Intelligent calibration method, system and storage medium for photoelectric sensor

Abstract

The intelligent calibration method, system and storage medium of the photoelectric sensor provided by the present application relate to the field of sensor calibration technology. Photoelectric sensor data are generated through photoelectric sensor environment analysis. The ideal environment simulation is performed on the photoelectric sensor environment of the target photoelectric sensor in a time series to generate standard photoelectric sensor data. The sensor deviation analysis in a low-light environment is performed to determine the sensor deviation data. The intelligent illumination compensation analysis in the low-light environment is performed to generate initial illumination compensation parameters. The calibration optimization analysis is performed. The initial calibration result is corrected by the obtained optimized illumination calibration parameters. The problems of insufficient calibration accuracy, strong noise interference, poor adaptability to illumination changes, measurement deviation and insufficient stability of the photoelectric sensor in a low-light environment are solved, thereby achieving the effect of improving the measurement accuracy and stability of the photoelectric sensor in low-light conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of sensor calibration, and in particular to an intelligent calibration method, system and storage medium for a photoelectric sensor. Background Art

[0002] With the continuous development of science and technology, photoelectric sensors, as a key equipment widely used in industrial automation, environmental monitoring, smart home, security systems and other fields, have been widely used in a variety of measurement tasks such as light intensity, distance, object position, etc. However, the accuracy and stability problems of existing photoelectric sensors in low-light environments have not been effectively solved. Traditional photoelectric sensors convert and measure based on the received light signals. When the ambient light conditions are low, the signal output of the sensor is often limited by light changes, noise interference and the performance of the device itself. Especially in extremely low light conditions, traditional sensors are often unable to accurately capture weak light signals, resulting in inaccurate data or signal loss. In this environment, the performance of the sensor is reduced, affecting the feasibility and accuracy of its widespread application.

[0003] Existing photoelectric sensor calibration methods usually compare with standard data in a static environment and perform simplified deviation adjustments. However, these methods cannot effectively solve the problems of high noise, low signal-to-noise ratio and nonlinear response exhibited by sensors in low-light environments. In addition, most existing methods do not take into account factors such as dynamic illumination changes and sudden light source changes, so it is impossible to achieve accurate adaptation and self-correction of photoelectric sensors in different illumination environments. In addition, traditional illumination compensation methods mostly rely on fixed compensation models or simple gain adjustments, which cannot be adjusted dynamically according to environmental changes, and most methods fail to take into account the adaptability requirements of photoelectric sensors under different environmental conditions, resulting in unsatisfactory compensation effects. Therefore, how to accurately identify and compensate for sensor deviations in extremely low-light environments in combination with dynamically changing illumination data has become a problem that needs to be solved in current technology. Summary of the invention

[0004] The intelligent calibration method, system and storage medium of the photoelectric sensor provided in the present application are used to solve the technical problems that the prior art has insufficient calibration accuracy of photoelectric sensors in low-light environments, strong noise interference, poor adaptability to light changes, and cannot effectively solve the measurement deviation and stability of photoelectric sensors under extremely low light conditions.

[0005] In view of the above problems, the present application provides an intelligent calibration method, system and storage medium for a photoelectric sensor.

[0006] In a first aspect of the present application, a smart calibration method for a photoelectric sensor is provided, the method comprising: performing a photoelectric sensing environment analysis of a target photoelectric sensor in a time series to generate photoelectric sensing data; performing an ideal environment simulation on the photoelectric sensing environment of the target photoelectric sensor in a time series to generate standard photoelectric sensing data; performing a sensing deviation analysis in a low-light environment based on the photoelectric sensing data and the standard photoelectric sensing data to determine sensing deviation data; performing a smart illumination compensation analysis on the sensing deviation data in a low-light environment to generate initial illumination compensation parameters; performing a calibration optimization analysis on an initial calibration result generated by performing illumination compensation on the target photoelectric sensor based on the initial illumination compensation parameters, performing correction on the initial calibration result using the obtained optimized illumination calibration parameters to generate an optimized calibration result.

[0007] According to a second aspect of the present application, a smart calibration system for a photoelectric sensor is provided, the system comprising: an environment analysis module for performing a photoelectric sensing environment analysis of a target photoelectric sensor in a time series to generate photoelectric sensing data; an environment simulation module for performing an ideal environment simulation of the photoelectric sensing environment of the target photoelectric sensor in a time series to generate standard photoelectric sensing data; a deviation analysis module for performing a sensing deviation analysis in a low-light environment based on the photoelectric sensing data and the standard photoelectric sensing data to determine the sensing deviation data; a compensation analysis module for performing a smart illumination compensation analysis on the sensing deviation data in a low-light environment to generate initial illumination compensation parameters; and a calibration optimization module for performing a calibration optimization analysis on an initial calibration result generated by performing illumination compensation on the target photoelectric sensor based on the initial illumination compensation parameters, performing correction on the initial calibration result using the obtained optimized illumination calibration parameters to generate an optimized calibration result.

[0008] According to a third aspect disclosed in the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, any step of the first aspect disclosed in the present application is implemented.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The method provided in the embodiment of the present application generates photoelectric sensor data by performing a photoelectric sensor environment analysis of the target photoelectric sensor in a time series; performs an ideal environment simulation on the photoelectric sensor environment of the target photoelectric sensor in a time series to generate standard photoelectric sensor data; performs a sensor deviation analysis in a low-light environment based on the photoelectric sensor data and the standard photoelectric sensor data to determine the sensor deviation data; performs an intelligent illumination compensation analysis in a low-light environment on the sensor deviation data to generate initial illumination compensation parameters; performs a calibration optimization analysis on an initial calibration result generated by performing illumination compensation on the target photoelectric sensor based on the initial illumination compensation parameters, performs correction on the initial calibration result using the obtained optimized illumination calibration parameters, and generates an optimized calibration result, thereby solving the technical problems of insufficient calibration accuracy, strong noise interference, and poor adaptability to illumination changes of photoelectric sensors in low-light environments, and being unable to effectively solve the measurement deviation and stability of photoelectric sensors under extremely low illumination conditions, and achieving the technical effect of improving the measurement accuracy and stability of photoelectric sensors under low-light conditions, thereby optimizing the calibration effect of the sensor. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic flow chart of an intelligent calibration method for a photoelectric sensor is provided for this application.

[0012] Figure 2 A schematic diagram of the structure of an intelligent calibration system for a photoelectric sensor is provided for this application.

[0013] Explanation of the reference numerals: environmental analysis module 11 , environmental simulation module 12 , deviation analysis module 13 , compensation analysis module 14 , calibration optimization module 15 . DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0015] Embodiment 1, as Figure 1 As shown, the present application provides an intelligent calibration method for a photoelectric sensor, the method comprising:

[0016] Conduct photoelectric sensing environment analysis of the target photoelectric sensor in time series and generate photoelectric sensing data.

