Height detection method and device of intelligent door lock, computer device and storage medium

Abstract

The present application relates to the technical field of intelligent lock, and discloses a height detection method and device of an intelligent door lock, computer equipment and a storage medium, the method comprising: detecting the motion characteristics of a target object within the preset range of the intelligent door lock; when the motion characteristics meet the preset characteristics, acquiring an image frame sequence of the target object collected by the intelligent door lock; identifying an image frame in which the human body characteristics of the target object meet the preset conditions in the image frame sequence, to obtain at least one valid image frame; determining the current height value of the target object according to the valid image frame, and controlling the intelligent door lock to perform a control operation corresponding to the current height value. The present application solves the problems of the face recognition intelligent lock, such as the inconvenience caused by the failure of verification and the entry into the trial protection mode due to the inability to accurately identify children with insufficient height, and the lack of child growth monitoring record function.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent lock, and particularly relates to a height detection method and device of an intelligent door lock, a computer device and a storage medium. BACKGROUND

[0002] With the rapid progress of science and technology, intelligent locks are increasingly widely used in modern families and gradually replace traditional mechanical locks. Among them, face recognition intelligent door locks have become a popular choice in the market due to their convenience and high security. Such intelligent locks usually rely on radar to sense the approach of a human body, and once a human body is detected, the lock is automatically awakened and the face recognition function is quickly started to realize rapid unlocking operation, providing users with a convenient door entry experience.

[0003] However, the current face recognition intelligent lock has obvious defects. When a child with insufficient height approaches the intelligent lock, the radar will mistakenly awaken the lock as a normal user. Due to the limited height of the child, the camera can usually only capture half a face, which leads to a failed face recognition verification. After multiple verification failures, the lock enters a trial protection mode and cannot be verified to open the door again within a period of time. This not only brings great inconvenience to children using the intelligent lock, but also causes distress to parents, seriously affecting the user's experience of using the intelligent lock. In addition, the existing intelligent lock technology lacks attention to the growth of children and fails to fully utilize its own functions to provide auxiliary monitoring and recording functions for the healthy growth of children. SUMMARY

[0004] Therefore, the embodiments of the present application provide a height detection method and device of an intelligent door lock, a computer device and a storage medium to solve the problem that the face recognition intelligent lock cannot accurately identify children with insufficient height, leading to verification failure and entering a trial protection mode, which brings inconvenience to users, and the lack of a child growth monitoring and recording function.

[0005] In a first aspect, the embodiments of the present application provide a height detection method of an intelligent door lock, which comprises:

[0006] detecting a motion feature of a target object within a preset range of an intelligent door lock;

[0007] when the motion feature meets a preset feature, acquiring an image frame sequence of the target object collected by the intelligent door lock;

[0008] identifying an image frame in which a human feature of the target object meets a preset condition in the image frame sequence, to obtain at least one valid image frame;

[0009] determining a current height value of the target object according to the valid image frame, and controlling the intelligent door lock to perform a control operation corresponding to the current height value.

[0010] Further, the image frame in which the human feature of the target object in the image frame sequence meets the preset condition is obtained at least one effective image frame, comprising:

[0011] Identify the target object in the image frame sequence of the image frame;

[0012] Determine the key part feature of the target object in the image frame, and compare the key part feature with the preset feature to obtain a comparison result;

[0013] According to the comparison result, the image frame in which the image frame sequence meets the preset condition is determined, and at least one effective image frame is obtained.

[0014] Further, the current height value of the target object is determined according to the effective image frame, comprising:

[0015] Obtain the installation height value of the target lens on the intelligent door lock;

[0016] Detect the distance value between the target object and the target lens, and measure the angle value between the center of the picture of the effective image frame and the top part of the target object;

[0017] Based on the installation height value, the distance value and the angle value, the current height value of the target object is calculated.

[0018] Further, the control operation corresponding to the current height value of the intelligent door lock is controlled, comprising:

[0019] Compare the current height value with the preset height value;

[0020] If the current height value is less than or equal to the preset height value, the growth monitoring function of the intelligent door lock is triggered, and the growth curve of the target object is constructed according to the current height value;

[0021] Or, if the current height value is greater than the preset height value, the wake-up operation of the intelligent door lock is executed, and the face recognition function of the intelligent door lock is triggered.

[0022] Further, the growth monitoring function of the intelligent door lock is triggered, and the growth curve of the target object is constructed according to the current height value, comprising:

[0023] Obtain the historical height value of the target object;

[0024] Analyze the current height value and the historical height value to obtain the height change trend of the target object;

[0025] construct a growth curve based on the height change trend, and display the growth curve of the target object to the intelligent door lock.

[0026] Further, after determining the current height value of the target object according to the effective image frame, the method further comprises:

[0027] detecting a target object in the effective image frame, wherein the target object is an object capable of lifting a human body and having a bearing function;

[0028] matching the shape feature of the target object with a preset shape feature in a preset object database to obtain a matching result;

[0029] if the matching result is a matching success, correcting the current height value based on the shape feature of the target object to obtain a corrected current height value.

[0030] Further, the correcting the current height value based on the shape feature of the target object to obtain a corrected current height value comprises:

[0031] labeling an edge of the target object according to the shape feature to obtain a first labeling position and a second labeling position, wherein the first labeling position is used to represent an upper edge position of the target object, and the second labeling position is used to represent a lower edge position of the target object;

[0032] calculating a labeling distance between the first labeling position and the second labeling position;

[0033] correcting the current height value according to the labeling distance to obtain a corrected current height value.

