Adaptive lighting method, system and equipment based on event camera driving

Abstract

The invention discloses a self-adaptive lighting method, system and device based on event camera driving, and relates to the technical field of self-adaptive lighting, and the method comprises the steps: setting a digital twin model according to a power grid topological structure connected with an event camera and each power device; connecting a power grid event library in which a plurality of power grid security maintenance tasks are written; collecting a brightness change event flow in the target application scene; performing multi-target constraint optimization control to obtain an illumination priority sequence; and configuring an event triggering mechanism according to the illumination control matrix, and performing adaptive adjustment on the partition illumination parameters corresponding to the illumination partitions by taking the illumination effect as a feedback quantity. The technical problems that in the prior art, adaptability of illumination regulation and control and power grid safety is insufficient, and the illumination effect is difficult to accurately match scene requirements are solved, and the technical effects that adaptive illumination accurate regulation and control based on event camera driving are achieved, and the power grid safety stability and the illumination effect adaptability are improved are achieved.

Description

Technical Field

[0001] The present invention relates to the field of adaptive lighting technology, and in particular to an adaptive lighting method, system and device driven by an event camera. Background Art

[0002] With the development of science and technology, the application of lighting systems in various scenarios has become more and more extensive, and the demand for their intelligent and precise control has become increasingly urgent. In existing technologies, traditional lighting systems mostly rely on preset modes or simple sensor feedback, which makes it difficult to accurately adapt to complex and changing actual scenarios. For example, in large buildings, the functional differences between different areas lead to different lighting requirements. Traditional lighting control cannot flexibly and accurately adjust the lighting parameters of each zone based on factors such as real-time personnel activities, ambient brightness, and grid load. In terms of camera applications, the current technology that uses cameras to assist in lighting adjustment generally has the problem of insufficient mining of scene information. It can only make simple adjustments based on limited brightness detection and cannot comprehensively consider key factors such as the frequency of events and the importance of the scene. As a result, the lighting effect is out of line with actual needs, and there is a lack of effective response in the connection with grid security tasks. It is easy to cause instability of the lighting system when the grid load changes, and it is impossible to achieve coordinated optimization of lighting control and grid security.

[0003] Existing technologies have technical problems such as insufficient compatibility between lighting control and power grid security, and difficulty in accurately matching lighting effects with scene requirements. Summary of the Invention

[0004] The present application provides an adaptive lighting method, system and equipment driven by an event camera, which is used to solve the technical problems in the existing technology that lighting control and grid security are insufficiently adaptable and the lighting effect is difficult to accurately match the scene requirements.

[0005] In view of the above problems, the present application provides an adaptive lighting method, system and device driven by an event camera.

[0006] In a first aspect of the present application, an adaptive lighting method based on event camera driving is provided, the method comprising: A digital twin model is set up according to the power grid topology and various power equipment connected to the event camera; a power grid event library that writes multiple power grid security maintenance tasks is connected; the brightness change event stream in the target application scenario is collected by the event camera, the spatiotemporal characteristics of the events are extracted, and a lighting control matrix associated with each lighting partition is formulated in combination with the uneven illumination index; based on the digital twin model, a type of power grid security maintenance task corresponding to the power grid event library is introduced, and multi-objective constraint optimization control is performed with the brightness adjustment coefficient, color temperature parameter and refresh frequency of each lighting partition to obtain a lighting priority sequence; according to the lighting control matrix, in combination with the lighting priority sequence, an event triggering mechanism is configured, and the lighting parameters corresponding to each lighting partition are adaptively adjusted with the lighting effect as the feedback quantity.

[0007] A second aspect of the present application provides an event camera-driven adaptive lighting system, the system comprising: A digital twin model setting module is used to set up a digital twin model based on the power grid topology and various power equipment connected to the event camera; a power grid event library connection module is used to connect to the power grid event library that writes multiple power grid security maintenance tasks; an event spatiotemporal feature extraction module is used to collect the brightness change event stream in the target application scenario through the event camera, extract the event spatiotemporal features, and formulate a lighting control matrix associated with each lighting partition in combination with the uneven illumination index; a lighting priority sequence acquisition module is used to introduce a type of power grid security maintenance task corresponding to the power grid event library based on the digital twin model, and perform multi-objective constraint optimization control with the brightness adjustment coefficient, color temperature parameter and refresh frequency of each lighting partition to obtain a lighting priority sequence; an adaptive adjustment module is used to configure an event trigger mechanism based on the lighting control matrix and in combination with the lighting priority sequence, and perform adaptive adjustment of the partition lighting parameters corresponding to each lighting partition with the lighting effect as the feedback amount.