[0017] Specifically, the performance of photosensors varies under different lighting conditions. Therefore, before calibration, their behavior characteristics under various lighting environments must be fully evaluated to ensure the accuracy and reliability of subsequent compensation methods.

[0018] The target photoelectric sensor refers to a specific sensor device that needs to be calibrated. Its function is to measure the light intensity in the environment and convert it into an electrical signal for subsequent processing. In this process, the sensor will be affected by different environmental factors, such as light intensity, light wavelength and its fluctuations. In order to effectively evaluate the performance of the target sensor under various environmental conditions, it is necessary to conduct photoelectric sensing environment analysis by collecting its continuous data in a time series. A time series refers to a data set composed of continuous measurement results of ambient light by the sensor at different times. The time series contains the response records of the photoelectric sensor to changes in ambient light, usually including fluctuations in light intensity, spectral characteristics and other possible influencing factors. By analyzing these data, we can understand the response characteristics of the photoelectric sensor to changes in light in different time periods, which helps the subsequent compensation process to accurately correct the sensor deviation.

[0019] Photoelectric sensor data refers to the raw data related to light intensity and spectral characteristics obtained by photoelectric sensors. These data usually include the value of light intensity at a specific time point, the change pattern of light (such as periodic and non-periodic fluctuations), and the spectral information related thereto. By collecting and analyzing these data, it is possible to provide a quantitative basis for the performance characteristics of photoelectric sensors under different lighting conditions, thereby providing sufficient data support for the subsequent standard data simulation, sensor deviation analysis, and light compensation. When performing photoelectric sensing environment analysis, it is first necessary to place the target photoelectric sensor under different lighting conditions and continuously record the changes in light over a period of time. At this time, the light intensity output value of the sensor will continue to change, and this change contains all the information about the impact of the external environment on the sensor. When analyzing these data, the focus is on identifying the fluctuation law of light intensity and the impact of different light source characteristics (such as periodic light source or non-periodic light source) on the sensor response. For example, when the sensor is placed under the irradiation of a periodic light source (such as sunlight or artificial lighting), the output signal of the photoelectric sensor will show regular fluctuations; while under the irradiation of a non-periodic light source, the output of the sensor may show irregular fluctuations. For example, if the light intensity undergoes a dramatic change during a certain period of time (such as a sudden change from cloudy to sunny), the output of the sensor will reflect a sharp rise or fall in light intensity. By collecting data during this period and combining it with the law of light changes, the key photoelectric sensing data during this period can be extracted. These data reflect the response of the target photoelectric sensor to changes in light intensity under specific conditions, and are an important basis for subsequent sensor deviation analysis and compensation steps.

[0020] In summary, by analyzing the photoelectric sensing environment of the target photoelectric sensor in a time series, the generated photoelectric sensing data contains a comprehensive record of the photoelectric sensor's response to ambient light changes, providing the necessary basis for subsequent calibration steps. This analysis process ensures that the performance of the sensor in various lighting environments can be fully evaluated and quantified, providing reliable data support for subsequent standard data generation, deviation analysis, and light compensation steps.

[0021] An ideal environment simulation is performed on the photoelectric sensing environment of the target photoelectric sensor in a time series to generate standard photoelectric sensing data.

[0022] Optionally, by simulating an ideal lighting environment, reference data can be generated to compare and analyze the actual data of the target photoelectric sensor, identify deviations and compensate for them. By comparing with the standard data, the sensor can be calibrated more accurately and its measurement accuracy in low light environments can be improved.

[0023] Ideal environment simulation refers to generating a set of reference data that is not interfered by noise and has stable lighting conditions by assuming the performance of photoelectric sensors in an ideal lighting environment. In practical applications, the response of sensors may be affected due to certain fluctuations in light intensity and environmental conditions. In order to solve this problem, it is necessary to eliminate these interference factors by simulating an ideal lighting environment and generate standard photoelectric sensing data based on this environment. The core of this process lies in the construction and simulation of an ideal environment.

[0024] In the ideal environment simulation process, we first need to analyze the performance of the target photoelectric sensor under periodic illumination time series. Periodic illumination time series usually refers to the lighting environment where the light source intensity fluctuates regularly, such as the change of sunlight throughout the day or the periodic switching of artificial lighting equipment. In such an environment, the response of the photoelectric sensor should show regular fluctuations. By simulating this regular fluctuation, we can generate periodic ideal data, that is, simulated sensor response data under ideal periodic illumination conditions. These data are not interfered by any noise and only reflect the performance of the sensor under ideal conditions.

[0025] Next, the performance of the target photoelectric sensor under non-periodic illumination time series is simulated. Non-periodic illumination time series usually refers to an illumination environment where the light intensity changes without obvious periodicity, such as sudden illumination changes or random light source interference. In this environment, the response of the photoelectric sensor no longer shows regular fluctuations, but random intensity changes. By simulating the performance of the sensor under non-periodic illumination conditions, non-periodic ideal data can be generated. These data also do not contain noise interference and only represent the response of the sensor under ideal non-periodic illumination conditions.

[0026] In this process, the periodic ideal data and the non-periodic ideal data are combined to generate the final standard photoelectric sensing data. This standard data combines the performance of the target photoelectric sensor in an ideal lighting environment, and can provide accurate and reliable reference data regardless of whether it is under regularly changing periodic lighting or irregularly changing non-periodic lighting. By combining periodic data with non-periodic data to generate standard photoelectric sensing data, the data can cover more types of lighting environments, thus providing a comprehensive reference for subsequent sensor deviation analysis.

[0027] In summary, by simulating the ideal environment of the photoelectric sensing environment of the target photoelectric sensor in a time series, the generated standard photoelectric sensing data provides an accurate and interference-free reference data set for the subsequent calibration step. This step effectively constructs an ideal lighting environment and generates standard data by combining the simulation of periodic and non-periodic lighting environments, providing a reliable basis for subsequent sensing deviation analysis and lighting compensation.

[0028] A sensing deviation analysis is performed in a low-light environment based on the photoelectric sensing data and the standard photoelectric sensing data to determine sensing deviation data.

[0029] For example, the deviations exhibited by the photoelectric sensor in low-light environments are identified and quantified, especially under conditions of high noise and low light intensity. Through this analysis, accurate deviation data support can be provided for subsequent light compensation and calibration, thereby improving the accuracy and reliability of the sensor in low-light conditions.

