Intelligent self-adaptive illumination adjustment light supplement lamp system and control method thereof

Abstract

The invention discloses an intelligent self-adaptive illumination adjustment light supplement lamp system and a control method thereof, particularly relates to the technical field of light supplement lamp control, and is used for solving the problem of insufficient intelligent self-adaption of a light supplement lamp. The method comprises the following steps: acquiring illumination original data of a global monitoring area and a target area, expanding low-light dynamic response through nonlinear logarithmic correction, and accurately quantifying local illumination deviation and change rate thereof by using a logarithmic proportional function based on preset target illumination so as to generate an adaptive adjustment signal; meanwhile, the running state of the light supplement lamp is divided in combination with a state machine structure, a sliding mode surface is further constructed through mapping of local illumination errors and the change rate, a sliding mode control law is determined through a smooth approximation function, illumination abnormity caused by sudden disturbance is effectively restrained, and finally a self-adaptive adjustment signal and a sliding mode control signal are fused, so that the light supplement lamp is obtained. Accurate control of light supplement lamp output is achieved, and therefore the stability and definition of night monitoring images are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of supplementary light control, and more specifically, to an intelligent adaptive light-adjusting supplementary light system and its control method. Background Art

[0002] In the night road environment, the lighting conditions are usually relatively poor. Especially in special sections such as moonless, starless, or blocked, tunnel sections, the natural light source is insufficient, which easily leads to limited visibility of drivers and difficult identification of pedestrians. Although traditional street lights can provide basic lighting, in the case of uneven light distribution, coexistence of local dark areas and strong reflection areas, they cannot meet the requirements of high-quality road monitoring and safe driving. Therefore, the supplementary light technology has emerged. By intelligently adjusting the supplementary lights, the local light on the road is supplemented and optimized, and the overall lighting uniformity and image acquisition quality are improved.

[0003] Deficiencies of the prior art: Existing night monitoring faces the problems of drastic changes in environmental light and local sudden interferences (such as vehicle high and low beam lights, street light flashes, and other sudden light sources), resulting in overexposure or underexposure in local areas of the monitoring screen, seriously affecting image clarity and detail capture. Traditional supplementary light methods mainly rely on fixed parameter control, which is difficult to adapt to rapidly changing light conditions in real time. Their adjustment strategies lack flexibility and cannot correct local light anomalies in a timely manner. At the same time, due to the insufficient response of light sensors in low light areas, the collected data often has obvious non-linear distortion, resulting in a large deviation between the actual light and the detected value, further reducing the control accuracy. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides an intelligent adaptive light-adjusting supplementary light system and its control method to solve the problem of insufficient intelligent adaptability of supplementary lights in the above-mentioned background art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An intelligent adaptive light-adjusting supplementary light control method, including the following steps:

[0007] Obtain the global and target area light raw data of the camera monitoring area, use non-linear logarithmic correction to expand the low light response range, and determine the local light deviation and change rate through a logarithmic proportional function according to the preset target light intensity;

[0008] Generate an adaptive adjustment signal according to the dynamic changes of the local light deviation and change rate, and divide the operating state of the supplementary light by combining a state machine structure;

[0009] Construct a sliding mode surface based on the mapping of local illumination error and change rate, identify the degree of deviation from the target state, and determine the sliding mode control law and generate a sliding mode control signal through a smooth approximation function to suppress the illumination anomaly caused by sudden disturbances;

[0010] Fuse the adaptive adjustment signal and the sliding mode control signal, and control the output of the fill light according to the fusion result.

[0011] In a preferred embodiment, obtain the global and target area illumination raw data of the camera monitoring area, and use non-linear logarithmic correction to expand the low-light response range. The specific process is as follows:

[0012] Obtain the global illumination raw data of the camera monitoring area through a high-sensitivity optical sensor;

[0013] Use local photosensitive elements or capture video frames from the monitoring camera as the local illumination raw data of the camera monitoring area;

[0014] Calibrate and preprocess the image of the global illumination raw data and the local illumination raw data, and correct the sensor response.

[0015] In a preferred embodiment, and according to the preset target illumination intensity, determine the local illumination deviation and change rate through a logarithmic ratio function. The specific process is as follows:

[0016] Perform region segmentation on the image to determine the target area corresponding to the fill light control, and use a brightness estimator for analysis. Define the local brightness value expression as: where LMBE is the local median brightness estimator, and the median of the pixel brightness in the image area is used as the area representative value to determine the dominant illumination level in the area; x and y respectively represent the horizontal and vertical two-dimensional spatial coordinates of the pixels on the image plane, and t represents the time variable;

[0017] Set the desired target illumination intensity I target ;

[0018] Use the error function of logarithmic ratio to determine the relative difference between local illumination deficiency and over-intensity, and define the local illumination deviation expression as: where δ is a positive constant.

