object is a living object. If the active object is determined to be a living object, the first image is recognized, and the target object is determined based on the recognition result. If the active object is determined to be an inanimate object, such as a sweeping robot, the subsequent recognition process is not performed. After the active object is determined to be a living object, the recognition result of the first image can be matched with the user data in the local database. If the match is successful, the matched user is determined as the target object. Alternatively, the recognition result of the first image is matched with the object data in the online database. If an animal such as a cat or a dog is matched, the subsequent recognition process is not performed.

[0044] In an exemplary embodiment, the process of adjusting the current optical zoom focal length when the smart door lock performs image acquisition on the target object to the target optical zoom focal length according to the profile type may include: determining the telephoto focal length corresponding to the human profile when the profile type is determined to be a human profile; determining the target optical zoom focal length according to the telephoto focal length, and adjusting the current optical zoom focal length to the target optical zoom focal length. This intelligent focal length adjustment strategy can ensure that the human profile can be clearly captured even at a long distance, and is suitable for the management of personnel entering and exiting open spaces such as large entrances and parking lots.

[0045] In this embodiment, face recognition needs to take into account different human height ranges. Without using a wide-angle lens (wide-angle lens has large distortion), the lens focal length (i.e., the target optical zoom focal length) can be set to about 1 meter.

[0046] In an exemplary embodiment, a technical solution is also proposed for adjusting the current optical zoom focal length of the smart door lock to the target optical zoom focal length when capturing images of the target object according to the contour type, and the specific steps include: determining the near focus focal length corresponding to the palm contour when determining that the contour type is a palm contour; determining the target optical zoom focal length according to the near focus focal length, and adjusting the current optical zoom focal length to the target optical zoom focal length. In this way, by comparing with the face database, rapid identity authentication can be achieved, which is suitable for passages that require rapid passage, such as subway stations, airports, etc.

[0047] In this embodiment, it should be noted that the palm vein recognition process is to shoot the shadow left by the hemoglobin in the veins of the user's palm after absorbing infrared rays, obtain the shadow image of the palm vein, and recognize the shadow image. Since the power consumption of the smart door lock is not high and the infrared power is small, the farther the palm is, the more blurred the shadow image is, and the lens focal length can be set to about 0.2 meters.

[0048] In an exemplary embodiment, the process of determining the object type of the target object based on the comparison result of the object image and the preset image is described by the following steps: determining the image selected from the face database as the preset image, and calculating the image similarity between the object image and the preset image; when it is determined that the image similarity is higher than the preset similarity, determining the face object bound to the preset image from the face database, and determining the object type indicated by the face object as the object type of the target object. In addition, the above embodiment can realize rapid identification and authority verification of the preset object by comparing with the face database, and can realize the opening of the door lock by remote command even without direct contact, which greatly improves the practicality and convenience of the smart door lock.

[0049] It should be noted that the above embodiment corresponds to the outline type of a human outline, and the object image represents a face image.

[0050] Optionally, for the palm contour, when the object image represents a palm image, an image selected from a locally stored palm database may be determined as the preset image, and the image similarity between the object image and the preset image may be calculated; when it is determined that the image similarity is higher than the preset similarity, the palm vein information bound to the preset image is determined from the palm database, and the user indicated by the palm vein information is determined as the target object. Then, the smart door lock is controlled based on whether the user indicated by the palm vein information has the unlocking authority. For example, if the user indicated by the palm vein information has the unlocking authority, the smart door lock is controlled to open.

[0051] In an exemplary embodiment, an implementation scheme for calculating the image similarity between the object image and the preset image is further provided, including: using a face detection algorithm to detect a first face in the object image and a second face in the preset image, and aligning the first face with the second face; extracting a first feature vector of the first face, and extracting a second feature vector of the second face; calculating the cosine similarity between the first feature vector and the second feature vector, and determining the cosine similarity as the image similarity. This feature vector-based similarity calculation method can improve the accuracy and efficiency of identity authentication and is suitable for scenarios requiring high-precision recognition.