[0030] Low-light environment refers to conditions with weak light intensity, insufficient or unstable ambient light sources. In this environment, photoelectric sensors often face problems such as low signal strength and large noise interference, resulting in inaccurate or unstable measurement results. When performing sensor deviation analysis in a low-light environment, it is first necessary to place the target photoelectric sensor in such a low-light environment and collect actual photoelectric sensor data for comparison and analysis. Next, the photoelectric sensor data is compared with the standard photoelectric sensor data. Photoelectric sensor data refers to the actual light data measured by the target photoelectric sensor at different time points in a low-light environment, which contains the response characteristics of the photoelectric sensor in this environment. The standard photoelectric sensor data is the data generated during the simulation of an ideal environment, representing the ideal response of the photoelectric sensor under ideal lighting conditions. By comparing these two sets of data, the deviations caused by the low-light environment can be accurately identified, especially the errors caused by noise signals.

[0031] Sensor deviation analysis is to further identify and quantify the response error of the photoelectric sensor in a low-light environment by analyzing the difference between the photoelectric sensor data and the standard photoelectric sensor data. The core task of this process is to form a deviation data set by detecting and quantifying these deviations, which will help the subsequent intelligent compensation algorithm to identify the deficiencies of the photoelectric sensor in a low-light environment, so as to implement targeted calibration measures. In this step, the deviation analysis focuses on low-light noise signals. In a low-light environment, the output of the sensor is not only affected by changes in light intensity, but may also be interfered by other environmental noise. Common noise signals include slight fluctuations in ambient light, thermal noise inside the device, and external electromagnetic interference. By identifying and analyzing these noise signals, the effective signal and noise signal in a low-light environment can be effectively separated, thereby providing an accurate basis for subsequent compensation. For example, when the target photoelectric sensor detects changes in light intensity under low-light conditions, errors may occur due to device performance limitations or environmental interference. At this time, by comparing the standard photoelectric sensor data, it can be found that there is a certain deviation between the output of the sensor and the ideal data, and these deviations can be further subdivided into periodic noise and non-periodic noise through noise analysis. Periodic noise may come from the stability of the light source, while non-periodic noise may be caused by the characteristics of the device itself or sudden changes in the external environment. Through this deviation analysis, the final sensor deviation data will include all error sources of the photoelectric sensor in a low-light environment, including periodic noise, non-periodic noise and the influence of other environmental factors. These deviation data will provide necessary information support for the generation of intelligent light compensation in the subsequent steps, ensuring that the generation of compensation parameters can accurately reflect the actual performance of the sensor in a low-light environment.

[0032] In summary, the sensor deviation analysis in low-light environment based on the photoelectric sensor data and the standard photoelectric sensor data can accurately identify the deviation of the photoelectric sensor in low-light environment and quantify these deviations as sensor deviation data. This analysis provides important basic data for subsequent intelligent light compensation analysis, thereby effectively improving the calibration accuracy of the photoelectric sensor in low-light conditions.

[0033] The sensing deviation data is subjected to intelligent illumination compensation analysis in a low-light environment to generate initial illumination compensation parameters.

[0034] Furthermore, based on the aforementioned sensor deviation data, especially in low-light environments, intelligent compensation analysis is performed to compensate for the deviation of the photoelectric sensor caused by low-light conditions. Through this compensation analysis process, compensation parameters for optimizing the sensor measurement accuracy can be generated, and these compensation parameters will provide an accurate reference for subsequent calibration optimization.

[0035] The sensor deviation data is obtained by comparing the photoelectric sensor data of the target photoelectric sensor in a low-light environment with the standard photoelectric sensor data. This data set includes various deviation information of the photoelectric sensor in a low-light environment, such as the influence of periodic noise, non-periodic noise and other interference factors. Therefore, this data set provides the necessary basis for further compensation analysis and helps the system determine the compensation target. When performing intelligent illumination compensation analysis, the periodic noise signal needs to be compensated first. Periodic noise usually refers to noise signals that repeat continuously within a certain period. This type of noise often comes from the fluctuation of the ambient light source, such as changes in sunlight or the switch of artificial lighting. In a low-light environment, the influence of periodic noise signals on photoelectric sensors is more obvious, resulting in regular fluctuations in the sensor output signal. In order to eliminate this interference, the system will perform environmental adaptive gain adjustment on the periodic noise signal. This gain adjustment analyzes the fluctuation amplitude of the periodic noise and dynamically adjusts the compensation gain to ensure that the sensor output signal is more stable, thereby improving the measurement accuracy. For example, assume that the target photoelectric sensor is in a low-light environment and the light intensity fluctuates periodically over time (such as changes in sunlight). At this time, the sensor may have periodic fluctuation errors, resulting in unstable measurement results. Through adaptive gain adjustment, the system dynamically adjusts the gain according to the fluctuation amplitude, thereby eliminating these periodic fluctuations and ensuring that the output signal is closer to the actual light intensity.

[0036] Next, compensation is performed for non-periodic noise signals. Non-periodic noise refers to noise signals that do not have a clear periodicity and are usually sudden, which may be caused by sudden changes in the external environment (such as changes in cloud cover or interference in the operating status of the device). In low-light environments, the impact of non-periodic noise on photoelectric sensors is particularly significant, which may cause instantaneous light intensity offsets. In order to accurately compensate for this noise, abnormal noise detection technology is used to identify and eliminate non-periodic noise signals by setting a threshold for sudden noise. When abnormal noise exceeding the threshold is detected in the signal, these data points are automatically excluded from the sensing data, thereby reducing the impact of noise on the performance of the photoelectric sensor. For example, if the target photoelectric sensor detects a sudden change in light, resulting in a sudden intensity fluctuation in the output signal, the system will detect this change through the set threshold and regard it as sudden noise. Through the regression prediction method, the system can predict the impact of this sudden noise and eliminate these irregular noise data. When processing non-periodic noise signals, the regression prediction method is an important compensation technology. This method predicts the possible fluctuation of sudden noise by analyzing the change trend of non-periodic noise in historical data, and adjusts the compensation strategy based on the prediction results. This process can further remove the irregular parts of the noise signal and improve the accuracy of the data. Finally, the weight evaluation of the non-periodic noise signal is another key step in the compensation process. This step further optimizes the compensation effect by evaluating the weight of the non-periodic noise signal after the noise is removed. By evaluating the weight of the noise signal, the system can determine the adjustment range of the compensation parameters according to the intensity and interference of the noise, so as to more accurately compensate for the deviation in low-light environments.

[0037] Through the above compensation analysis of periodic and non-periodic noise signals, the initial illumination compensation parameters are finally generated. These compensation parameters can effectively adjust the response of the photoelectric sensor, thereby improving its measurement accuracy and stability in low-light environments. The initial compensation parameters will provide the necessary basic data for the subsequent calibration optimization steps, ensuring that the sensor performs more reliably under complex lighting conditions.

[0038] In summary, through intelligent illumination compensation analysis of sensor deviation data, combined with environmental adaptive gain adjustment, abnormal noise detection, regression prediction and other technical means, the final generated initial illumination compensation parameters provide an accurate compensation basis for the low-light environment calibration of photoelectric sensors. This process significantly improves the measurement accuracy and stability of photoelectric sensors in low-light environments by accurately compensating for periodic and non-periodic noise.

