Lamp equipment control method and device, electronic equipment and readable storage medium
By acquiring thermal radiation signals and facial images, and combining thermal imaging and facial feature vector fusion to identify the elderly, the problem of the inability to accurately identify the elderly in existing technologies has been solved, enabling personalized lighting control and improving the lighting experience for the elderly.
Patent Information
- Application Number
- CN202511712084.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-20
- Publication Date
- 2026-03-06
AI Technical Summary
Existing lighting equipment cannot accurately identify elderly people, making it difficult to provide personalized lighting services for them.
By acquiring thermal radiation signals and facial images of the target area, and fusing thermal imaging information and facial image feature vectors, combined with a support vector machine classifier, it is determined whether the person is elderly, and the lighting equipment is controlled based on the determination result.
It enables accurate identification and personalized lighting control for the elderly, meeting their lighting needs and improving the safety and comfort of lighting.
Smart Images
Figure CN121619706A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of equipment control technology, specifically relating to a lighting equipment control method and device, electronic equipment, and readable storage medium. Background Technology
[0002] Existing solutions rely on simple human body sensors for identification. However, these sensors can only detect the presence of someone and cannot accurately distinguish whether someone is elderly, making it difficult to provide personalized lighting services tailored to their needs. Therefore, they fail to meet the individualized lighting requirements of the elderly due to conditions such as declining vision. Summary of the Invention
[0003] The purpose of this application is to provide a lighting equipment control method and device, electronic device, and readable storage medium that can solve the problems of not being able to accurately identify elderly people and not being able to provide targeted personalized services for the elderly.
[0004] To solve the above-mentioned technical problems, this application is implemented as follows: In a first aspect, embodiments of this application provide a lighting equipment control method, the method comprising: Acquire thermal radiation signals and facial images of the target living organism within the target area; Thermal imaging information of the target living body is generated based on the thermal radiation information; Based on the thermal imaging information and the facial image, determine whether the target living person is a target person who meets the preset age range; When the target living person is determined to be a target person within a preset age range, the lighting equipment in the target area is controlled.
[0005] Optionally, the method for determining whether the target living person belongs to a preset age group based on the thermal imaging information and the facial image includes: A first feature vector corresponding to the thermal imaging information is generated based on the thermal imaging templates pre-existing in the database. A second feature vector corresponding to the facial features is generated based on a deep learning model; The first feature vector and the second feature vector are fused to generate the target feature vector; The target feature vector is input into a preset SVM classifier, which can be used to classify people into preset age groups and output the probability information that the target live subject is a target person who meets the preset age group.
[0006] Optionally, fusing the first feature vector and the second feature vector to generate the target feature vector includes: Obtain the first weight data of the first feature vector; Obtain the second weight data of the second feature vector; Determine the first product of the first weight data and the first feature vector; Determine the second product of the second weight data and the second feature vector; The first product and the second product are added together to generate the target feature vector.
[0007] Optionally, it also includes: When the probability information is greater than a preset probability threshold, the target living person is determined to be a target person who meets the preset age range.
[0008] Optionally, when determining that the target living person is a target individual within a preset age range, controlling the lighting equipment in the target area includes: When the target living person is determined to be a target person within a preset age range, if the voice information of the target person is detected, the lighting equipment in the target area is controlled to be turned on.
[0009] Optionally, when determining that the target living person is a target individual within a preset age range, controlling the lighting equipment in the target area includes: When the target living person is determined to be a target person who falls within a preset age range, the action information and / or voice information of the target person are acquired; When it is determined that the action information and / or the sound information are abnormal, the first lighting parameters of the lighting equipment in the target area are determined; The lighting equipment is controlled according to the first lighting parameters.
[0010] Optionally, it also includes: When there are no abnormalities in the action information and the sound information, determine the second lighting parameters of the lighting equipment in the target area; The lighting equipment is controlled according to the second lighting parameters.
[0011] Optionally, it also includes: If there are no abnormalities in the action information and the sound information, and if the sound information is a voice command from the target person, then the lighting equipment in the target area is controlled according to the voice command.
[0012] Optionally, when determining that the target living person is a target individual within a preset age range, controlling the lighting equipment in the target area includes: When the target living person is determined to be a target person within a preset age range, the sleep monitoring information of the target person is obtained; The lighting equipment within the target area is controlled based on the sleep monitoring information.
[0013] Optionally, controlling the lighting equipment within the target area based on the sleep monitoring information includes: The sleep status information of the target person is determined based on the sleep monitoring information; The lighting equipment within the target area is controlled according to the sleep state information.
[0014] Optionally, controlling the lighting equipment within the target area based on the sleep monitoring information includes: The real-time sleep stage of the target person is determined based on the sleep monitoring information; The lighting equipment within the target area is controlled according to the real-time sleep stage.