[0034] In a second aspect, an embodiment of the present application provides a face recognition method of an intelligent door lock, and the method comprises:

[0035] obtaining a current height value of a target object in a preset range of the intelligent door lock;

[0036] determining whether the current height value reaches a preset height value;

[0037] if the preset height value is reached, enabling a face recognition function of the intelligent door lock to perform face recognition on the target object to obtain a first recognition result, or if the preset height value is not reached, enabling an auxiliary recognition function of the intelligent door lock to control a cloud platform of the intelligent door lock to perform a moving operation until a face region of the target object is in a recognition position to obtain a second recognition result.

[0038] Further, the gimbal of the smart door lock is controlled to perform a moving operation until a face region of the target object is in a recognition position, and a second recognition result is obtained, including:

[0039] An effective image frame collected by the smart door lock is obtained.

[0040] A missing condition of a face feature in the effective image frame is detected.

[0041] A moving direction of a gimbal in the smart door lock is determined according to the missing condition, and the gimbal is controlled to perform a moving operation according to the moving direction until the face feature is located in a recognition region of the smart door lock, and a second recognition result is obtained.

[0042] In a third aspect, an embodiment of the present application provides a height detection device of a smart door lock, and the device includes:

[0043] A detection module is configured to detect a motion feature of a target object in a preset range of a smart door lock.

[0044] A first obtaining module is configured to obtain an image frame sequence of the target object collected by the smart door lock when the motion feature meets a preset feature.

[0045] An identification module is configured to identify, in the image frame sequence, an image frame in which a human body feature of the target object meets a preset condition, and obtain at least one effective image frame.

[0046] A determination module is configured to determine a current height value of the target object according to the effective image frame, and control the smart door lock to perform a control operation corresponding to the current height value.

[0047] In a fourth aspect, an embodiment of the present application provides a face recognition device of a smart door lock, and the device includes:

[0048] A second obtaining module is configured to obtain a current height value of a target object in a preset range of a smart door lock.

[0049] A judgment module is configured to judge whether the current height value reaches a preset height value.

[0050] An enabling module is configured to enable a face recognition function of the smart door lock to perform face recognition on the target object and obtain a first recognition result if the preset height value is reached, or enable an auxiliary recognition function of the smart door lock to control a gimbal of the smart door lock to perform a moving operation until a face region of the target object is in a recognition position, and obtain a second recognition result if the preset height value is not reached.

[0051] In a fifth aspect, an embodiment of the present application provides a computer device, comprising a memory and a processor, which are communicatively connected with each other, and the memory stores computer instructions, and the processor executes the computer instructions to perform the method in the first aspect or any of the corresponding embodiments.

[0052] In a sixth aspect, an embodiment of the present application provides a computer readable storage medium, which stores computer instructions, and the computer instructions are used to make a computer perform the method in the first aspect or any of the corresponding embodiments.

[0053] The method provided by the embodiments of the present application has the following beneficial effects:

[0054] The method provided by the embodiments of the present application can help to accurately locate the object that needs to be detected in height, reduce unnecessary waste of computing resources and improve detection efficiency by detecting the motion characteristics of the target object in the preset range of the intelligent door lock. When the motion characteristics meet the preset characteristics, the image frame sequence is obtained, the effective data can be obtained, and the interference of invalid data is avoided. The effective image frame is obtained by identifying the image frame meeting the preset condition, which can improve the accuracy of subsequent height calculation and ensure the reliability of data source. The current height value is determined according to the effective image frame, which can realize accurate measurement of the height of the target object, effectively solve the problem that the face recognition intelligent lock enters the test protection mode due to the failure of verification caused by the failure to accurately identify the height of children, and also provide a data basis for the growth monitoring function, which is helpful for paying attention to the growth of children and recording the height change trend to construct a growth curve and provide intuitive information for the growth of children for parents.

[0055] The method provided by the embodiments of the present application further improves the accuracy of height measurement by obtaining the installation height value of the target lens on the intelligent door lock, detecting the distance value between the target object and the target lens, and measuring the angle value between the center of the effective image frame and the top part of the target object when determining the current height value. In the step of identifying the image frame in which the human body characteristics of the target object meet the preset condition in the image frame sequence, the effective image frame is determined by determining the characteristics of the key parts and comparing with the preset characteristics, which enhances the accuracy and reliability of identification. In addition, the target object in the effective image frame is detected and the current height value is corrected by shape feature matching, which can exclude the height misjudgment caused by the height-increasing object, make the height detection result more real and accurate, and further improve the stability and practicality of the entire intelligent door lock height detection function.

[0056] The method provided by the embodiment of the application can provide basic data for subsequent judgment by acquiring the current height value of the target object in the preset range of the intelligent door lock, so that the intelligent door lock can flexibly adjust the recognition strategy according to the actual height of the target object. By judging whether the current height value reaches the preset height value, different height scenarios are distinguished, so as to avoid the recognition process being disordered or failing due to height mismatch, and the stability and reliability of recognition are improved. When the preset height value is reached, the face recognition function is enabled, so that identity verification can be completed in a normal height scenario, the unlocking process is simplified, and the convenience and fluency of daily use are enhanced. When the preset height value is not reached, the auxiliary recognition function is enabled and the PTZ is controlled to move, fully considering children or short people, ensuring that special height groups can use smoothly, expanding the application range, embodying the humanized design, and automatically adjusting the PTZ to accurately position the face area, effectively reducing the recognition failure risk caused by manual or deviation, further improving the recognition accuracy and success rate, and strengthening the adaptability and stability of the product in complex scenarios. BRIEF DESCRIPTION OF DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the specific embodiments of the present application or the prior art, the drawings needed to be used in the specific embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0058] Figure 1 is a flowchart of a height detection method of an intelligent door lock according to an embodiment of the present application;

[0059] Figure 2 is a schematic diagram of height detection under the lens view angle of an intelligent door lock according to an embodiment of the present application.