[0008] A third aspect of the present application provides an electronic device comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the adaptive lighting method based on event camera driving provided in the present application.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: A digital twin model is established based on the grid topology and various power equipment connected to the event camera. This model connects to a grid event library that stores multiple grid security maintenance tasks. The event camera collects the brightness change event stream in the target application scenario and extracts the event's spatiotemporal characteristics. Multi-objective constrained optimization control is then performed to obtain a lighting priority sequence. An event triggering mechanism is configured based on the lighting control matrix and the lighting priority sequence, and adaptively adjusts the lighting parameters corresponding to each lighting zone using the lighting effect as feedback. This achieves the technical effect of achieving precise adaptive lighting control driven by the event camera, improving grid security and stability, and improving the adaptability of lighting effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic flow chart of an adaptive lighting method driven by an event camera provided in an embodiment of the present application.

[0012] Figure 2 A schematic diagram of the structure of an adaptive lighting system driven by an event camera provided in an embodiment of the present application.

[0013] Figure 3 This is a schematic diagram of the structure of an electronic device provided in this application.

[0014] Explanation of the accompanying drawings: digital twin model setting module 10, power grid event library connection module 20, event spatiotemporal feature extraction module 30, lighting priority sequence acquisition module 40, adaptive adjustment module 50, processor 21, memory 22, input device 23, output device 24. DETAILED DESCRIPTION

[0015] This application provides an adaptive lighting method, system and equipment driven by an event camera, which is used to solve the technical problems in the existing technology that lighting control and power grid security are insufficiently adaptable, and the lighting effect is difficult to accurately match the scene requirements.

[0016] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative work are within the scope of protection of this application.

[0017] Example 1, as Figure 1 As shown, the present application provides an adaptive lighting method based on event camera driving, the method comprising: Step S100: Set up a digital twin model based on the power grid topology and various power equipment connected to the event camera.

[0018] Specifically, a digital twin model fully mirroring the physical grid is constructed based on the grid topology (covering the connections between transmission lines, substations, and distribution nodes) that establishes communication with the event camera, as well as the model parameters and operating status data (such as voltage, current, and load factor) of each power device in the grid (such as transformers, switches, and lighting fixtures). This model synchronizes key indicators of power devices in real time and accurately simulates the dynamic operating state of the grid, providing a virtual simulation foundation for the subsequent development of lighting control strategies in conjunction with grid security maintenance tasks. The model's settings directly link the scene lighting data collected by the event camera with the grid system, ensuring consistency between lighting control and grid operating status.

[0019] Step S200: connecting to and writing into a power grid event library of multiple power grid security maintenance tasks.

[0020] Specifically, a communication connection is established with the power grid event database, which has multiple pre-written grid security maintenance tasks. These tasks cover operational instructions and execution standards for various scenarios, such as equipment inspections, fault repairs, load balancing, and power safety warnings. The task data in the database is read through an interface protocol, enabling classified storage and rapid recall of maintenance tasks. Each task contains information such as associated power equipment operating parameters and user behavior samples. This provides a basis for subsequently selecting a grid security maintenance task from the database and associating it with lighting control optimization, ensuring that the lighting adjustment strategy is compatible with grid security maintenance requirements.

[0021] Step S300: The event camera collects the brightness change event stream in the target application scene, extracts the spatiotemporal features of the event, and formulates a lighting control matrix associated with each lighting partition in combination with the uneven illumination index.

[0022] Specifically, the event camera is activated to conduct real-time monitoring of the target application scene (such as office buildings, industrial parks, etc.), and the brightness change event stream caused by lighting changes in the scene is collected; the spatiotemporal features are extracted from the event stream, where the temporal features include the order and frequency of events, and the spatial features include the pixel coordinate distribution of events in the scene; the lighting unevenness index is determined by calculating the ratio of the maximum brightness value to the minimum brightness value in the scene, and the target application scene is divided into various lighting partitions in the form of an M×N grid. Combined with the event density heat map (generated based on spatiotemporal features) and the lighting unevenness index, a lighting control matrix associated with each lighting partition is proposed. The matrix element value is positively correlated with the event density in the corresponding lighting partition, which intuitively reflects the lighting adjustment needs of each partition and provides basic data support for the subsequent adaptive adjustment of lighting parameters.

[0023] Step S400: Based on the digital twin model, a type of grid security maintenance task corresponding to the grid event library is introduced, and multi-objective constraint optimization control is performed with the brightness adjustment coefficient, color temperature parameter and refresh frequency of each lighting partition to obtain a lighting priority sequence.

