Identification method, identification device and door lock system

The integration of human body and face recognition in smart door locks optimizes power usage and security by dynamically adjusting camera usage, addressing frequent triggering and user cooperation issues, enhancing user experience and system stability.

CN119068583APending Publication Date: 2024-12-03ZHEJIANG SUNNY INTELLIGENT OPTICAL TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411533965.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-31
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Existing smart door locks with integrated cat's eye and face recognition modules face issues with high energy consumption due to frequent triggering, system overload, misrecognition, and the need for user cooperation, affecting user experience and security.

Method used

An identification method that integrates human body recognition and face recognition, dynamically adjusting camera usage based on human body detection results to optimize power consumption and reduce false alarms, ensuring accurate identity verification without user cooperation.

Benefits of technology

The method reduces unnecessary power consumption, minimizes false alarms, enhances security, and improves user experience by integrating human body and face recognition technologies, ensuring smooth operation and efficient energy management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119068583A_ABST
    Figure CN119068583A_ABST
Patent Text Reader

Abstract

The invention provides an identification method, an identification device and a door lock system, which can solve the problem of frequent triggering without action cooperation of a user, improve the unlocking fluency and improve the use experience of the user. The recognition method comprises the steps that when an inductive sensor detects that an object enters a recognition range, a first camera is started to collect a first image for human body detection; judging whether a human body is detected; if yes, performing human body recognition based on the current human body; if not, closing the first camera; comparing the human body recognition result with a pre-stored database to judge whether the current human body is a stranger; turning off the first camera in response to the fact that the current human body is a high-frequency stranger; in response to the fact that the current human body is not a stranger, a second camera is started to collect a second image for face recognition, and an unlocking program is executed after face verification succeeds.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent door locks, and in particular to an identification method, an identification device and a door lock system. Background Art

[0002] With the development of intelligent technology, the application of smart door locks has gradually become popular. Existing smart door locks often integrate cat's eye and face recognition modules. A common usage scenario is: when someone enters the monitoring range of the door lock, the PIR (Passive Infrared) sensor or radar on the door lock is triggered, and the cat's eye and face recognition modules will be activated respectively, that is, the cat's eye starts automatic recording, and the face recognition module performs face verification, and the two modules are independent of each other and do not affect each other.

[0003] However, this type of smart door lock with integrated cat-eye and face recognition modules still faces some problems and challenges in practical applications. For example, the continuously running camera and recognition module consume a lot of power, especially when frequently triggered. How to effectively manage energy consumption is an important issue. In addition, frequent triggering of the recognition module is also a huge test for the face recognition system, which may cause system overload or misrecognition.

[0004] An existing solution is to first use the first camera and the second camera to collect the first image and the second image of the target respectively, and send the second image to the display for display, and then use the control module to perform biometric identification on the target based on the first image and the second image, and drive the door lock component based on the identification result. However, although this solution uses the information of the cat's eye camera for double verification of biometric identification, it achieves optimal utilization of resources, can reduce costs and improve door opening safety, but there is still a problem of frequent triggering.

[0005] To solve the problem of frequent triggering, another existing solution is to use cameras for monitoring, gesture recognition, and line of sight recognition to add predefined user cooperation actions before performing face recognition. However, although this solution can avoid the frequent triggering to a certain extent, it requires the user's action cooperation, which greatly affects the smoothness of door opening and thus affects the user experience. Summary of the invention

[0006] One advantage of the present invention is that it provides an identification method, an identification device and a door lock system, which can solve the problem of frequent triggering without the need for user cooperation, thereby improving the smoothness of unlocking and the user's experience.

[0007] Another advantage of the present invention is that it provides an identification method, an identification device and a door lock system. In one embodiment of the present invention, the identification method integrates human body recognition and face recognition technology, so that the door lock system can effectively identify and record all people in front of the door to improve security.