[0060] Figure 3 is a structural block diagram of a height detection system of an intelligent door lock according to an embodiment of the present application;

[0061] Figure 4 is a flowchart of a face recognition method of an intelligent door lock according to an embodiment of the present application;

[0062] Figure 5 is a structural block diagram of a height detection device of an intelligent door lock according to an embodiment of the present application;

[0063] Figure 6 is a structural block diagram of a face recognition device of an intelligent door lock according to an embodiment of the present application;

[0064] Figure 7 is a hardware structure schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0065] So that the purposes, technical solutions and advantages of the embodiments of the present application are more apparent, the following will describe the technical solutions in the embodiments of the present application in a clear and complete manner with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0066] According to the embodiments of the present application, a height detection method and device of a smart door lock, a computer device and a storage medium are provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0067] In the present embodiment, a height detection method of a smart door lock is provided, Figure 1 is a flowchart of the height detection method of the smart door lock according to the embodiments of the present application, as Figure 1 shown, the flow includes the following steps:

[0068] Step S11, detecting the motion characteristics of the target object within the preset range of the smart door lock.

[0069] In the present embodiment, the radar device of the smart door lock continuously monitors the preset range. When an object approaches, the motion speed, trajectory and other information of the object are analyzed to detect the motion characteristics. If the motion speed is within the normal human walking speed range (such as between 0.5 meters per second and 2 meters per second) and the motion trajectory changes regularly in a straight line or a slight curve, similar to the path of a human walking towards the door, it is determined that the object meets the preset characteristics, which provides a basis for subsequent accurate acquisition of image frame sequences, avoids unnecessary operations caused by non-human targets (such as small animals running quickly, wind blowing debris, etc.), and improves the system resource utilization efficiency and detection accuracy.

[0070] Step S12, when the motion characteristics meet the preset characteristics, acquiring the image frame sequence of the target object collected by the smart door lock.

[0071] In the embodiments of the present application, when it is detected that the motion characteristics of the target object meet the preset characteristics, that is, it is determined that an object similar to a human walking approaches the intelligent door lock, the intelligent lock control system activates the camera to capture images at a specific frame rate (for example, 20 frames per second), and obtains a sequence of continuous door image frames. The sequence can record the state changes of the target object in front of the door, providing a data basis for subsequent identification of human characteristics and calculation of height. The capture time stamp of each image frame is recorded during acquisition, facilitating time sequence correlation and data filtering during multi-frame image analysis, thereby improving the accuracy and reliability of the height detection process, enabling the intelligent door lock to accurately determine the height and perform corresponding operations.

[0072] Step S13: identifying, in the image frame sequence, an image frame in which the human characteristics of the target object meet the preset conditions, to obtain at least one valid image frame.

[0073] In the embodiments of the present application, step S13 includes the following steps A1-A3:

[0074] Step A1: identifying the target object in the image frames in the image frame sequence.

[0075] Specifically, after obtaining the target object image frame sequence collected by the intelligent door lock, the target object in each image frame is first identified to provide a basis for subsequent related human characteristic analysis operations. In actual implementation, a target detection module of a computer vision algorithm can be used to process each image frame. For example, a YOLO series algorithm or a Faster R-CNN deep learning target detection algorithm can be used. These algorithms run on a high-performance embedded processor of the intelligent lock. A pre-trained model containing a large number of human images is used to scan each image frame, and the region where the target object (human body) is located is framed out, thereby achieving target object identification.

[0076] Step A2: determining the key part features of the target object in the image frame, and comparing the key part features with preset features to obtain a comparison result.

[0077] Specifically, after identifying the target object in the image frame, the key part features of the target object need to be determined and compared with the preset features. The key part features can include the positions and shapes of the head, shoulders, waist, knees, feet, etc., which are used to judge the human posture and calculate the height. The preset features are standard feature ranges of the corresponding key parts of a normal human body, and the comparison can determine whether the key parts are normal. In terms of implementation, the key part features can be determined by using human posture estimation related technologies in computer vision algorithms, such as using the OpenPose algorithm to detect human key points and output coordinate positions and other information, based on which the features such as key part shapes and relative position relationships are analyzed. The preset features are reasonable range values obtained by statistical analysis of key part data of a large number of normal human postures, and the actual detected key part features are compared with the preset features. If the key part features are within the preset range, it is determined that the key parts are normal, and if the key part features exceed the preset range, it is determined that the key parts are abnormal.

[0078] Step A3, determine the image frames in the image frame sequence that meet the preset condition according to the comparison result, and obtain at least one effective image frame.

[0079] Specifically, the image frames in the image frame sequence that meet the preset condition are determined according to the comparison result, and these image frames are screened out as effective image frames for subsequent analysis and processing. The preset condition is set based on the comparison result of the key part features, and the image frame in which the key part features of the human body all meet the preset feature range is determined to meet the preset condition. The implementation is to write a screening logic code according to the set comparison determination rule, run the code on the embedded processor of the smart lock, and traverse each frame in the image frame sequence. If the features of the human body in a certain frame image are all within the preset normal feature range after comparison, it is determined that the frame image meets the preset condition, and it is marked as an effective image frame and collected to form an effective image frame set for subsequent determination of the current height value of the target object and the like.

[0080] Step S14, determining the current height value of the target object according to the effective image frame, and controlling the smart door lock to perform a control operation corresponding to the current height value.

