Child lock control method, device and equipment, medium, program product and electrical equipment

Abstract

The invention relates to the technical field of household appliance control, and discloses a child lock control method, device and equipment, a medium, a program product and electrical equipment. Performing feature extraction on the whole body action video to obtain behavior feature information and gait feature information of the monitored target; performing comprehensive analysis according to the behavior feature information and the gait feature information, and judging whether the monitoring target is a child; and controlling the child lock based on the judgment result. By performing action analysis on the monitored target, whether the approaching target is a child or not can be automatically judged, intelligent control is performed on the child lock, manual operation of a user is not needed, and the use process is simplified, so that the situations such as misoperation or imitation operation of the child are avoided, the safety, reliability and operation convenience of electrical equipment are improved, and the user experience is improved. And the trust of the user on the electrical equipment is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of household appliance control technology, and in particular to a child lock control method, device, equipment, medium, program product and electrical equipment. Background Art

[0002] Child locks are a crucial safety feature in household appliances, preventing children from misoperating them and potentially causing safety hazards or damaging the appliance. Currently, household appliances are typically equipped with mechanical child locks, which require manual operation by the user, such as turning a knob, pressing a button, or performing a specific key combination. However, these child locks are inconvenient for the elderly and those with limited mobility, and can be easily misoperated or disengaged by children imitating adult operations, posing a safety hazard. Summary of the Invention

[0003] In view of this, the present invention provides a child lock control method, device, equipment, medium, program product and electrical equipment to solve the problem that child lock control is inconvenient to operate and still has safety hazards.

[0004] In a first aspect, the present invention provides a child lock control method, which is applied to electrical equipment equipped with a child lock, and the method includes: obtaining a full-body motion video of a monitored target; performing feature extraction on the full-body motion video to obtain behavioral feature information and gait feature information of the monitored target; performing a comprehensive analysis based on the behavioral feature information and gait feature information to determine whether the monitored target is a child; and controlling the child lock based on the judgment result.

[0005] The child lock control method provided by the present invention extracts corresponding behavioral and gait features from a full-body motion video of a monitored target, performs a comprehensive analysis based on the extracted behavioral and gait feature information, determines whether the monitored target is a child, and controls the child lock based on the judgment result. By analyzing the motion of the monitored target, the present invention can automatically determine whether the approaching target is a child and intelligently control the child lock, eliminating the need for manual user operation and simplifying the use process, thereby preventing children from operating the device incorrectly or imitating the user's operation. This improves the safety, reliability, and ease of operation of electrical equipment and enhances user trust in the equipment.

[0006] In an optional embodiment, before obtaining the full-body movement video of the monitored target, the method further includes: obtaining heat distribution information of the initial target, and judging whether the initial target is a human target based on the heat distribution information; if the initial target is determined to be a human target, obtaining the horizontal distance between the bottom of the human target and the electrical device, and the straight-line distance between the top of the human target and the electrical device, and determining the body height of the human target based on the horizontal distance and the straight-line distance; judging whether the body height is less than a preset height threshold, and judging whether the horizontal distance is less than a preset safety distance threshold; if the body height is less than the preset height threshold, and the horizontal distance is less than the preset safety distance threshold, then judging the human target to be a monitored target.

[0007] The present invention can determine that the target approaching the electrical equipment is a human being by judging based on the heat distribution and height of the target, and preliminarily determine that the target is a child, thereby preventing the child lock from being opened due to the approach of non-human objects or adults, which would cause operational inconvenience to the normal operation of the electrical equipment.

[0008] In an optional embodiment, before determining that the human target is a monitoring target, the method also includes: determining whether the duration of the body height being less than a preset height threshold is greater than a preset time threshold; if the duration is greater than the preset time threshold, the human target is determined to be a monitoring target.

[0009] By judging the time when the height is less than a preset height threshold, the present invention can further determine that the target is a child, avoid misidentification caused by actions such as bending or squatting when an adult approaches, and improve the accuracy of child lock control.

[0010] In an optional embodiment, feature extraction is performed on the whole-body motion video to obtain behavioral feature information of the monitoring target, including: identifying the first preset body key point of the monitoring target in each frame of the whole-body motion video, and determining the first position information of the first preset body key point in each frame of the whole-body motion video; determining the movement amplitude of the monitoring target according to the first position information corresponding to each frame of the whole-body motion video; and determining the movement frequency of the monitoring target according to the first position information corresponding to continuous frames of the whole-body motion video.

[0011] By extracting behavioral features of the monitoring target, the present invention can capture the unique behavioral features of children, including large movement amplitude and fast movement, thereby providing reference information for further determining whether the monitoring target is a child.

[0012] In an optional embodiment, feature extraction is performed on the whole-body motion video to obtain gait feature information of the monitored target, including: identifying the foot key points and the second preset body key points of the monitored target in each frame of the whole-body motion video, and determining the second position information and third position information corresponding to the foot key points and the second preset body key points in each frame of the whole-body motion video; determining the stride and step frequency of the monitored target based on the second position information corresponding to the continuous frames of the whole-body motion video; and determining the posture characteristics of the monitored target based on the third position information corresponding to the continuous frames of the whole-body motion video.

