A lighting control method and system based on differentiated threshold and trajectory tracking

Abstract

The application belongs to the technical field of lighting control, and specifically discloses a lighting control method and system based on differentiated threshold and trajectory tracking, which comprises the following steps: collecting historical light adjustment data in a preset lighting area, classifying and analyzing the collected data, and calculating optimal lighting threshold values corresponding to various scenes; deploying multiple sensors in the lighting area to form a grid-shaped detection area, and calculating the current position and moving trajectory of a person in real time; generating a brightness distribution field conforming to the Gaussian distribution law according to the position of the person, and controlling the brightness output of each unit in real time; and based on the speed and moving direction of the person, adjusting the brightness of the lighting area twice. Through the above technical scheme, the application realizes the adaptive adjustment of the lighting threshold values in different areas and the dynamic tracking control of the trajectory of the person, effectively improves the intelligent level and energy-saving effect of the lighting system, improves the lighting experience of the user, and is suitable for various complex lighting environments.

Description

Technical Field

[0001] This invention belongs to the field of lighting control technology, specifically relating to a lighting control method and system based on differentiated thresholds and trajectory tracking. Background Technology

[0002] Lighting systems are an indispensable and important component. Traditional lighting systems typically use fixed brightness settings and cannot be intelligently adjusted according to the actual ambient light intensity and human activity. For example, when there is sufficient natural light during the day, indoor lights still maintain a high brightness, resulting in unnecessary energy consumption. In unoccupied areas, lights are also kept on, wasting a lot of electricity and increasing operating costs, which does not conform to the development concept of energy conservation and environmental protection.

[0003] Existing lighting control systems mostly employ fixed thresholds or single logic for adjustment, typically relying on manual switching, timed control, or triggering by a single sensor, which presents significant limitations. First, the traditional "one-size-fits-all" control strategy cannot meet the lighting needs of different areas, resulting in insufficient brightness in high-priority areas and wasted light energy in less important areas. Second, existing control logic lacks flexibility, making it difficult to adapt to dynamic scene changes such as conference rooms, and lacks intelligent response mechanisms for real-time personnel movement. Furthermore, traditional solutions often struggle to strike a balance between energy saving and user experience; for example, while lowering overall brightness saves energy, it reduces the lighting experience in critical areas, impacting user satisfaction.

[0004] Patent CN202411979967.9 discloses an IoT-based smart lighting control system that combines light sensors, human body sensors, and weather linkage to achieve lighting control based on fixed thresholds and compensation coefficients. While this method possesses a certain degree of intelligence, the threshold setting is relatively rigid, lacking the ability to dynamically adjust the thresholds for different regions, seasons, and weather conditions, making it difficult to meet varying lighting needs. Furthermore, its human body sensor-based control rules are relatively simple; when people move within the area, the current lighting cannot adapt to the new location's lighting requirements in a timely manner, resulting in a response lag, reducing the level of intelligence, and requiring manual adjustments by the user. Summary of the Invention

[0005] This invention addresses the problems in the prior art by providing a lighting control method and system based on differentiated thresholds and trajectory tracking. This solves the problem that the threshold setting in the prior art is relatively rigid and lacks the ability to dynamically adjust the threshold under different regions, seasons, and weather conditions. At the same time, it solves the problem that when people move within the area, the current lighting cannot adapt to the lighting needs of the new location in a timely manner, resulting in response lag and the need for manual adjustment by the user.

[0006] The technical solution adopted in this invention is as follows:

[0007] In a first aspect, this application provides a lighting control method based on differentiated thresholds and trajectory tracking, the method comprising the following steps:

[0008] Step S1: Collect historical illumination adjustment data within multiple preset lighting areas;

[0009] Step S2: Classify the historical illumination adjustment data, analyze each type of data based on the clustering algorithm, and calculate the corresponding optimal illumination threshold.

[0010] Step S3: Deploy sensors within the lighting area to form a grid-like detection area, fuse trigger information from multiple sensors, and calculate the current position and real-time movement trajectory of personnel within the lighting area;

[0011] Step S4: Divide the lighting area into multiple independent lighting areas, generate a brightness distribution field centered on the person's current position within the lighting area, and update it in real time within a set time interval.