[0081] In the embodiments of the present application, the current height value of the target object is determined according to the effective image frame, including the following steps B1-B3:

[0082] Step B1, obtaining the installation height value of the target lens on the smart door lock.

[0083] Specifically, the installation height value of the target lens on the smart door lock is first obtained, which is a known fixed parameter and plays a basic role in calculating the height of the target object. It is an important reference data in the height calculation process. The implementation is that after the smart door lock is installed, the installer can use a tape measure or other accurate measuring tool to measure the distance from the ground to the center position of the lens and record it, and store it in the configuration parameter storage area for subsequent height calculation. The standard installation height value corresponding to the conventional door body is pre-set during the production process and is fixed in the program code as the default value, and then it is updated according to the actual installation situation to ensure the accuracy of the value used for height calculation.

[0084] Step B2, detecting the distance value between the target object and the target lens, and measuring the angle value between the center of the effective image frame and the top part of the target object.

[0085] Specifically, the distance value of the target object and the target lens and the angle value of the center of the effective image frame and the top of the head of the target object are detected, which respectively affect the height calculation result under the geometric relationship and are necessary elements for constructing a right triangle model to calculate the height. The height can be calculated according to the geometric principle in combination with the two. Specifically, the distance value can be detected by using the radar ranging function of the smart lock. After the target object enters the preset range, the radar calculates the distance value according to the corresponding principle (such as the speed of light and the round-trip time of the signal) by emitting, receiving and analyzing the signal propagation time. The angle value is measured by using the angle measurement module of the computer vision algorithm. The coordinate positions of the center of the picture and the top of the head of the target object are determined, and then the angle value is calculated by using the trigonometric function, thereby providing support for accurately calculating the height.

[0086] Step B3, calculating the current height value of the target object based on the installation height value, the distance value and the angle value.

[0087] Specifically, after obtaining the relevant values, the current height of the target object, i.e., the current height value, can be calculated according to the geometric principle of the right triangle and the specific mathematical formula, thereby realizing quantitative calculation. According to the tangent function of the trigonometric function and the length relationship of the right triangle, the height calculation formula is as follows:

[0088]

[0089] Among them, H is the current height value of the target object; Y is the installation height value; θ is the angle value; and X is the distance value.

[0090] As an example, as shown in Figure 2 , it is assumed that the cat eye camera installation height Y is 110 cm. If the height of the target object exceeds the door lock installation height value Y, the distance X of the target object from the door lock is 150 cm, and the angle θ between the center of the picture and the top of the head of the target object can be calculated by the cat eye camera to be 30°. Then the height H of the target object can be calculated to be 196 cm. If the height of the target object does not exceed the door lock installation height value Y, the distance X of the target object from the door lock is 100 cm, and the angle θ between the center of the picture and the top of the head of the target object can be calculated by the cat eye camera to be -10°. Then the height H of the target object can be calculated to be 92.4 cm.

[0091] In the embodiments of the present application, the control operation corresponding to the current height value is performed on the smart door lock, including the following steps C1-C3:

[0092] Step C1, comparing the current height value with the preset height value.

[0093] Specifically, the preset height value is a standard height value pre-set for distinguishing different situations. The preset height value can be configured in the intelligent door lock system setting. The user can set it according to the actual scene requirement (such as the height limit situation of children at home) or set a default value according to the common height classification standard when the product is shipped and store it in the configuration parameter storage area. By comparing the actual measured current height value, the height range of the target object can be determined, and the subsequent corresponding operation of the intelligent door lock can be determined.

[0094] Step C2, if the current height value is less than or equal to the preset height value, triggering the growth monitoring function of the intelligent door lock, and constructing the growth curve of the target object according to the current height value.

[0095] Specifically, when the current height value is less than or equal to the preset height value through comparison, the growth monitoring function of the intelligent door lock is triggered, and the growth curve of the target object is constructed according to the current height value. This is because if the height of the target object is in this range, it is likely that the target object is a child or other population that needs to be concerned about its growth. By constructing the growth curve, the change trend of the height of the target object over time can be intuitively recorded, and the user can easily understand the growth status of the target object.

[0096] In the embodiments of the present application, step C2 includes the following steps C21-C23:

[0097] Step C21, obtaining the historical height value of the target object.

[0098] Specifically, the historical height value is the height data of the target object at different time points recorded in the same measurement manner before, which is an important basis data for constructing the growth curve. The intelligent door lock storage area will create a special space to store the past measured height data. These data can be stored in order according to time sequence or measurement serial number, etc. When constructing the growth curve, the system will read the corresponding historical height value information from it, and prepare for subsequent analysis.

[0099] Step C22, analyzing the current height value and the historical height value to obtain the height change trend of the target object.

[0100] Specifically, the current height value and the obtained historical height value are analyzed, and the height data at different time points are statistically analyzed, such as calculating the height difference between adjacent time points, observing the change of growth speed, etc., to obtain the height change trend of the target object, and determine whether it is stable growth, rapid growth or slow growth, etc. The implementation method is to use simple mathematical statistical method, such as calculating the height growth rate by dividing the difference between the height values measured at adjacent two times by the corresponding time interval, or drawing a scatter plot to observe the distribution rule of data points to judge the height change trend. These analysis operations can be realized by running corresponding data analysis code in the embedded processor of the intelligent door lock.

[0101] Step C23, constructing a growth curve based on the height change trend, and displaying the growth curve of the target object to the smart door lock.

