Projector and method and system for controlling optical parameters of a projector

Abstract

The application discloses a kind of projector and the optical parameter regulation and control method and system of projector, method includes the real-time acquisition of multiple dimensions optical parameters of projection environment, and based on timestamp alignment generation fusion data stream, parameter includes real-time ambient illumination and color gamut deviation value;According to real-time ambient illumination dynamic calculation brightness adjustment weight and contrast adjustment weight, input fusion data stream into reinforcement learning model, output high-level strategy parameter for adjusting the above weight;According to the weight after adjustment generation brightness and contrast control instruction, and convert color gamut deviation value into saturation compensation coefficient;Finally, control instruction and compensation coefficient are sent to execution unit and carry out optical parameter regulation and control.The application realizes the space-time alignment and fusion of multiple dimensions environmental data, realizes the collaborative optimization of brightness and contrast by layered intelligent decision, and carries out color saturation joint compensation in HSV space, effectively improves the level of projection picture under complex environment light and color fidelity.

Description

Technical Field

[0001] This invention belongs to the technical field of projector optical parameter adjustment methods, specifically relating to a projector and a method and system for adjusting the optical parameters of a projector. Background Technology

[0002] With the rapid development of smart display technology, projectors have been widely used in various scenarios such as home theaters, business offices, and educational projection. The display effect of a projector depends not only on its own optical hardware performance but also significantly on the lighting conditions of the environment. In a less-than-ideal dark room environment, stray light can significantly reduce the contrast of the projected image, leading to loss of color saturation, washed-out appearance, and loss of detail. Therefore, dynamically adjusting the projector's optical parameters according to the complex and ever-changing projection environment has become a core issue in improving the user experience.

[0003] Currently, most projectors on the market have some degree of ambient light adaptive adjustment. Traditional solutions mainly rely on a single ambient light sensor to collect ambient illuminance and, based on a preset linear mapping table or simple threshold judgment, adjust the projector's backlight brightness or basic contrast to increase or decrease as a whole.

[0004] However, the aforementioned existing technologies have the following shortcomings in practical applications: First, existing technologies suffer from limited environmental perception and isolated adjustment strategies. Traditional solutions often focus solely on changes in ambient illuminance, neglecting the impact of key optical parameters such as ambient light color temperature, projection area reflectivity, and color gamut deviation. In the real physical world, changes in ambient light are multi-dimensionally coupled, and brightness adjustment based solely on illuminance can easily lead to an imbalance in image contrast. Furthermore, existing systems typically treat brightness, contrast, and color compensation as independent modules when adjusting parameters, lacking a mechanism for coordination and weight allocation among multiple parameters, making it difficult to achieve optimal overall image presentation under complex lighting conditions.

[0005] Secondly, existing adjustment mechanisms have a low level of intelligence and are unable to cope with complex, dynamically changing scenarios. Control methods based on fixed mapping tables or simple logical rules are static and lagging. When the projection environment experiences rapid, nonlinear changes in illumination, traditional algorithms cannot learn from historical control effects and iterate their strategies, leading to large system response delays, over-adjustment or under-adjustment, and even instability phenomena such as screen flickering.

[0006] Furthermore, existing technologies often lack high-level strategic guidance when performing brightness and contrast compensation, easily leading to local optimization at the expense of the overall viewing experience. For example, simply increasing brightness under strong light, while improving details in dark areas, causes overexposure in bright areas, thus destroying the overall image's sense of depth. Moreover, existing systems often lack precise and real-time compensation mechanisms for color saturation when brightness changes, resulting in severe color dilution (i.e., washed-out colors) after brightness increases, failing to maintain the original color realism and expressiveness.

[0007] Finally, existing projectors lack robust anomaly handling and self-calibration mechanisms when dealing with sudden changes in environmental parameters or abnormal sensor data. When receiving a sudden change signal, conventional systems often blindly follow the signal and adjust accordingly, resulting in severe shaking of the projected image. Furthermore, under long-term operation or extreme interference, the lack of proactive benchmark calibration methods easily leads to parameter drift, causing the control system to gradually deviate from its optimal operating range. Summary of the Invention

[0008] The technical problem to be solved by the present invention is to overcome the problems of single adjustment dimension, slow response, lack of color compensation and insufficient system robustness of the existing projector optical parameter adjustment technology, so as to provide a projector and a method and system for adjusting the optical parameters of the projector.