[0024] Specifically, relying on the constructed digital twin model to simulate the dynamic operation status of the power grid, a type of power grid security maintenance task is selected from the power grid event library. This type of task is determined by mining the power equipment group of any one of the multiple tasks (i.e., the first power grid security maintenance task), including power equipment operation status parameters and user behavior sample data; the brightness adjustment coefficient, color temperature parameters and refresh frequency of each lighting zone are used as optimization variables. On the basis of satisfying the multi-objective balance configuration of minimizing lighting energy consumption (corresponding to the brightness adjustment coefficient), maximizing the scene color rendering index (corresponding to the color temperature parameter), and minimizing the stroboscopic effect (corresponding to the refresh frequency), combined with the lighting adjustment constraints corresponding to different power grid load rate intervals, the event frequency, scene importance, and power grid security task relevance are set as priority evaluation indicators; when the difference in the priority evaluation scores of each lighting zone is greater than or equal to the difference threshold, they are arranged in descending order by score; when the score difference is less than the difference threshold, they are sorted in chronological order of event occurrence, and finally a lighting priority sequence is obtained.

[0025] Step S500: configuring an event triggering mechanism according to the lighting control matrix and in combination with the lighting priority sequence, and adaptively adjusting the zone lighting parameters corresponding to each lighting zone using the lighting effect as feedback.

[0026] Specifically, an event triggering mechanism is configured based on the adjustment requirements of each lighting zone in the lighting control matrix and the execution order of the lighting priority sequence (for example, the adjustment process is immediately initiated when the brightness change event of a high-priority zone exceeds a set threshold). The adjusted brightness change event stream is captured in real time through an event camera, and the deviation rate between the actual lighting effect and the target effect is calculated. Based on this deviation rate, the brightness adjustment coefficient of the corresponding zone is adjusted using a proportional-integral control method. When a lighting zone still fails to achieve the target effect after U consecutive adjustments (U ≥ 3), the color temperature compensation mechanism is activated. The color temperature difference between the actual color temperature of the current scene and the target color temperature is first obtained. Then, based on the human eye's sensitivity curve to color temperature, the color temperature offset Δλ is determined (where Δλ takes a positive value in the warm light zone and a negative value in the cold light zone). The color temperature parameters of the zone are adjusted through the LED driver circuit. At the same time, the event density, grid load rate, and user behavior data during the adjustment process are synchronously recorded, and the priority evaluation index is updated to achieve dynamic adaptive adjustment of the lighting parameters corresponding to each lighting zone.

[0027] In one possible implementation, step S300 further includes: Step S310: determining the uneven illumination index by the ratio of the maximum brightness value to the minimum brightness value in the target application scene.

[0028] Step S320: Divide the target application scene into lighting partitions of an M×N grid, and formulate a lighting control matrix under multi-bit grayscale according to the event density heat map and the illumination unevenness index.

[0029] Specifically, an event camera is used to collect brightness data in the target application scene, and the maximum and minimum brightness values ​​in the scene are extracted from the collected brightness change event stream. By calculating the ratio of these two values, the illumination unevenness index that can quantitatively reflect the uniformity of the scene illumination distribution is determined. The larger the ratio, the more significant the brightness difference between different areas in the scene and the more uneven the illumination distribution; conversely, it indicates that the illumination distribution is relatively balanced. This index provides a key quantitative basis for the subsequent division of lighting zones and the formulation of the lighting control matrix.

[0030] The target application scene is divided into M×N (M and N are both positive integers) independent lighting zones according to the preset spatial grid division rules. Each zone corresponds to a specific physical area within the scene. Based on the spatiotemporal clustering analysis of the brightness change event stream (with the event occurrence timestamp as the temporal dimension and the pixel coordinates corresponding to the event as the spatial dimension), an event density heat map is generated to intuitively reflect the density of brightness change events in each zone. Combined with the determined illumination unevenness index (used to quantify the overall illumination distribution differences in the scene), a lighting control matrix is ​​formulated in 8-bit grayscale (grayscale values ​​range from 0-255, where 0 corresponds to the lowest brightness adjustment requirement and 255 corresponds to the highest brightness adjustment requirement). The row and column indices of the matrix correspond to the positions of each lighting zone in the M×N grid, respectively. The grayscale values ​​of the matrix elements are positively correlated with the event density within the corresponding zone. At the same time, the grayscale values ​​of areas with high brightness differences are enhanced and corrected with reference to the illumination unevenness index, so that the matrix element values ​​accurately reflect the actual lighting adjustment requirement level of each zone, realizing a direct association between the lighting control matrix and 8-bit grayscale brightness adjustment.

[0031] In one possible implementation, step S300 further includes: Step S330: The matrix element values ​​of the lighting control matrix are positively correlated with the event density in each lighting partition of the association mapping.