[0039] A calibration optimization analysis is performed on an initial calibration result generated by performing illumination compensation on the target photoelectric sensor based on the initial illumination compensation parameters, and the initial calibration result is corrected using the obtained optimized illumination calibration parameters to generate an optimized calibration result.

[0040] Specifically, by further optimizing the initial calibration results, the calibration effect of the photoelectric sensor in a low-light environment is ensured to be optimal, thereby improving the measurement accuracy and reliability of the sensor in practical applications. The initial light compensation parameters are compensation parameters obtained through the aforementioned intelligent light compensation analysis steps, and these parameters have made preliminary adjustments to the deviations of the target photoelectric sensor in a low-light environment. By applying these initial compensation parameters to calibrate the output signal of the target photoelectric sensor, the sensor can provide more accurate measurement results under low-light conditions. However, since the initial compensation parameters may still have certain errors or fail to completely eliminate the nonlinear response of the sensor under extreme lighting conditions, the initial calibration results need to be further optimized.

[0041] During the illumination compensation process, the output of the target photoelectric sensor is adjusted according to the initial illumination compensation parameters to compensate for the deviation caused by low light conditions. Specifically, by compensating the photoelectric response of the sensor, the influence of the fluctuation of light intensity on the sensor measurement results is eliminated, ensuring that its output signal in a low light environment is closer to the actual illumination conditions. On this basis, the initial calibration result is generated, that is, the preliminary calibration data of the compensated photoelectric sensor output signal. Next, the calibration optimization analysis is the process of further optimizing the initial calibration result. In this process, the residual errors or inaccuracies that may exist in the initial calibration results are analyzed, especially for nonlinear responses, periodic noise and other disturbance factors in low light environments. The optimization process includes adjustments at multiple levels, such as dynamically adjusting the compensation parameters, optimizing the gain settings of the sensor, and correcting possible system errors. The core of this process is to continuously optimize the compensation parameters through the system's internal algorithms, reduce the error range, and improve the accuracy of the calibration results.

[0042] Specifically, the optimization of the illumination calibration parameters is to adjust the compensation parameters by comparing the initial calibration results with the standard data and the reference data set, so that it is more consistent with the actual response of the target photoelectric sensor in a low-light environment. This optimization process not only takes into account the deviation in the initial calibration results, but also combines multiple factors, such as the volatility of the light source, changes in ambient temperature, and long-term drift of the sensor. The optimization algorithm automatically adjusts the compensation parameters by analyzing these factors to ensure that the deviation between the illumination data output by the sensor and the actual illumination intensity is as small as possible. For example, assuming that the target photoelectric sensor still has a slight deviation after the initial calibration, which is manifested in the inaccurate response under certain specific illumination intensities, these responses are calibrated by the optimization algorithm, and the gain, compensation duration, threshold and other parameters are adjusted so that the output signal of the sensor more accurately reflects the actual illumination intensity under various low-light conditions. Finally, the initial calibration results are corrected by the obtained optimized illumination calibration parameters. This correction process is to apply the optimized compensation parameters to the initial calibration results, thereby further improving the accuracy of the calibration. The initial calibration results are adjusted by optimizing the calibration parameters, so that the output signal of the sensor is closer to the actual illumination intensity, eliminating the influence of deviation and noise in low-light environments. Ultimately, the corrected result is the optimized calibration result, that is, the final calibration data of the photoelectric sensor after optimized compensation in a low-light environment. This result can provide more stable and accurate light measurement values, ensuring that the photoelectric sensor can perform excellently under various low-light conditions.

[0043] In summary, by performing illumination compensation on the target photoelectric sensor based on the initial illumination compensation parameters, an initial calibration result is generated, and correction is performed by optimizing the illumination calibration parameters to finally generate an optimized calibration result. This process effectively eliminates deviations and errors in low-light environments by further optimizing the initial calibration results, thereby ensuring the measurement accuracy and stability of the photoelectric sensor in complex lighting environments.

[0044] Furthermore, a photoelectric sensing environment analysis of the target photoelectric sensor in a time series is performed to generate photoelectric sensing data, including: collecting light intensity fluctuations and spectral characteristics of the target photoelectric sensor in a photoelectric sensing environment, and performing a lighting stability analysis based on the light intensity fluctuations and spectral characteristics; extracting periodic lighting time series and non-periodic lighting time series from periodic lighting data and non-periodic lighting data obtained based on stability results of the light intensity fluctuations and spectral characteristics under preset weights, respectively, to generate the photoelectric sensing data.

[0045] In a specific embodiment, the target photoelectric sensor collects data in different lighting environments and records the light intensity fluctuations and spectral characteristics in the environment. Light intensity fluctuations refer to changes in the intensity of the light source over time, which may be due to fluctuations in the light source in the environment or the influence of other factors. The spectral characteristics are the distribution of light at different wavelengths, which usually affect the response characteristics of the photoelectric sensor. In order to accurately evaluate the performance of the target photoelectric sensor in different environments, it is first necessary to perform a light stability analysis. This analysis evaluates the stability of the lighting environment by processing the collected light intensity fluctuations and spectral characteristics data. The goal of the light stability analysis is to determine whether the ambient light source is stable and whether there are significant fluctuations or irregular changes. For example, the light in some environments may show periodic fluctuations (such as day and night) or non-periodic fluctuations (such as cloud cover) over time. This stability analysis helps to determine whether the sensor's response is stable under different lighting conditions and provides support for subsequent compensation analysis.

[0046] Next, according to the stability results of light intensity fluctuation and spectral characteristics under preset weights, periodic illumination data and non-periodic illumination data are further extracted. In this process, the collected light intensity fluctuation and spectral characteristics are first weighted by the set weight coefficient. The setting of weights is determined according to the environmental characteristics and the characteristics of the photoelectric sensor to ensure the accuracy of the stability analysis. By classifying the light intensity fluctuation and spectral characteristics, periodic illumination time series and non-periodic illumination time series can be extracted. Periodic illumination time series refers to the time series data of sensor response when the intensity of the light source fluctuates regularly, for example, the change process of sunlight during the day. Non-periodic illumination time series refers to the time series data of sensor response when the intensity of the light source does not have obvious periodic regular changes. This type of data usually comes from sudden illumination changes or interference. Through this step, the photoelectric sensor data finally generated includes periodic and non-periodic illumination time series. These data contain the response characteristics of the sensor under different illumination conditions, help identify the regularity and stability of illumination changes, and provide key data support for subsequent sensor calibration, deviation analysis and compensation processes.