[0102] Specifically, the growth curve of the target object can be displayed on the smart door lock with display function, or transmitted to the external device such as mobile phone APP connected thereto through Bluetooth, Wi-Fi or other communication methods for display. The user can intuitively understand the height change of the target object. The implementation method is to use a graph drawing algorithm, with time as the horizontal axis and height value as the vertical axis, to connect the height data points corresponding to each time point to form a curve to show the change trend. When displayed on the smart door lock, the display driver program is called to present the curve image, and when transmitted to the APP end, the APP displays the relevant data according to the predetermined interface layout and drawing rules.

[0103] Step C3, if the current height value is greater than the preset height value, the wake-up operation of the smart door lock is performed, and the face recognition function of the smart door lock is triggered.

[0104] Specifically, after determining the current height value of the target object, the current height value is compared with the preset height value. If the current height value is greater than the preset height value, the wake-up operation of the smart door lock is performed, that is, the system issues an instruction to activate the relevant function module, so that it changes from standby or low-power state to normal working state, such as lighting the display screen, starting the sensor, etc., to prepare for subsequent face recognition and other operations. Then the face recognition function is triggered, and the smart door lock uses the built-in camera and other image acquisition devices to obtain the face image of the target object again, and analyzes and compares it through the pre-stored face recognition algorithm and model to determine the identity legitimacy. If the recognition is successful, the lock opening operation and other operations are performed according to the preset permissions and settings. If the recognition fails, an alarm or a prompt is issued to the user to perform other identity verification methods.

[0105] In the embodiments of the present application, after determining the current height value of the target object according to the valid image frame, the method further includes the following steps S21-S23:

[0106] Step S21, detecting the target object in the valid image frame, wherein the target object is an object capable of raising the human body and having a bearing function.

[0107] In the embodiments of the present application, after determining the current height value of the target object according to the valid image frame, the target object in the valid image frame can also be detected, wherein the target object refers to those objects capable of raising the human body and having a bearing function, such as paper boxes, stools and the like commonly seen in daily life. In order to realize this detection, the object detection technology in computer vision algorithm can be used to identify and classify each object in the valid image frame, and the target object meeting the above characteristics is screened out.

[0108] Step S22, match the shape feature of the target object with the preset shape feature in the preset object database to obtain a matching result.

[0109] In the embodiment of the present application, the shape feature of the target object is matched with the preset shape feature in the preset object database. First, the preset shape feature information of various common cushioning objects such as paper boxes, stools, etc. is extracted from the preset object database, wherein the feature information can include the shape, contour, texture and other visual features of the object. Then, the corresponding shape feature of the target object detected in the effective image frame is compared one by one, and whether the two are matched is determined by calculating the similarity between the features, and finally the matching result is obtained. For example, if the detected object contour, shape and other features are highly similar to the preset shape feature of the paper box in the database, it can be determined that the matching is successful; otherwise, the matching fails.

[0110] Step S23, if the matching result is matching success, the current height value is corrected based on the shape feature of the target object to obtain a corrected current height value.

[0111] In the embodiment of the present application, step S23 includes the following steps D1-D3:

[0112] Step D1, marking the edge of the target object according to the shape feature to obtain a first marking position and a second marking position, wherein the first marking position is used to represent the upper edge position of the target object, and the second marking position is used to represent the lower edge position of the target object.

[0113] Specifically, first, the target object in the image is identified by using a computer vision algorithm to determine its specific position and range in the image, and this process involves image segmentation algorithm and other technologies. Through the analysis of the color, texture, edge and other features of the image, the target object is separated from the background. After identifying the target object, the edge of the object is detected by using edge detection operators such as Sobel operator and Canny operator, the pixel change of the object edge is highlighted to more clearly determine the contour, and then the uppermost and lowermost boundary points of the target object contour are found as the first marking position and the second marking position respectively. Finally, the determined first marking position and second marking position are marked and recorded as (x1, y1) and (x2, y2) in the form of image coordinates with the top-left corner of the two-dimensional image plane as the origin, the horizontal right as the positive direction of x-axis, and the vertical down as the positive direction of y-axis.

[0114] Step D2, calculating the marking distance between the first marking position and the second marking position.

[0115] Specifically, when calculating the marker distance between the first marker position (x1, y1) and the second marker position (x2, y2), the calculation method includes but is not limited to the following: Euclidean distance: the straight-line distance between two points can be obtained, which is applicable in most cases. Manhattan distance: when the target object shape is regular and the image distribution is approximately horizontal or vertical, it can be used to approximately calculate the marker distance. Compared with the Euclidean distance, it focuses more on the sum of horizontal and vertical distances, and is simple to calculate, and can more intuitively reflect the size characteristics of the object in a specific scenario. Actual distance conversion: the distances calculated above are mostly pixel distances of the image. To obtain the marker distance corresponding to the actual height of the target object, it is necessary to convert it according to the image scale. If it is known that each pixel represents an actual length of a centimeters, then the actual marker distance is the pixel distance multiplied by a centimeters / pixel, thereby obtaining the marker distance value in centimeters, so as to unify the calculation and comparison with other actual height values.

[0116] Step D3, correcting the current height value according to the marker distance to obtain a corrected current height value.

[0117] Specifically, after calculating the marker distance, the height of the target object corresponding to the marker distance needs to be subtracted from the previously obtained current height value. First, determine the height correspondence. Since the marker distance represents the vertical size of the target object in the image, the actual height value corresponding to the marker distance can be determined by using the known image scale or other geometric relationships. For example, when the marker distance is b pixels and each pixel represents an actual height of h centimeters, the actual height of the target object is b*h centimeters, and the corrected current height value is H' = H-b*h centimeters. Through this correction, the height measurement error caused by the target object raising the human body can be effectively eliminated, so that the height value is closer to the true height, thereby improving the accuracy and reliability of the height measurement.