[0032] Step S340: performing spatiotemporal clustering on the brightness change event stream in the target application scene, and generating the event density heat map with the event occurrence timestamp as the time dimension and the pixel coordinates as the space dimension.

[0033] Specifically, the value of each matrix element in the lighting control matrix is ​​positively correlated with the event density within the lighting partition to which it is associated. That is, the denser the brightness change events within a lighting partition (the higher the event density), the larger the matrix element value corresponding to the partition in the lighting control matrix. In this way, the size of the matrix element value can intuitively reflect the strength of the lighting adjustment demand of each lighting partition, ensuring that the matrix can accurately map the lighting control priority of different partitions due to differences in event density.

[0034] A spatiotemporal clustering operation is performed on the brightness change event stream collected by the event camera in the target application scenario. During the clustering process, the timestamp of the event is used as the time dimension to accurately record the distribution order and frequency of each event on the time axis; at the same time, the pixel coordinates corresponding to the event are used as the spatial dimension to clarify the specific location of each event in the physical space of the scene; by integrating the event timing characteristics of the time dimension and the event distribution characteristics of the spatial dimension, the events are clustered and grouped, so that events with similar timestamps and adjacent pixel coordinates are aggregated into the same clustering unit, and finally an event density heat map is generated that can intuitively present the density of brightness change events in each lighting zone. The darker the color in the heat map, the higher the event density of the corresponding zone, and vice versa, which provides a visualization basis for the event distribution of each zone for the subsequent formulation of the lighting control matrix.

[0035] In one possible implementation, step S400 further includes: Step S410: performing power equipment group mining based on the first power grid security maintenance task among the plurality of power grid security maintenance tasks to determine a type of power grid security maintenance task.

[0036] Step S420: wherein the type of power grid security maintenance task includes power equipment operating status parameters and user behavior sample data, and the first power grid security maintenance task is any one of the multiple power grid security maintenance tasks.

[0037] Specifically, any one of the multiple power grid security maintenance tasks (covering equipment inspection, fault repair, load balancing adjustment, etc.) pre-written in the power grid event library is selected as the first power grid security maintenance task. By analyzing the operation objects, execution scope and related equipment involved in the task, the power equipment group directly related to the task (such as transformers, switches, lighting fixtures, etc. in a specific area) is discovered, and the task set containing the relevant operation instructions and execution standards of the equipment group is determined as a type of power grid security maintenance task, providing targeted task basis for the subsequent optimization of lighting control in combination with power grid security needs.

[0038] It is clear that a type of grid security maintenance task identified contains two core information: one is the operating status parameters of the power equipment related to this type of task (such as the voltage, current, load rate of the equipment, and other data reflecting the real-time operating status of the equipment); the other is the user's behavior sample data in the target application scenario (such as user activity area, length of stay, and other behavioral information reflecting the user's lighting needs); at the same time, the source of this type of task is any one selected from multiple grid security maintenance tasks in the power grid event library, that is, the first grid security maintenance task. By mining the power equipment group of any task, a targeted type of grid security maintenance task is finally formed, which provides specific data support for the subsequent multi-objective constraint optimization of lighting control.

[0039] In one possible implementation, step S400 further includes: Step S430: performing a balanced optimization configuration based on the minimum lighting energy consumption corresponding to the brightness adjustment coefficient of each lighting zone, the maximum scene color rendering index corresponding to the color temperature parameter, and the minimum stroboscopic effect corresponding to the refresh frequency.

[0040] Step S440: At the same time, define lighting adjustment constraint conditions corresponding to different grid load rate intervals.

[0041] Specifically, for each lighting zone, a multi-objective balanced optimization configuration is performed with the brightness adjustment coefficient, color temperature parameters, and refresh rate as the core optimization variables. The brightness adjustment coefficient is adjusted to minimize lighting energy consumption, reducing overall energy consumption by rationally controlling the brightness output intensity of each zone. The color temperature parameter is set to maximize the scene color rendering index to ensure the true restoration of the colors of objects in the scene. The refresh rate is adjusted to minimize the stroboscopic effect to reduce visual fatigue or discomfort caused by frequency inappropriateness. Through the coordinated adjustment of these three parameters, a multi-dimensional balance is achieved while meeting the constraints of each target, making the lighting effect both energy-efficient and efficient while ensuring visual comfort and color authenticity, providing an optimization foundation for the subsequent generation of lighting priority sequences.