[0047] In summary, the process of generating photoelectric sensing data by analyzing the photoelectric sensing environment of the target photoelectric sensor in a time series is to collect and analyze light intensity fluctuations and spectral characteristics, combine stability analysis with the extraction of periodic / non-periodic illumination data, and ensure that accurate and comprehensive data support can be provided for the compensation and calibration of the sensor under different illumination conditions. This process lays a solid data foundation for subsequent sensor deviation analysis and intelligent illumination compensation.

[0048] Furthermore, an ideal environment simulation is performed on the photoelectric sensing environment of the target photoelectric sensor in a time series to generate standard photoelectric sensing data, including: analyzing the ideal photoelectric sensing environment of the target photoelectric sensor in a periodic illumination time series to generate periodic ideal data; analyzing the ideal photoelectric sensing environment of the target photoelectric sensor in a non-periodic illumination time series to generate non-periodic ideal data; and combining the periodic ideal data with the non-periodic ideal data to generate the standard photoelectric sensing data.

[0049] Specifically, periodic illumination time series refers to the situation where the intensity of the light source fluctuates regularly over time, such as changes in sunlight or periodic adjustments of artificial lighting. In this environment, the response signal of the target photoelectric sensor should show corresponding periodic changes. In order to generate periodic ideal data, the system analyzes the ideal performance of the target photoelectric sensor under periodic illumination conditions. This analysis is based on the known law of light source fluctuations and simulates the ideal response data of the sensor when the light intensity changes. Periodic ideal data represents the response of the photoelectric sensor to periodic illumination fluctuations under ideal, interference-free conditions. Generally, such data should show a stable and regular fluctuation pattern. For example, in the case of daylight changes, the sensor will produce periodic changes in light intensity as the sun rises and falls. By simulating this process, ideal photoelectric sensor response data is generated. Such data is used as a reference standard and can accurately reflect the ideal response of the photoelectric sensor to illumination fluctuations in the absence of noise and other interference. Secondly, non-periodic illumination time series refers to the irregular changes in light source intensity, which are usually caused by sudden illumination changes, such as cloud cover or other environmental changes. In this environment, the response signal of the target photoelectric sensor shows irregular or sudden fluctuations. In order to generate non-periodic ideal data, it is necessary to simulate the performance of the target photoelectric sensor under non-periodic lighting conditions. The ideal response data of the sensor under such conditions is generated by simulating the suddenness of the light source change. Non-periodic ideal data represents the ideal performance of the sensor under non-periodic lighting conditions, without any interference or error. For example, when clouds suddenly block the sunlight, causing the light intensity to decrease or change rapidly, the sensor's response data should accurately reflect this change. By simulating this process, the system generates non-periodic ideal data for use as a reference standard. Finally, the complete standard photoelectric sensor data is generated by combining the periodic ideal data with the non-periodic ideal data. This data combines the ideal response of the photoelectric sensor under two typical lighting environments, and fully covers the performance under periodic and non-periodic lighting conditions. As the benchmark data, the standard photoelectric sensor data can reflect the accurate response of the photoelectric sensor under an ideal environment without interference, thereby providing a reference for subsequent deviation analysis and compensation, and by fully simulating the sensor response under different lighting conditions, the accuracy and effectiveness of the calibration analysis are ensured.

[0050] Furthermore, a sensing deviation analysis is performed in a low-light environment based on the photoelectric sensing data and the standard photoelectric sensing data to determine the sensing deviation data, including: identifying the low-light environment of the standard photoelectric sensing data based on the noise signal characteristics to obtain a low-light noise signal; identifying the low-light environment of the photoelectric sensing data based on the noise signal characteristics to obtain an actual noise signal; and identifying real-time periodic noise signals and non-periodic noise signals in the actual noise signal through the low-light noise signal as the sensing deviation data.

[0051] Furthermore, low-light environment recognition is a key step in analyzing the response of photoelectric sensors under low-light conditions. The signals of photoelectric sensors in low-light environments are often accompanied by strong noise interference, which may come from environmental factors, internal interference of the device, etc. In this step, the standard photoelectric sensor data is used as the ideal reference data. By performing low-light environment recognition on it, the low-light noise signal can be effectively distinguished. The low-light noise signal refers to the part of the sensor output signal under low-light conditions that is weak or unmeasurable due to the change in ambient light, which is usually manifested as a noise component in the data. By performing low-light environment recognition on the standard data, these noise signals generated by environmental influences can be detected as the basis for subsequent analysis. For example, when the photoelectric sensor is in a weak light environment, its output signal may show weak fluctuations, which are not caused by real light changes, but by device noise or extremely low-intensity light changes. By performing low-light environment recognition on the standard photoelectric sensor data, these noise signals can be extracted from the ideal data, which can be used as a reference for subsequent actual data deviation analysis. The low-light environment recognition of photoelectric sensor data is to perform a similar analysis on the actual collected data. This step extracts the actual noise signal by identifying the response signal of the photoelectric sensor in a low-light environment. The actual noise signal refers to the deviation data generated by the noise interference of the photoelectric sensor in a low-light environment. These signals are usually affected by factors such as unstable lighting, external electromagnetic interference, and internal nonlinearity of the device, and may be different from the noise signals in the standard photoelectric sensor data. Therefore, firstly, the actual noise signal is captured through low-light environment recognition, and a basis is provided for subsequent noise classification. For example, assuming that in a low-light environment, the output signal of the photoelectric sensor fluctuates, but these fluctuations are not caused by changes in the external light source, but are due to factors such as the response characteristics of the device itself or electromagnetic interference, then these fluctuations are identified as actual noise signals and prepared for further noise analysis.

[0052] Subsequently, the actual noise signal is further analyzed based on the low-light noise signal to identify the periodic noise signal and the non-periodic noise signal. By identifying the periodic and non-periodic noise signals, different types of noise can be effectively distinguished, and the sensor deviation data can be determined based on their impact on the performance of the photoelectric sensor. This deviation data is the core data set for compensation and calibration, covering all sources of error of the photoelectric sensor in a low-light environment. The identification of periodic and non-periodic noise signals can help the system accurately quantify the impact of these noises on the sensor output and provide accurate data support for the subsequent compensation process.

[0053] Furthermore, the sensing deviation data is subjected to intelligent illumination compensation analysis in a low-light environment to generate initial illumination compensation parameters, including: performing environmental adaptive gain adjustment on the periodic noise signal of the sensing deviation data to generate periodic noise compensation parameters; performing abnormal noise detection on the non-periodic noise signal of the sensing deviation data based on a burst noise threshold to generate burst noise data; performing regression prediction of the burst noise data on the non-periodic noise signal, removing the burst noise data and predicted noise data from the non-periodic noise signal, and performing noise weight evaluation of the removed noise signal; performing environmental adaptive gain adjustment based on the removed noise weight to generate non-periodic noise compensation parameters; and generating the initial illumination compensation parameters by combining the periodic noise compensation parameters with the non-periodic noise compensation parameters.