[0118] In the embodiment, a height detection system of a smart door lock is provided, Figure 3 is a structural block diagram of the height detection system of the smart door lock according to the embodiment of the present application, as Figure 3 shown, the system comprises an image acquisition unit 100, an image processing unit 200, a height detection unit 300 and a door lock control unit 400;

[0119] The image acquisition unit 100 is configured to acquire a sequence of image frames containing a target object in the area in front of the smart door lock through the camera of the smart door lock, and send the sequence of image frames to the image processing unit 200;

[0120] The image processing unit 200 is configured to process the acquired sequence of image frames and select valid image frames for height detection, and send the valid image frames to the height detection unit 300;

[0121] The height detection unit 300 is configured to calculate the current height value of the target object according to the effective image frame and the related parameters, and send the current height value to the door lock control unit 400.

[0122] The door lock control unit 400 is configured to perform corresponding door lock control operation according to the current height value of the target object, such as touch length monitoring or face recognition function.

[0123] In the embodiment, an unlocking method of the intelligent door lock is also provided, Figure 4 is a flowchart of the height detection method of the intelligent door lock according to the embodiment of the present application, as shown in the figure, the flow includes the following steps: Figure 4

[0124] Step S31, obtaining the current height value of the target object within the preset range of the intelligent door lock.

[0125] It should be noted that in the normal use condition of the intelligent door lock, the distance between the user and the door lock is relatively fixed when the user performs identity verification, and is generally within 1 meter. If the height of the child is in a specific condition, so that only part of the face is within the recognition range of the camera, it is easy to cause recognition deviation, at this time, the recognition angle of the camera needs to be adjusted, for example, by means of a cloud platform. The effective recognition angle of the door lock camera is generally between 155 degrees and 185 degrees, and only when the face is within this angle range, the face can be recognized.

[0126] In the embodiment of the present application, the intelligent door lock can obtain the current height value of the target object in various ways. For example, by using the distance sensor and image analysis technology built in the door lock, the approximate distance between the target object and the door lock is measured first, and then the body contour or key part (such as the top of the head) of the target object in the captured image frame is recognized, and the relative height value is calculated by combining the preset geometric relationship and algorithm. This step is like building a basic framework for the subsequent recognition process. Only when the height of the target object is clear, can the accurate recognition operation be carried out, and the recognition failure or low efficiency caused by blindly using a single recognition mode can be avoided.

[0127] Step S32, judging whether the current height value reaches the preset height value.

[0128] ​In the embodiments of the present application, the preset height value is a key threshold determined through a large number of experiments and data analysis. Its setting comprehensively considers the installation height of the door lock camera, the height distribution range of common adults and children, and the best recognition area of the face recognition algorithm and other factors. By comparing the obtained current height value, the door lock system can quickly judge the height type of the target object, whether it belongs to the adult of regular height or the lower height group (such as children) that needs special treatment. This judgment process is like an intelligent distributor, which can guide the recognition process to the most suitable path according to different situations, improve the flexibility and accuracy of the entire recognition system, and reduce the recognition failure or resource waste caused by false judgment.

[0129] Step S33, if the preset height value is reached, the face recognition function of the intelligent door lock is enabled to perform face recognition on the target object to obtain a first recognition result, or if the preset height value is not reached, the auxiliary recognition function of the intelligent door lock is enabled to control the PTZ of the intelligent door lock to perform a moving operation until the face region of the target object is in a recognition position to obtain a second recognition result.

[0130] In the embodiments of the present application, if the height of the target object reaches the preset height value, the face region is usually in the regular recognition area of the door lock camera, and the face recognition function is directly enabled for the most efficient and convenient. It captures face images with the help of image acquisition devices, extracts and analyzes information such as features, contours, and textures with specific algorithms, compares and matches with stored legal user face data, obtains a first recognition result to determine whether to unlock. This way can quickly and accurately verify the identity in adult daily scenarios, significantly improving the user experience.

[0131] In the embodiments of the present application, if the preset height value is not reached, the auxiliary recognition function of the intelligent door lock is enabled to control the PTZ of the intelligent door lock to perform a moving operation until the face region of the target object is in a recognition position to obtain a second recognition result, including the following steps E1-E3:

[0132] Step E1, obtaining an effective image frame collected by the intelligent door lock.

[0133] Specifically, after the intelligent door lock enables the auxiliary recognition function, it screens out effective image frames, which can be the effective image frames mentioned in step A3, and will not be described in detail here.

[0134] Step E2, detecting the missing situation of the face feature in the effective image frame.

[0135] Specifically, the image recognition and analysis algorithm is used to detect the face region in each valid image frame to check whether there is a problem of missing part of the face features. For example, only half of the face is captured, resulting in the key face organs such as eyes and nose not being completely presented; or due to the angle problem, the mouth and other parts are not present in the image, which all belong to the face feature missing situation. The intelligent door lock marks which specific face elements are missing in the current valid image frame by carefully comparing each feature that a normal complete face should have, and determines the completeness of the face presented in the current image through detection and analysis, thereby providing a key basis for determining how the PTZ should move to fill in the missing face features and let the face be completely presented in the recognition area for the next step.

[0136] Step E3, determining the moving direction of the PTZ in the intelligent door lock according to the missing situation, and controlling the PTZ to perform a moving operation according to the moving direction until the face features are located in the recognition area of the intelligent door lock, and obtaining a second recognition result.