[0008] Another advantage of the present invention is that it provides an identification method, an identification device and a door lock system. In one embodiment of the present invention, the identification method can avoid unnecessary power consumption by optimizing the trigger conditions, thereby helping to improve the energy efficiency of the system and achieve energy-saving management.

[0009] Another advantage of the present invention is to provide an identification method, an identification device and a door lock system. In one embodiment of the present invention, the identification method can reduce the possibility of false alarms and improve the stability of the door lock system and the user experience.

[0010] Another advantage of the present invention is that it provides an identification method, an identification device and a door lock system, wherein, in one embodiment of the present invention, the identification device can automatically mark frequently appearing strangers and take corresponding measures when they appear again, so as to further save energy consumption and improve security protection capabilities.

[0011] Another advantage of the present invention is that it provides an identification method, an identification device and a door lock system, wherein, in one embodiment of the present invention, the identification device is capable of all-weather monitoring, not only ensuring effective monitoring under various lighting conditions, but also ensuring high-precision facial recognition in various environments.

[0012] Another advantage of the present invention is that it provides an identification method, an identification device and a door lock system. In one embodiment of the present invention, the door lock system can realize the organic combination of human body recognition and face recognition, making the maintenance and upgrading of the system more convenient and improving the user experience.

[0013] Another advantage of the present invention is to provide an identification method, an identification device and a door lock system, wherein in order to achieve the above-mentioned purpose, no complicated structure and design are required in the present invention. Therefore, the present invention successfully and effectively provides a solution, not only providing a simple identification method, an identification device and a door lock system, but also increasing the practicality and reliability of the identification method, the identification device and the door lock system.

[0014] In order to achieve at least one of the above advantages or other advantages and purposes of the present invention, the present invention provides an identification method, comprising the steps of: When the sensing sensor detects that an object has entered the recognition range, the first camera is turned on to collect a first image for human body detection; Determine whether a human body is detected: if so, perform human body recognition based on the current human body; if not, turn off the first camera; Compare the human body recognition result with the pre-stored database to determine whether the current human body is a stranger; In response to the current human body being a high-frequency stranger, turning off the first camera; and In response to the current human body being non-stranger, the second camera is turned on to capture a second image for face recognition, and an unlocking procedure is executed after the face verification is successful.

[0015] According to one embodiment of the present application, in the step of determining whether a human body is detected: if so, performing human body recognition based on the current human body; if not, turning off the first camera: performing human body recognition in combination with prior knowledge of key point detection.

[0016] According to one embodiment of the present application, in the step of turning on the second camera in response to the current human body being a non-stranger to capture a second image for face recognition, and executing the unlocking procedure after the face verification is successful: face detection, face quality assessment, feature extraction and feature comparison are performed in sequence for the captured second image, so as to indicate that the face verification is successful when the comparison is successful.

[0017] According to one embodiment of the present application, the identification method further comprises the steps of: In response to the current human body being a general stranger, performing face detection based on the first image to determine whether the detected face meets a face recognition condition; In response to satisfying the face recognition condition, turning on the second camera to capture the second image for face recognition, and executing the unlocking procedure after the face verification is successful; and In response to not meeting the face recognition condition, turning off the first camera.

[0018] According to one embodiment of the present application, in the step of performing face detection based on the first image to determine whether the detected face meets face recognition conditions in response to the current human body being a general stranger: performing face image quality assessment based on the detected face to determine that the detected face meets face recognition conditions when the detected face image meets quality requirements.

[0019] According to one embodiment of the present application, in response to meeting the face recognition condition, turning on the second camera to capture a second image for face recognition, and executing the unlocking procedure after the face verification is successful: first set the face recognition parameters, and then turn on the second camera to perform the face verification operation.

[0020] According to an embodiment of the present application, face recognition parameters are set to increase the recognition threshold of feature comparison.