[0054] Optionally, in order to eliminate the influence of periodic noise, gain adjustment is performed according to the amplitude and change law of the noise signal. Environmental adaptive gain adjustment refers to automatically adjusting the gain coefficient according to the characteristics of the light fluctuation in the current environment to enhance the effective part of the signal and suppress periodic noise. Through this adjustment, the interference of light intensity changes on the sensor output signal can be reduced to ensure a more stable sensor response. Finally, the generated periodic noise compensation parameters will be used to correct the influence of periodic noise on the sensor output. For non-periodic noise signals, in order to effectively detect and eliminate these noises, abnormal noise detection is first performed according to the burst noise threshold. The goal of this process is to identify the burst noise signals appearing in the data by setting a threshold. Burst noise is usually manifested as sudden changes in light intensity in a short period of time, and these changes are beyond the range of normal light fluctuations. By detecting and marking these burst noise data, burst noise data is generated. Subsequently, the burst noise data in the non-periodic noise signal is predicted by a regression prediction method, and the abnormal data is eliminated. Regression prediction refers to predicting the possible change trend of burst noise based on the noise characteristics in historical data. The predicted burst noise data and other irregular fluctuation data are removed from the non-periodic noise signal, thereby reducing the interference of noise on the output of the photoelectric sensor. Next, the noise weight of the removed noise signal is evaluated. This process is used to determine which noise signals have the greatest impact on the illumination compensation and perform weighted compensation according to their weights. Through the noise weight evaluation, the compensation strategy can be accurately adjusted to ensure that the non-periodic noise is fully suppressed. Finally, the non-periodic noise signal is subjected to environmental adaptive gain adjustment based on the removed noise weight to generate non-periodic noise compensation parameters. This gain adjustment process is similar to the processing of periodic noise, but it is aimed at the characteristics of non-periodic noise signals. Through the gain adjustment of the non-periodic noise signal, the compensation parameters can be dynamically adjusted to minimize the impact of environmental interference on the output of the photoelectric sensor and improve the accuracy of the sensor in low-light environments. Finally, the system combines the periodic noise compensation parameters with the non-periodic noise compensation parameters to generate the initial illumination compensation parameters. These two parameters are respectively for the compensation of periodic and non-periodic noise. The combined compensation parameters will comprehensively improve the response accuracy and stability of the sensor in low-light environments, providing data support for subsequent calibration optimization. In summary, the final generated initial illumination compensation parameters can significantly improve the measurement accuracy of the photoelectric sensor in low-light environments. This process provides an accurate compensation basis for subsequent calibration, ensuring the stability and reliability of the photoelectric sensor under various low-light conditions.

[0055] Furthermore, generating an optimized calibration result includes: performing image scale decomposition on the initial calibration result to obtain a decomposed image, identifying a low-light area, and generating a low-light area; performing multi-scale enhancement on the low-light area and a neighboring illuminated area to generate a regional illumination calibration coefficient; and performing multi-scale fusion of the decomposed image based on the regional illumination calibration coefficient to generate the optimized calibration result.

[0056] Exemplarily, the initial calibration result is obtained through intelligent illumination compensation analysis, and the output of the photoelectric sensor has been basically compensated through this preliminary calibration. However, since there may still be some local illumination differences that are difficult to fully compensate in low-light environments, the initial calibration result needs to be further decomposed through image scale decomposition technology to identify finer illumination differences. Image scale decomposition is a technique that decomposes an image or signal at different scales (i.e., different resolutions) to better reveal potential detail information in the image. In this step, low-light areas can be identified after decomposing the image. These areas are usually parts where the sensor output signal is weak due to insufficient light intensity. Next, low-light area identification is used to determine which areas in the initial calibration result have low-light problems. Low-light areas are usually manifested as dark areas or areas with high noise in images or signals. These areas often affect the measurement accuracy of the sensor due to insufficient light intensity. Identifying these low-light areas provides a basis for subsequent optimization processing, allowing the system to focus on improving the calibration effect of these specific areas. Once the low-light area is identified, multi-scale enhancement is combined to enhance the low-light area in combination with the neighboring illumination area. Neighborhood illumination regions refer to regions with relatively good illumination conditions adjacent to low-light regions. By combining the information of these neighborhood illumination regions, low-light regions can be enhanced at multiple scales according to the illumination intensity and characteristics of the surrounding regions. Multiscale enhancement refers to enhancing the brightness or contrast of low-light regions at different resolutions and scales to improve their visibility and accuracy in the overall image. This method can effectively increase the brightness of low-light regions and make them closer to the illumination level of neighborhood regions, thereby reducing the impact of low-light regions on sensor output signals. The generated regional illumination calibration coefficient is used to quantify this enhancement effect. The regional illumination calibration coefficient is a value calculated based on the enhancement relationship between the low-light region and the neighborhood illumination region, representing the adjustment ratio required in the enhancement process. This coefficient provides a key parameter for subsequent image fusion, making the calibration process more accurate and detailed. Finally, multiscale fusion of decomposed images is performed based on the regional illumination calibration coefficient. Multiscale fusion is the process of fusing image or signal data processed at different scales into a final result. By fusing the enhanced low-light area with other areas at multiple scales, uniform illumination adjustment can be achieved across the entire image, ensuring that illumination levels in each area remain consistent. The calibration coefficients in the fusion process ensure that while enhancing the low-light area, unnecessary over-adjustments are not introduced, thereby avoiding over-processing or distortion of the image or signal. Ultimately, the result after multi-scale fusion is the optimized calibration result, which more accurately reflects the true response of the target photoelectric sensor in a low-light environment.Optimizing the calibration results not only improves the measurement accuracy in low-light areas, but also ensures the lighting balance of the overall image or signal, making the sensor's output signal closer to the actual light intensity.

[0057] Furthermore, the low-light area is combined with the neighboring light area for multi-scale enhancement, including: based on the light enhancement threshold obtained by local brightness estimation of the low-light area, the low-light area is adaptively enhanced in combination with the neighboring light area to obtain adaptive enhanced light; first enhanced light and second enhanced light are extracted according to the adaptive enhanced light, wherein the first enhanced light and the second enhanced light are neighborhood enhanced light; enhancement difference is calculated for the first enhanced light and the second enhanced light, the enhancement difference is extracted and identified based on the enhancement difference threshold, and the feedback is given to the adaptive enhancement process until any neighborhood enhanced light of the adaptive enhanced light meets the enhancement difference threshold.