[0013] By extracting gait features from the monitoring target, the present invention can capture the unique gait characteristics of children, including biomechanical characteristics such as a small stride, a fast walking speed, and obvious fluctuations in the center of gravity, thereby providing reference information for further determining whether the monitoring target is a child.

[0014] In an optional embodiment, a comprehensive analysis is performed based on the behavioral characteristic information and the gait characteristic information to determine whether the monitored target is a child, including: obtaining a predetermined first weight of the behavioral characteristic information and a second weight of the gait characteristic information; standardizing the behavioral characteristic information and the gait characteristic information to obtain standardized behavioral characteristic values ​​and gait characteristic values; performing weighted averaging on the standardized behavioral characteristic values ​​and gait characteristic values, and the corresponding first weight and second weight to obtain a comprehensive action characteristic value; and determining whether the comprehensive action characteristic value exceeds a preset characteristic threshold, and if so, determining that the monitored target is a child.

[0015] By conducting a comprehensive analysis based on behavioral characteristics and gait characteristics, the present invention can construct a double-layer verification mechanism to accurately determine whether the monitored target is a child, prevent misidentification to the greatest extent, improve the accuracy and reliability of child approach detection, and thereby improve the reliability, stability and safety of electrical equipment.

[0016] In an optional embodiment, the child lock is controlled based on the judgment result, including: if the monitored target is a child, the child lock is turned on, otherwise the child lock is controlled to be in a closed state; real-time judgment is made as to whether the horizontal distance exceeds a preset safety threshold, if so, the child lock is turned off, otherwise the child lock is controlled to be in an open state.

[0017] The present invention can intelligently control the child lock by identifying the target approaching as a child and identifying the child leaving. The user does not need to manually operate the child lock, and it also avoids the occurrence of accidental triggering of the child by mechanical child lock control, thereby enhancing the user's trust in the product and improving the user experience.

[0018] In the second aspect, the present invention provides a child lock control device, which is applied to electrical equipment equipped with a child lock. The device includes: a video acquisition module, which is used to obtain a full-body movement video of the monitored target; a feature extraction module, which is used to extract features from the full-body movement video to obtain behavioral feature information and gait feature information of the monitored target; a target recognition module, which is used to perform a comprehensive analysis based on the behavioral feature information and gait feature information to determine whether the monitored target is a child; and a child lock control module, which is used to control the child lock based on the judgment result.

[0019] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to thereby execute the child lock control method of the first aspect or any corresponding embodiment thereof.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the child lock control method of the first aspect or any corresponding embodiment thereof.

[0021] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions, which are used to enable a computer to execute the child lock control method of the first aspect or any corresponding embodiment thereof.

[0022] In the sixth aspect, the present invention provides an electrical device, including: a child lock, a control module and a video acquisition device; the child lock is used to put the electrical device in a locked state; the video acquisition device is used to capture a full-body motion video of the monitored target; the control module is connected to the child lock and the control module, and is used to execute the child lock control method of the above-mentioned first aspect or any corresponding embodiment thereof based on the full-body motion video, and control the child lock.

[0023] Because the electrical equipment works based on the child lock control method and has the same effect as the child lock control method, it will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0025] Figure 1 is a flowchart of a child lock control method according to an embodiment of the present invention;

[0026] Figure 2 2 is a schematic diagram of a feature extraction process of a child lock control method according to an embodiment of the present invention;

[0027] Figure 3 1 is a schematic diagram of a child lock unlocking process according to a child lock control method according to an embodiment of the present invention;

[0028] Figure 4 is a flow chart of another child lock control method according to an embodiment of the present invention;

[0029] Figure 5 is a schematic diagram of height calculation according to another child lock control method according to an embodiment of the present invention;

[0030] Figure 6 2. It is a schematic diagram of a child lock closing process according to another child lock control method according to an embodiment of the present invention;

[0031] Figure 7 is a flowchart of another child lock control method according to an embodiment of the present invention;

[0032] Figure 8 is a structural block diagram of a child lock control device according to an embodiment of the present invention;

[0033] Figure 9 is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention;

[0034] Figure 10 2 is a schematic diagram of the system composition of an electrical device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0036] The embodiment of the present invention is applicable to the scenario where a child lock is used to prevent children from operating the electric heater by mistake during the use of household appliances, with electric heaters being used as an example. Electric heaters are a common household appliance and are widely used for heating in winter. However, there are certain safety hazards in the use of electric heaters, especially for children. The surface temperature of the electric heater is extremely high during operation, and the surface temperature of some heaters can reach 80°C-120°C. If a child turns on the electric heater by himself without the control of the child lock, or if a child turns on the electric heater by mistake with the control of the child lock, burns may occur. The embodiment of the present invention provides a child lock control method, which achieves the effect of accurately identifying children and intelligently controlling the child lock by comprehensively analyzing the behavioral characteristics and gait characteristics of the monitoring target.