[0015] Secondly, embodiments of this application provide a device for controlling lighting equipment, the device comprising: The live data acquisition module is used to acquire thermal radiation signals and facial images of the target live body in the target area; A thermal imaging information generation module is used to generate thermal imaging information of the target living body based on the thermal radiation information; The target person determination module is used to determine whether the target living person is a target person who meets the preset age range based on the thermal imaging information and the facial image. The lighting equipment control module is used to control the lighting equipment in the target area when it is determined that the target living person is a target person who meets the preset age range.
[0016] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method described in the first aspect.
[0017] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.
[0018] In this application embodiment, thermal radiation signals and facial images of the target living body in the target area can be acquired, and then the elderly population can be accurately identified based on thermal imaging and facial images. Targeted lighting control schemes can be set for the elderly population to meet their lighting needs. Attached Figure Description
[0019] Figure 1This is a flowchart illustrating the steps of a lighting equipment control method according to an embodiment of this application; Figure 2 This is a flowchart of another lighting equipment control method in the embodiments of this application; Figure 3 This is a flowchart of another lighting equipment control method in the embodiments of this application; Figure 4 This is a flowchart illustrating the intelligent lighting system in the embodiments of this application; Figure 5 This is a schematic diagram of the structure of a lighting equipment control device according to an embodiment of this application; Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation
[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0021] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.
[0022] The lighting equipment control method provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.
[0023] Reference Figure 1 The flowchart illustrates the steps of a lighting equipment control method according to an embodiment of this application, specifically including the following steps: Step S101: Acquire thermal radiation signals and facial images of the target living body in the target area; In this embodiment, an intelligent lighting system can be set up. The intelligent lighting system may include an infrared device for collecting thermal radiation signals from living bodies and an image acquisition device (such as a camera) for collecting facial images of living bodies. It may also include lighting equipment. The intelligent lighting system can realize intelligent control of the lighting equipment based on the analysis of the collected data to deal with living bodies of different ages. In this embodiment, it can accurately identify elderly people and carry out targeted lighting control for the elderly population.
[0024] In practical applications, after the table activates the intelligent lighting system, it can collect data on the target living body within the target area, obtaining the thermal radiation signal and facial image of the target living body.
[0025] Step S102: Generate thermal imaging information of the target living body according to the thermal radiation information; Intelligent lighting systems can convert acquired thermal radiation signals into thermal imaging information of the target living body.
[0026] In practical applications, all objects above absolute zero (-273.15°C) radiate electromagnetic waves, and living organisms are no exception. The intensity and wavelength distribution of this radiation are closely related to the surface temperature and emissivity of the object. For the human body and most objects at room temperature, thermal radiation is mainly located in the infrared band (especially the mid-far infrared, with wavelengths of approximately 7-14 micrometers).
[0027] The core component of a thermal imager is an infrared detector. The working principle of an infrared detector is that the detector absorbs the infrared radiation emitted by the target, causing a slight change in its own temperature, which in turn causes a change in some of its physical properties.
[0028] The process of converting thermal radiation information into thermal imaging information can be summarized as follows: The electrical signal generated by the detector element is extremely weak and needs to be amplified by a highly precise amplifier. The amplified analog electrical signal is then converted into a digital signal by an analog-to-digital converter. The original data matrix, containing a large amount of interference and errors, cannot be directly used to display the image and must undergo complex algorithm correction and processing. Specifically, algorithm correction and processing can include non-uniformity correction, temperature-radiation relationship conversion, and environmental compensation processing.
[0029] After algorithmic correction, a temperature matrix is obtained in which each pixel corresponds to a temperature value. Then, pseudo-color mapping, image enhancement and display are performed based on the temperature matrix to obtain a thermal image.
[0030] In one embodiment of this application, when the target is a living organism (such as a human or animal), one or more of the following should also be considered: (1) Dynamic range: The body temperature range of living organisms is relatively narrow (for example, the human body is about 30°C-42°C). Thermal imagers can be optimized for this range to display richer temperature details.
[0031] (2) Blood circulation and metabolism: Thermal imaging can reflect the blood circulation under the skin and the inflammatory area (usually manifested as an abnormally high temperature area), which is very useful in medical diagnosis (such as breast screening, pain source localization) and veterinary fields.
[0032] (3) Physiological activities: Emotional fluctuations, tension, eating and other activities can cause subtle changes in local body temperature, and high-performance thermal imaging cameras can capture these changes.
[0033] (4) Environmental adaptability: Living organisms are usually in complex environments, so the above-mentioned environmental compensation and emissivity settings are particularly important. For example, the emissivity of sweaty skin will change when measuring it.