[0058] Specifically, local brightness estimation is performed based on the low-light area to obtain a light enhancement threshold. Local brightness estimation is a method for calculating the average or standard deviation of the light intensity in the area by analyzing the brightness distribution of the low-light area. Through this estimation, the degree of insufficient brightness of the low-light area relative to the surrounding area can be judged, and the light enhancement threshold can be set according to its brightness. The light enhancement threshold represents the minimum degree of enhancement required for the low-light area, ensuring that the enhanced light value can reach or approach the light level of the neighboring area. This threshold provides a reference standard for subsequent enhancement processing. Next, the low-light area is adaptively enhanced based on the calculated light enhancement threshold. Adaptive enhancement processing refers to dynamically adjusting the enhancement factor according to the specific brightness of each low-light area, so as to perform an appropriate amount of light enhancement according to the degree of insufficient brightness. The purpose of this enhancement processing is to increase the brightness of the low-light area to an appropriate level while avoiding distortion caused by excessive enhancement. Combining the neighboring light area means taking into account the brightness characteristics of the surrounding light areas when enhancing the low-light area, ensuring that the enhanced effect will not be significantly different from the surrounding areas, thereby achieving a smooth transition. Afterwards, the first enhanced illumination and the second enhanced illumination are extracted based on the adaptive enhanced illumination. The two enhanced illumination values ​​represent the enhanced illumination intensity of the low-light area and the neighboring illuminated area, respectively. The first enhanced illumination and the second enhanced illumination are usually a reflection of the neighborhood enhanced illumination, indicating the illumination intensity of the low-light area and the neighboring area after the enhancement process. The two enhanced illumination values ​​can be adaptively adjusted to ensure that the brightness difference between the low-light area and the neighboring illuminated area is effectively compensated. For example, the illumination of the low-light area is enhanced to the illumination level of the neighboring area, so that the illumination difference between the two is effectively balanced. This enhancement not only improves the brightness of the low-light area, but also ensures the illumination consistency of the overall image or signal. Next, the enhanced difference calculation is performed on the first enhanced illumination and the second enhanced illumination. The enhanced difference calculation is the process of quantifying the brightness difference between the enhanced low-light area and the neighboring area, with the aim of ensuring that the illumination difference between the enhanced low-light area and the neighboring area does not exceed the set threshold. Through this calculation, it can be determined whether the lighting enhancement effect meets the expected requirements. If the difference is large, the enhancement parameters will be further adjusted to achieve a smoother lighting transition. Finally, the enhancement difference is extracted and identified based on the enhancement difference threshold, and further fed back to the adaptive enhancement processing. The enhancement difference threshold is a preset value used to determine when the enhanced lighting difference is greater than a certain critical value and needs to be readjusted. By extracting and identifying the enhancement difference, the error in the enhancement process can be monitored in real time and fed back to the adaptive enhancement processing module to ensure that the difference between the low-light area and the neighboring lighting area continues to decrease. This process will continue until any neighboring enhanced lighting of the adaptive enhanced lighting meets the set enhancement difference threshold.Finally, after multiple adjustments, the neighborhood enhanced illumination of the adaptive enhanced illumination meets the preset enhanced difference threshold, ensuring that the brightness of the low-light area is appropriately improved, and the transition during the illumination enhancement process is smoother, without obvious abrupt boundaries or brightness fluctuations. In summary, by combining the low-light area with the neighborhood illumination area for multi-scale enhancement, the illumination intensity of the low-light area can be effectively improved through adaptive gain adjustment and enhanced difference calculation, while ensuring its balance with the illumination of the neighborhood area, and finally achieving high-quality illumination calibration.

[0059] Embodiment 2, based on the same inventive concept as the intelligent calibration method of the photoelectric sensor in the above embodiment, Figure 2 As shown, the present application provides an intelligent calibration system for a photoelectric sensor, the system comprising:

[0060] The environment analysis module 11 is used to analyze the photoelectric sensing environment of the target photoelectric sensor in a time series and generate photoelectric sensing data.

[0061] The environment simulation module 12 is used to perform an ideal environment simulation on the photoelectric sensing environment of the target photoelectric sensor in a time series to generate standard photoelectric sensing data.

[0062] The deviation analysis module 13 is used to perform a sensing deviation analysis in a low-light environment based on the photoelectric sensing data and the standard photoelectric sensing data to determine sensing deviation data.

[0063] The compensation analysis module 14 is used to perform intelligent illumination compensation analysis on the sensing deviation data in a low-light environment to generate initial illumination compensation parameters.

[0064] The calibration optimization module 15 is used to perform calibration optimization analysis on an initial calibration result generated by performing illumination compensation on the target photoelectric sensor based on the initial illumination compensation parameters, and to calibrate the initial calibration result using the obtained optimized illumination calibration parameters to generate an optimized calibration result.

[0065] Furthermore, the environmental analysis module 11 is also used to perform the following steps: collecting the light intensity fluctuation and spectral characteristics of the target photoelectric sensor in the photoelectric sensing environment, and performing a light stability analysis based on the light intensity fluctuation and spectral characteristics; extracting periodic light time series and non-periodic light time series from the periodic light data and non-periodic light data obtained based on the stability results of the light intensity fluctuation and spectral characteristics under preset weights, respectively, to generate the photoelectric sensing data.

[0066] Furthermore, the environmental simulation module 12 is also used to perform the following steps: analyzing the ideal photoelectric sensing environment of the target photoelectric sensor under a periodic illumination time series to generate periodic ideal data; analyzing the ideal photoelectric sensing environment of the target photoelectric sensor under a non-periodic illumination time series to generate non-periodic ideal data; combining the periodic ideal data with the non-periodic ideal data to generate the standard photoelectric sensing data.

[0067] Furthermore, the deviation analysis module 13 is also used to perform the following steps: based on the noise signal characteristics, the standard photoelectric sensor data is identified in a low-light environment to obtain a low-light noise signal; based on the noise signal characteristics, the photoelectric sensor data is identified in a low-light environment to obtain an actual noise signal; and through the low-light noise signal, real-time periodic noise signals and non-periodic noise signals in the actual noise signal are identified as the sensing deviation data.

[0068] Furthermore, the compensation analysis module 14 is also used to perform the following steps: perform environmental adaptive gain adjustment on the periodic noise signal of the sensor deviation data to generate periodic noise compensation parameters; perform abnormal noise detection on the non-periodic noise signal of the sensor deviation data based on the burst noise threshold to generate burst noise data; perform regression prediction of the burst noise data on the non-periodic noise signal, remove the burst noise data and the predicted noise data from the non-periodic noise signal, and evaluate the noise weight of the removed noise signal; perform environmental adaptive gain adjustment based on the removed noise weight to generate non-periodic noise compensation parameters; and generate the initial illumination compensation parameters by combining the periodic noise compensation parameters with the non-periodic noise compensation parameters.