[0012] Step S5: Control the brightness output of the corresponding lighting area according to the optimal lighting threshold and brightness distribution field;

[0013] Step S6: Based on the movement speed and direction of the personnel, perform secondary compensation adjustment on the brightness of the corresponding lighting area.

[0014] Furthermore, in step S1, the historical lighting adjustment data includes the light intensity of the lighting area, the user's desired brightness corresponding to the user's manually adjusted brightness, the current time, season, weather type, natural light intensity, and light intensity of adjacent areas, and the data is associated with and stored with the corresponding lighting area identifier.

[0015] Furthermore, in step S2, newly collected data is periodically introduced to retrain the clustering algorithm. The newly collected data is merged with existing historical illumination adjustment data to update the optimal illumination threshold for each region and replace the original cluster center parameters.

[0016] Furthermore, in step S3, the sensor is an infrared array sensor or a millimeter-wave radar. The sensor's detection grid is numbered, the time series of personnel triggering each detection grid is recorded, and the current position coordinates and real-time movement trajectory vector of the personnel in the lighting area are calculated based on the time series.

[0017] Furthermore, the calculation of the personnel's current position coordinates and real-time movement trajectory vector includes:

[0018] Using sensors to trigger the spatial coordinates of the grid and trigger time Construct the weighted centroid formula:

[0019]

[0020] Among them, weight , This is the time decay coefficient;

[0021] Personnel location at continuous time points and By performing a difference operation, we obtain the personnel movement velocity vector:

[0022]

[0023] Where, the magnitude of the velocity vector is The direction angle is:

[0024]

[0025] The velocity vectors at multiple time points are then fitted into a smooth trajectory curve.

[0026] Furthermore, in step S4, the brightness distribution field conforms to the Gaussian function distribution law, and the formula for the brightness distribution field is:

[0027]

[0028] in, The coordinates of the current position. Center brightness, This represents the standard deviation of brightness decay.

[0029] Furthermore, in step S6, when predicting the next position of the person, based on the velocity vector... With direction vector After compensation, the formula for the luminance distribution field is:

[0030]

[0031] in:

[0032]

[0033] To start from the current position Point to coordinates The direction angle, This is the speed compensation coefficient;

[0034]

[0035] Let be the amplification factor of velocity on brightness diffusion, when The larger the angle The smaller the value, the greater the compensation value.

[0036] Secondly, this application provides a lighting control system based on differentiated thresholds and trajectory tracking, used to implement the lighting control method based on differentiated thresholds and trajectory tracking as described in the first aspect. The system includes:

[0037] The data acquisition module is used to acquire historical illumination adjustment data for the preset lighting area;

[0038] The threshold generation module is used to classify historical illumination adjustment data, analyze each type of data based on a clustering algorithm, and calculate and generate the corresponding optimal illumination threshold.

[0039] The sensor deployment module is used to deploy sensors within the lighting area to form a grid-like detection area and collect sensor trigger information.

[0040] The position trajectory calculation module is used to fuse multiple sensor trigger information to calculate the current position and real-time movement trajectory of the personnel within the lighting area;

[0041] The lighting area control module is used to generate a brightness distribution field based on the current location of the person and control the brightness output of the corresponding lighting area according to the optimal lighting threshold.

[0042] The trajectory prediction module is used to perform secondary compensation and adjust the brightness of the corresponding lighting area based on the real-time movement speed and direction of the personnel.

[0043] Furthermore, the sensors include infrared array sensors or millimeter-wave radar, and the position trajectory calculation module specifically includes a weighted centroid calculation unit based on sensor-triggered grid numbers and a trajectory smoothing processing unit.

[0044] Furthermore, the brightness distribution field conforms to the Gaussian function distribution law, and the trajectory prediction module performs brightness distribution compensation adjustment based on the velocity vector and direction angle.

[0045] As can be seen from the above technical solutions, the advantages of the present invention are:

[0046] By introducing a regionally differentiated threshold learning mechanism and a dynamic dimming method based on human trajectory, the intelligence level and energy-saving effect of lighting control have been significantly improved.