[0037] According to an embodiment of the present invention, an embodiment of a child lock control method is 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 a 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.

[0038] In this embodiment, a child lock control method is provided, which can be used for the above-mentioned electrical appliances, such as electric heaters, washing machines, electric fans, etc. Figure 1 : is a flow chart of a child lock control method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0039] Step S101: Acquire a full-body motion video of the monitored target.

[0040] Specifically, in an embodiment of the present invention, taking an electric heater as an example, a camera is deployed on the electric heater, which can capture images of the monitoring target when the monitoring target approaches. In order to accurately determine whether the monitoring target is a child, the camera installed on the electric heater uses a wide-angle high-definition lens with a resolution of 1080P or above, which can clearly capture the full-body movement details of the monitoring target. The camera installation angle is determined according to the acquisition results to ensure that it can cover a certain radius around the electric heater, such as a radius of 1.5 meters to 2 meters. It can not only fully capture the full-body movements close to the monitoring target, but also avoid image distortion caused by improper shooting angles, which affects the extraction of feature information. Correspondingly, if Figure 2 As shown, the embodiment of the present invention obtains a full-body motion video of the monitoring target captured by a camera. The full-body motion video contains rich feature information of the monitoring target, which can provide a key basis for accurately judging whether the monitoring target is a child.

[0041] Step S102 : extracting features from the whole-body motion video to obtain behavioral feature information and gait feature information of the monitored target.

[0042] Specifically, in the embodiments of the present invention, there are significant differences between children and adults due to differences in physiological development stages, motor skills, etc. For example, in terms of body shape, children are relatively short, and the proportions of various body parts are significantly different from those of adults, such as the head accounts for a larger proportion and the limbs are shorter; in terms of movement, children have unique movement patterns, such as smaller steps and faster stride frequency when walking, larger arm swing amplitude and obvious fluctuation of body center of gravity when running, and jumping, squatting, crawling and other movements that adults rarely perform when playing; in terms of facial appearance, children have significant differences from adults in terms of bone development, skin condition, facial features and facial expression characteristics. Among the above differences, only the height difference in body shape is relatively intuitive, the facial aspect is not intuitive, and the movement aspect is the most intuitive. Therefore, the embodiments of the present invention extract movement features from the whole-body movement video, including behavior feature extraction and gait feature extraction, so as to obtain behavior feature information and gait feature information of the monitoring target.

[0043] In some optional embodiments, the embodiments of the present invention use the OpenCV (Open Source Computer Vision Library) library to process each frame in the video and extract the behavioral feature information and gait feature information in each frame or consecutive frames. OpenCV is a powerful open source computer vision library that contains multiple functional modules, covering all aspects of computer vision, including: image processing, feature detection and description, target detection and recognition, video analysis, machine learning, etc. The process of extracting behavioral features and gait features from video frames using the OpenCV library includes: video preprocessing (noise reduction of full-body action videos, and segmentation of full-body action videos into independent action segments), human body detection and tracking (tracking the same monitoring target in different video frames), behavioral feature extraction and gait feature extraction. In the process of behavioral feature extraction and gait feature extraction, it is necessary to predetermine the key points of the body of the monitoring target, and determine the behavioral feature information and gait feature information based on the position information of the key points of the body.

[0044] Step S103: Perform a comprehensive analysis based on the behavior feature information and the gait feature information to determine whether the monitored target is a child.

[0045] Specifically, in an embodiment of the present invention, behavioral characteristic information and gait characteristic information correspond to different aspects of the motion characteristics of the monitored target. To improve the accuracy and reliability of child approach detection, the behavioral characteristic information and gait characteristic information are combined to form a two-layer verification mechanism. In this embodiment of the present invention, corresponding weight coefficients are pre-set for the behavioral characteristic information and gait characteristic information. By taking a weighted average of the behavioral characteristic information and gait characteristic information, a comprehensive motion characteristic value of the monitored target is obtained. The comprehensive motion characteristic value is then compared with a pre-set characteristic threshold to determine whether the monitored target is a child.

[0046] In some optional implementations, in order to ensure the reliability of the comprehensive analysis based on the behavioral characteristic information and the gait characteristic information, the embodiment of the present invention further deploys a sensor on the electric heater, and uses the sensor data (such as the height data of the monitored target and the distance data between the monitored target and the electric heater, but not limited to this) to determine whether the monitored target is a child. Figure 2 As shown, a convolutional neural network (CNN) is used to process full-body motion videos, fuse them with sensor data, and train the model based on the combined judgment results of the two data sets. Furthermore, based on the model's misjudgment rate, the aforementioned weight coefficients and feature thresholds are adjusted, and the model is optimized using long-term data collection to improve its accuracy and generalization ability, ensuring stable performance across different datasets and accurately distinguishing children from adults.