[0052] In one embodiment, the comparison process of the object image and the preset image can be described in combination with the following steps: First, a face detection algorithm is used to locate and detect the face in the image. Among them, the face detection algorithm can be implemented by a deep learning model such as a Haar cascade classifier, HOG+SVM or a deep neural network. After the face is detected, the face is aligned to ensure that the faces in different images are in similar postures and positions. This can be achieved by detecting key facial feature points (such as eyes, nose and mouth) and applying an affine transformation. Next, a pre-trained deep learning model is used to extract features from the detected face. The deep learning model can convert the face image into a high-dimensional feature vector. The feature vector of the face image to be compared is compared with the feature vector in the local face library. For example, the distance between the feature vectors (such as Euclidean distance or cosine similarity) is compared with a preset threshold. If the distance is less than the threshold, the two faces are considered to be the same person; if it is greater than the threshold, they are considered to be different people. Finally, the matching face information is output according to the comparison result, or if there is no match, the information that no match is found is output.

[0053] In an exemplary embodiment, in order to better understand the implementation scheme of controlling the opening of the smart door lock based on the object type, the following implementation steps are further proposed: obtaining all control permissions bound to the object type; when it is determined that the face object belongs to a preset object and all control permissions include unlocking permissions for controlling the opening of the smart door lock, controlling the opening of the smart door lock, wherein the information of the preset object has been entered into the smart door lock; when it is determined that all control permissions do not include unlocking permissions for controlling the opening of the smart door lock, generating a prompt message of unlocking failure, and sending the prompt message to other objects, and controlling the opening of the smart door lock based on the unlocking instructions of the other objects, wherein the other objects have unlocking permissions for controlling the opening of the smart door lock. This permission verification and remote control mechanism not only improves the security of the door lock, but also enhances the flexibility and convenience of the door lock, and is suitable for scenarios such as family member management and remote visitor authorization.

[0054] Optionally, the door lock can be controlled to open in combination with the number of recognition times. For example, if the number of times the unlocking failure prompt message is generated is less than 3 times, the recognition is determined to be successful, and the smart door lock can be controlled to open. Otherwise, a prompt message is generated to remind the target object to enter information, or a prompt message is generated to remind the target object to modify permissions, or an alarm message of abnormal unlocking of the door lock can be generated. This information can help users understand the unlocking situation, improve the user's interactive experience, and improve the security of the smart door lock.

[0055] In order to better understand the process of the above-mentioned door lock control method based on palm vein technology, the implementation method process of the above-mentioned door lock control based on palm vein technology is described below in combination with an optional embodiment, but it is not used to limit the technical solution of the embodiment of the present application.

[0056] In this embodiment, a door lock control method based on palm vein technology is provided. Figure 3 is a flow chart of a door lock control method based on palm vein technology according to an embodiment of the present application, such as Figure 3 As shown, the specific steps are as follows:

[0057] Step 1: The human body approaches the door lock (depending on the trigger source) to wake up the dormant door lock.

[0058] Step 2: Start the embedded operating system, turn on the camera, and start biometric image acquisition.

[0059] Step 3: AI visual blur searches for human and palm outlines.

[0060] Step 4-1: Detecting a human outline. If the initial judgment is that it is a human outline, the next layer will be started when the system is started to perform specific face recognition and other judgments.

[0061] Step 4-2, the optical zoom device is adjusted to 1 meter telephoto (small field of view). Before starting face recognition, the optical focal length is adjusted to 1 meter telephoto. Then the face is captured and photographed for facial recognition.

[0062] Step 4-3: Collect facial information and perform algorithm comparison with the local database.

[0063] Step 5-1, detecting the palm contour.

[0064] Step 5-2, execute the optical zoom device to adjust to 0.2m close focus (large field of view). Before palm recognition, adjust the optical focal length to 0.2m close focus by optical zoom, and turn on the infrared fill light. It should be noted that what is captured at this moment is the shadow image formed by the palm veins absorbing infrared light. It is understandable that increasing the close focus will increase the field of view of the shooting, and the complete palm including the palm tip and the base of the palm can be captured.