[0021] According to another aspect of the present application, the present application further provides an identification device, including: Inductive sensors; First camera; A second camera; and A processing module, wherein the processing module has a built-in human body recognition algorithm and a face recognition algorithm, and the processing module is communicatively connected to the sensing sensor, the first camera and the second camera, for executing the steps of any of the above-mentioned recognition methods.

[0022] According to one embodiment of the present application, the sensing sensor is a radar sensor or a PIR sensor; the first camera is a cat's eye camera; and the second camera is a single infrared camera or a TOF camera.

[0023] According to another aspect of the present application, the present application further provides a door lock system, comprising: a door lock body; and The above-mentioned identification device is installed on the door lock body and is used to control the door lock body to execute the unlocking procedure when the face verification is successful. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flowchart of an identification method according to an embodiment of the present application; Figure 2 is a schematic block diagram of an identification device according to an embodiment of the present application; Figure 3 An application example of the identification device according to the above embodiment of the present application is shown; Figure 4 It is a block diagram of a door lock system according to an embodiment of the present application.

[0025] Explanation of main component symbols: 1. Door lock system; 10. Identification device; 11. Induction sensor; 12. First camera; 13. Second camera; 14. Processing module; 20. Door lock body.

[0026] The above description of the main component symbols is combined with the accompanying drawings and specific implementation methods to further illustrate the present invention in detail. DETAILED DESCRIPTION

[0027] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0028] In the present invention, the term "one" in the claims and the specification should be understood as "one or more", that is, in one embodiment, the number of an element can be one, while in another embodiment, the number of the element can be multiple. Unless it is clearly indicated in the disclosure of the present invention that the number of the element is only one, the term "one" cannot be understood as unique or single, and the term "one" cannot be understood as a limitation on the quantity.

[0029] In the description of the present invention, it should be understood that "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through a medium. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0030] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0031] Considering that the existing solutions either still have the problem of frequent triggering, or although they can avoid the frequent triggering to a certain extent, they require the user's action cooperation, which greatly affects the smoothness of door opening and thus affects the user experience. In view of this, the present application creatively proposes a recognition method, a recognition device and a door lock system, which can solve the problem of frequent triggering without the need for user action cooperation, improve the smoothness of door opening and improve the user experience.

[0032] Specifically, refer to the accompanying drawings of the specification of this application. Figure 1 According to an embodiment of the present application, a recognition method is provided, which may include the steps of: S100: When the sensing sensor detects that an object has entered the recognition range, the first camera is turned on to collect a first image for human body detection; S200: Determine whether a human body is detected: if so, perform human body recognition based on the current human body; if not, turn off the first camera; S300: comparing the human body recognition result with a pre-stored database to determine whether the current human body is a stranger; S400: In response to the current human body being a high-frequency stranger, turning off the first camera; and S500: In response to the current human body being a non-stranger, turning on the second camera to capture a second image for face recognition, and executing an unlocking procedure after the face verification is successful.

[0033] It is worth noting that the high-frequency strangers mentioned in this application refer to the strangers that appear frequently when the system marks them, and the strangers are confirmed by the user as high-frequency strangers (such as neighbors next door or property personnel, etc.); the non-strangers mentioned in this application refer to the human body images detected at the beginning of the module return, and the corresponding human body images are confirmed by the user as non-strangers (such as the user himself and his family, etc.). It is understandable that the information of high-frequency strangers and non-strangers mentioned in this application (including human body information and face information) are stored in the database for management.