[0034] Step S103: Determine whether the target living person is a target person within a preset age range based on the thermal imaging information and the facial image; After obtaining thermal imaging data and facial images, the two can be combined to analyze and determine whether the target person belongs to a preset age group. The target person can be an elderly person older than the preset age. The intelligent lighting system in this embodiment can be personalized for the elderly to ensure their safety.
[0035] In one embodiment of this application, determining whether the target living person is a target individual within a preset age range based on the thermal imaging information and the facial image may include the following sub-steps: Sub-step S11: Generate the first feature vector corresponding to the thermal imaging information based on the thermal imaging templates pre-existing in the database; In practical applications, thermal imaging data can be preprocessed. Then, local binary mode and gray-level co-occurrence matrix analysis can be used to analyze texture and generate a feature vector of a first preset dimension. Simultaneously, the generated feature dimensions can be compared and filtered using pre-existing thermal imaging templates in a database to obtain the first feature vector.
[0036] The preprocessing of thermal imaging data may include using adaptive histogram equalization to improve image contrast, segmenting facial regions based on temperature gradients, and normalizing temperature values to the [0,1] range to eliminate environmental interference.
[0037] The specific process of obtaining the first feature vector by comparing and filtering the generated feature dimensions using pre-existing thermal imaging templates in the database can be as follows: The feature vector is compared with the pre-existing thermal imaging templates for the elderly in the database using cosine similarity, and only matching results with a similarity higher than 0.85 are retained as the first feature vector. This improves the recognition accuracy.
[0038] Sub-step S12: Generate the second feature vector corresponding to the facial features based on the deep learning model; In practical applications, facial features can be preprocessed and then a pre-trained deep learning model can be introduced to generate a second feature vector corresponding to the facial features.
[0039] The preprocessing of facial features may include: performing face detection and alignment on facial images captured by a high-definition camera, locating key points using the MTCNN algorithm, unifying the alignment pose through affine transformation, and then eliminating uneven lighting through histogram matching.
[0040] In one example, a ResNet-18 deep learning model can be used to analyze facial contours (quantify the degree of jawline blurring), wrinkle distribution (calculate the wrinkle density index W value > 0.35) and facial feature proportions (such as the inter-eye distance ratio p1 < 0.25) to generate a second feature vector of a second preset dimension.
[0041] Sub-step S13: Fuse the first feature vector and the second feature vector to generate the target feature vector; After obtaining the first feature vector and the second feature vector, the target feature vector is obtained by fusing the first feature vector and the second feature vector. By combining thermal imaging features and facial features to analyze the liveness of the target, the accuracy of the liveness identification can be improved.
[0042] Sub-step S14: Input the target feature vector into a preset SVM classifier. The SVM classifier can be used to classify people into preset age groups and output the probability information that the target live object is a target person who meets the preset age group.
[0043] After obtaining the target feature vector, the target feature vector can be input into an SVM (Support Vector Machine) classifier to classify people of different age groups and output the probability information that the target live object is a target person who meets the preset age group.
[0044] In one embodiment of this application, when the probability information is greater than a preset probability threshold, the target living person is determined to be a target person who meets the preset age range.
[0045] In one embodiment of this application, fusing the first feature vector and the second feature vector to generate a target feature vector includes: obtaining first weight data of the first feature vector; obtaining second weight data of the second feature vector; determining a first product of the first weight data and the first feature vector; determining a second product of the second weight data and the second feature vector; and adding the first product and the second product to generate the target feature vector.
[0046] In practical applications, the target feature vector = first weight data * first feature vector + second weight data * second feature vector.
[0047] The first weight data and the second weight data can be set according to the actual scenario, and this application embodiment does not impose too many restrictions on them.
[0048] For example, when identifying elderly people, the intelligent lighting system first preprocesses the thermal imaging data captured by the infrared sensor. This includes using adaptive histogram equalization to improve image contrast, segmenting facial regions based on temperature gradients, and normalizing temperature values to the [0,1] range to eliminate environmental interference. Simultaneously, it performs face detection and alignment on facial images captured by a high-definition camera, using the MTCNN algorithm to locate key points and perform affine transformations to unify the alignment posture, and then using histogram matching to eliminate uneven illumination. Thermal imaging feature extraction uses local binary mode and gray-level co-occurrence matrix analysis to generate a 21-dimensional feature vector. This vector is then compared with over 10,000 pre-stored thermal imaging templates of elderly people in the database using cosine similarity, retaining only matching results with similarity higher than 0.85. Facial features are analyzed using a lightweight ResNet-18 deep learning model to analyze facial contours (quantifying the degree of jawline blur), wrinkle distribution (calculating wrinkle density index W value > 0.35), and facial proportions (such as inter-eye distance ratio p1 < 0.25), generating a 35-dimensional feature vector.