[0047] Independent threshold libraries are established for different lighting areas. By combining historical lighting adjustment data, time, season and weather information, the optimal threshold is dynamically generated through clustering algorithms to achieve adaptive adjustment of the threshold. This avoids the rigidity problem of traditional uniform thresholds, effectively matches the lighting needs of different areas and environments, and reduces light energy waste.

[0048] By deploying infrared array sensors or millimeter-wave radar within the illuminated area to form a grid-like detection zone, precise tracking of personnel position and real-time movement trajectories is achieved. Utilizing algorithms based on weighted centroids and trajectory smoothing, a Gaussian-distributed brightness field centered on the person's current position is dynamically generated, enabling localized dimming. This allows for real-time adaptation to personnel movement, enhancing the user experience.

[0049] This invention predicts location and pre-adjusts brightness based on the speed and direction of human movement, further optimizing the response and balancing energy saving and lighting comfort. Experimental results show that, compared with traditional threshold algorithms, this invention can significantly reduce energy consumption while ensuring a good lighting experience, achieving the dual goals of energy saving and intelligent lighting. Attached Figure Description

[0050] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is a flowchart illustrating the steps of the lighting control method based on differential thresholds and trajectory tracking in the embodiment. Detailed Implementation

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] Please see Figure 1 As shown, this invention provides a lighting control method based on differentiated thresholds and trajectory tracking, comprising the following steps:

[0054] Step S1: Collect historical lighting adjustment data within multiple preset lighting areas. The collected data includes the regional light intensity detected by the light sensor, the brightness value manually adjusted by the user (user's desired brightness), the current time, season, weather type, natural light intensity, and the light intensity of adjacent areas. The above data is associated with and stored with the corresponding lighting area identifier. The sampling period is a preset fixed time interval.

[0055] Step S2: Classify the historical lighting adjustment data collected in Step S1. Based on a clustering algorithm (such as K-means algorithm), group and analyze the data according to region type, weather type and time period. For each type of data, calculate and generate the corresponding optimal lighting threshold to guide subsequent automatic dimming control.

[0056] In this embodiment, newly collected data is periodically introduced to retrain the clustering algorithm. The newly collected data is merged with existing historical illumination adjustment data to update the optimal illumination threshold for each region and replace the original cluster center parameters.

[0057] In the initial stage of system operation, light sensors and necessary environmental data acquisition devices (such as temperature and humidity sensors and weather interface modules) are deployed in each preset lighting area to continuously record ambient light intensity, user-adjusted brightness (i.e., user-desired brightness), time information (including hour, day of the week, and season), weather type, and the corresponding area type. Simultaneously, the data is mapped to physical space using area numbers, forming a dataset containing the following fields:

[0058] Data={AreaType,WeatherType,TimeSlot,AmbientLux,UserLux}

[0059] Among them, TimeSlot is the time period, which can be discretely segmented (e.g., 08:00–10:00 is the morning period), WeatherType is the weather, which can be derived from real-time weather API or inferred from local sensors (sunny, cloudy, rainy, etc.), AreaType is the area type, which is defined on-site (meeting room, corridor, office area, etc.), AmbientLux is the ambient light intensity, reflecting the objective value of the current natural light or mixed light, and UserLux is the user's desired brightness, which is used as supervisory data in subsequent threshold calculations to reflect the user's preference for the brightness of the scene.

[0060] In the data preprocessing stage, missing data is imputed using the mean or nearest neighbor, outliers (such as sudden changes in illumination without weather changes) are removed, and discrete features such as AreaType, WeatherType, and TimeSlot are encoded into numerical features (such as One-Hot encoding or integer encoding). The resulting feature vector takes the following form:

[0061] x=[AreaCode,WeatherCode,TimeCode,AmbientLux]

[0062] AreaCode is the area code, WeatherCode is the weather code, and TimeCode is the time period code.

[0063] All feature vectors are input into the K-means clustering algorithm. The choice of K can be determined using the elbow method, which calculates the total squared error within each cluster (SSE) for different K values ​​and selects the K value at the inflection point as the optimal number of clusters. The iterative process of K-means clustering is as follows:

[0064] Step 1: Randomly select K initial cluster centers.