[0137] Specifically, based on the missing situation of the face features in the valid image frame detected in the foregoing, the system starts to develop a moving strategy for the PTZ. If it is detected that the forehead part of the face features is missing in the image, it indicates that the camera shooting angle is too low, and then the PTZ needs to move upward by a certain angle to raise the shooting angle so as to capture the forehead part; if the chin part of the features is missing, it indicates that the shooting angle is too high, and then the PTZ should move downward to adjust the angle. Moreover, during the moving process, it is not a one-time large-amplitude movement, but a small-amplitude high-frequency adjustment according to the intelligent search path, for example, the initial small-amplitude high-frequency up-and-down swing scanning is performed, and at the same time, the camera continuously captures images and detects whether the face region enters a more optimal recognition range. When the face region approaches the image center but is not yet in the best recognition position, the PID control algorithm is used to calculate the motor rotation angle and speed according to the deviation amount for fine adjustment, so that the camera can track the face until it is stably located in the center of the best recognition area. During the whole process, it is continuously concerned whether the face features are completely presented, and when the face region is stably located in the image center standard recognition area and the face features are complete and clear after being verified by multiple images, it indicates that the conditions for accurate recognition have been met, and then the auxiliary recognition function stops the movement of the PTZ, triggers the face recognition process, performs feature extraction, comparison and matching with the legal user face data based on the complete and clear face image, and finally obtains a second recognition result to determine whether to unlock.

[0138] A height detection device of a smart door lock and an unlocking device of a smart door lock are also provided in the embodiment. The device is used to implement the above embodiment and preferred embodiments, and details have been described above. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and contemplated.

[0139] The embodiment provides a height detection device of a smart door lock, as shown in the accompanying drawings, comprising: Figure 5

[0140] A detection module 51 is configured to detect a motion feature of a target object within a preset range of the smart door lock.

[0141] A first acquisition module 52 is configured to acquire an image frame sequence of the target object collected by the smart door lock when the motion feature meets a preset feature.

[0142] An identification module 53 is configured to identify an image frame in which a human feature of the target object meets a preset condition in the image frame sequence, to obtain at least one valid image frame.

[0143] A processing module 54 is configured to determine a current height value of the target object according to the valid image frame, and control the smart door lock to perform a control operation corresponding to the current height value.

[0144] In an optional embodiment of the present application, the first acquisition module 52 is configured to identify the target object in the image frame in the image frame sequence, determine a key part feature of the target object in the image frame, and compare the key part feature with a preset feature to obtain a comparison result, and determine an image frame meeting a preset condition in the image frame sequence according to the comparison result to obtain at least one valid image frame.

[0145] In an optional embodiment of the present application, the processing module 54 further comprises an acquisition sub-module and a control sub-module.

[0146] The acquisition sub-module is configured to acquire an installation height value of a target lens on the smart door lock, detect a distance value between the target object and the target lens, measure an angle value between a picture center of the valid image frame and a top part of the target object, and calculate the current height value of the target object based on the installation height value, the distance value and the angle value.

[0147] The control sub-module is configured to compare the current height value with a preset height value, trigger a growth monitoring function of the smart door lock according to the current height value to construct a growth curve of the target object if the current height value is less than or equal to the preset height value, or perform a wake-up operation of the smart door lock and trigger a face recognition function of the smart door lock if the current height value is greater than the preset height value. ​

[0148] The control submodule is configured to acquire a historical height value of the target object; analyze the current height value and the historical height value to obtain a height change trend of the target object; construct a growth curve based on the height change trend; and display the growth curve of the target object to the smart door lock.

[0149] In an optional embodiment of the present application, the device further comprises a correction module configured to detect a target object in the valid image frame, wherein the target object is an object capable of elevating a human body and having a bearing function; match a shape feature of the target object with a preset shape feature in a preset object database to obtain a matching result; and correct the current height value based on the shape feature of the target object to obtain a corrected current height value if the matching result is a matching success.

[0150] In an optional embodiment of the present application, the correction module is configured to mark edges of the target object according to the shape feature to obtain a first marking position and a second marking position, wherein the first marking position is used to represent an upper edge position of the target object, and the second marking position is used to represent a lower edge position of the target object; calculate a marking distance between the first marking position and the second marking position; and correct the current height value according to the marking distance to obtain a corrected current height value.

[0151] The present embodiment provides a face recognition device of a smart door lock, as shown in Figure 6 , comprising:

[0152] The second acquisition module 61 is configured to acquire a current height value of a target object within a preset range of the smart door lock.

[0153] The judgment module 62 is configured to judge whether the current height value reaches a preset height value.

[0154] The enabling module 63 is configured to enable a face recognition function of the smart door lock to perform face recognition on the target object to obtain a first recognition result if the preset height value is reached, or enable an auxiliary recognition function of the smart door lock to control a PTZ of the smart door lock to perform a moving operation until a face region of the target object is in a recognition position to obtain a second recognition result if the preset height value is not reached.

[0155] In an optional embodiment of the present application, the enabling module 63 is configured to acquire a valid image frame collected by the smart door lock; detect a missing condition of a face feature in the valid image frame; determine a moving direction of the PTZ of the smart door lock according to the missing condition, and control the PTZ to perform a moving operation according to the moving direction until the face feature is located in a recognition region of the smart door lock to obtain the second recognition result.

[0156] Please refer to Figure 7 , Figure 7is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system).

[0157] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0158] The memory 20 stores instructions that can be executed by at least one processor 10, so as to enable at least one processor 10 to execute the method shown in the above embodiment.