[0034] In this way, on the one hand, the recognition method of the present application can respond when an object enters the recognition range, so as to turn on the first camera for video monitoring and perform human body detection on the first image collected by the first camera; if no human body is detected, it means that no one is close to the door lock (it may be other small animals entering the recognition range), and the first camera is turned off to stop recording, so that the door lock returns to the standby state, avoiding frequent triggering of the door lock system by small animals or other irrelevant factors, which helps to reduce the possibility of false alarms and improve the stability and user experience of the system; on the other hand, the recognition method of the present application can determine whether the current human body is a stranger based on the human body recognition result when a human body is detected. If it is a high-frequency stranger, it means that there is no need to open the door (it may be a neighbor or property staff passing by), and the first camera is turned off to stop recording, so that the door lock returns to the standby state, avoiding unnecessary power consumption, so as to save energy and improve the energy efficiency of the system. In other words, the recognition method of the present application can dynamically adjust the working state of each module according to the actual situation through an intelligent algorithm. For example, when a frequently appearing stranger is detected, some functions can be temporarily turned off to save energy. Especially in the case of frequent triggering, unnecessary power consumption can be avoided by optimizing the triggering conditions, thereby improving the energy efficiency of the system.

[0035] In addition, when the recognition method of the present application determines that the current human body is not a stranger, the second camera will be turned on, and the second image captured by the second camera will be recognized by face recognition to provide more accurate identity verification, ensuring that only authorized persons can open the door lock, thereby improving the security of the system. In other words, the recognition method of the present application integrates human recognition technology and face recognition technology, and can not only use human recognition technology to detect activities in front of the door in a wider range, but also accurately identify approaching persons even in complex environments, and can also use face recognition technology to provide more accurate identity verification, so as to ensure that only authorized non-strangers can open the door lock without the need for user action cooperation, thereby improving the smoothness of unlocking and improving the user experience.

[0036] For example, in step S200 of the recognition method of the present application, human body recognition can be performed in combination with prior knowledge of key point detection, thereby reducing the difficulty of human body recognition. For example, key point information can be added when storing a human body database to distinguish the front and back information of the body, so that the front and back are first judged and then recognized during the recognition process, thereby reducing the difficulty of recognition.

[0037] In addition, in step S500 of the recognition method of the present application, face detection, face quality assessment, feature extraction and feature comparison are performed in sequence for the second image collected. If the comparison is successful, it indicates that the face verification is successful, and the unlocking information is sent to the door lock, so that the door lock executes the unlocking procedure, and then the door lock enters the standby state. It is understandable that in the case of extremely low probability, the comparison may fail. If the face recognition is a high-frequency stranger, the first camera and the second camera are turned off, so that the door lock returns to the standby state.

[0038] According to the above embodiments of the present application, Figure 1 As shown, the identification method may further include the steps of: S600: In response to the current human body being a general stranger, performing face detection based on the first image to determine whether the detected face meets a face recognition condition; S700: In response to satisfying the face recognition condition, turning on the second camera to capture the second image for face recognition, and executing the unlocking procedure after the face verification is successful; and S800: In response to not meeting the face recognition condition, turning off the first camera.

[0039] It is worth noting that the general strangers mentioned in this application refer to all persons except high-frequency strangers and non-strangers. In this way, when the user and his family members make mistakes in human body recognition due to factors such as changes in clothing and posture, the recognition method of this application can still perform face detection based on the first image first, and then turn on the second camera for face recognition when the detected face meets the face recognition conditions, and execute the unlocking procedure after the face verification is successful, so as to avoid the problem that the user and his family members cannot unlock the door due to human body recognition errors. It can be understood that if the detected face meets the face recognition conditions, it indicates that the current human body (general stranger) is facing the door body, and it is believed that it has the intention to open the door, so the recognition method of this application turns on the second camera for more accurate face recognition to execute the face verification procedure; and if the detected face does not meet the face recognition conditions, it means that the current human body may be facing away from the door body, and it is believed that it has no intention to open the door, so the recognition method of this application directly turns off the first camera, so that the door lock returns to the standby state, and there is no need to execute the subsequent face recognition program, avoiding unnecessary power consumption, which helps to improve the energy efficiency of the system.

[0040] Optionally, in step S600 of the recognition method of the present application, a facial image quality assessment is performed based on the detected face, so that when the detected facial image meets the quality requirements, it is determined that the detected face meets the facial recognition condition.