[0065] Step 2: Assign each data point to the nearest cluster center (using Euclidean distance metric).

[0066] Step 3: Calculate the new center of each cluster (take the mean of each feature).

[0067] Step 4: Repeat steps 2 and 3 until the cluster centers converge or the maximum number of iterations is reached.

[0068] After clustering, each cluster corresponds to a type of composite scene data consisting of "region type + weather type + time period". For the data of each cluster, the optimal balance point between UserLux and AmbientLux within that cluster is calculated as the optimal lighting threshold for that cluster. In this embodiment, the following formula is used for calculation:

[0069]

[0070] in, , These are the weights for ambient light and the user's desired brightness, respectively, and can be adjusted according to an energy-saving or user-experience-first strategy (e.g., ...). =0.4, =0.6).

[0071] The optimal illumination thresholds for all clusters are stored in a threshold library as key-value pairs, with the key being (AreaType, WeatherType, TimeSlot) and the value being the corresponding T_opt.

[0072] When the system is running in real time, the currently detected area type, weather type and time period information will be encoded into feature vectors, matched to the corresponding cluster category in the threshold library, and the pre-calculated T_opt will be called as the lighting threshold for the current scene to achieve differentiated and adaptive lighting control.

[0073] Once the system collects new historical data, it can periodically (e.g., daily or weekly) re-execute the above clustering and threshold generation process to achieve dynamic updating and self-optimization of the threshold.

[0074] Step S3: Deploy infrared array sensors or millimeter-wave radar within the illuminated area to form a grid-like detection area, fusing trigger information from multiple sensors. By calculating the weighted centroid of the spatial coordinates and trigger times of the sensor trigger grid, the current position coordinates of the person are obtained in real time. The position at consecutive moments is differentially calculated to obtain the person's velocity vector and direction angle. Then, the velocity vectors at multiple moments are fitted to form a smooth movement trajectory.

[0075] The calculation of the personnel's current position coordinates and real-time movement trajectory vector includes:

[0076] Using sensors to trigger the spatial coordinates of the grid and trigger time Construct the weighted centroid formula:

[0077]

[0078] Among them, weight , This is the time decay coefficient;

[0079] Personnel location at continuous time points and By performing a difference operation, we obtain the personnel movement velocity vector:

[0080]

[0081] Where, the magnitude of the velocity vector is The direction angle is:

[0082]

[0083] The velocity vectors at multiple time points are then fitted into a smooth trajectory curve.

[0084] Step S4: Divide the lighting area into multiple independent lighting zones, typically 60cm × 60cm in size. Based on the current position of the person, generate a brightness distribution field within the corresponding lighting zone, centered on the person's position and conforming to a Gaussian function distribution. The brightness distribution field includes the center brightness and the standard deviation of brightness attenuation. The system updates the brightness distribution field in real time at set time intervals to achieve dynamic response.

[0085] The brightness distribution field follows a Gaussian function distribution law, and the formula for the brightness distribution field is:

[0086]

[0087] in, The coordinates of the current position. Center brightness, This represents the standard deviation of brightness decay.

[0088] Step S5: Based on the optimal lighting threshold generated in step S2 and the brightness distribution field in step S4, control the brightness output of the corresponding lighting area. Through local dimming control, achieve the light intensity that meets the threshold conditions, while ensuring spatial gradation of lighting, thus achieving a balance between energy saving and user experience.

[0089] Step S6: Based on the movement speed and direction of the personnel, perform secondary compensation adjustment on the brightness of the corresponding lighting area.

[0090] The brightness distribution field is compensated and adjusted based on the velocity vector and direction angle to achieve secondary compensation adjustment of the brightness of the corresponding lighting area, ensuring the foresight and continuity of the lighting response.

[0091] When predicting the next position of a person, based on the velocity vector With direction vector After compensation, the formula for the luminance distribution field is:

[0092]

[0093] in:

[0094]

[0095] To start from the current position Point to coordinates The direction angle, This is the speed compensation coefficient;

[0096]

[0097] Let be the amplification factor of velocity on brightness diffusion, when The larger the angle The smaller the value, the greater the compensation value.