[0009] A method for adjusting the optical parameters of a projector, comprising the following steps: Step S1: Real-time acquisition of multi-dimensional optical parameters of the projection environment, and generation of fused data stream based on timestamp alignment; the multi-dimensional optical parameters include at least real-time ambient illuminance and color gamut deviation values; Step S2: Dynamically calculate the brightness adjustment weight and contrast adjustment weight based on the real-time ambient illuminance; simultaneously, input the fused data stream into a preset reinforcement learning model and output high-level policy parameters, which include the adjustment amount of the brightness adjustment weight and contrast adjustment weight; Step S3: Generate brightness and contrast control instructions based on the adjusted brightness adjustment weight and contrast adjustment weight, and convert the color gamut deviation value into a saturation compensation coefficient in the HSV color space. Step S4: Send the control command and saturation compensation coefficient to the execution unit to control the optical output parameters of the projector.

[0010] Furthermore, the step of dynamically calculating the brightness adjustment weight and contrast adjustment weight based on the real-time ambient illuminance includes: the brightness adjustment weight is determined based on the ratio of the real-time ambient illuminance to the maximum tolerable illuminance threshold; the contrast adjustment weight is determined based on the brightness adjustment weight, and the sum of the brightness adjustment weight and the contrast adjustment weight is a constant.

[0011] Furthermore, the input state of the reinforcement learning model includes real-time sensor data, the current projection parameter state, and historical control data retrieved from non-volatile memory; the output action of the reinforcement learning model is high-level policy parameters, which are passed to the low-level control module to generate the final execution instruction.

[0012] Furthermore, the reinforcement learning model updates the decision strategy through iterative learning. Its reward function is calculated based on color difference and adjustment delay, with the optimization objective being to minimize color difference and adjustment delay. The color difference is determined based on the difference between the current projected color and the preset standard color in the CIELab color space. The adjustment delay is defined as the time difference from the start of parameter acquisition to the completion of parameter adjustment by the execution unit.

[0013] Furthermore, the step of directly converting the color gamut deviation value into a saturation compensation coefficient includes: the saturation compensation coefficient is determined based on the color gamut deviation value according to a linear proportional relationship, and the saturation compensation coefficient is sent directly as a control signal to the execution unit to drive the electronic filter without going through a reinforcement learning model.

[0014] Furthermore, the real-time acquisition of multi-dimensional optical parameters includes: acquiring ambient illuminance and color temperature, capturing the pixel matrix of the projection area and aligning the resolution, acquiring spectral data and inputting it into the CIELab model to calculate the color gamut deviation value; and generating the fused data stream by aligning the multi-source data through timestamps.

[0015] Furthermore, the control of the optical output parameters of the projector includes: performing full-process iteration at a preset frequency based on time series data stream processing technology; during the control process, monitoring parameter fluctuations in real time, and when a parameter mutation is detected to exceed a preset threshold, triggering an abnormal interruption response thread, freezing the current projection parameters and projecting a test image for self-calibration, and regenerating the benchmark mapping table.

[0016] Furthermore, the response logic of the execution unit includes: the light source driving circuit outputs a frequency modulation signal according to the brightness and color temperature control instructions; the liquid lens applies a voltage signal according to the focal length and distortion control instructions to achieve zoom and angle compensation; and the electronic filter adjusts the transmittance according to the saturation compensation coefficient.

[0017] An optical parameter control system for a projector, comprising: The parameter detection unit is used to collect multi-dimensional optical parameters of the projection environment in real time and generate a fused data stream based on timestamp alignment; the multi-dimensional optical parameters include at least real-time ambient illuminance and color gamut deviation values; The control unit is used to dynamically calculate the brightness adjustment weight and contrast adjustment weight based on the real-time ambient illuminance; input the fused data stream to a preset reinforcement learning model, output high-level strategy parameters, the high-level strategy parameters including the adjustment amount of the brightness adjustment weight and contrast adjustment weight; generate brightness and contrast control instructions based on the adjusted weights, and convert the color gamut deviation value into a saturation compensation coefficient in the HSV color space. The execution unit is used to receive the control command and saturation compensation coefficient, and to control the optical output parameters of the projector.