[0047] In some optional embodiments, in order to prevent misidentification (to avoid mistakenly opening the child lock by identifying the user bending over or passing by quickly as a child), in the judgment process, the model has the advantage of long-term learning. By long-term recording and analysis of the movement patterns of approaching people, a more accurate behavior feature library is established, actions that are inconsistent with normal behavior patterns are identified, all misjudgments are recorded, the causes of misjudgments are analyzed, and the optimization model can effectively reduce misjudgments.

[0048] In some optional implementations, the embodiments of the present invention may further add image processing and face recognition based on the full-body motion video captured by the camera to more accurately determine whether the approaching monitoring target is a child. Image processing and face recognition are conventional technical means in this field and will not be described in detail here.

[0049] Step S104: Control the child lock based on the judgment result.

[0050] Specifically, in the embodiment of the present invention, Figure 3 As shown in the figure, under normal circumstances, the child lock of the electric heater is initially in the off state, and the approaching monitoring target is detected in real time. If the monitoring target is determined to be a child, it is determined that a child is approaching, and the child lock is automatically opened. If the monitoring target is determined to be an adult, the normal operation state is maintained, that is, the child lock is not opened. If it is in the on state at this time, the child lock can be controlled to be closed, thereby facilitating user operation.

[0051] The child lock control method provided by the present invention extracts corresponding behavioral and gait features from a full-body motion video of a monitored target, performs a comprehensive analysis based on the extracted behavioral and gait feature information, determines whether the monitored target is a child, and controls the child lock based on the judgment result. By analyzing the motion of the monitored target, the present invention can automatically determine whether the approaching target is a child and intelligently control the child lock, eliminating the need for manual user operation and simplifying the use process, thereby preventing children from operating the device incorrectly or imitating the user's operation. This improves the safety, reliability, and ease of operation of electrical equipment and enhances user trust in the equipment.

[0052] In this embodiment, a child lock control method is provided, which can be used for the above-mentioned electrical appliances, such as electric heaters, washing machines, electric fans, etc. Figure 4 : is a flow chart of a child lock control method according to an embodiment of the present invention. Figure 4 As shown, the process includes the following steps:

[0053] Step S401: Obtain heat distribution information of an initial target, and determine whether the initial target is a human target based on the heat distribution information.

[0054] Specifically, in the embodiments of the present invention, an electric heater is used as an example. Infrared sensors are installed on the heater, which can sense infrared radiation emitted by objects. The temperature of different parts of the human body varies, forming a unique heat distribution pattern. The core (such as the torso) has a relatively high and stable temperature, the extremities are slightly lower, and the head is somewhere in between. In a heat distribution map captured by an infrared sensor, the human body typically appears as a higher temperature in the center and gradually decreasing temperature at the edges, with distinct human contours. Compared to the human body, the heat distribution characteristics of other objects are significantly different. For example, objects at normal temperatures, such as furniture and clothing, radiate low infrared energy and appear as uniformly low-temperature areas on a heat distribution map. While the electric heater itself has a high temperature, its heat distribution is concentrated in the heat-generating area, resulting in a shape that differs significantly from the human body. Furthermore, while the heat distribution of pets is similar to that of humans, their body shape and temperature distribution ratios differ. For example, pets like cats and dogs are smaller, and their heads and extremities contribute a relatively large proportion of their heat, distinguishing them from humans. Therefore, embodiments of the present invention pre-set a radiation intensity threshold. By analyzing the heat distribution information near the initial target, the infrared radiation intensity of the initial target is determined. If the infrared radiation intensity of the initial target exceeds the radiation intensity threshold, the initial target near the electric heater is determined to be a human target. To improve the accuracy of the judgment, further analysis of the contour or shape corresponding to the heat distribution information can be performed, etc., which is not limited here.

[0055] Step S402: If the initial target is determined to be a human target, the horizontal distance between the bottom of the human target and the electrical device and the straight-line distance between the top of the human target and the electrical device are obtained, and the body height of the human target is determined based on the horizontal distance and the straight-line distance.

[0056] Specifically, in an embodiment of the present invention, an ultrasonic sensor is also deployed on the electric heater. The ultrasonic sensor measures the distance from the ultrasonic sensor to the human body by emitting high-frequency sound waves (>20kHz) and receiving reflected echoes. In order to avoid errors caused by the height of the electric heater itself, the ultrasonic sensor is installed below the electric heater. The ultrasonic sensor measures the straight-line distance x from the ultrasonic sensor to the top of the person, and the horizontal distance L from the ultrasonic sensor to the bottom of the person, as shown in FIG. Figure 5 As shown, the body height h close to the human target is calculated according to the Pythagorean theorem:

[0057] Step S403, determine whether the body height is less than the preset height threshold, and determine whether the horizontal distance is less than the preset safety distance threshold. If the body height is less than the preset height threshold and the horizontal distance is less than the preset safety distance threshold, the human target is determined to be a monitoring target.