[0098] In some embodiments, this application provides a lighting control system based on differentiated thresholds and trajectory tracking, the system comprising:

[0099] The data acquisition module is used to acquire historical lighting adjustment data within a preset lighting area. The acquired data includes ambient light intensity, user-manually adjusted brightness, time information, season, weather type, natural light intensity, and light intensity of neighboring areas, and the data is associated with and saved with the corresponding area identifier.

[0100] The threshold generation module is responsible for classifying and processing the collected historical lighting adjustment data. Based on clustering algorithms (such as K-means algorithm), it divides and analyzes the data according to regional characteristics, weather type and time period, and generates the optimal lighting threshold for each category for subsequent automatic dimming control.

[0101] The sensor deployment module arranges infrared array sensors or millimeter-wave radar in the lighting area to form a grid-like detection area, collecting trigger information from multiple sensors in real time to ensure comprehensive coverage of personnel activities.

[0102] The position trajectory calculation module integrates the trigger data from the above-mentioned multiple sensors, and through weighted centroid calculation and time series analysis, determines the precise position and movement trajectory of personnel within the lighting area in real time, providing an accurate spatial reference for dynamic dimming.

[0103] The lighting area control module generates a brightness distribution field that conforms to the Gaussian distribution law based on the current position of the person. At the same time, it combines the optimal lighting threshold output by the threshold generation module to dynamically control the brightness output of each lighting area, so as to realize refined and energy-saving lighting adjustment within the area.

[0104] The trajectory prediction module is used to perform secondary compensation and adjust the brightness of the corresponding lighting area based on the real-time movement speed and direction of people, thereby improving the response speed and adaptability of the lighting system and ensuring the continuity and comfort of the user experience.

[0105] In some embodiments, this application provides a terminal, including:

[0106] Memory for storing lighting control programs based on differential thresholds and trajectory tracking;

[0107] A processor is configured to implement the steps of the lighting control method based on differential threshold and trajectory tracking when executing the lighting control system based on differential threshold and trajectory tracking.

[0108] In some embodiments, this application provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the lighting control method based on differentiated thresholds and trajectory tracking.

[0109] It is understood that the systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, which can be a personal computer, a laptop computer, a personal digital assistant, a tablet computer, a wearable device, or any combination of these devices.

[0110] In a typical configuration, a computer includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0111] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0112] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0113] It should also be noted that 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 limitation, 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 said element.

[0114] It should be understood that although the terms first, second, third, etc., may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of one or more embodiments of this specification, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "in response to a determination," or "when," or "in the event of a determination."

[0115] The above description is merely a preferred embodiment of one or more embodiments of this specification and is not intended to limit the scope of one or more embodiments of this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of this specification should be included within the scope of protection of one or more embodiments of this specification.

Claims

1. A lighting control method based on differentiated thresholds and trajectory tracking, characterized in that, Includes the following steps: Step S1: Collect historical illumination adjustment data within multiple preset lighting areas; Step S2: Classify the historical illumination adjustment data, analyze each type of data based on the clustering algorithm, and calculate the corresponding optimal illumination threshold. Step S3: Deploy sensors within the lighting area to form a grid-like detection area, fuse trigger information from multiple sensors, and calculate the current position and real-time movement trajectory of personnel within the lighting area; In step S3, the sensor is an infrared array sensor or a millimeter-wave radar. The sensor's detection grid is numbered, the time series of personnel triggering each detection grid is recorded, and the current position coordinates and real-time movement trajectory vector of the personnel in the lighting area are calculated based on the time series. The calculation of the personnel's current position coordinates and real-time movement trajectory vector includes: Using sensors to trigger the spatial coordinates of the grid and trigger time Construct the weighted centroid formula: Among them, weight , This is the time decay coefficient; Personnel location at continuous time points and By performing a difference operation, we obtain the personnel movement velocity vector: Where, the magnitude of the velocity vector is The direction angle is: And fit the velocity vectors at multiple time points into a smooth trajectory curve; Step S4: Divide the lighting area into multiple independent lighting areas, generate a brightness distribution field centered on the location of the person within the lighting area, and update it in real time within a set time interval; In step S4, the brightness distribution field conforms to the Gaussian function distribution law, and the formula for the brightness distribution field is: in, The coordinates of the current position. Center brightness, The standard deviation of brightness decay; Step S5: Control the brightness output of the corresponding lighting area according to the optimal lighting threshold and brightness distribution field; Step S6: Based on the movement speed and direction of the personnel, perform secondary compensation adjustment on the brightness of the corresponding lighting area; In step S6, when predicting the next position of the person, based on the velocity vector... With direction vector After compensation, the formula for the luminance distribution field is: in: To start from the current position Point to coordinates The direction angle, This is the speed compensation coefficient; Let be the amplification factor of velocity on brightness diffusion, when The larger the angle The smaller the value, the greater the compensation value.