[0019] When the local brightness value is lower than the target illumination intensity and the local illumination deviation is greater than 1, the local illumination deviation is greater than 0, indicating insufficient fill light;

[0020] When the local brightness value exceeds the target illumination intensity and the local illumination deviation is less than 1, the local illumination deviation is less than 0, indicating over-intense illumination;

[0021] Estimate the dynamic error quantity, use a high-precision numerical differentiation method to calculate the error derivative and use it as the rate of change. The expression of the error derivative is as follows:

[0022] In a preferred embodiment, according to the dynamic changes of the local illumination deviation and the rate of change, generate an adaptive adjustment signal, and combine with the state machine structure to divide the operating state of the supplementary light. The specific steps are as follows:

[0023] Take the local illumination deviation and the rate of change as the basic input, and use a PID controller to generate a basic control signal;

[0024] Use the basic control signal generated by the PID controller as the adaptive control signal to adjust the supplementary light;

[0025] Construct a state machine to divide the operating state of the supplementary light into three states: normal adjustment, mutation response, and steady-state recovery;

[0026] According to the local illumination deviation data in the recent period, use the trend line fitting or moving window method to estimate the development trend of the error in the short term in the future;

[0027] When both the local illumination deviation and the rate of change are within the predetermined safe range, no adjustment is made, and the operating state of the supplementary light is the normal adjustment state;

[0028] When it is monitored that the local illumination deviation or the rate of change exceeds the corresponding safe range within the specified time, trigger event-driven, and the operating state of the supplementary light switches to the mutation response state to quickly respond to local sudden changes;

[0029] When it is detected that the local illumination deviation starts to return and tends to be stable, the operating state of the supplementary light enters the steady-state recovery state.

[0030] In a preferred embodiment, construct a sliding mode surface according to the mapping of the local illumination error and the rate of change, identify the degree of deviation from the target state, and determine the sliding mode control law and generate a sliding mode control signal through a smooth approximation function to suppress the illumination anomaly caused by sudden disturbances. The specific process is as follows:

[0031] Use a logarithmic function to perform a nonlinear transformation on the local illumination deviation and the rate of change, and construct a sliding mode surface. The expression is as follows: Among them, sgn(e(t)) is the sign function, which is used to return the sign of e(t); ln(1 + |e(t)|) is a nonlinear mapping of the error; λ is a positive design parameter used to balance the influence of the error and the rate of change of the error; Similarly used to process the rate of change of the error;

[0032] After constructing the sliding mode surface, design the sliding mode control law to compensate for the disturbance. The design steps are as follows:

[0033] The designed sliding mode control law is as follows: where k is the positive control gain; φ is the boundary layer parameter; tanh(·) is the hyperbolic tangent function, and the output range is [-1, 1];

[0034] Take the designed sliding mode control law as the sliding mode control signal to adjust the supplementary light.

[0035] In a preferred embodiment, fuse the adaptive adjustment signal and the sliding mode control signal, and control the output of the supplementary light according to the fusion result. The specific process is as follows:

[0036] Use a non-linear function as the mixing factor, and the design form of the non-linear function is: where s(t) is the constructed sliding mode surface; ξ is the design parameter and is greater than 0, which is used to control the critical level for the non-linear function to start; p is the exponential parameter, which is used to adjust the steepness of the conversion process of the mixing function;

[0037] Fuse the adaptive control signal u PID (t) and the sliding mode control signal u SMC (t) non-linearly, and the expression of the final control signal obtained is: u(t) = u PID (t) + η(t)u SMC (t);

[0038] After the final control signal is generated, adjust the output brightness and color temperature of the supplementary light according to the final control signal.