[0042] During the lighting control optimization process, the lighting adjustment constraints corresponding to different grid load rate intervals are defined simultaneously. That is, according to the load rate monitored by the grid in real time (such as low load rate, medium load rate, high load rate and other classification standards), different limit ranges are set for the brightness adjustment coefficient, color temperature parameters and refresh frequency of each lighting zone. For example, when the grid is in a high load rate interval, the maximum value of the brightness adjustment coefficient is constrained to reduce lighting energy consumption and avoid increasing the burden on the grid; when it is in a low load rate interval, the limit of the brightness adjustment coefficient can be appropriately relaxed to improve the lighting effect. At the same time, differentiated constraints are imposed on the adjustable range of the color temperature parameters and the fluctuation threshold of the refresh frequency for different load rate intervals to ensure that the lighting adjustment behavior is adapted to the grid load status, while meeting the lighting needs and ensuring the safe and stable operation of the grid.

[0043] In one possible implementation, step S430 further includes: Step S431: setting priority evaluation indicators including event frequency, scenario importance, and grid security task relevance.

[0044] Step S432: Based on the priority evaluation index, when the difference in the priority evaluation scores of the lighting zones is greater than or equal to a difference threshold, the lighting zones are arranged in descending order according to their priority evaluation scores to obtain the lighting priority sequence.

[0045] Step S433: When the difference in the priority evaluation scores of the lighting zones is less than the difference threshold, the zones are sorted in order of event occurrence time.

[0046] Specifically, an evaluation index system is established to evaluate the lighting adjustment priority of each lighting zone. This system includes three core indicators: event frequency, scene importance, and grid security task relevance. Among them, event frequency reflects the frequency of brightness change events within each lighting zone; scene importance reflects the functional importance of each zone in the target application scenario (such as the distinction between critical work areas and general access areas); grid security task relevance measures the closeness of the connection between the lighting status of each zone and the currently introduced type of grid security maintenance tasks. Through the comprehensive evaluation of these three indicators, a quantitative basis is provided for the subsequent determination of the lighting priority sequence of each lighting zone.

[0047] Based on the three priority evaluation indicators of event frequency, scene importance, and grid security task relevance, a comprehensive score is calculated for each lighting zone (through weighted summation, different weights are assigned to each indicator according to its importance and then accumulated); a difference threshold is set (such as 10% of the score or a fixed score), the scores of each zone are compared pairwise, and the maximum difference is calculated; when the maximum difference is greater than or equal to the preset difference threshold, a sorting algorithm (such as quick sort) is called to sort all lighting zones in descending order according to their priority evaluation scores from high to low, and a lighting priority sequence is generated to ensure that zones with high scores are given priority when adjusting lighting parameters.

[0048] After calculating the priority evaluation scores of each lighting zone based on priority evaluation indicators such as event frequency, scene importance, and grid security task relevance, if the score difference between the zones is less than the preset difference threshold, the score will no longer be used as the sorting basis. Instead, the zones will be sorted according to the time when the brightness change events occurred in each lighting zone. That is, the lighting zone where the brightness change event occurred first will be ranked first, and the one that occurred later will be ranked last. This will form a lighting priority sequence to ensure that when the score difference is small, the order of lighting adjustment can be reasonably determined based on the temporal logic of the event occurrence.

[0049] In one possible implementation, step S500 further includes: Step S510: The adjusted brightness event stream is collected through an event camera to obtain a deviation rate between the actual lighting effect and the target effect.

[0050] Step S520: Based on the deviation rate between the actual lighting effect and the target effect, the brightness adjustment coefficient is adjusted using proportional-integral control.

[0051] Step S530: For the lighting zones that have not met the standards after U consecutive adjustments, a color temperature compensation mechanism is activated to correct the visual brightness perception through color temperature offset, where U is greater than or equal to 3.

[0052] Specifically, after adjusting the lighting parameters of each lighting zone, the event camera is used to continuously collect the brightness change event stream in the target application scenario. The event stream contains the dynamic change information of the brightness of each area after adjustment; by analyzing and processing the collected brightness change event stream, the actual monitored brightness data is compared and calculated with the preset target brightness effect, so as to obtain the deviation rate between the actual lighting effect and the target effect. This deviation rate can quantitatively reflect the accuracy of the current lighting adjustment and provide a basis for subsequent further parameter optimization.

[0053] After determining the deviation rate between the actual lighting effect and the target effect, a proportional-integral control algorithm is used to adjust the brightness adjustment coefficient for each lighting zone. The proportional control component directly generates an adjustment based on the deviation rate to quickly respond to the current deviation; the integral control component accumulates the deviation rate to eliminate long-standing steady-state errors. The combination of these two algorithms allows the brightness adjustment coefficient to be accurately and stably adjusted to minimize the deviation, gradually narrowing the gap between the actual lighting effect and the target effect, achieving precise control of lighting brightness.