[0065] Step 5-3, collect palm vein information and compare it with the local database. During the comparison, the distribution of palm veins can be determined to determine whether the user has the right to open the door. If so, the door opening action is executed. Otherwise, the judgment is repeated.

[0066] Step 6: Is the facial information comparison successful? If yes, proceed to step 12; otherwise, proceed to step 8.

[0067] Step 7: Is the palm vein information comparison successful? If yes, proceed to step 12; otherwise, proceed to step 9.

[0068] Step 8, determine whether the number of recognition failures exceeds 3. If yes, execute step 10, otherwise execute step 3.

[0069] Step 9, determine whether the number of recognition failures exceeds 3. If yes, execute step 11, otherwise execute step 3.

[0070] Step 10, remind the user that the authentication failed.

[0071] Step 11, remind the user that the authentication failed.

[0072] Step 12: Control the lock device to perform an unlocking action.

[0073] The above embodiment innovatively adopts the optical zoom method to first judge the outline of objects at a longer distance. The device focal length is adjusted according to the human outline and palm outline, and finally two types of images are obtained at far focus and near focus respectively, and image comparison is performed between the obtained images and the images stored on the device. It ensures that the smart door lock can accurately capture the image of the target object at different distances and scenes, improves the accuracy and security of palm vein recognition, and is suitable for a variety of security access control scenarios such as homes, offices, and hotels.

[0074] Optionally, in an exemplary embodiment, a smart door lock is also provided to implement the above-mentioned door lock control method based on palm vein technology. The smart door lock achieves rapid response and precise control by efficiently processing biometric data. It is also possible to continuously optimize the recognition algorithm and control strategy through software upgrades to improve the adaptability and user experience of the device, and is suitable for various scenarios with high requirements for security and intelligence, such as smart communities, smart office buildings, smart hotels, etc., to provide users with safer, more convenient and intelligent access control solutions. In addition, the smart door lock can also be connected to the Internet of Things platform to achieve remote monitoring and management, further enhance security, and provide users with all-round security protection.

[0075] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0076] Figure 4 is a structural block diagram of a door lock control device based on palm vein technology according to an embodiment of the present application, such as Figure 4 As shown, including:

[0077] The recognition module 42 is used to perform contour recognition on the target object within the sensing range of the smart door lock to obtain the contour type;

[0078] An adjustment module 44 is used to adjust the current optical zoom focal length when the smart door lock performs image acquisition on the target object to a target optical zoom focal length according to the contour type, and obtain an object image obtained by performing image acquisition using the target optical zoom focal length;

[0079] The control module 46 is used to determine the object type of the target object according to the comparison result between the object image and the preset image, and control the smart door lock to open based on the object type.

[0080] Through the above device, the target object located within the sensing range of the smart door lock is identified by contour recognition to obtain the contour type; the current optical zoom focal length when the smart door lock performs image acquisition on the target object is adjusted to the target optical zoom focal length according to the contour type, and the object image obtained by using the target optical zoom focal length for image acquisition is obtained; the object type of the target object is determined according to the comparison result between the object image and the preset image, and the smart door lock is controlled to open based on the object type. This application uses contour recognition and intelligent adjustment of the optical zoom focal length to make the smart door lock compatible with the face recognition means at far focus and the palm vein recognition means at near focus, so that the image of the target object can be acquired more accurately, and then the object type can be determined by image comparison, which not only improves the security of the door lock, but also improves the recognition speed and accuracy of the user in the door entry scene, optimizes the user experience, especially in the recognition of human contours and palm contours, can automatically adjust the focal length according to different object types, improve the clarity of image acquisition, and thus improve the accuracy of subsequent recognition. It can be seen that the adoption of the above technical solution solves the technical problem of how to quickly and accurately identify the user's identity and unlock the door for the user. It can quickly identify the user's identity, realize precise control of the smart door lock, and improve the unlocking efficiency.