[0049] The intelligent lighting system can fuse thermal imaging and facial features into a 56-dimensional vector, and dynamically allocate weights using an adaptive weighting strategy (thermal imaging weight = 0.6 × thermal imaging confidence, facial weight = 0.4 × facial confidence). The vector is then input into an SVM classifier for final decision-making. If the output probability is greater than 0.85, the system determines the individual to be elderly and triggers an age-friendly lighting mode; otherwise, it rejects the identification.
[0050] Step S104: When it is determined that the target living person is a target person who meets the preset age range, control the lighting equipment in the target area.
[0051] In an intelligent lighting system, a lighting control logic can be pre-set for a target group (such as the elderly). When the target is determined to be a person within the preset age range, the pre-set lighting control logic can be directly applied to control the lighting equipment in the target area. This lighting control logic fully considers the characteristics of the target person and is set to meet the personalized lighting needs of the target person in the target area.
[0052] For example, a senior citizen mode can be set up, which can specifically increase the color rendering index of lights, turn on the night light mode, and increase the volume of voice broadcasts to cater to the elderly population.
[0053] In this application embodiment, thermal radiation signals and facial images of the target living body in the target area can be acquired, and then the elderly population can be accurately identified based on thermal imaging and facial images. Targeted lighting control schemes can be set for the elderly population to meet their lighting needs.
[0054] Reference Figure 2 The flowchart illustrates the steps of a lighting equipment control method according to an embodiment of this application, specifically including the following steps: Step S201: Acquire thermal radiation signals and facial images of the target living body in the target area; Step S202: Generate thermal imaging information of the target living body according to the thermal radiation information; Step S203: Determine whether the target living person is a target person within a preset age range based on the thermal imaging information and the facial image; Step S204: When it is determined that the target living person is a target person who meets the preset age range, the action information and / or voice information of the target person are obtained; To comprehensively ensure the safety of the elderly, the room is meticulously equipped with a distributed network of sound sensors and high-precision motion sensors. The motion sensors utilize advanced microelectromechanical systems (MEMS) technology to accurately monitor every movement and posture of the elderly, analyzing key indicators such as walking speed, stride changes, and weight shifts in real time. The sound sensors possess powerful sound recognition and analysis capabilities, accurately distinguishing specific sound signals such as shouts and abnormal coughs from complex environmental sounds.
[0055] In intelligent lighting systems, motion and sound information of target personnel can be acquired from distributed sound sensors and high-precision motion sensor networks. Based on this motion and sound information, lighting equipment can be controlled to ensure the safety of the target personnel.
[0056] Step S205: When it is determined that there is an abnormality in the action information and / or the sound information, the first lighting parameters of the lighting equipment in the target area are determined; In practical applications, after obtaining motion information and / or sound information, it can be determined whether there is an anomaly. For example, if the body's center of gravity sways beyond a preset safety threshold within a short period of time, or if the gait suddenly becomes disordered, or if the sound sensor detects abnormal sound signals such as shouting or unusually violent coughing, then the motion and sound information can be determined to be abnormal. At this time, the first lighting parameters of the lighting equipment in the target area set for this abnormal state can be determined. These first lighting parameters increase the light intensity compared to the normal state, so that the abnormal state of the user can be viewed in a timely manner. For example, the brightness of the lights in the area will rapidly increase to more than 85% within 0.5 seconds, illuminating the entire space like daytime, providing sufficient lighting conditions for possible emergencies.
[0057] In practical applications, the process of determining body center of gravity swaying is as follows: The motion sensor, equipped with an accelerometer and gyroscope (core components of MEMS technology), can monitor changes in acceleration and angle of human movement in real time. When an elderly person walks, the sensor captures acceleration data (such as vibrations in the up-down, forward-backward, and left-right directions) and angular velocity data (such as changes in body tilt angle) of various parts of the body to infer the dynamic changes in the body's center of gravity. The system presets safety thresholds (such as the amplitude of center of gravity swaying exceeding a set value or the duration exceeding a threshold). If the sensor detects abnormal amplitude of body center of gravity swaying within a short period of time (such as violent swaying caused by gait instability), it is judged as a potential risk and a response is triggered (such as increasing the brightness of lights).
[0058] The process of determining gait disorder is as follows: The motion sensor has a built-in accelerometer and gyroscope (core components of MEMS technology), which can monitor changes in acceleration and angle of human movement in real time. Gait characteristics during walking are recorded using accelerometers, for example: (1) Calculate the stride length by analyzing the periodic fluctuations of the acceleration signal. If the stride length suddenly decreases or irregular fluctuations occur (such as excessive stride length differences), it may indicate gait disorder.