[0054] During the process of multiple adjustments to the brightness adjustment coefficients of each lighting zone, if the actual lighting effect of a lighting zone still does not reach the preset target effect after U consecutive adjustments (U ≥ 3), the color temperature compensation mechanism will be activated; this mechanism produces a color temperature offset by changing the color temperature parameters of the lighting zone, and uses the difference in the human eye's perception of brightness under different color temperatures to indirectly correct the visual brightness perception, thereby improving the lighting effect of the zone without relying solely on brightness adjustment. This ensures that even if brightness adjustment is limited or difficult to achieve, the actual lighting needs can still be met through color temperature adjustment.

[0055] In one possible implementation, step S530 further includes: Step S531: Obtain the color temperature difference between the actual color temperature of the current scene and the target color temperature.

[0056] Step S532: Based on the color temperature difference and in combination with the human eye's sensitivity curve to color temperature, a color temperature offset Δλ is determined, where λ is the center wavelength, Δλ in the warm light region takes a positive value, and Δλ in the cold light region takes a negative value.

[0057] Step S533: Using the color temperature offset Δλ, the LED driving circuit adjusts the color temperature parameters of the corresponding lighting partition, and simultaneously records the event density, grid load rate, and user behavior data during the adjustment process to update the priority evaluation index.

[0058] Specifically, the actual color temperature value in the current target application scene is collected in real time through the color temperature detection device, and the target color temperature value corresponding to the scene preset in the system is called up at the same time. The difference between the actual color temperature value and the target color temperature value is calculated to obtain the color temperature difference between the two. This difference can intuitively reflect the degree of deviation of the current scene color temperature from the ideal state, and provide basic data support for subsequent color temperature adjustment.

[0059] First, the actual color temperature value of the current scene is collected through the color temperature sensor, and the color temperature difference is calculated compared with the preset target color temperature value. The pre-stored human eye sensitivity curve data to color temperature is called (this curve reflects the sensitivity of the human eye perception in different color temperature ranges). The color temperature difference is substituted into the curve model for matching calculation to determine the required color temperature offset Δλ (where λ is the central wavelength of the scene lighting source). If the target color temperature belongs to the warm light range (such as 2700K-3500K), Δλ is assigned a positive value. If it belongs to the cold light range (such as 5000K-6500K), Δλ is assigned a negative value. This achieves accurate determination of the color temperature offset that conforms to the perception characteristics of the human eye.

[0060] Based on the determined color temperature offset Δλ, the color temperature parameters of the corresponding lighting zone are precisely adjusted through the LED driver circuit, so that the actual color temperature of the zone approaches the target color temperature according to the offset. During the adjustment process, the density of brightness change events within the lighting zone, the current power grid load rate, and user behavior data in the area are synchronously recorded. Based on this recorded data, the priority evaluation indicators including event frequency, scene importance, and grid security task relevance are updated to ensure that the priority evaluation can accurately reflect the current lighting status and scene requirements, providing a basis for subsequent lighting control optimization.

[0061] The second embodiment is based on the same inventive concept as the adaptive lighting method driven by an event camera in the above embodiment. Figure 2 As shown, the present application provides an adaptive lighting system driven by an event camera. The system and method embodiments in the present application are based on the same inventive concept. The system includes: The digital twin model setting module 10 is used to set the digital twin model according to the power grid topology and various power equipment connected to the event camera.

[0062] The power grid event library connection module 20 is used to connect to the power grid event library in which multiple power grid security maintenance tasks are written.

[0063] The event spatiotemporal feature extraction module 30 is used to collect the brightness change event stream in the target application scene through the event camera, extract the event spatiotemporal features, and formulate a lighting control matrix associated with each lighting partition in combination with the uneven illumination index.

[0064] The lighting priority sequence acquisition module 40 is used to introduce a type of power grid security maintenance task corresponding to the power grid event library based on the digital twin model, and perform multi-objective constraint optimization control with the brightness adjustment coefficient, color temperature parameter and refresh frequency of each lighting zone to obtain a lighting priority sequence.

[0065] The adaptive adjustment module 50 is used to configure an event trigger mechanism according to the lighting control matrix and the lighting priority sequence, and to adaptively adjust the zone lighting parameters corresponding to each lighting zone using the lighting effect as feedback.

[0066] Furthermore, the system is also used to implement the following functions: The illumination unevenness index is determined by the ratio of the maximum brightness value to the minimum brightness value in the target application scene. The target application scene is divided into lighting partitions of an M×N grid, and a lighting control matrix under multi-bit grayscale is formulated based on the event density heat map and the illumination unevenness index.