[0018] A projector includes an intelligent projection unit and the aforementioned optical parameter control system; the intelligent projection unit comprises a light source module, a display chip, and a projection lens assembly, used to generate and project images, and is controlled by the execution unit of the optical parameter control system.

[0019] Beneficial Effects: This invention discloses a method for adjusting the optical parameters of a projector. By synchronously collecting multi-dimensional optical parameters, including at least real-time ambient illuminance and color gamut deviation values, and generating a fused data stream based on timestamp alignment, it eliminates the temporal misalignment of multi-source data, ensuring the integrity and synchronization of environmental state restoration, and providing solid data support for subsequent precise adjustment. This invention adopts a hierarchical control architecture of basic weight calculation and high-level strategy correction. First, the basic adjustment weights of brightness and contrast are dynamically calculated based on real-time ambient illuminance, ensuring basic light and shadow adaptation. Then, a reinforcement learning model is introduced to perform deep analysis of the fused data stream, outputting high-level strategy parameters to intelligently correct the basic weights. This mechanism endows the system with self-learning and dynamic optimization capabilities, breaking the limitations of traditional fixed mapping rules. Brightness and contrast adjustment is no longer a mechanical linear increase or decrease, but can achieve synergistic complementarity according to complex environments, effectively avoiding overexposure or stark black in the image, and significantly improving visual depth.

[0020] This invention adjusts brightness parameters while directly converting the color gamut deviation value, which reflects ambient color shift, to the HSV color space to generate a saturation compensation coefficient. Based on the human visual perception mechanism, this design simultaneously and precisely compensates for color saturation changes when brightness and contrast shift, effectively mitigating color dilution and shift caused by ambient light. This ensures that the projected image maintains vibrant, rich, and realistic colors under any lighting conditions. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of the main method steps of the present invention; Figure 2 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0023] To make the above-mentioned objectives, features, and advantages of this application more apparent and understandable, the specific embodiments of this application are described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a thorough understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of this application. Therefore, this application is not limited to the specific embodiments disclosed below.

[0024] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0025] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "joining," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0026] Example 1: This embodiment provides a method for adjusting the optical parameters of a projector, referring to... Figure 1 This includes the following steps: In step S1, multi-dimensional optical parameters of the projection environment are acquired in real time, and a fused data stream is generated based on timestamp alignment; the multi-dimensional optical parameters include at least real-time ambient illuminance and color gamut deviation values.

[0027] Specifically, data is acquired through a multi-source sensor array in the parameter detection unit: an ambient light sensor (e.g., MAX44009, range 0-100,000 lux) is used to acquire ambient illuminance E at a frequency of 100Hz. env Color temperature; an image sensor (e.g., OV2740 CMOS) is used to capture the RGB pixel matrix of the projection area, and it is aligned to a resolution of 1920×1080 using a bilinear interpolation algorithm; a spectrometer is used to collect spectral data in the 380-780nm band via a beam splitter, and the data is input into the CIELab model to calculate the color gamut deviation value ΔC, expressed as: ΔC = |Measured value - 98% AdobeRGB|.

[0028] Multi-source data are aligned with timestamps (accuracy ±0.1ms) to generate a fused data stream.

[0029] In step S2, the brightness adjustment weight and contrast adjustment weight are dynamically calculated based on the real-time ambient illuminance. At the same time, the fused data stream is input into a preset reinforcement learning model, and high-level policy parameters are output, including the adjustment amount of the brightness adjustment weight and contrast adjustment weight.

[0030] Specifically, the control unit (e.g., a Xilinx Zynq-7000 FPGA) runs a dynamic weight allocation algorithm to adjust the brightness weights. Based on real-time ambient illuminance With the maximum tolerance illuminance threshold The ratio is determined, and the contrast adjustment weight is adjusted. Based on the determination of brightness adjustment weights, and since the sum of the two is a constant, the formula is as follows: ; =1- ; in, The default value is 80,000 lux.