[0059] (2) By calculating the number of steps per unit time (step frequency), if the step frequency fluctuates drastically or is irregular (such as sudden pause, acceleration or deceleration), it is judged as abnormal.
[0060] By combining gyroscope data, the body's swaying angle and stability during walking can be analyzed. For example, excessive lateral swaying or forward and backward swaying during gait may indicate unsteady walking.
[0061] In one embodiment of this application, when an abnormality is determined to exist in the action information and / or the sound information, an alarm message can be generated and sent to the terminal of the guardian corresponding to the target person. The alarm message may include not only the specific room location where the abnormality occurred, but also a brief description of the situation, such as "An elderly person was detected to be in the bedroom and the lighting has been increased," and automatically pushes real-time footage from the camera in that area (if permitted by the guardian), so that the guardian can fully understand the situation and take appropriate action immediately.
[0062] Step S206: Control the lighting equipment according to the first lighting parameters.
[0063] In one embodiment of this application, when there are no abnormalities in the action information and the sound information, a second lighting parameter of the lighting equipment in the target area is determined; and the lighting equipment is controlled according to the second lighting parameter.
[0064] If there are no abnormalities in the motion and sound information, the lighting can be controlled according to the second lighting parameters set for the target personnel. The light intensity in the second lighting parameters is weaker than the light intensity in the first lighting parameters.
[0065] In one embodiment of this application, when there are no abnormalities in the action information and the sound information, if the sound information is a voice command of the target person, then the lighting equipment in the target area is controlled according to the voice command.
[0066] In this embodiment of the application, when a target person is identified, the lighting parameters can be adjusted by combining sound information and motion information to ensure the safety of the target person.
[0067] Reference Figure 3 The flowchart illustrates another lighting device control method according to an embodiment of this application, which specifically includes the following steps: Step S301: Acquire thermal radiation signals and facial images of the target living body in the target area; Step S302: Generate thermal imaging information of the target living body according to the thermal radiation information; Step S303: Determine whether the target living person is a target person within a preset age range based on the thermal imaging information and the facial image; Step S304: When it is determined that the target living person is a target person who meets the preset age range, obtain the sleep monitoring information of the target person; In practical applications, smart lighting systems can also be deeply integrated with various third-party sleep monitoring devices, such as smart bracelets, smart mattresses, and head-mounted sleep monitors, all of which can be easily connected.
[0068] Furthermore, when the intelligent lighting system determines that the target living person is within a preset age range, it can obtain the sleep monitoring information of the target person and then combine the sleep monitoring information to control the lighting fixtures.
[0069] Step S305: Control the lighting equipment in the target area according to the sleep monitoring information.
[0070] After obtaining sleep monitoring information, the lighting equipment in the target area can be dynamically controlled based on different sleep monitoring information to ensure that the target user gets better rest.
[0071] In one embodiment of this application, controlling the lighting equipment in the target area based on the sleep monitoring information includes: determining the sleep state information of the target person based on the sleep monitoring information; and controlling the lighting equipment in the target area according to the sleep state information.
[0072] Specifically, sleep status information can be categorized as sleep quality status. In practical applications, sleep monitoring devices can assess the sleep quality status of elderly individuals by real-time monitoring and analysis of multi-dimensional data such as heart rate variability, body movement, and electroencephalogram (EEG).
[0073] When the sleep status information indicates that the target person's sleep status is good, the lighting fixtures can maintain the current lighting parameters. When the sleep status information indicates that the target person's sleep status is poor, the lighting fixture parameters can be adjusted according to the current sleep status information to adjust the target person's sleep status.
[0074] For example, when the system detects that an elderly person is not sleeping well, such as having difficulty falling asleep, frequent awakenings, or prolonged periods of light sleep, the intelligent lighting system will automatically and precisely adjust the color and brightness of the bedroom lights based on big data analysis and intelligent algorithms. Before falling asleep, the system will gradually dim the light from 50% of normal brightness in a slow and natural manner, reducing it to about 10% over 5-8 minutes. At the same time, the light color will smoothly switch from bright white to a warm and soft yellow, with the color temperature precisely adjusted between 2500K and 2700K, creating a warm and tranquil atmosphere reminiscent of the afterglow of the evening sunset.
[0075] Specifically, the methods for monitoring sleep status information are as follows: (1) Heart rate variability (HRV) analysis: Data source: Heart rate data acquired via photoplethysmography (PPG) sensors or electrocardiogram (ECG) devices.
[0076] Analysis indicator: Low frequency / high frequency ratio (LF / HF): reflects the balance between the sympathetic and parasympathetic nervous systems. An abnormally high LF / HF ratio may indicate anxiety or stress during sleep.