[0067] Furthermore, the system is also used to implement the following functions: The matrix element values ​​of the lighting control matrix are positively correlated with the event density within each lighting partition of the associated mapping; the brightness change event stream in the target application scenario is spatiotemporally clustered, and the event density heat map is generated with the event occurrence timestamp as the time dimension and the pixel coordinates as the spatial dimension.

[0068] Furthermore, the system is also used to implement the following functions: Based on the first power grid security maintenance task among the multiple power grid security maintenance tasks, power equipment group mining is performed to determine a type of power grid security maintenance task; wherein, the type of power grid security maintenance task includes power equipment operating status parameters and user behavior sample data, and the first power grid security maintenance task is any one of the multiple power grid security maintenance tasks.

[0069] Furthermore, the system is also used to implement the following functions: A balanced optimization configuration is performed based on the minimized lighting energy consumption corresponding to the brightness adjustment coefficient of each lighting zone, the maximized scene color rendering index corresponding to the color temperature parameter, and the minimized stroboscopic effect corresponding to the refresh frequency; at the same time, lighting adjustment constraints corresponding to different grid load rate intervals are defined.

[0070] Furthermore, the system is also used to implement the following functions: Priority evaluation indicators including event frequency, scene importance, and power grid security task relevance are set; based on the priority evaluation indicators, when the difference in priority evaluation scores of the various lighting zones is greater than or equal to a difference threshold, the lighting zones are arranged in descending order according to their priority evaluation scores to obtain the lighting priority sequence; when the difference in priority evaluation scores of the various lighting zones is less than the difference threshold, the zones are sorted in chronological order of event occurrence.

[0071] Furthermore, the system is also used to implement the following functions: Through the event camera, the adjusted brightness event stream is collected to obtain the deviation rate between the actual lighting effect and the target effect; based on the deviation rate between the actual lighting effect and the target effect, the proportional-integral control is used to adjust the brightness adjustment coefficient; for lighting partitions that still do not meet the standards after U consecutive adjustments, the color temperature compensation mechanism is activated to correct the visual brightness perception through color temperature offset, with U greater than or equal to 3.

[0072] Furthermore, the system is also used to implement the following functions: Obtain the color temperature difference between the actual color temperature of the current scene and the target color temperature; based on the color temperature difference and in combination with the human eye's sensitivity curve to color temperature, determine the color temperature offset Δλ, where λ is the center wavelength, Δλ takes a positive value in the warm light zone, and Δλ takes a negative value in the cold light zone; adjust the color temperature parameters of the corresponding lighting zone using the LED drive circuit based on the color temperature offset Δλ, synchronously record the event density, grid load rate, and user behavior data during the adjustment process, and update the priority evaluation index.

[0073] Example 3, Figure 3 A structural schematic diagram of an electronic device provided for the adaptive lighting method driven by an event camera of the present invention shows a block diagram of an exemplary electronic device suitable for implementing an embodiment of the present invention. Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention. Figure 3 As shown, the electronic device includes a processor 21, a memory 22, an input device 23 and an output device 24; the number of processors 21 in the electronic device can be one or more. Figure 3 Taking a processor 21 as an example, the processor 21, memory 22, input device 23 and output device 24 in the electronic device can be connected through a bus or other means. Figure 3 The bus connection is taken as an example.

[0074] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0075] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0076] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. An adaptive lighting method driven by an event camera, characterized in that: The method comprises: Set up a digital twin model based on the grid topology and various power equipment connected to the event camera; Connect to the power grid event library that writes multiple power grid security maintenance tasks; The event camera collects the brightness change event stream in the target application scene, extracts the spatiotemporal characteristics of the event, and formulates a lighting control matrix associated with each lighting partition in combination with the uneven illumination index; Based on the digital twin model, a type of grid security maintenance task corresponding to the grid event library is introduced, and multi-objective constraint optimization control is performed based on the brightness adjustment coefficient, color temperature parameter and refresh frequency of each lighting zone to obtain a lighting priority sequence; According to the lighting control matrix and in combination with the lighting priority sequence, an event triggering mechanism is configured, and adaptive adjustment of the zone lighting parameters corresponding to each lighting zone is performed with the lighting effect as feedback.

2. The adaptive lighting method based on event camera driving according to claim 1, characterized in that: The method of formulating a lighting control matrix associated with each lighting zone in combination with the uneven illumination index includes: Determining the uneven illumination index by the ratio of the maximum brightness value to the minimum brightness value in the target application scene; The target application scenario is divided into lighting partitions of an M×N grid, and a lighting control matrix under multi-bit grayscale is formulated according to the event density heat map and the illumination unevenness index.