[0058] Specifically, in an embodiment of the present invention, the user can set a safety distance threshold (determine the distance of a child approaching the electric heater) and a child height threshold (determine the height of children in the home) according to actual conditions on the user end corresponding to the electric heater. For example, when a child with a height of less than 1.2 meters approaches the electric heater by 0.5 meters, the child lock function is automatically turned on. Therefore, after obtaining the horizontal distance L and body height h of the human target, the embodiment of the present invention compares them with the corresponding preset safety distance threshold and preset height threshold respectively. If the body height is less than the preset height threshold and the horizontal distance is less than the preset safety distance threshold, it is preliminarily determined that the person approaching the electric heater is a child.

[0059] In some optional embodiments, in order to prevent an adult from bending over or squatting when approaching an electric heater, which may cause the measured body height to be less than a preset height threshold and thus cause a misjudgment, the embodiments of the present invention record the duration of meeting the conditions after determining that the body height is less than the preset height threshold. If the duration is greater than a preset time threshold, for example, 3s, the human target is determined to be a child and is used as a monitoring target.

[0060] Step S404: Obtain the full body motion video of the monitored target. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0061] Step S405: Extract features from the whole-body action video to obtain behavioral feature information and gait feature information of the monitored target. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0062] Step S406: Perform a comprehensive analysis based on the behavior feature information and gait feature information to determine whether the monitored target is a child. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0063] Step S407: Control the child lock based on the judgment result.

[0064] Specifically, the above step S407 includes:

[0065] Step S4071: If the monitored target is a child, the child lock is turned on; otherwise, the child lock is turned off. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0066] Step S4072: determine in real time whether the horizontal distance exceeds a preset safety threshold. If so, turn off the child lock; otherwise, keep the child lock on.

[0067] Specifically, in the embodiment of the present invention, Figure 6 As shown, when the monitored target is determined to be a child and the child lock is turned on, the horizontal distance between the bottom of the monitored target and the electric heater is continuously updated in real time, and a determination is made in real time whether the horizontal distance exceeds the preset safety threshold L. If the horizontal distance exceeds the preset safety threshold, the child is determined to be still nearby, and the child lock remains engaged. If the horizontal distance is less than the preset safety distance, the child is determined to have left, and the child lock is automatically turned off.

[0068] The child lock control method provided by the present invention extracts corresponding behavioral and gait features from a full-body motion video of the monitored target, performs a comprehensive analysis based on the extracted behavioral and gait feature information, determines whether the monitored target is a child, and controls the child lock based on the judgment result. Through multi-sensor fusion analysis, the present invention can automatically determine whether the approaching target is a child and intelligently control the child lock, eliminating the need for manual user operation and simplifying the use process, thereby preventing children from operating the device incorrectly or imitating the user's operation. This improves the safety, reliability, and operational convenience of electrical equipment and enhances user trust in the device.

[0069] In this embodiment, a child lock control method is provided, which can be used for the above-mentioned electrical appliances, such as electric heaters, washing machines, electric fans, etc. Figure 7 : is a flow chart of a child lock control method according to an embodiment of the present invention. Figure 7 As shown, the process includes the following steps:

[0070] Step S701: Obtain the full body motion video of the monitoring target. Figure 4 Step S404 of the illustrated embodiment will not be described in detail here.

[0071] Step S702: extract features from the whole-body motion video to obtain behavioral feature information and gait feature information of the monitored target.

[0072] Specifically, the above step S702 includes:

[0073] Step S7021, identify the first preset body key point of the monitoring target in each frame of the whole-body motion video, and determine the first position information of the first preset body key point in each frame of the whole-body motion video; determine the movement amplitude of the monitoring target according to the first position information corresponding to each frame of the whole-body motion video; determine the movement frequency of the monitoring target according to the first position information corresponding to the continuous frames of the whole-body motion video.

[0074] Specifically, in an embodiment of the present invention, the extraction of behavioral features includes the determination of motion amplitude and motion frequency. First, for motion amplitude, each frame in the whole-body motion video is processed using the OpenCV library to identify the first preset body key point (such as hands, legs) of the monitoring target in each frame of the whole-body motion video, and determine the first position information of the first preset body key point in each frame of the whole-body motion video. The displacement of the preset body key point is calculated based on the first position information, and then the motion amplitude is measured, including jumping height, waving amplitude, etc., which is only used as an example and is not limited to this. Secondly, for motion frequency, the moving speed is determined based on the first position information corresponding to the first preset body key point in continuous frames, reflecting the speed of the monitoring target's motion. The speed can be obtained by dividing the displacement corresponding to the first position information by the time interval, thereby measuring the motion frequency of the monitoring target. Compared with adults, children usually move faster.