[0077] RMSSD (Root Mean Square of the Difference Between Adjacent RR Intervals): Measures short-term fluctuations in heart rate variability. A significantly decreased RMSSD may indicate poor sleep quality (such as prolonged light sleep).
[0078] Abnormality detection: When the HRV index is consistently below the normal range or fluctuates drastically, the system determines that the sleep state is poor.
[0079] (2) Analysis of body movement: Data source: Body activity during sleep is recorded via inertial measurement unit (IMU) or pressure sensors (such as smart mattresses).
[0080] Analysis indicators: Body movement frequency: Frequent body movements at night (e.g., more than 5 times per hour) may indicate difficulty falling asleep or a prolonged period of light sleep.
[0081] Body movement intensity: The amplitude of body movement is determined by acceleration data. Violent turning over or sitting up may indicate sleep interruption.
[0082] Anomaly detection: When body movement data deviates significantly from the normal sleep pattern (such as the number of body movements at night being lower than the threshold), the system determines that the sleep quality has declined.
[0083] (3) Electroencephalogram (EEG) analysis Data source: Brainwave data collected via electrodes in a head-mounted sleep monitor or smart mattress.
[0084] Analysis indicators: Sleep stage segmentation: Identify sleep stages (such as N1 / N2 / N3 stages, REM stage) based on brain wave frequency and power distribution.
[0085] Excessive light sleep period: If the N1 / N2 stage ratio exceeds the normal range (e.g., >50%), it may indicate insufficient deep sleep.
[0086] REM phase abnormalities: If REM phases occur too early or too late, it may be related to sleep rhythm disorders.
[0087] Sleep efficiency: The ratio of total sleep time to time spent in bed. A sleep efficiency below 85% may indicate difficulty falling asleep or frequent awakenings.
[0088] Anomaly detection: By combining sleep stage distribution and sleep efficiency data, the system can determine whether there are problems such as difficulty falling asleep, frequent awakenings, or excessively long light sleep periods.
[0089] (3) Multi-dimensional data fusion and decision-making: Algorithm model: The system may use machine learning models (such as random forests and neural networks) or rule engines to comprehensively analyze data such as HRV, body movement, and EEG.
[0090] Thresholds and pattern recognition: For example: If HRV is abnormal, body movements are frequent, and the proportion of light sleep exceeds the threshold, it is judged as "poor sleep state" and lighting adjustments are triggered (such as reducing light brightness and adjusting color temperature).
[0091] If frequent awakenings or insufficient deep sleep are detected, lighting strategies are dynamically optimized (such as simulating changes in natural light to promote sleep cycles).
[0092] In one embodiment of this application, controlling the lighting equipment in the target area based on the sleep monitoring information includes: determining the real-time sleep stage of the target person based on the sleep monitoring information; and controlling the lighting equipment in the target area according to the real-time sleep stage.
[0093] In practical applications, throughout the sleep process, the intelligent lighting system can dynamically adjust the brightness and color of the lights based on changes in different sleep stages reported by sleep monitoring devices. For example, when entering a light sleep stage, the light brightness is appropriately reduced; as the awakening stage approaches, the light brightness is gradually increased and the color temperature is slightly raised to simulate the natural dawn process, helping the elderly wake up naturally in the morning and improving sleep quality and overall sleep experience. Through such a comprehensive, meticulous, and innovative implementation method, a safe, comfortable, and intelligent living lighting environment is created for the elderly, providing them with all-round care and protection.
[0094] Reference Figure 4 The diagram below illustrates the process of an intelligent lighting system in an embodiment of the present invention. The process includes the following steps: (1) After the intelligent lighting system is started, the system is initialized and the parameters are prepared.
[0095] (2) Obtain thermal radiation information and facial images, and determine whether elderly people are identified. If no elderly people are identified, maintain the normal lighting mode and continue monitoring. When an elderly person is identified, switch to elderly mode, increase the light display index, turn on the night light mode, and increase the voice broadcast volume.
[0096] (3) Determine whether abnormal movement or abnormal sound is detected; (4) When abnormal movement or sound is detected, increase the brightness of the lights and send an alarm message to the guardian.
[0097] (5) If no abnormal movement or sound is detected, determine whether a third-party sleep monitoring device is connected and whether the sleep state is poor; (6) When sleep is poor, adjust the light color and brightness according to the instructions. When sleep is normal, maintain the current lighting status.
[0098] It should be noted that the lighting equipment control method provided in this application embodiment can be executed by a lighting equipment control device, or a control module in the lighting equipment control device for executing the method of loading lighting equipment control. This application embodiment uses the execution of the loading lighting equipment control method by a lighting equipment control device as an example to illustrate the lighting equipment control method provided in this application embodiment.