[0081] In an exemplary embodiment, the identification module 42 is also used to: perform contour recognition on a target object within the sensing range of the smart door lock to obtain a contour type. Before performing contour recognition on a target object within the sensing range of the smart door lock to obtain a contour type, further, when it is determined that the smart door lock is in a sleep mode, use an external sensing device of the smart door lock to monitor whether there is an active object within the sensing range; when it is determined that the external sensing device of the smart door lock detects the presence of an active object within the sensing range, collect a first image of the active object; obtain a recognition result of the first image, and determine the target object based on the recognition result.

[0082] In an exemplary embodiment, the adjustment module 44 is further used to: when it is determined that the outline type is a human-shaped outline, determine the telephoto focal length corresponding to the human-shaped outline; determine the target optical zoom focal length according to the telephoto focal length, and adjust the current optical zoom focal length to the target optical zoom focal length.

[0083] In an exemplary embodiment, the adjustment module 44 is further used to: when it is determined that the contour type is a palm-shaped contour, determine the near focus focal length corresponding to the palm-shaped contour; determine the target optical zoom focal length according to the near focus focal length, and adjust the current optical zoom focal length to the target optical zoom focal length.

[0084] In an exemplary embodiment, the control module 46 is also used to illustrate the process of determining the object type of the target object based on the comparison result of the object image and the preset image through the following steps: determining the image selected from the face database as the preset image, and calculating the image similarity between the object image and the preset image; when it is determined that the image similarity is higher than the preset similarity, determining the face object bound to the preset image from the face database, and determining the object type indicated by the face object as the object type of the target object.

[0085] In an exemplary embodiment, the control module 46 is further used to: use a face detection algorithm to detect a first face in the object image and a second face in the preset image, and perform face alignment on the first face and the second face; extract a first feature vector of the first face, and extract a second feature vector of the second face; calculate the cosine similarity between the first feature vector and the second feature vector, and determine the cosine similarity as the image similarity.

[0086] In an exemplary embodiment, the control module 46 is also used to: obtain all control permissions bound to the object type; when it is determined that the face object belongs to a preset object and all control permissions include unlocking permissions for controlling the opening of the smart door lock, control the opening of the smart door lock, wherein the information of the preset object has been entered into the smart door lock; when it is determined that all control permissions do not include unlocking permissions for controlling the opening of the smart door lock, generate a prompt message of unlocking failure, and send the prompt message to other objects, and control the opening of the smart door lock based on the unlocking instructions of the other objects, wherein the other objects have unlocking permissions for controlling the opening of the smart door lock.

[0087] An embodiment of the present application further provides a storage medium, which includes a stored program, wherein the program executes any of the above methods when it is run.

[0088] Optionally, in this embodiment, the storage medium may be configured to store program codes for executing the following steps:

[0089] S1, performing contour recognition on a target object within the sensing range of the smart door lock to obtain a contour type;

[0090] S2, adjusting the current optical zoom focal length when the smart door lock performs image acquisition on the target object to the target optical zoom focal length according to the contour type, and acquiring an object image obtained by performing image acquisition using the target optical zoom focal length;

[0091] S3, determining the object type of the target object according to the comparison result between the object image and the preset image, and controlling the smart door lock to open based on the object type.

[0092] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0093] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0094] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0095] S1, performing contour recognition on a target object within the sensing range of the smart door lock to obtain a contour type;

[0096] S2, adjusting the current optical zoom focal length when the smart door lock performs image acquisition on the target object to the target optical zoom focal length according to the contour type, and acquiring an object image obtained by performing image acquisition using the target optical zoom focal length;

[0097] S3, determining the object type of the target object according to the comparison result between the object image and the preset image, and controlling the smart door lock to open based on the object type.