[0039] The intelligent adaptive lighting adjustment supplementary light system for implementing the above intelligent adaptive lighting adjustment supplementary light control method includes:

[0040] The lighting data acquisition module is used to acquire the global and target area lighting raw data of the camera monitoring area, use non-linear logarithmic correction to expand the low-light response range, and determine the local lighting deviation and change rate through the logarithmic ratio function according to the preset target lighting intensity;

[0041] The supplementary light state division module is used to generate an adaptive adjustment signal according to the dynamic change of the local lighting deviation and change rate, and divide the operating state of the supplementary light in combination with the state machine structure;

[0042] The sliding mode control module is used to construct a sliding mode surface according to the mapping of the local lighting error and change rate, identify the degree of deviation from the target state, and determine the sliding mode control law and generate the sliding mode control signal through the smooth approximation function to suppress the lighting anomaly caused by sudden disturbances;

[0043] The fill light management module is used to fuse the adaptive adjustment signal and the sliding mode control signal, and control the output of the fill light according to the fusion result.

[0044] The technical effects and advantages of the present invention:

[0045] By collecting the original light data of the global and target areas in the monitoring area, the present invention uses highly sensitive sensors and cameras to obtain environmental and local brightness information respectively. After conversion by the non-linear logarithmic correction function, the low-light response range is effectively expanded. Then, according to the preset target illumination, the logarithmic proportional function is used to accurately quantify the local illumination deviation and its change rate, thereby generating an adaptive adjustment signal. Subsequently, combined with the state machine structure, the operating state of the fill light is divided into three modes: conventional adjustment, mutation response, and steady-state recovery, enabling the system to automatically switch control strategies under different light interferences. Further, a non-linear sliding mode surface is constructed using the local illumination error and change rate, and a robust control law is designed using a smooth approximation function to effectively suppress the illumination anomaly caused by sudden disturbances. Finally, the adaptive adjustment signal and the robust compensation signal are fused through non-linear mixing to achieve precise control of the output of the fill light, thereby significantly improving the stability and clarity of night monitoring images and meeting the security monitoring requirements in complex lighting environments. Description of the Drawings

[0046] Figure 1 It is a flowchart of the intelligent adaptive light adjustment fill light control method of the present invention.

[0047] Figure 2 It is a schematic structural diagram of the intelligent adaptive light adjustment fill light system of the present invention. Detailed Embodiments

[0048] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0049] Embodiment 1: As Figure 1 shown, the intelligent adaptive light adjustment fill light control method includes the following steps:

[0050] Obtain the original light data of the global and target areas in the camera monitoring area, use non-linear logarithmic correction to expand the low-light response range, and determine the local light deviation and change rate through the logarithmic proportional function according to the preset target light intensity;

[0051] Generate an adaptive adjustment signal according to the dynamic changes of the local light deviation and change rate, and divide the operating state of the fill light in combination with the state machine structure;

[0052] Construct a sliding mode surface based on the mapping of local illumination error and change rate, identify the degree of deviation from the target state, and determine the sliding mode control law and generate a sliding mode control signal through a smooth approximation function to suppress the illumination anomaly caused by sudden disturbances;

[0053] Fuse the adaptive adjustment signal and the sliding mode control signal, and control the output of the fill light according to the fusion result.

[0054] In the night video surveillance scenario, the surveillance often faces the problem of dynamic changes in illumination conditions. Due to the influence of external environmental factors (such as vehicle passing, street lamp switching, weather changes, etc.), the illumination intensity in a local area may change significantly instantaneously, which will directly affect the clarity and detail performance of the surveillance image;

[0055] Step 1, perform data acquisition and error calculation, and the specific steps are as follows:

[0056] Obtain the global illumination raw data of the camera surveillance area, that is, use a high-sensitivity light sensor to obtain the overall environmental illumination of the surveillance area, and its original output is denoted as: This data is used to correct the overall illumination baseline of the system to ensure that subsequent local measurements have a reference basis;

[0057] Obtain the local illumination raw data of the camera surveillance area, and obtain the pixel intensity distribution within the target area by using local photosensitive elements or directly capturing video frames from the surveillance camera, denoted as: Among them, Ω represents the fill light area to be adjusted. This data provides the original information of the local illumination state;

[0058] Calibrate and preprocess the global illumination raw data and the local illumination raw data to correct the sensor response and extract the brightness characteristics within the area respectively;

[0059] Sensor response calibration should take into account the non-linear response of the light sensor, and apply the non-linear correction function f(·) to transform the original illumination data. For example, select logarithmic transformation to expand the dynamic range of the low-light interval, and the calibration formula is: I cali (t) = f(I raw (t)) = ln(I raw (t) + ∈), where I raw (t) represents the original illumination data directly collected at time t (the original illumination data includes the global illumination raw data and the local illumination raw data), ∈ is a constant to prevent logarithmic singularity, and the global and local data respectively go through this step to form and