[0099] Reference Figure 5 The diagram shows a schematic of the structure of a lighting equipment control device according to an embodiment of this application, which specifically includes the following modules: The live data acquisition module 501 is used to acquire thermal radiation signals and facial images of the target live body in the target area; The thermal imaging information generation module 502 is used to generate thermal imaging information of the target living body according to the thermal radiation information; The target person determination module 503 is used to determine whether the target living person is a target person who meets the preset age range based on the thermal imaging information and the facial image. The lighting equipment control module 504 is used to control the lighting equipment in the target area when it is determined that the target living person is a target person who meets the preset age range.
[0100] In one embodiment of this application, the target personnel determination module 503 includes the following device: The first feature vector generation submodule is used to generate a first feature vector corresponding to the thermal imaging information based on the thermal imaging template in a pre-existing database. The second feature vector generation submodule is used to generate the second feature vector corresponding to the facial features based on a deep learning model. The target feature vector generation submodule is used to fuse the first feature vector and the second feature vector to generate a target feature vector. The probability information generation submodule is used to input the target feature vector into a preset SVM classifier. The SVM classifier can be used to classify people into preset age groups and output the probability information that the target live subject is a target person who meets the preset age group.
[0101] In one embodiment of this application, the target feature vector generation submodule may include: The first weight data acquisition unit is used to acquire the first weight data of the first feature vector; The second weight data acquisition unit is used to acquire the second weight data of the second feature vector; The first product determination unit is used to determine the first product of the first weight data and the first feature vector; The second product determination unit is used to determine the second product of the second weight data and the second feature vector; The target feature vector generation unit is used to add the first product and the second product to generate the target feature vector.
[0102] In one embodiment of this application, the apparatus further includes: The target person determination module is used to determine that the target living person is a target person who meets the preset age range when the probability information is greater than the preset probability threshold.
[0103] In one embodiment of this application, the lighting equipment control module 504 may include: The first control submodule is used to control the lighting equipment in the target area to turn on when the target living person is determined to be a target person within a preset age range and the voice information of the target person is detected.
[0104] In one embodiment of this application, the lighting equipment control module 504 may include: The motion and sound determination submodule is used to acquire motion information and / or sound information of the target person when the target living person is determined to be a target person who meets the preset age range. The first lighting parameter determination submodule is used to determine the first lighting parameters of the lighting equipment in the target area when it is determined that there is an abnormality in the action information and / or the sound information; The first lighting equipment control submodule is used to control the lighting equipment according to the first lighting parameters.
[0105] In one embodiment of this application, the lighting equipment control module 504 may further include: The second lighting parameter determination submodule is used to determine the second lighting parameters of the lighting equipment in the target area when there are no abnormalities in the action information and the sound information; The second lighting equipment control submodule is used to control the lighting equipment according to the second lighting parameters.
[0106] In one embodiment of this application, the lighting equipment control module 504 may further include: The third lighting equipment control module is used to control the lighting equipment in the target area according to the voice command if the voice command is a voice instruction from the target person, when there are no abnormalities in the action information and the sound information.
[0107] In one embodiment of this application, the lighting equipment control module 504 may include: The sleep monitoring information acquisition submodule is used to acquire the sleep monitoring information of the target person when it is determined that the target living person is a target person who meets the preset age range; The fourth lighting control submodule is used to control the lighting equipment in the target area based on the sleep monitoring information.
[0108] In one embodiment of this application, the fourth lighting control submodule may include: A sleep state information determination unit is used to determine the sleep state information of the target person based on the sleep monitoring information; A lighting equipment control unit is used to control the lighting equipment in the target area according to the sleep state information.
[0109] In one embodiment of this application, the lighting equipment control unit may include: A real-time sleep stage determination subunit is used to determine the real-time sleep stage of the target person based on the sleep monitoring information. A lighting equipment determination subunit is used to control the lighting equipment within the target area according to the real-time sleep phase.
[0110] In this application embodiment, thermal radiation signals and facial images of the target living body in the target area can be acquired, and then the elderly population can be accurately identified based on thermal imaging and facial images. Targeted lighting control schemes can be set for the elderly population to meet their lighting needs.
[0111] The lighting equipment control device in this application embodiment can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This application embodiment does not impose specific limitations.
[0112] The lighting equipment control device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.
[0113] The lighting equipment control device provided in this application embodiment can achieve... Figures 1 to 4 The various processes implemented by the lighting equipment control device in the method embodiment will not be described again here to avoid repetition.
[0114] Optionally, this application embodiment also provides an electronic device, including a processor 1010, a memory 1009, and a program or instructions stored in the memory 1009 and executable on the processor 1010. When the program or instructions are executed by the processor 1010, they implement the various processes of the above-described lighting device control method embodiment and achieve the same technical effect. To avoid repetition, they will not be described again here.