[0075] Step S7022, identify the foot key points and the second preset body key points of the monitoring target in each frame of the whole-body motion video, and determine the second position information and third position information corresponding to the foot key points and the second preset body key points in each frame of the whole-body motion video; determine the stride and step frequency of the monitoring target based on the second position information corresponding to the continuous frame whole-body motion video; determine the posture characteristics of the monitoring target based on the third position information corresponding to the continuous frame whole-body motion video.

[0076] Specifically, in an embodiment of the present invention, gait feature extraction includes determining stride length, cadence, and posture. First, for stride length and cadence, the OpenCV library is used to process each frame in the video. The foot key points of the monitored subject are identified in the full-body motion video, and the second position information of the foot key points in each frame is determined. The stride length of the monitored subject is then calculated based on the second position information corresponding to the foot key points in consecutive frames. Compared to adults, children generally have smaller strides. Simultaneously, the movement speed of the foot key points between consecutive frames is calculated to reflect the speed of the gait. The movement speed can be obtained by dividing the corresponding position of the second position information by the time interval, thereby measuring the cadence of the monitored subject. Compared to adults, children generally have faster walking speeds. Second, for posture, the second preset body key points (such as shoulders and head) of the monitored subject are identified in each frame of the full-body motion video, and the third position information of the second preset body key points in each frame of the full-body motion video is determined. The swing angle of the monitored subject's body is determined based on the relative position of the third position information between consecutive frames. The posture characteristics of the monitored subject's walking are analyzed to determine whether the monitored subject's walking is stable. Compared to adults, children's posture is less stable.

[0077] Step S703: Perform comprehensive analysis based on the behavior feature information and the gait feature information to determine whether the monitored target is a child.

[0078] Specifically, the above step S703 includes:

[0079] Step S7031: Obtain a predetermined first weight of the behavior feature information and a predetermined second weight of the gait feature information.

[0080] Specifically, in an embodiment of the present invention, corresponding weights are set in advance for the movement amplitude and movement frequency in the behavioral feature information, and the stride, cadence, and posture features in the gait feature information based on the child's movement characteristics. For example, the weight of the movement amplitude is 0.3, the weight of the movement frequency is 0.2, the weight of the stride is 0.2, the weight of the cadence is 0.2, and the weight of the posture feature is 0.1. This is only an example and is not limited to this. In addition, the embodiment of the present invention adjusts the weight of each feature information through the above-mentioned model construction and model optimization to ensure that the judgment result is more accurate.

[0081] Step S7032: normalize the behavior feature information and the gait feature information to obtain standardized behavior feature values ​​and gait feature values.

[0082] Specifically, in this embodiment of the present invention, the aforementioned feature information, while movement amplitude and stride length, have the same physical concept, movement frequency and cadence have the same physical concept, is different from the other feature information, and the different feature information may not have the same dimensions. Therefore, in order to comprehensively analyze the various feature information, it is necessary to normalize the various feature information to ensure that they have the same dimensions. For example, movement amplitude and stride length can be normalized to the range [0, 1].

[0083] Step S7033: performing weighted averaging on the standardized behavior feature value and gait feature value, and the corresponding first weight and second weight to obtain a comprehensive action feature value.

[0084] Specifically, in an embodiment of the present invention, the behavioral feature value and the gait feature value are combined into a comprehensive feature vector. For example, the feature vector can be expressed as: [movement amplitude, movement frequency, stride length, cadence, posture feature]. Then, according to the predetermined weights, each feature value is weighted averaged to calculate the comprehensive action feature value. Taking the weight of the movement amplitude as 0.3, the weight of the movement frequency as 0.2, the weight of the stride length as 0.2, the weight of the cadence as 0.2, and the weight of the posture feature as 0.1 as an example, the calculation formula is: comprehensive action feature value = movement amplitude * 0.3 + movement frequency * 0.2 + stride length * 0.2 + cadence * 0.2 + posture feature * 0.1.

[0085] Step S7034, determine whether the comprehensive action feature value exceeds the preset feature threshold, if so, determine that the monitored target is a child.

[0086] Specifically, in an embodiment of the present invention, through the above-mentioned model training and model optimization, the feature threshold with the most accurate judgment result can be determined, for example 0.6. When the calculated comprehensive motion feature exceeds this feature threshold, it is judged that the monitoring target is a child, that is, the person approaching the electric heater at this time is a child, and corresponding protective measures need to be triggered to automatically control the child lock. The child lock is opened when it is determined that a child is approaching, and the child lock is kept open when it is determined that the child is still nearby, and the child lock is closed after it is determined that the child has left.

[0087] Step S704: Control the child lock based on the judgment result. Figure 4 Step S407 of the illustrated embodiment will not be described in detail here.