[0031] Simultaneously, the fused data stream is input into a pre-defined reinforcement learning model (such as a Q-learning model). The input states of this reinforcement learning model include: real-time sensor data (such as ambient illuminance E). envThe model includes: color temperature, color gamut deviation value ΔC, projection distance, etc.; current projection parameter status (current brightness, contrast, saturation, etc.); and historical adjustment data retrieved from non-volatile memory (such as eMMC memory). The model's output actions are high-level strategy parameters, which may include adjustments to the brightness adjustment weights, contrast adjustment weights, and target color space offset parameters. These high-level strategy parameters are passed to the low-level control modules (such as the color gamut mapping module and the light source driving algorithm) to generate the final execution instructions.

[0032] In this embodiment, the reinforcement learning model updates its decision-making policy through iterative learning, and its reward function R is based on the color difference ΔE and the modulation delay T. delay The calculations are performed with the optimization goal of minimizing color difference and adjustment delay. The color difference ΔE is determined based on the difference between the current projected color and the preset standard color in the CIELab color space (e.g., using the CIEDE2000 color difference formula or Euclidean distance); a smaller ΔE value indicates more accurate color reproduction. The adjustment delay T... delay Defined as the time difference, in milliseconds, from the timestamp when the parameter detection unit collects environmental data to the timestamp when the execution unit completes parameter adjustment. The reward function will use T... delay As a penalty, it aims to incentivize the model to pursue the ultimate response speed while ensuring accuracy.

[0033] As a preferred embodiment, the reward function is defined as: R= ; Specifically, the color difference ΔE is based on the CIELab color model. After the spectral analyzer in the parameter detection unit acquires the projected spectral data, it calculates the Euclidean distance between the current projected color and the preset standard color in the CIELab color space, expressed as: = ; Specifically, the input state of the Q-learning model ( ) is a multi-dimensional vector that includes real-time sensor data (ambient illuminance) The data includes the color gamut deviation value ΔC, the current optical parameter status, and historical control data retrieved from non-volatile memory.

[0034] Output action ( This refers to the control strategy selected based on the current state, specifically manifested as generating a continuous set of control instructions, which may include dynamic weights. , The model learns iteratively through a large number of state-action pairs, using specific numerical values ​​or fine-tuning commands to the execution unit, and finally outputs the decision that yields the highest cumulative reward (i.e., optimal color accuracy and fastest speed).

[0035] In this embodiment, the reinforcement learning model is trained using historical data.

[0036] In step S3, brightness and contrast adjustment instructions are generated based on the adjusted brightness adjustment weight and contrast adjustment weight, and the color gamut deviation value is converted into a saturation compensation coefficient in the HSV color space.

[0037] In a preferred embodiment of this invention, the adjusted brightness adjustment weight and contrast adjustment weight are multiplied by the preset corresponding maximum adjustment range to obtain the corresponding actual adjustment range control command, which directly adjusts the brightness and contrast of the corresponding projector.

[0038] Specifically, the control unit adjusts the high-level policy parameters output by the reinforcement learning model. and Adjustments are made, and brightness and contrast control commands are generated. Simultaneously, the color gamut mapping module built into the control unit directly converts the color gamut deviation value ΔC into a saturation compensation coefficient in the HSV color space. Determined by a linear proportional relationship, expressed as: = ; The saturation compensation coefficient is used directly as a clear control signal without going through a reinforcement learning model.

[0039] In step S4, the control command and saturation compensation coefficient are sent to the execution unit to control the optical output parameters of the projector.

[0040] The response logic of the execution unit includes: the light source driving circuit (e.g., LT3956 chip) outputs a PWM frequency modulation signal (duty cycle ±18%) according to the brightness and color temperature control instructions to adjust the light source brightness and color temperature; the liquid lens applies a 0-5V voltage signal according to the focal length and distortion control instructions to achieve millisecond-level zoom (response time ≤2ms) and angle compensation with 0.1° accuracy; the electronic filter adjusts the transmittance according to the saturation compensation coefficient (e.g., ΔT = Ksat × 10%).

[0041] Furthermore, based on time-series data stream processing technology, the entire process iteration is executed at a preset frequency (no less than 10Hz, i.e., a full process iteration is performed every 100ms). During the control process, parameter fluctuations are monitored in real time. When a parameter mutation is detected that exceeds a preset threshold (such as a brightness mutation > 20% or a color difference ΔE > 5), an abnormal interruption response thread is triggered, the current projection parameters are frozen, and a Gradient Map test image is projected for self-calibration, and a benchmark mapping table is regenerated.