[0041] Optionally, in step S700 of the recognition method of the present application, the face recognition parameters are set first, and then the second camera is turned on to perform the face verification operation. For example, when the detected face meets the face recognition conditions, the face parameters are set first to increase the recognition threshold of the feature comparison, and then the second camera is turned on to collect the second image for face recognition, and the unlocking procedure is executed after the face verification is successful to prevent the problem of misidentification by strangers.

[0042] It is worth mentioning that according to another aspect of the present application, Figure 2 As shown, an embodiment of the present application further provides a recognition device 10, which may include a sensing sensor 11, a first camera 12, a second camera 13, and a processing module 14 with a built-in human recognition algorithm and a face recognition algorithm, and the processing module 14 can be communicatively connected to the sensing sensor 11, the first camera 12, and the second camera 13, and is used to execute the steps of the above-mentioned recognition method.

[0043] Optionally, the inductive sensor 11 is implemented as a radar sensor for detecting whether a moving object enters a recognition range. It is understandable that in other examples of the present application, the inductive sensor 11 may also be implemented as a PIR sensor.

[0044] Optionally, the first camera 12 is implemented as a cat's eye camera, which is used to obtain monitoring videos or images within the camera range to perform human body detection on objects entering the recognition range, and can realize human body recognition, which is used to detect and monitor strangers passing by the door, thereby enhancing security monitoring capabilities.

[0045] Preferably, the cat's eye camera can be implemented as a dual-channel camera, in which case the first image collected is a color image containing color information in a bright environment and an infrared image in a dim environment, so as to have the ability to clearly image both during the day and at night, ensuring all-weather monitoring effects. It is understandable that the cat's eye camera used in this application can use high resolution and infrared night vision technology to ensure effective monitoring under various light conditions.

[0046] Optionally, the second camera 13 is implemented as a single infrared camera, which is used to capture a human body detected by the cat's eye camera to obtain a face image for face recognition, so as to send a signal to unlock the door lock when the face verification is successful. It is understandable that in other examples of the present application, the second camera 13 can also be implemented as a TOF (Time-of-Flight) camera, etc.

[0047] It is worth noting that in the recognition device 10 of the present application, the output data streams of a cat's eye camera and a single infrared camera will enter the same set of I / O (Input / Output) and computing devices, so as to implement human body recognition and face recognition algorithms based on the above hardware.

[0048] For example, Figure 3 As shown, when the radar senses that a moving object has entered the recognition range, the cat's eye camera is turned on to collect the first image and enter the human body recognition algorithm: first, human body detection is performed based on the first image, and it is determined whether a human body is detected: if not, the cat's eye recording is turned off; if yes, human body recognition is performed; then, it is determined whether the detected human body is a high-frequency stranger: if yes, it is determined whether the user has set it to turn off the cat's eye when a high-frequency stranger appears, and the cat's eye recording is turned off if the user has set it; if no, it is further determined whether the detected human body is a general stranger; thereafter, if the detected human body is not a general stranger, the face recognition algorithm is entered; if the detected human body is a general stranger, face detection is performed, and it is determined whether the face recognition conditions are met through face image quality evaluation: if no, it ends and the cat's eye camera is turned off; if yes, the face recognition algorithm is entered.

[0049] like Figure 3 As shown, when entering the face recognition algorithm, the face recognition parameters are set first, and then the infrared camera is turned on to collect the second image; then, based on the second image, face detection, face image quality assessment, liveness detection, feature extraction and feature comparison are performed in sequence; after that, it is determined whether the feature comparison is successful. If so, it indicates that the face verification is successful and the unlocking procedure is executed. It can be understood that the information of high-frequency strangers and non-strangers is stored in the database so as to participate in human recognition in the human recognition algorithm and participate in feature comparison in the face recognition algorithm.