[0115] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.
[0116] Figure 6 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of this application. The electronic device 1000 includes, but is not limited to, the following components: radio frequency unit 1001, network module 1002, audio output unit 1003, input unit 1004, sensor 1005, display unit 1006, user input unit 1007, interface unit 1008, memory 1009, and processor 1010.
[0117] Those skilled in the art will understand that the electronic device 1000 may also include a power supply (such as a battery) for supplying power to various components. The power supply can be logically connected to the processor 1010 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. x The electronic device structure shown does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here. This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described lighting equipment control method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.
[0118] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.
[0119] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.
[0120] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
[0121] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.
[0122] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.
Claims
1. A luminaire device control method, characterized by, The method comprises: acquiring thermal radiation signals and face images of a target living body in a target area; generating thermal imaging information of the target living body according to the thermal radiation information; judging whether the target living body is a target person of a preset age range according to the thermal imaging information and the face images; controlling a lamp device in the target area when it is determined that the target living body is a target person of a preset age range.
2. The method of claim 1, wherein, The judgment whether the target living body is a target person of a preset age range according to the thermal imaging information and the face images comprises: generating a first feature vector corresponding to the thermal imaging information based on a pre-existing thermal imaging template in a database; generating a second feature vector corresponding to the face features based on a deep learning model; fusing the first feature vector and the second feature vector to generate a target feature vector; inputting the target feature vector into a preset SVM classifier which can be used for preset age range personnel division to output probability information that the target living body is a target person of a preset age range.
3. The method of claim 2, wherein, The fusion of the first feature vector and the second feature vector to generate a target feature vector comprises: acquiring first weight data of the first feature vector; acquiring second weight data of the second feature vector; determining a first product of the first weight data and the first feature vector; determining a second product of the second weight data and the second feature vector; adding the first product and the second product to generate a target feature vector.
4. The method according to claim 2 or 3, characterized in that, Further comprising: when the probability information is greater than a preset probability threshold, determining that the target living body is a target person of a preset age range.
5. The method of claim 1, wherein, The control of the lamp device in the target area when it is determined that the target living body is a target person of a preset age range comprises: when it is determined that the target living body is a target person of a preset age range, controlling the lamp device in the target area to turn on if voice information of the target person is detected.
6. The method of claim 1, wherein, The control of the lamp device in the target area when it is determined that the target living body is a target person of a preset age range comprises: when it is determined that the target living body is a target person of a preset age range, acquiring action information and / or voice information of the target person; when it is determined that the action information and / or the voice information are abnormal, determining a first lamp parameter of the lamp device in the target area; controlling the lamp device according to the first lamp parameter.
7. The method of claim 6, wherein, Further comprising: when the action information and the voice information are not abnormal, determining a second lamp parameter of the lamp device in the target area; controlling the lamp device according to the second lamp parameter.
8. The method according to claim 6 or 7, characterized in that, Further comprising: when the action information and the voice information are not abnormal, if the voice information is a voice instruction of the target person, controlling the lamp device in the target area according to the voice instruction.
9. The method of claim 1, wherein, The control of the lamp device in the target area when it is determined that the target living body is a target person of a preset age range comprises: When it is determined that the target living body is the target person meeting the preset age range, sleep monitoring information of the target person is acquired; The light fixture device in the target area is controlled according to the sleep monitoring information.
10. The method of claim 9, wherein, The light fixture device in the target area is controlled according to the sleep monitoring information, including: The sleep state information of the target person is determined according to the sleep monitoring information; The light fixture device in the target area is controlled according to the sleep state information.
11. The method of claim 9, wherein, The light fixture device in the target area is controlled according to the sleep monitoring information, including: The real-time sleep stage of the target person is determined according to the sleep monitoring information; The light fixture device in the target area is controlled according to the real-time sleep stage.
12. A luminaire device control apparatus, characterized by: The device includes: A living body data acquisition module, configured to acquire a thermal radiation signal and a face image of a target living body in a target area; A thermal imaging information generation module, configured to generate thermal imaging information of the target living body according to the thermal radiation information; A target person judgment module, configured to determine whether the target living body is a target person meeting a preset age range according to the thermal imaging information and the face image; A light fixture device control module, configured to control a light fixture device in the target area when it is determined that the target living body is the target person meeting the preset age range.
13. An electronic device, comprising: A processor, a memory, and a program or instruction stored in the memory and executable on the processor, the program or instruction being executed by the processor to implement the light fixture device control method of claims 1-11.
14. A readable storage medium, characterized by, The program or instruction is stored on the readable storage medium, and the program or instruction is executed by the processor to implement the light fixture device control method of claims 1-11.