[0098] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0099] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0100] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0101] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A door lock control method based on palm vein technology, characterized in that: Applied to smart door locks, including: Performing contour recognition on a target object within the sensing range of the smart door lock to obtain a contour type; Adjusting the current optical zoom focal length when the smart door lock performs image acquisition on the target object to the target optical zoom focal length according to the contour type, and acquiring an object image obtained by performing image acquisition using the target optical zoom focal length; The object type of the target object is determined according to a comparison result between the object image and a preset image, and the smart door lock is controlled to open based on the object type.

2. The door lock control method based on palm vein technology according to claim 1 is characterized in that: Before performing contour recognition on a target object within the sensing range of the smart door lock to obtain a contour type, the method further includes: When it is determined that the smart door lock is in the sleep mode, using the external sensing device of the smart door lock to monitor whether there is an active object within the sensing range; When it is determined that the external sensing device of the smart door lock detects that there is a moving object within the sensing range, capturing a first image of the moving object; A recognition result of recognizing the first image is obtained, and the target object is determined according to the recognition result.

3. The door lock control method based on palm vein technology according to claim 1 is characterized in that: Adjusting the current optical zoom focal length when the smart door lock collects an image of the target object to the target optical zoom focal length according to the contour type, including: In the case where it is determined that the outline type is a human-shaped outline, determining a telephoto focal length corresponding to the human-shaped outline; The target optical zoom focal length is determined according to the telephoto focal length, and the current optical zoom focal length is adjusted to the target optical zoom focal length.

4. The door lock control method based on palm vein technology according to claim 1 is characterized in that: Adjusting the current optical zoom focal length when the smart door lock collects an image of the target object to the target optical zoom focal length according to the contour type includes: In the case where it is determined that the contour type is a palm-shaped contour, determining a near focus focal length corresponding to the palm-shaped contour; The target optical zoom focal length is determined according to the near focus focal length, and the current optical zoom focal length is adjusted to the target optical zoom focal length.

5. The door lock control method based on palm vein technology according to claim 1 is characterized in that: Determining the object type of the target object according to a comparison result between the object image and a preset image includes: Determining an image selected from a face database as the preset image, and calculating the image similarity between the object image and the preset image; When it is determined that the image similarity is higher than a preset similarity, a face object bound to the preset image is determined from the face database, and an object type indicated by the face object is determined as the object type of the target object.

6. The door lock control method based on palm vein technology according to claim 5 is characterized in that: Calculating the image similarity between the object image and the preset image includes: Using a face detection algorithm to detect a first face in the object image and a second face in the preset image, and performing face alignment on the first face and the second face; A first feature vector of the first face is extracted, and a second feature vector of the second face is extracted; a cosine similarity between the first feature vector and the second feature vector is calculated, and the cosine similarity is determined as the image similarity.

7. The door lock control method based on palm vein technology according to claim 5 is characterized in that: Controlling the smart door lock to open based on the object type includes: Get all control permissions bound to the object type; When it is determined that the face object belongs to a preset object and all the control permissions include an unlocking permission for controlling the opening of the smart door lock, controlling the smart door lock to open, wherein the information of the preset object has been entered into the smart door lock; When it is determined that all the control permissions do not include the unlocking permission for controlling the opening of the smart door lock, a prompt message of unlocking failure is generated and the prompt message is sent to other objects, and the smart door lock is controlled to open based on the unlocking instructions of the other objects, wherein the other objects have the unlocking permission for controlling the opening of the smart door lock.

8. A door lock control device based on palm vein technology, characterized in that: include: The recognition module is used to perform contour recognition on the target object within the sensing range of the smart door lock to obtain the contour type; An adjustment module, used to adjust the current optical zoom focal length when the smart door lock performs image acquisition on the target object to a target optical zoom focal length according to the contour type, and obtain an object image obtained by performing image acquisition using the target optical zoom focal length; A control module is used to determine the object type of the target object according to the comparison result of the object image and the preset image, and control the opening of the smart door lock based on the object type.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 7 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.

Images