[0069] Furthermore, the calibration optimization module 15 is also used to perform the following steps: perform low-light area identification on the decomposed image obtained by performing image scale decomposition on the initial calibration result to generate a low-light area; perform multi-scale enhancement on the low-light area and the neighboring light area to generate a regional light calibration coefficient; perform multi-scale fusion of the decomposed image based on the regional light calibration coefficient to generate the optimized calibration result.

[0070] Furthermore, the calibration optimization module 15 is also used to perform the following steps: based on the illumination enhancement threshold obtained by local brightness estimation of the low-light area, adaptively enhance the low-light area in combination with the neighborhood illumination area to obtain adaptive enhanced illumination; extract first enhanced illumination and second enhanced illumination according to the adaptive enhanced illumination, wherein the first enhanced illumination and the second enhanced illumination are neighborhood enhanced illumination; calculate the enhancement difference between the first enhanced illumination and the second enhanced illumination, extract and identify the enhancement difference based on the enhancement difference threshold, and feed it back to the adaptive enhancement processing until any neighborhood enhanced illumination of the adaptive enhanced illumination meets the enhancement difference threshold.

[0071] Embodiment three, based on the same inventive concept as the intelligent calibration method of the photoelectric sensor in the aforementioned embodiment, the present application also provides a storage medium, on which a computer program is stored, and when the computer program is executed, the steps of any one of the methods described in the aforementioned embodiment one are implemented.

[0072] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0073] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An intelligent calibration method for a photoelectric sensor, characterized in that: include: Conduct photoelectric sensing environment analysis of the target photoelectric sensor in time series and generate photoelectric sensing data; Performing an ideal environment simulation on the photoelectric sensing environment of the target photoelectric sensor in a time series to generate standard photoelectric sensing data; Performing a sensing deviation analysis in a low light environment based on the photoelectric sensing data and the standard photoelectric sensing data to determine the sensing deviation data includes: Based on the noise signal characteristics, the standard photoelectric sensor data is subjected to low-light environment recognition to obtain a low-light noise signal; Based on the noise signal characteristics, the photoelectric sensing data is subjected to low-light environment recognition to obtain an actual noise signal; identifying a real-time periodic noise signal and a non-periodic noise signal in the actual noise signal through the low-light noise signal as the sensing deviation data; Performing intelligent illumination compensation analysis on the sensor deviation data in a low-light environment to generate initial illumination compensation parameters, including: Performing environment adaptive gain adjustment on the periodic noise signal of the sensing deviation data to generate a periodic noise compensation parameter; Performing abnormal noise detection on the non-periodic noise signal of the sensing deviation data based on a burst noise threshold to generate burst noise data; Performing regression prediction of burst noise data on the non-periodic noise signal, removing the burst noise data and predicted noise data from the non-periodic noise signal, and performing noise weight evaluation of the removed noise signal; Performing environment adaptive gain adjustment based on the removed noise weights to generate non-periodic noise compensation parameters; Combining the periodic noise compensation parameter with the non-periodic noise compensation parameter to generate the initial illumination compensation parameter; A calibration optimization analysis is performed on an initial calibration result generated by performing illumination compensation on the target photoelectric sensor based on the initial illumination compensation parameters, and the initial calibration result is corrected using the obtained optimized illumination calibration parameters to generate an optimized calibration result.

2. The intelligent calibration method of a photoelectric sensor according to claim 1, characterized in that: Perform photoelectric sensing environment analysis of the target photoelectric sensor in time series and generate photoelectric sensing data, including: Collecting light intensity fluctuations and spectral characteristics of the target photoelectric sensor in a photoelectric sensing environment, and performing light stability analysis based on the light intensity fluctuations and spectral characteristics; The photoelectric sensing data is generated by extracting a periodic illumination time series and a non-periodic illumination time series from the periodic illumination data and the non-periodic illumination data obtained according to the stability results of the light intensity fluctuation and the spectral characteristics under preset weights.

3. The intelligent calibration method of a photoelectric sensor as claimed in claim 2, characterized in that: An ideal environment simulation is performed on the photoelectric sensing environment of the target photoelectric sensor in a time series to generate standard photoelectric sensing data, including: Analyzing the ideal photoelectric sensing environment of the target photoelectric sensor under the periodic illumination time series to generate periodic ideal data; Analyzing an ideal photoelectric sensing environment of the target photoelectric sensor under a non-periodic illumination time series to generate non-periodic ideal data; The standard photoelectric sensing data is generated by combining the periodic ideal data with the non-periodic ideal data.

4. The intelligent calibration method of a photoelectric sensor according to claim 1, characterized in that: Generates Picture Control results including: Performing image scale decomposition on the initial calibration result to obtain a decomposed image, and identifying a low-light area to generate a low-light area; Perform multi-scale enhancement on the low-light area and the neighboring light area to generate a regional light calibration coefficient; Multi-scale fusion of the decomposed images is performed based on the regional illumination calibration coefficients to generate the optimized calibration result.

5. The intelligent calibration method of a photoelectric sensor as claimed in claim 4, characterized in that: The low-light area is combined with the neighboring light area to perform multi-scale enhancement combination, including: Based on the illumination enhancement threshold obtained by estimating the local brightness of the low-illuminance area, the low-illuminance area is subjected to adaptive enhancement processing in combination with the neighboring illumination area to obtain adaptive enhanced illumination; Extracting a first enhanced lighting and a second enhanced lighting according to the adaptive enhanced lighting, wherein the first enhanced lighting and the second enhanced lighting are neighborhood enhanced lighting; An enhancement difference is calculated for the first enhanced lighting and the second enhanced lighting, and the enhancement difference is extracted and identified based on an enhancement difference threshold, and fed back to the adaptive enhancement process until any neighboring enhanced lighting of the adaptive enhanced lighting meets the enhancement difference threshold.

6. Intelligent calibration system for photoelectric sensors, characterized in that: The system for implementing the intelligent calibration method of the photoelectric sensor according to any one of claims 1 to 5 comprises: An environmental analysis module is used to analyze the photoelectric sensing environment of the target photoelectric sensor in a time series and generate photoelectric sensing data; An environment simulation module, used to perform an ideal environment simulation on the photoelectric sensing environment of the target photoelectric sensor in a time series to generate standard photoelectric sensing data; a deviation analysis module, configured to perform a sensing deviation analysis in a low-light environment based on the photoelectric sensing data and the standard photoelectric sensing data, and determine sensing deviation data; A compensation analysis module, used to perform intelligent illumination compensation analysis on the sensing deviation data in a low-light environment to generate initial illumination compensation parameters; The calibration optimization module is used to perform calibration optimization analysis on an initial calibration result generated by performing illumination compensation on the target photoelectric sensor based on the initial illumination compensation parameters, and to perform correction on the initial calibration result using the obtained optimized illumination calibration parameters to generate an optimized calibration result.

7. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent calibration method for a photoelectric sensor according to any one of claims 1 to 5 are implemented.

Images