2. The lighting control method based on differentiated thresholds and trajectory tracking according to claim 1, characterized in that, In step S1, the historical lighting adjustment data includes the light intensity of the lighting area, the user's desired brightness corresponding to the user's manual brightness adjustment, the current time, season, weather type, natural light intensity, and light intensity of adjacent areas, and the data is associated with and stored with the corresponding lighting area identifier.

3. The lighting control method based on differentiated thresholds and trajectory tracking according to claim 2, characterized in that, In step S2, newly collected data is periodically introduced to retrain the clustering algorithm. The newly collected data is merged with existing historical illumination adjustment data to update the optimal illumination threshold for each region and replace the original cluster center parameters.

4. A lighting control system based on differentiated thresholds and trajectory tracking, used to implement the lighting control method based on differentiated thresholds and trajectory tracking as described in claim 1, characterized in that, The system includes: The data acquisition module is used to acquire historical illumination adjustment data for the preset lighting area; The threshold generation module is used to classify historical illumination adjustment data, analyze each type of data based on a clustering algorithm, and calculate and generate the corresponding optimal illumination threshold. The sensor deployment module is used to deploy sensors within the lighting area to form a grid-like detection area and collect sensor trigger information. The sensor is an infrared array sensor or a millimeter-wave radar. The sensor's detection grid is numbered, the time series of personnel triggering each detection grid is recorded, and the current position coordinates and real-time movement trajectory vector of the personnel in the lighting area are calculated based on the time series. The position trajectory calculation module is used to fuse multiple sensor trigger information to calculate the current position and real-time movement trajectory of the personnel within the lighting area; The calculation of the personnel's current position coordinates and real-time movement trajectory vector includes: Using sensors to trigger the spatial coordinates of the grid and trigger time Construct the weighted centroid formula: Among them, weight , This is the time decay coefficient; Personnel location at continuous time points and By performing a difference operation, we obtain the personnel movement velocity vector: Where, the magnitude of the velocity vector is The direction angle is: And fit the velocity vectors at multiple time points into a smooth trajectory curve; The lighting area control module is used to generate a brightness distribution field based on the current location of the person and control the brightness output of the corresponding lighting area according to the optimal lighting threshold. The brightness distribution field follows a Gaussian function distribution law, and the formula for the brightness distribution field is: in, The coordinates of the current position. Center brightness, The standard deviation of brightness decay; The trajectory prediction module is used to predict the next location of a person based on their real-time movement trajectory and a short time series prediction algorithm, and to adjust the brightness of the corresponding lighting area through secondary compensation. When predicting the next position of a person, based on the velocity vector With direction vector After compensation, the formula for the luminance distribution field is: in: To start from the current position Point to coordinates The direction angle, This is the speed compensation coefficient; Let be the amplification factor of velocity on brightness diffusion, when The larger the angle The smaller the value, the greater the compensation value.

5. The lighting control system based on differentiated threshold and trajectory tracking according to claim 4, characterized in that, The sensors include infrared array sensors or millimeter-wave radars, and the position trajectory calculation module specifically includes a weighted centroid calculation unit based on sensor-triggered grid numbers and a trajectory smoothing processing unit.

6. The lighting control system based on differentiated threshold and trajectory tracking according to claim 4 or 5, characterized in that, The brightness distribution field conforms to the Gaussian function distribution law, and the trajectory prediction module performs brightness distribution compensation and adjustment based on the velocity vector and direction angle.

Images