[0088] The child lock control method provided by the present invention extracts corresponding behavioral and gait features from a full-body motion video of a monitored target, performs a comprehensive analysis based on the extracted behavioral and gait feature information, determines whether the monitored target is a child, and controls the child lock based on the judgment result. By analyzing the motion of the monitored target, the present invention can automatically determine whether the approaching target is a child and intelligently control the child lock, eliminating the need for manual user operation and simplifying the use process, thereby preventing children from operating the device incorrectly or imitating the user's operation. This improves the safety, reliability, and ease of operation of electrical equipment and enhances user trust in the equipment.

[0089] This embodiment also provides a child lock control device for implementing the above-mentioned embodiments and preferred embodiments. Details already described will not be repeated. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0090] This embodiment provides a child lock control device, such as Figure 8 Shown, including:

[0091] The video acquisition module 801 is used to acquire the whole body motion video of the monitored target.

[0092] The feature extraction module 802 is used to extract features from the whole-body motion video to obtain behavioral feature information and gait feature information of the monitored target.

[0093] The target recognition module 803 is used to perform a comprehensive analysis based on the behavior feature information and the gait feature information to determine whether the monitored target is a child.

[0094] The child lock control module 804 is used to control the child lock based on the judgment result.

[0095] In some optional embodiments, the device further comprises:

[0096] The first target judgment module is used to obtain heat distribution information of the initial target and judge whether the initial target is a human target based on the heat distribution information.

[0097] The target information determination module is used to obtain the horizontal distance between the bottom of the human target and the electrical equipment, and the straight-line distance between the top of the human target and the electrical equipment if the initial target is determined to be a human target, and determine the body height of the human target based on the horizontal distance and the straight-line distance.

[0098] The second target judgment module is used to judge whether the body height is less than the preset height threshold and whether the horizontal distance is less than the preset safety distance threshold. If the body height is less than the preset height threshold and the horizontal distance is less than the preset safety distance threshold, the human target is determined to be the monitoring target.

[0099] The third target judgment module is used to judge whether the duration of the body height being less than the preset height threshold is greater than the preset time threshold. If the duration is greater than the preset time threshold, the human target is determined to be the monitoring target.

[0100] In some optional implementations, the feature extraction module 802 includes:

[0101] The behavioral feature extraction unit is used to identify the first preset body key point of the monitoring target in each frame of the whole-body action video, and determine the first position information of the first preset body key point in each frame of the whole-body action video; determine the movement amplitude of the monitoring target according to the first position information corresponding to each frame of the whole-body action video; and determine the movement frequency of the monitoring target according to the first position information corresponding to consecutive frames of the whole-body action video.

[0102] The gait feature extraction unit is used to identify the foot key points and the second preset body key points of the monitored target in each frame of the whole-body motion video, and determine the second position information and third position information corresponding to the foot key points and the second preset body key points in each frame of the whole-body motion video; determine the stride and step frequency of the monitored target based on the second position information corresponding to the continuous frames of the whole-body motion video; and determine the posture characteristics of the monitored target based on the third position information corresponding to the continuous frames of the whole-body motion video.

[0103] In some optional implementations, the target identification module 803 includes:

[0104] The weight determination unit is used to obtain a predetermined first weight of the behavior feature information and a second weight of the gait feature information.

[0105] The data processing unit is used to perform standardization processing on the behavior characteristic information and the gait characteristic information to obtain standardized behavior characteristic values ​​and gait characteristic values.

[0106] The weighted averaging unit is used to perform weighted averaging based on the standardized behavior feature value and gait feature value, and the corresponding first weight and second weight to obtain a comprehensive action feature value.

[0107] The fourth target judgment unit is used to judge whether the comprehensive action feature value exceeds a preset feature threshold. If so, it is determined that the monitored target is a child.

[0108] In some optional implementations, the child lock control module 804 includes:

[0109] The control unit is turned on to turn on the child lock if the monitored target is a child, otherwise the child lock is controlled to be in the off state.

[0110] The closing control subunit is used to determine in real time whether the horizontal distance exceeds the preset safety threshold. If it exceeds, the child lock is turned off, otherwise the child lock is controlled to be on.

[0111] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0112] The child lock control device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0113] The embodiment of the present invention also provides a computer device having the above Figure 8 Child lock control shown.

[0114] See also Figure 9 , Figure 9 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 9 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). Figure 9 A processor 10 is taken as an example.

[0115] 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.

[0116] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0117] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, 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 combinations thereof.

[0118] 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.

[0119] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 9 The bus connection is taken as an example.

[0120] The input device 30 can receive input digital or character information and generate key signal input related to user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a trackpad, a touch pad, an indicator stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 can include a display device, an auxiliary lighting device (e.g., an LED), and a tactile feedback device (e.g., a vibration motor). The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display, and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0121] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0122] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0123] The embodiment of the present invention further provides an electrical device, comprising: a child lock, a control module and a video acquisition device; the child lock is used to lock the electrical device; the video acquisition device is used to acquire a full-body motion video of the monitored target; the control module is connected to the child lock and the control module, and is used to perform the above-mentioned Figure 1 、 Figure 4 or Figure 7 The child lock control method shown in FIG. 1 is used to control the child lock.