3. The adaptive lighting method based on event camera driving according to claim 2, characterized in that: The method of formulating a lighting control matrix associated with each lighting zone in combination with the uneven illumination index includes: The matrix element values ​​of the lighting control matrix are positively correlated with the event density in each lighting partition of the association mapping; The brightness change event stream in the target application scenario is subjected to spatiotemporal clustering, and the event density heat map is generated with the event occurrence timestamp as the time dimension and the pixel coordinate as the space dimension.

4. The adaptive lighting method based on event camera driving according to claim 1, characterized in that: Introducing a type of power grid security maintenance task corresponding to the power grid event library, the method includes: Performing power equipment group mining based on a first power grid security maintenance task among the multiple power grid security maintenance tasks to determine a type of power grid security maintenance task; Among them, the type of power grid security maintenance tasks includes power equipment operating status parameters and user behavior sample data, and the first power grid security maintenance task is any one of the multiple power grid security maintenance tasks.

5. The adaptive lighting method based on event camera driving according to claim 4, characterized in that: Performing multi-objective constraint optimization control based on the brightness adjustment coefficient, color temperature parameter, and refresh frequency of each lighting zone to obtain a lighting priority sequence, the method comprising: Balanced optimization configuration is performed based on minimizing illumination energy consumption corresponding to the brightness adjustment coefficient of each lighting zone, maximizing scene color rendering index corresponding to the color temperature parameter, and minimizing stroboscopic effect corresponding to the refresh frequency; At the same time, the lighting adjustment constraints corresponding to different grid load rate intervals are defined.

6. The adaptive lighting method based on event camera driving according to claim 5, characterized in that: The method comprises: Setting priority evaluation indicators including event frequency, scenario importance, and grid security task relevance; Based on the priority evaluation index, when the difference between the priority evaluation scores of the respective lighting zones is greater than or equal to a difference threshold, the lighting zones are arranged in descending order according to their priority evaluation scores to obtain the lighting priority sequence; When the difference in the priority evaluation scores of the lighting zones is less than the difference threshold, the zones are sorted in order of the time of event occurrence.

7. The adaptive lighting method based on event camera driving according to claim 6, characterized in that: Adaptive adjustment of the zone lighting parameters corresponding to each lighting zone is performed using the lighting effect as feedback, the method comprising: The event camera is used to collect the adjusted brightness event stream and obtain the deviation rate between the actual lighting effect and the target effect; Based on the deviation rate between the actual lighting effect and the target effect, the proportional-integral control is used to adjust the brightness adjustment coefficient; For lighting zones that fail to meet the standards after U consecutive adjustments, the color temperature compensation mechanism is activated to correct the visual brightness perception through color temperature offset, with U greater than or equal to 3.

8. The adaptive lighting method based on event camera driving according to claim 7, characterized in that: For lighting zones that fail to meet the standards after U consecutive adjustments, a color temperature compensation mechanism is activated, the method comprising: Get the color temperature difference between the actual color temperature of the current scene and the target color temperature; Based on the color temperature difference and in combination with the human eye's sensitivity curve to color temperature, a color temperature offset Δλ is determined, where λ is the center wavelength, Δλ in the warm light region takes a positive value, and Δλ in the cold light region takes a negative value; The color temperature parameters of the corresponding lighting partition are adjusted by the LED driving circuit through the color temperature offset Δλ, and the event density, grid load rate and user behavior data during the adjustment process are simultaneously recorded to update the priority evaluation index.

9. An adaptive lighting system driven by an event camera, characterized in that: The system is used to implement the adaptive lighting method based on event camera driving according to any one of claims 1 to 8, and the system includes: A digital twin model setting module is used to set up a digital twin model based on the topology of the power grid and various power equipment connected to the event camera; A power grid event library connection module is used to connect to the power grid event library that writes multiple power grid security maintenance tasks; An event spatiotemporal feature extraction module is used to collect the brightness change event stream in the target application scene through the event camera, extract the event spatiotemporal features, and formulate a lighting control matrix associated with each lighting partition in combination with the uneven illumination index; A lighting priority sequence acquisition module is configured to, based on a digital twin model, introduce a type of power grid security maintenance task corresponding to the power grid event library, perform multi-objective constraint optimization control based on the brightness adjustment coefficient, color temperature parameter, and refresh frequency of each lighting zone, and obtain a lighting priority sequence; The adaptive adjustment module is used to configure an event trigger mechanism according to the lighting control matrix and the lighting priority sequence, and to adaptively adjust the zone lighting parameters corresponding to each lighting zone based on the lighting effect as feedback.

10. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; Wherein, the processor is used to execute the adaptive lighting method based on event camera driving according to any one of claims 1 to 8.

Images