[0060] The nonlinear correction function is used to expand the low-light dynamic range. Light sensors tend to respond weakly in low-light conditions, that is, small changes in light intensity may not be reflected linearly. Logarithmic transformation can stretch small input values ​​so that small changes in the low-light area appear as larger numerical differences after conversion, thereby improving the sensitivity of the sensor in low-light environments;

[0061] Perform region segmentation and brightness estimation. For the images obtained by the surveillance camera, use the preprocessing algorithm (including noise suppression and contrast adjustment) to segment the images, so as to determine the target area corresponding to the fill light control. Use a brightness estimator to define the local brightness value as follows: Among them, LMBE is a local median brightness estimator, which uses the median brightness of pixels in the image area as the regional representative value to capture the dominant light level in the area and avoid being affected by individual extreme values; x and y represent the horizontal and vertical two-dimensional spatial coordinates of the pixel on the image plane, identifying the specific position in the target area; t represents the time variable, that is, the image data collected at time t;

[0062] According to the design requirements of the monitoring system and the need for supplementary lighting, a desired target light intensity I is determined in advance. target ,The target illumination intensity can be experimentally calibrated according to the environmental requirements and camera imaging characteristics;

[0063] The error function using a logarithmic scale emphasizes the relative difference between insufficient and excessive local lighting, and is defined as: Here, δ is a small positive constant used to avoid the division by zero problem.

[0064] When I local (t) lower than I target When the local illumination deviation is greater than 1, the logarithmic value e(t) is greater than 0, indicating insufficient fill light;

[0065] When I local (t) Exceed I target When the local illumination deviation is less than 1, the logarithmic value (t) is less than 0, indicating that the illumination is too strong;

[0066] This nonlinear error function mathematically guarantees the sensitivity to relative deviations and can provide a balanced control signal in different illumination ranges;

[0067] Furthermore, the error dynamics are estimated, and the error derivative is calculated using a high-precision numerical differentiation method as the rate of change. Anti-noise filtering is combined to ensure that the control performance is not affected by noise amplification during data transmission. The error derivative (rate of change) expression is:

[0068] Calculated local illumination deviation e(t) and rate of change As the core input signal of the control algorithm.

[0069] Step 2: Perform adaptive PID control on the fill light. That is, aiming at the characteristics of local light sudden interference in night monitoring, with the state machine and event-driven mechanism as the leading, taking into account continuous control and discrete state switching, to achieve intelligent response and adaptive adjustment to the error signal. The specific steps are as follows:

[0070] Using the local light deviation and its change rate as the basic input, a PID controller is used to generate a basic control signal: In the formula, K p , K i and K d are the proportional, integral, and differential gains respectively;

[0071] Determine the critical gain and critical oscillation period through the Ziegler-Nichols method to calculate the initial values of K p , K i and K d Apply the preliminarily estimated parameters to the system simulation or the actual system. By observing the system response (such as rise time, overshoot, steady-state error, and oscillation situation), further adjust the parameters until the design index is reached. This process may use iterative optimization algorithms or manual debugging. By changing one parameter and observing the dynamic response of the system, and then combining the adjustment of the other two parameters to obtain the best match;

[0072] The three terms of the above formula respectively represent the contributions of the current error, the cumulative historical error, and the error change rate, which can achieve continuous dimming. However, fixed parameters often have insufficient or excessive responses when facing sudden local light interference, and it is difficult to balance fast response and smooth adjustment at the same time;

[0073] Use the basic control signal generated by the PID controller as the adaptive control signal to adjust the fill light;

[0074] Construct a state machine structure. The constructed state machine divides the operating state of the fill light into three states: normal adjustment, mutation response, and steady-state recovery, so as to use different control strategies according to the signal characteristics;

[0075] According to the local light deviation data in the recent several periods, use the trend line fitting or moving window method to estimate the development trend of the error in the short term in the future;

[0076] When both the local light deviation e(t) and the change rate are within the predetermined safe range, it indicates that the environmental light changes smoothly. The fill light system only needs to perform smooth adjustment with a conventional low gain. At this time, it is in the normal adjustment state, and the basic PID control parameters are used to achieve smooth and low-gain adjustment;

[0077] When it is detected that the local light deviation or its rate of change exceeds the safe range within an extremely short period of time (for example, the local light deviation rapidly amplifies or suddenly drops), an event-driven trigger (such as rapid switching of the vehicle's high and low beams) is activated, and the system switches to the mutation response state. At this time, preset high-gain control parameters are used to quickly respond to local sudden changes;