[0159] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created based on the use of a computer device for displaying a small program landing page, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0160] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0161] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0162] The embodiments of the present application further provide a computer readable storage medium, the method according to the embodiments of the present application can be implemented in hardware, firmware, or be implemented as computer codes recorded in a storage medium, or be implemented by downloading and storing in a remote storage medium or non-transitory machine readable storage medium and storing in a local storage medium, so that the method described herein can be processed by such software in a storage medium using a general purpose computer, a special purpose processor, or programmable or special hardware. Wherein, the storage medium can be a disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk or a solid state disk, etc.; further, the storage medium can also include a combination of the above-mentioned types of memories. It can be understood that the computer, processor, microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer codes, when the software or computer codes are accessed and executed by the computer, processor or hardware, the method shown in the above embodiments is implemented.

[0163] Although the embodiments of the present application are described in conjunction with the drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A height detection method of a smart door lock, characterized by, The method comprises: Detect the motion characteristics of the target object within the preset range of the smart door lock; When the motion feature meets the preset feature, obtaining a sequence of image frames of the target object captured by the smart door lock; Identifying an image frame in the image frame sequence whose human body features of the target object meet a preset condition, and obtaining at least one valid image frame; Determine the current height value of the target object according to the valid image frame, and control the smart door lock to perform a control operation corresponding to the current height value; After determining the current height value of the target object based on the valid image frame, the method further includes: detecting the target object in the valid image frame, wherein the target object is an object that can elevate a human body and has a load-bearing function; matching the appearance features of the target object with preset appearance features in a preset object database to obtain a matching result; if the matching result is a successful match, correcting the current height value based on the appearance features of the target object to obtain a corrected current height value.

2. The method of claim 1, wherein, The step of identifying an image frame in the image frame sequence whose human features of the target object meet a preset condition and obtaining at least one valid image frame comprises: identifying a target object in an image frame of the sequence of image frames; Determining key part features of the target object in the image frame, and comparing the key part features with preset features to obtain a comparison result; An image frame in the image frame sequence that meets a preset condition is determined according to the comparison result to obtain at least one valid image frame.

3. The method of claim 1, wherein, Determining the current height value of the target object according to the valid image frame includes: Obtaining the installation height value of the target lens on the smart door lock; Detecting the distance between the target object and the target lens, and measuring the angle between the center of the effective image frame and the top of the target object's head; A current height value of the target object is calculated based on the installation height value, the distance value, and the angle value.

4. The method of claim 1, wherein, The controlling the smart door lock to perform a control operation corresponding to the current height value includes: Comparing the current altitude value with a preset altitude value; If the current height value is less than or equal to the preset height value, the growth monitoring function of the smart door lock is triggered, and a growth curve of the target object is constructed according to the current height value; Alternatively, if the current height value is greater than the preset height value, the wake-up operation of the smart door lock is executed and the face recognition function of the smart door lock is triggered.

5. The method of claim 4, wherein, The triggering of the growth monitoring function of the smart door lock and constructing a growth curve of the target object according to the current height value includes: Obtaining the historical height value of the target object; Analyze the current height value and the historical height values ​​to obtain a height change trend of the target object; A growth curve is constructed based on the height change trend, and the growth curve of the target object is displayed on the smart door lock.

6. The method of claim 1, wherein, The correcting the current height value based on the shape feature of the target object to obtain a corrected current height value includes: According to the contour feature, an edge of the target object is marked to obtain a first marking position and a second marking position, wherein the first marking position is used to represent an upper edge position of the target object, and the second marking position is used to represent a lower edge position of the target object; A marking distance between the first marking position and the second marking position is calculated; The current height value is corrected according to the marking distance to obtain a corrected current height value.

7. The method of claim 1, wherein, After the current height value of the target object is determined according to the effective image frame, the method further comprises: obtaining the current height value of the target object in the preset range of the intelligent door lock; determining whether the current height value reaches a preset height value; if the preset height value is reached, enabling the face recognition function of the intelligent door lock to perform face recognition on the target object to obtain a first recognition result, or if the preset height value is not reached, enabling the auxiliary recognition function of the intelligent door lock to control the gimbal of the intelligent door lock to perform a moving operation until the face region of the target object is in a recognition position to obtain a second recognition result.

8. The method of claim 7, wherein, The control of the gimbal of the intelligent door lock to perform a moving operation until the face region of the target object is in a recognition position to obtain a second recognition result comprises: obtaining an effective image frame collected by the intelligent door lock; detecting a missing condition of a face feature in the effective image frame; determining a moving direction of the gimbal of the intelligent door lock according to the missing condition, and controlling the gimbal to perform a moving operation according to the moving direction until the face feature is located in a recognition region of the intelligent door lock to obtain a second recognition result.

9. A height detection device for a smart door lock, characterized in that: The device comprises: a detection module configured to detect a motion feature of a target object in a preset range of an intelligent door lock; a first obtaining module configured to, when the motion feature meets a preset feature, obtain an image frame sequence of the target object collected by the intelligent door lock; an identification module configured to identify, in the image frame sequence, an image frame in which a human body feature of the target object meets a preset condition to obtain at least one effective image frame; a determination module configured to determine a current height value of the target object according to the effective image frame, and control the intelligent door lock to perform a control operation corresponding to the current height value; The device further comprises a correction module configured to detect a target object in an effective image frame, wherein the target object is an object capable of elevating a human body and having a bearing function; match a contour feature of the target object with a preset contour feature in a preset object database to obtain a matching result; if the matching result is a matching success, correct the current height value based on the contour feature of the target object to obtain a corrected current height value.

10. A computer device, comprising: comprise: a memory and a processor, which are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the method in any one of claims 1 to 8.

11. A computer readable storage medium, characterized in that, The computer readable storage medium stores computer instructions, and the computer instructions are used to make a computer execute the method in any one of claims 1 to 8.

Images