[0050] It is worth mentioning that according to another aspect of the present application, Figure 4 As shown, the present application further provides a door lock system 1, which may include the above-mentioned recognition device 10 and a door lock body 20, wherein the recognition device 10 is mounted on the door lock body 20, and is used to control the door lock body 20 to execute an unlocking procedure when face verification is successful.

[0051] In this way, the door lock system of the present application integrates human body recognition technology and face recognition technology, realizes the organic combination of human body recognition and face recognition, and provides a comprehensive security solution; at the same time, the door lock system of the present application makes system maintenance and upgrades more convenient through modular design, which helps to improve the user experience.

[0052] 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.

[0053] The above embodiments only express several implementation methods of the present invention, 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 ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention.

Claims

1. An identification method, characterized in that Includes steps: When the sensing sensor detects that an object has entered the recognition range, the first camera is turned on to collect a first image for human body detection; Determine whether a human body is detected: if so, perform human body recognition based on the current human body; If not, turn off the first camera; Compare the human body recognition result with the pre-stored database to determine whether the current human body is a stranger; In response to the current human body being a high-frequency stranger, turning off the first camera; as well as In response to the current human body being non-stranger, the second camera is turned on to capture a second image for face recognition, and an unlocking procedure is executed after the face verification is successful.

2. The identification method according to claim 1, characterized in that: In the step of determining whether a human body is detected: if so, performing human body recognition based on the current human body; if not, turning off the first camera: performing human body recognition in combination with prior knowledge of key point detection.

3. The identification method according to claim 1, characterized in that: In the step of turning on the second camera to capture a second image for face recognition in response to the current human body being non-stranger, and executing the unlocking procedure after the face verification is successful: face detection, face quality assessment, feature extraction and feature comparison are performed in sequence for the captured second image, so that when the comparison is successful, it indicates that the face verification is successful.

4. The identification method according to any one of claims 1 to 3, characterized in that: The identification method further comprises the steps of: In response to the current human body being a general stranger, performing face detection based on the first image to determine whether the detected face meets a face recognition condition; In response to satisfying the face recognition condition, turning on the second camera to capture the second image for face recognition, and executing the unlocking procedure after the face verification is successful; as well as In response to not meeting the face recognition condition, turning off the first camera.

5. The identification method according to claim 4, characterized in that: In the step of performing face detection based on the first image to determine whether the detected face meets face recognition conditions in response to the current human body being a general stranger: performing face image quality assessment based on the detected face to determine that the detected face meets face recognition conditions when the detected face image meets quality requirements.

6. The identification method according to claim 4, characterized in that: In response to meeting the face recognition condition, turning on the second camera to capture the second image for face recognition, and executing the unlocking procedure after the face verification is successful: first set the face recognition parameters, and then turn on the second camera to perform the face verification operation.

7. The identification method according to claim 6, characterized in that: By setting the face recognition parameters, the recognition threshold of feature comparison can be increased.

8. An identification device, characterized in that include: Inductive sensors; First camera; Second camera; as well as A processing module, wherein the processing module has a built-in human body recognition algorithm and a face recognition algorithm, and the processing module is communicatively connected to the sensing sensor, the first camera, and the second camera, for executing the steps of the recognition method as described in any one of claims 1 to claim 7.

9. The identification device according to claim 8, characterized in that The sensing sensor is a radar sensor or a PIR sensor; the first camera is a cat's eye camera; and the second camera is a single infrared camera or a TOF camera.

10. Door lock system, characterized in that, include: Door lock body; and According to the identification device as described in claim 8 or claim 9, the identification device is installed on the door lock body, and is used to control the door lock body to execute an unlocking procedure when face verification is successful.

Citation Information

Patent Citations

  • Method for detecting and identifying intrusion

    CN102521578A

  • Access control method, device and equipment and computer readable storage medium

    CN113160475A

  • Equipment awakening method and device, equipment and storage medium

    CN115240296A

  • Intelligence lock and system

    CN205314704U

  • Smart door system with facial recognition function

    KR102341883B1