[0042] Example 2: This embodiment provides an optical parameter control system for a projector, employing the method described in Embodiment 1. The system includes: The parameter detection unit is used to acquire multi-dimensional optical parameters of the projection environment in real time and generate a fused data stream based on timestamp alignment; the multi-dimensional optical parameters include at least real-time ambient illuminance and color gamut deviation values. The parameter detection unit includes an ambient light sensor (such as MAX44009), an image sensor (such as OV2740 CMOS), a spectrum analyzer, a distance sensor, and a surface reflectivity detection module, etc.

[0043] The control unit dynamically calculates brightness and contrast adjustment weights based on the real-time ambient illuminance; inputs the fused data stream to a preset reinforcement learning model, and outputs high-level policy parameters, including adjustments to the brightness and contrast adjustment weights; generates brightness and contrast control instructions based on the adjusted weights, and converts the color gamut deviation value into a saturation compensation coefficient in the HSV color space. The control unit incorporates a multi-dimensional fusion processor (such as a Xilinx Zynq-7000 FPGA) and a parameter optimization algorithm library, including a dynamic weight allocation module, a parameter coupling decoupling module, a color gamut mapping module, and a Q-learning reinforcement learning model. Historical data is stored in non-volatile memory (such as eMMC).

[0044] The execution unit is used to receive the control commands and saturation compensation coefficients, and to adjust the optical output parameters of the projector. The execution unit includes a light source driving circuit (such as LT3956), a lens motor assembly (including a liquid lens and a piezoelectric ceramic actuator), and an electronic filter.

[0045] Example 3: This embodiment provides a projector, including an intelligent projection unit and an optical parameter control system as described in Embodiment 2.

[0046] The intelligent projection unit comprises a light source module, a display chip, and a projection lens assembly, used to generate and project images, and controlled by the execution unit of the optical parameter control system. Specifically, the light source module consists of an RGB three-color laser module (wavelength 638nm / 520nm / 450nm) and a white LED mixing array. The execution unit independently controls the output power of each light source channel through PWM frequency modulation technology. The display chip can be a 0.47-inch DMD chip, supporting a resolution of 1920×1080. The projection lens assembly includes an EFL 8-12mm variable liquid lens and a piezoelectric ceramic actuator, responding to the execution unit's commands to achieve 0.1° accuracy angle compensation and millisecond-level zoom.

[0047] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0048] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0049] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for adjusting the optical parameters of a projector, characterized in that, Includes the following steps: Real-time acquisition of multi-dimensional optical parameters of the projection environment, and generation of fused data stream based on timestamp alignment; The multi-dimensional optical parameters include at least real-time ambient illuminance and color gamut deviation value ΔC; The brightness adjustment weight and contrast adjustment weight are dynamically calculated based on the real-time ambient illuminance. The brightness adjustment weight is determined based on the ratio of the real-time ambient illuminance to the maximum tolerable illuminance threshold, and the contrast adjustment weight is determined based on the brightness adjustment weight. The sum of the brightness adjustment weight and the contrast adjustment weight is a constant. Simultaneously, the fused data stream is input to a preset reinforcement learning model, which outputs high-level policy parameters. The high-level policy parameters include the adjustment amount of the brightness adjustment weight and the contrast adjustment weight. The reinforcement learning model updates the decision policy through iterative learning. Its reward function is calculated based on the color difference ΔE and the adjustment delay, with the optimization objective being to minimize the color difference and the adjustment delay. The color difference ΔE is determined based on the difference between the current projected color and the preset standard color in the CIELab color space. The adjustment delay is defined as the time difference from the start of parameter acquisition to the completion of parameter adjustment by the execution unit. Based on the adjusted brightness adjustment weight and contrast adjustment weight, brightness and contrast control instructions are generated, and the color gamut deviation value is converted into a saturation compensation coefficient in the HSV color space. The control command and saturation compensation coefficient are sent to the execution unit to control the optical output parameters of the projector.