[0078] When it is detected that the local light deviation begins to return and tends to be stable, the system automatically enters the steady-state recovery state. By gradually reducing the control gain, it prevents the oscillation of the fill light state caused by excessive gain and smoothly transitions back to the normal state;

[0079] If the prediction shows that the local light deviation is likely to continue to deteriorate in the future, the state machine is switched to the mutation response state in advance so as to take compensation measures in advance; on the contrary, when the prediction shows that the error will slowly recover, the system remains in or switches to the steady-state recovery state to help the fill light smoothly return to the normal adjustment state;

[0080] It should be noted that the safe range is usually preset based on the actual monitoring scenario through experimental measurement and on-site evaluation. By statistical analysis of the environmental light conditions and comparison with historical data, the safe working range applicable to the current fill light state and the critical point (critical threshold) for triggering state conversion are determined to ensure that the controller can respond stably and accurately under different light conditions.

[0081] The adaptive PID control design is to divide the operating state into three discrete states: normal regulation, mutation response, and steady-state recovery by introducing a state machine structure, and cooperate with the event-driven mechanism and short-term prediction to achieve intelligent judgment and adaptive adjustment of the error signal.

[0082] In the night monitoring scenario, the fill light needs to quickly respond to local sudden interferences. Although the adaptive PID can adjust parameters according to the error and its dynamic changes, there may be a risk of insufficient response or control oscillation when facing extreme disturbances.

[0083] Step 3, perform sliding mode control on the sudden local light interference, and the specific steps are as follows:

[0084] Obtain the local light deviation e(t) and its time derivative (rate of change) provided by Steps 1 and 2 As the basic inputs, these signals reflect the deviation between the target light and the actual local light and its changing trend;

[0085] Use the logarithmic function to perform non-linear conversion on the local light deviation and the rate of change to construct the sliding mode surface, and the expression is as follows: Among them, sgn(e(t)) is the sign function, which is used to return the sign of e(t), keep the sign of the sliding mode surface consistent with the error, and ensure the correct control direction; ln(1 + |e(t)|) non-linearly maps the error, so that there is still sufficient sensitivity in the low error region and will not be over-amplified in the high error region; λ is a positive design parameter used to balance the influence of the error and the error change rate. Similarly, it is used to process the change rate of the error and provide a response to dynamic disturbances.

[0086] The sign function is used to return the sign of the local light intensity deviation e(t), that is, it returns a positive value (usually +1) when e(t) is greater than zero, returns zero when e(t) is equal to zero, and returns a negative value (usually -1) when e(t) is less than zero.

[0087] The original local light intensity deviation signal and its dynamic information of the change rate are fused into a sliding mode surface s(t) through non-linear mapping, so that the supplementary light control system can quickly identify the degree of deviation from the target state through the sliding mode surface when facing large disturbances.

[0088] After constructing the sliding mode surface, the purpose of designing the sliding mode control law is to make the system state approach and stay on this surface in a finite time, so as to realize the compensation for disturbances. The design steps are as follows:

[0089] Using a smooth function to replace the sign function, the sliding mode control law is designed as: Among them, k is a positive control gain, which determines the correction force applied when the system state deviates from the sliding mode surface; φ is the boundary layer parameter, which defines the range of smooth approximation and avoids the oscillation caused by the switching of the ideal sign function (obtained through simulation or experiment); tanh(·) is the hyperbolic tangent function. It is used to provide a continuous and saturated output, and its output range is [-1, 1], ensuring that the output is close to -k or +k when s(t) is large, and the output smoothly transitions when s(t) is close to zero.

[0090] Taking the designed sliding mode control law as the sliding mode control signal to adjust the supplementary light.

[0091] The design of the sliding mode control law makes corrections when the system state (i.e., the value of the sliding mode surface) is large, so that the state quickly approaches the sliding mode surface; and when the state is close to the sliding mode surface, the control output smoothly decays, avoiding system oscillation caused by excessive correction, thus improving the fast response to sudden disturbances and taking into account the smoothness under steady state.