[0124] Specifically, in the embodiment of the present invention, taking an electric heater as an example, in addition to a child lock, a control module and a video acquisition device, the electric heater is also equipped with an infrared sensor and an ultrasonic sensor. Figure 10As shown, the internal system of the electric heater can be divided into three parts: the user end, which is used to set the control threshold, including: safety distance threshold, height threshold, etc.; the detection end, which is used to determine whether the target approaching is a child based on the data collected by the infrared sensor, ultrasonic sensor and video acquisition equipment; and the control end, which is used to automatically execute the child lock control according to the judgment result.

[0125] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A child lock control method, characterized in that: Applied to electrical equipment equipped with a child lock, the method includes: Obtain full-body motion video of the monitored target; Extracting features from the whole-body motion video to obtain behavioral feature information and gait feature information of the monitored target; Performing a comprehensive analysis based on the behavioral characteristic information and the gait characteristic information to determine whether the monitored target is a child; The child lock is controlled based on the judgment result.

2. The method according to claim 1, characterized in that Before acquiring the full-body motion video of the monitoring target, the method further includes: Acquiring heat distribution information of an initial target, and determining whether the initial target is a human target based on the heat distribution information; If the initial target is determined to be the human target, obtaining a horizontal distance between the bottom of the human target and the electrical device, and a straight-line distance between the top of the human target and the electrical device, and determining the body height of the human target based on the horizontal distance and the straight-line distance; Determine whether the body height is less than a preset height threshold, and determine whether the horizontal distance is less than a preset safety distance threshold. If the body height is less than the preset height threshold and the horizontal distance is less than the preset safety distance threshold, determine that the human target is the monitoring target.

3. The method according to claim 2, characterized in that Before determining the human target as the monitoring target, the method further includes: It is determined whether a duration during which the height of the body is less than the preset height threshold is greater than a preset time threshold; if the duration is greater than the preset time threshold, the human target is determined to be the monitoring target.

4. The method according to claim 1, wherein The extracting features from the whole-body action video to obtain behavioral feature information of the monitored target includes: Identifying a first preset body key point of the monitoring target in each frame of the full-body motion video, and determining first position information of the first preset body key point in each frame of the full-body motion video; determining the movement amplitude of the monitored target according to the first position information corresponding to each frame of the full-body movement video; The movement frequency of the monitored target is determined according to the first position information corresponding to the whole-body movement video in consecutive frames.

5. The method according to claim 1, wherein The extracting features from the whole-body motion video to obtain gait feature information of the monitored target includes: Identifying a foot key point and a second preset body key point of the monitoring target in each frame of the full-body motion video, and determining second position information and third position information corresponding to the foot key point and the second preset body key point in each frame of the full-body motion video; Determining the stride length and stride frequency of the monitored target based on second position information corresponding to the full-body motion video in consecutive frames; The posture feature of the monitoring target is determined according to the third position information corresponding to the full-body action video of consecutive frames.

6. The method according to claim 1, characterized in that The performing a comprehensive analysis based on the behavior characteristic information and the gait characteristic information to determine whether the monitoring target is a child includes: Obtaining a predetermined first weight of the behavior feature information and a predetermined second weight of the gait feature information; performing normalization processing on the behavior characteristic information and the gait characteristic information to obtain normalized behavior characteristic values ​​and gait characteristic values; Obtain a comprehensive action feature value by performing a weighted average based on the standardized behavior feature value and gait feature value, the corresponding first weight, and the second weight; It is determined whether the comprehensive action characteristic value exceeds a preset characteristic threshold value, and if so, it is determined that the monitored target is a child.

7. The method according to claim 2, characterized in that The controlling of the child lock based on the judgment result includes: If the monitored target is a child, the child lock is turned on; otherwise, the child lock is turned off; It is determined in real time whether the horizontal distance exceeds a preset safety threshold, and if so, the child lock is closed, otherwise the child lock is controlled to be in an open state.

8. A child lock control device, characterized in that: Applicable to electrical equipment equipped with a child lock, the device comprises: Video acquisition module, used to acquire full-body motion video of the monitored target; A feature extraction module is used to extract features from the whole-body motion video to obtain behavioral feature information and gait feature information of the monitored target; a target recognition module, configured to perform a comprehensive analysis based on the behavioral characteristic information and the gait characteristic information to determine whether the monitored target is a child; The child lock control module is used to control the child lock based on the judgment result.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the child lock control method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the child lock control method according to any one of claims 1 to 7.

11. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the child lock control method according to any one of claims 1 to 7.

12. An electrical device, characterized in that: include: Child lock, control module and video capture equipment; Child lock, used to keep electrical equipment in a locked state; Video acquisition equipment, used to capture full-body motion videos of the monitored target; A control module is connected to the child lock and the control module, and is used to execute the child lock control method according to any one of claims 1 to 7 based on the full-body motion video and control the child lock.

Images