2. The optical parameter control method for a projector according to claim 1, characterized in that, The brightness adjustment weight is determined based on the ratio of real-time ambient illuminance to the maximum tolerable illuminance threshold, expressed as: The contrast adjustment weight is determined based on the brightness adjustment weight, and the sum of the brightness adjustment weight and the contrast adjustment weight is a constant, expressed as follows: =1- ,in, For real-time ambient illuminance, This is the preset maximum tolerance illuminance threshold.

3. The method for adjusting the optical parameters of a projector according to claim 1, characterized in that, The input state of the reinforcement learning model includes the fused data stream, the current projection parameter state, and historical control data retrieved from non-volatile memory; the output of the reinforcement learning model is high-level policy parameters.

4. The optical parameter control method for a projector according to claim 1, characterized in that, The reward function of the reinforcement learning model is defined as: R = ;in, The color difference is determined based on the Euclidean distance between the current projected color and the preset standard color in the CIELab color space; The aforementioned adjustment delay.

5. The optical parameter control method for a projector according to claim 1, characterized in that, The saturation compensation coefficient is determined based on the color gamut deviation value in a linear proportional relationship. This saturation compensation coefficient is not processed by a reinforcement learning model and is directly sent as a control signal to the execution unit to drive the electronic filter. The saturation compensation coefficient Specifically, when > 0 o'clock ;when = 0 .

6. The method for adjusting the optical parameters of a projector according to claim 1, characterized in that, The real-time acquisition of multi-dimensional optical parameters of the projection environment includes: acquiring ambient illuminance and color temperature, capturing the pixel matrix of the projection area and aligning the resolution of the captured pixel matrix to 1920×1080 resolution, and inputting the acquired spectral data into the CIELab model to calculate the color gamut deviation value; the multi-source data are aligned with timestamps to generate the fused data stream.

7. The method for adjusting the optical parameters of a projector according to claim 1, characterized in that, The process of regulating the optical output parameters of the projector includes: using time-series data stream processing technology, performing a full-process iteration from real-time acquisition of the multi-dimensional optical parameters to regulating the optical output parameters of the projector at a preset frequency; during the regulation process, monitoring parameter fluctuations in real time, and when a parameter mutation is detected to exceed a preset threshold, triggering an abnormal interruption response thread, freezing the current projection parameters and projecting a test image for self-calibration.

8. The method for adjusting the optical parameters of a projector according to claim 1, characterized in that, The response logic of the execution unit includes: the light source driving circuit outputs a pulse width modulation signal according to the control command to adjust the light source brightness; and the electronic filter adjusts the transmittance according to the saturation compensation coefficient.

9. An optical parameter control system for a projector, characterized in that, include: The parameter detection unit is used to collect multi-dimensional optical parameters of the projection environment in real time and generate a fused data stream based on timestamp alignment. The multi-dimensional optical parameters include at least real-time ambient illuminance and color gamut deviation value ΔC; The control unit is used to dynamically calculate the brightness adjustment weight and the contrast adjustment weight based on the real-time ambient illuminance. The brightness adjustment weight is determined based on the ratio of the real-time ambient illuminance to the maximum tolerable illuminance threshold, and the contrast adjustment weight is determined based on the brightness adjustment weight. The sum of the brightness adjustment weight and the contrast adjustment weight is a constant. The fused data stream is input into a pre-set reinforcement learning model, which outputs high-level policy parameters. These parameters include adjustments to the brightness and contrast adjustment weights. The reinforcement learning model updates its decision-making strategy through iterative learning. Its reward function is calculated based on the color difference ΔE and the adjustment delay, with the optimization objective being to minimize the color difference and the adjustment delay. The color difference ΔE is determined based on the difference between the current projected color and the preset standard color in the CIELab color space. The adjustment delay is defined as the time difference from the start of parameter acquisition to the completion of parameter adjustment by the execution unit. Brightness and contrast adjustment instructions are generated based on the adjusted weights, and the color gamut deviation value is converted into a saturation compensation coefficient in the HSV color space. The execution unit is used to receive the control command and saturation compensation coefficient, and to control the optical output parameters of the projector.

10. A projector, characterized in that, It includes an intelligent projection unit and the optical parameter control system as described in claim 9; the intelligent projection unit includes a light source module, a display chip and a projection lens group, used to generate and project images, and is controlled by the execution unit of the optical parameter control system.

Images