[0092] It should be noted that the determination of the positive control gain and the boundary layer parameters is usually carried out by combining theoretical analysis and experimental debugging. The positive control gain needs to be large enough to overcome uncertainties and external disturbances and meet the finite-time reaching condition. Its value is generally calculated preliminarily based on the system dynamic model, the upper bound of the disturbance, and the stability criterion, and then determined through simulation and on-site debugging. The boundary layer parameters are used to construct a smooth approximation to reduce the chattering caused by switching. Their selection needs to strike a balance between reducing oscillations and maintaining a sufficient convergence speed, and the optimal values are also obtained through simulation analysis and experimental verification.

[0093] Step 4, comprehensively control the fill light to form a fill light control signal, that is, construct a comprehensive control signal that can maintain smooth adjustment under normal circumstances and quickly introduce robust compensation when encountering local sudden disturbances.

[0094] When the output of the adaptive PID can already meet the basic adjustment requirements, no unnecessary interference is introduced; while when the disturbance is significant and the sliding mode variable is large, the sliding mode control output is fully activated to compensate for sudden disturbances.

[0095] Use a non-linear function as the mixing factor, and its design form is: Among them, s(t) is the sliding mode surface constructed in step three, which is used to reflect the comprehensive information of the error signal and its dynamic changes; ξ>0 is a design parameter that controls the critical level for starting the non-linear function, that is, when |s(t)| exceeds ξ, the mixing factor quickly tends to saturation; p is an exponential parameter that adjusts the steepness of the conversion process of the mixing function, so that the mixing factor can approach 1 faster when the disturbance is large and remain at a low value when the disturbance is small.

[0096] The parameter ξ controls the critical level for starting the mixing function, and its value determines when the absolute value of the sliding mode surface reaches a certain value to start significantly activating the compensation effect of u SMC (t). This parameter needs to be determined based on experimental data and the amplitude of the light disturbance in the actual monitoring scenario to ensure that no redundant compensation is introduced when there is no disturbance and a rapid response can be achieved when there is a strong disturbance.

[0097] The parameter p is used to adjust the steepness of the mixing function, that is, the speed of transition in the process from low activation to full activation. A larger p will cause the mixing factor to rise rapidly when approaching the threshold, which is suitable for scenarios where rapid activation of robust control is required; a smaller p will make the transition smoother, which is suitable for scenarios with higher requirements for the smoothness of the transition process.

[0098] Non-linearly fuse the adaptive control signal u PID (t) and the sliding mode control signal u SMC (t) to obtain the expression of the final control signal as: u(t) = u PID (t) + η(t)u SMC (t);

[0099] When the local perturbation is small, i.e., |s(t)| is small, it is approximately 0, so that η(t) ≈ 0, and finally the control signal is mainly composed of u PID (t); when the perturbation is significant, |s(t)| >> ξ causes the tanh function to tend to 1, and then η(t) ≈ 1. At this time, the compensation effect of u SMC (t) is fully activated, and the final output is approximately equal to the sum of u PID (t) + u SMC (t);

[0100] After the final control signal is generated, this signal is transmitted through the interface and the control network to the fill light control system for execution. The fill light usually includes a dedicated power drive circuit, a dimming control unit, and a fill light source array. The fill light control system converts the digital control signal into an actual current adjustment signal, and then adjusts the output brightness and color temperature of the fill light, so as to achieve precise adjustment of the local illumination;

[0101] For example, in a night monitoring scenario, when a vehicle approaches the monitoring area, a strong headlight interference will suddenly appear in the external environment, resulting in an instant increase in the illumination of some local areas. At this time, the system generates a control signal u(t) through the previous data acquisition, error calculation, adaptive PID, and sliding mode control. This signal reflects the current requirement to reduce the fill light intensity in this area. After the fill light execution module receives this signal, the drive circuit quickly adjusts the working state of the LED array, such as adjusting the current magnitude, so that the LED output quickly decays, reducing the local illumination to balance the entire monitoring picture. On the contrary, when it is detected that the local illumination is insufficient, the execution module will increase the LED output in the corresponding area to increase the illumination to the target value. At the same time, a local light sensor is equipped to monitor the adjusted illumination in real time and feedback the result to the main control system to ensure that the actual output meets the target requirements. If there is a deviation, the control signal will be further adjusted.

[0102] It should be noted that the thresholds involved in the embodiments can be determined according to specific scenarios and requirements.

[0103] The present invention acquires the original illumination data of the global monitoring area and the target area, and uses highly sensitive sensors and cameras to obtain environmental and local brightness information respectively. After conversion by a non-linear logarithmic correction function, the low-light response range is effectively extended. Then, according to the preset target illumination, the logarithmic ratio function is used to accurately quantify the local illumination deviation and its change rate, thereby generating an adaptive adjustment signal. Subsequently, combined with the state machine structure, the operation state of the supplementary light is divided into three modes: conventional adjustment, mutation response, and steady-state recovery, enabling the system to automatically switch control strategies under different illumination interferences. Further, a non-linear sliding mode surface is constructed using the local illumination error and change rate, and a robust control law is designed using a smooth approximation function to effectively suppress the illumination anomaly caused by sudden disturbances. Finally, the adaptive adjustment signal and the robust compensation signal are fused through non-linear mixing to achieve precise control of the output of the supplementary light, thereby significantly improving the stability and clarity of night monitoring images and meeting the security monitoring requirements in complex illumination environments.

[0104] Embodiment 2: An intelligent adaptive illumination adjustment supplementary light system, as Figure 2 shown, specifically includes:

[0105] An illumination data acquisition module, which is used to acquire the original illumination data of the global and target areas of the camera monitoring area, extend the low-light response range using non-linear logarithmic correction, and determine the local illumination deviation and change rate through a logarithmic ratio function according to the preset target illumination intensity;

[0106] A supplementary light state division module, which is used to generate an adaptive adjustment signal according to the dynamic changes of the local illumination deviation and change rate, and divide the operation state of the supplementary light in combination with the state machine structure;

[0107] A sliding mode control module, which is used to construct a sliding mode surface according to the mapping of the local illumination error and change rate, identify the degree of deviation from the target state, and determine the sliding mode control law and generate a sliding mode control signal through a smooth approximation function to suppress the illumination anomaly caused by sudden disturbances;

[0108] A supplementary light management module, which is used to fuse the adaptive adjustment signal and the sliding mode control signal, and control the output of the supplementary light according to the fusion result.

[0109] The above formulas are all dimensionless and take their numerical calculations. Specifically, various means such as standardization can be used for dimensionless processing, which will not be elaborated here. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0110] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available media can be magnetic media (e.g., floppy disks, ATA hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state ATA hard disk.

[0111] It should be understood that in various embodiments of the present application, the order of the above processes is not necessarily the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0112] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0113] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0114] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, and it may be located in one place or distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] In addition, each functional unit in various embodiments of the present application may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0116] As described above, the above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. Intelligent adaptive illumination adjustment fill light control method, characterized in that: The steps include: Obtain the global and target area illumination raw data of the camera monitoring area, use nonlinear logarithmic correction to expand the low-light response range, and determine the local illumination deviation and change rate through a logarithmic proportional function based on the preset target illumination intensity; According to the dynamic changes of local illumination deviation and change rate, an adaptive adjustment signal is generated, and the operation state of the fill light is divided in combination with the state machine structure; The sliding mode surface is constructed based on the mapping of local illumination error and change rate, the degree of deviation from the target state is identified, and the sliding mode control law is determined and the sliding mode control signal is generated through the smooth approximate function to suppress the illumination anomaly caused by sudden disturbances. The adaptive adjustment signal is fused with the sliding mode control signal, and the output of the fill light is controlled according to the fusion result.

2. The intelligent adaptive illumination adjustment fill light control method according to claim 1, characterized in that: Obtain the global and target area illumination raw data of the camera monitoring area, and use nonlinear logarithmic correction to expand the low-light response range. The specific process is as follows: The global illumination raw data of the camera monitoring area is obtained through a high-sensitivity light sensor; Capturing video frames as local illumination raw data of the camera monitoring area through a local photosensitive element or from a monitoring camera; The global illumination raw data and the local illumination raw data are calibrated and image preprocessed to correct the sensor response.

3. The intelligent adaptive illumination adjustment fill light control method according to claim 2, characterized in that: According to the preset target light intensity, the local light deviation and change rate are determined through the logarithmic proportional function. The specific process is as follows: Perform region segmentation on the image to determine the target area corresponding to the fill light control, use the brightness estimator for analysis, and define the local brightness value expression as: Among them, LMBE is a local median brightness estimator, which takes the median brightness of pixels in the image area as the representative value of the area to determine the dominant illumination level in the area; x and y represent the horizontal and vertical two-dimensional spatial coordinates of the pixel on the image plane, respectively, and t represents the time variable; Set the desired target light intensity I target ; The relative difference between insufficient and excessive local illumination is determined using a logarithmic error function, and the local illumination deviation expression is defined as: Here, δ is a positive constant. When the local brightness value is lower than the target light intensity, the local light deviation is greater than 1, and the local light deviation is greater than 0, indicating insufficient fill light; When the local brightness value exceeds the target light intensity, the local light deviation is less than 1, and the local light deviation is less than 0, indicating that the light is too strong; To estimate the error dynamics, use a high-precision numerical differentiation method to calculate the error derivative and use it as the rate of change. The error derivative expression is:

4. The intelligent adaptive illumination adjustment fill light control method according to claim 3 is characterized in that: According to the dynamic changes of local illumination deviation and change rate, an adaptive adjustment signal is generated, and the operating state of the fill light is divided in combination with the state machine structure. The specific steps are as follows: The local illumination deviation and change rate are used as basic inputs to generate basic control signals using a PID controller; The PID controller will be used to generate the basic control signal as the adaptive control signal for fill light adjustment; Construct a state machine to divide the operation state of the fill light into three states: normal adjustment, sudden change response and steady-state recovery; Based on the local illumination deviation data in the most recent period, use trend line fitting or moving window method to estimate the development trend of the error in the short term in the future; When the local illumination deviation and the rate of change are both within the predetermined safety range, no adjustment is performed and the fill light is operated in a normal adjustment state; When it is detected that the local illumination deviation or change rate exceeds the corresponding safety range within the specified time, the event drive is triggered and the fill light operation state is switched to the sudden response state to respond quickly to local sudden changes; When it is detected that the local illumination deviation begins to return and tends to be stable, the operation state of the fill light enters a steady-state recovery state.

5. The intelligent adaptive illumination adjustment fill light control method according to claim 4, characterized in that: The sliding surface is constructed based on the mapping of local illumination error and change rate, the degree of deviation from the target state is identified, and the sliding mode control law is determined and the sliding mode control signal is generated through the smooth approximate function to suppress the illumination anomaly caused by sudden disturbances. The specific process is as follows: Use the logarithmic function to perform nonlinear transformation on the local illumination deviation and the rate of change to construct the sliding surface. The expression is as follows: Where sgn(e(t)) is a sign function that returns the sign of the local illumination deviation e(t); ln(1+|e(t)| performs a nonlinear mapping of the error; λ is a positive design parameter that balances the effects of the error and the error change rate; Used to treat the rate of change of error in the same way; After constructing the sliding surface, the sliding mode control law is designed to compensate for disturbances. The design steps are as follows: The designed sliding mode control law is: Where k is the positive control gain; φ is the boundary layer parameter; tanh(·) is the hyperbolic tangent function, and the output range is [-1, 1]; The designed sliding mode control law is used as the sliding mode control signal to adjust the fill light.

6. The intelligent adaptive illumination adjustment fill light control method according to claim 5, characterized in that: The adaptive adjustment signal is fused with the sliding mode control signal, and the output of the fill light is controlled according to the fusion result. The specific process is as follows: Using nonlinear function as mixing factor, the design form of nonlinear function is: Among them, s(t) is the constructed sliding surface; ξ is a design parameter, which is greater than 0 and is used to control the critical level of the nonlinear function startup; p is an exponential parameter, which is used to adjust the steepness of the hybrid function conversion process; The adaptive control signal u PID (t) and the sliding mode control signal u SMC (t) is nonlinearly integrated, and the expression of the final control signal is: u(t) = u PID (t)+η(t)u SMC (t); After the final control signal is generated, the output brightness and color temperature of the fill light are adjusted according to the final control signal.

7. An intelligent adaptive light adjustment fill light system, used to implement the intelligent adaptive light adjustment fill light control method according to any one of claims 1 to 6, characterized in that: include: The illumination data acquisition module is used to obtain the global and target area illumination raw data of the camera monitoring area, use nonlinear logarithmic correction to expand the low-light response range, and determine the local illumination deviation and change rate through a logarithmic proportional function according to the preset target illumination intensity; The fill light state division module is used to generate an adaptive adjustment signal according to the dynamic changes of the local illumination deviation and the change rate, and divide the fill light operation state in combination with the state machine structure; The sliding mode control module is used to construct a sliding mode surface based on the mapping of local illumination error and change rate, identify the degree of deviation from the target state, and determine the sliding mode control law and generate a sliding mode control signal through a smooth approximate function to suppress illumination anomalies caused by sudden disturbances; The fill light management module is used to fuse the adaptive adjustment signal with the sliding mode control signal and control the output of the fill light according to the fusion result.

Images