Night vision parameter adjustment method, device and computer readable storage medium

Abstract

The present application provides a method, device and computer-readable storage medium for adjusting night vision parameters, wherein the method comprises: analyzing the obtained ambient lighting parameters of the current environment to determine the lighting conditions of the current environment; determining the parameter adjustment range of each night vision parameter in the current environment according to the lighting conditions; and adjusting the corresponding night vision parameters of the night vision device based on the parameter adjustment range of each night vision parameter. The present application analyzes the obtained ambient lighting parameters to determine the lighting conditions of the current environment, and then determines the parameter adjustment range of each night vision parameter in the current environment based on the lighting conditions, thereby realizing automatic adjustment of night vision parameters and improving the efficiency and accuracy of night vision parameter adjustment.

Description

Technical Field

[0001] The present application relates to the field of image acquisition, and in particular to a method and device for adjusting night vision parameters and a computer-readable storage medium. Background Art

[0002] In traditional night vision equipment, parameter adjustment mainly relies on manual operation. This manual adjustment process usually involves fine-tuning key parameters such as brightness, contrast and clarity in order to achieve the best night vision effect.

[0003] However, due to the variability and complexity of the night environment, this process often needs to rely on the operator's experience and technical knowledge, and is therefore often inefficient and prone to errors. Summary of the invention

[0004] In view of this, an object of the embodiments of the present application is to provide a night vision parameter adjustment method, device and computer-readable storage medium, which can improve the efficiency and accuracy of night vision parameter adjustment.

[0005] In a first aspect, an embodiment of the present application provides a method for adjusting night vision parameters, including: analyzing the acquired ambient lighting parameters of the current environment to determine the lighting conditions of the current environment; determining a parameter adjustment range of each night vision parameter in the current environment based on the lighting conditions; and adjusting the corresponding night vision parameters of the night vision device based on the parameter adjustment range of each night vision parameter.

[0006] In the above implementation process, the acquired ambient lighting parameters are analyzed to determine the lighting conditions of the current environment, and then the parameter adjustment range of each night vision parameter in the current environment is determined based on the lighting conditions, so as to realize automatic adjustment of the night vision parameters and improve the efficiency and accuracy of the night vision parameter adjustment.

[0007] In one embodiment, the ambient lighting parameters include lighting intensity parameters and spectrum characteristics; the lighting conditions include: lighting intensity, lighting uniformity and spectrum type; the analysis of the acquired ambient lighting parameters of the current environment to determine the lighting conditions of the current environment includes: statistically acquiring the lighting intensity parameters of the current environment to determine the lighting intensity of the current environment; calculating the lighting difference values ​​of the lighting intensity parameters between various areas, and determining the lighting uniformity of the current environment based on the lighting difference values; determining the spectrum type of the current environment based on the spectrum characteristics.

[0008] In the above implementation process, by analyzing multiple parameters in the ambient lighting parameters separately, various lighting conditions such as light brightness, uniformity and spectrum type are determined, thereby improving the accuracy of ambient lighting parameter analysis and further improving the accuracy of lighting conditions.

[0009] In one embodiment, before determining the parameter adjustment range of each night vision parameter in the current environment according to the lighting conditions, the method also includes: establishing a preset model according to the lighting conditions and the equipment parameters of the night vision device; wherein the preset model is configured to determine the ideal adjustment range of each night vision parameter under various ambient lighting parameters; determining the parameter adjustment range of each night vision parameter in the current environment according to the lighting conditions includes: inputting the lighting conditions into the preset model to obtain the parameter adjustment range of each night vision parameter under the ambient lighting parameters.

[0010] In the above implementation process, by creating a preset model in advance, when determining the parameter adjustment range of each night vision parameter, the lighting conditions can be directly input into the preset model, and then the parameter adjustment range of each night vision parameter under the ambient lighting parameters can be obtained, thereby realizing the automatic determination of the parameter adjustment range of each night vision parameter, and improving the efficiency and accuracy of determining the parameter adjustment range of each night vision parameter.

[0011] In one embodiment, the establishing of a preset model according to the lighting condition and the equipment parameters of the night vision device includes: establishing an initial preset model according to the lighting condition and the equipment parameters of the night vision device; continuously acquiring ambient lighting parameters; when the ambient lighting parameters change, comparing the ambient lighting parameters with corresponding multiple set threshold ranges respectively to determine the set threshold range to which the ambient lighting parameters belong; determining a corresponding adjustment strategy according to the set threshold range to which the ambient lighting parameters belong; adjusting the model parameters of the initial preset model based on the adjustment strategy; inputting the lighting condition into the initial preset model after adjusting the model parameters to obtain a corresponding imaging effect; when the imaging effect reaches the expected effect, stopping adjusting the model parameters to obtain the preset model.

[0012] In the above implementation process, taking into account the changes in light, an initial preset model is established according to the lighting conditions and the equipment parameters of the night vision device, and the model parameters in the initial preset model are adjusted based on the ambient lighting parameters. The obtained preset model has the ability to adaptively adjust the parameter range according to changes in lighting conditions, thereby improving the accuracy of the preset model.

[0013] In one embodiment, after stopping adjusting the model parameters, the method also includes: combining multiple parameters in the ambient lighting parameters respectively to obtain multiple parameter combinations; predicting the corresponding image effects under each parameter combination through the preset model; determining the parameter range corresponding to the image effect that meets the expected effect; and optimizing the parameters within the parameter range according to the image effect and the expected effect.

[0014] In the above implementation process, when creating the preset model, the relationship between various night vision parameters is comprehensively considered, and the overall optimization of the parameters is achieved, so that relatively satisfactory image effects can be obtained in different environments. In addition, by allowing the algorithm to interact with the environment, a better parameter adjustment strategy can be obtained, thereby improving the preset model's ability to adapt to complex and changing lighting conditions.

[0015] In one embodiment, after stopping adjusting the model parameters, the method further includes: determining the sensitivity of each of the night vision parameters to the image effect; and determining the weight of each of the night vision parameters in the preset model optimization according to the sensitivity of the night vision parameters to the image quality.

[0016] In the above implementation process, the influence of night vision parameters on image effects can be increased by determining the weight of each parameter in the preset model optimization according to the sensitivity of the parameter to the image effect.

[0017] In one embodiment, the preset model is: in, is the light intensity, is the gain factor of the night vision device, is the aperture size of the night vision device, is the exposure time, is the pixel position The original image brightness value at is the pixel position The adjusted image brightness value at The differential of .

[0018] In one embodiment, the method also includes: measuring initial ambient lighting parameters of a specific environment through the night vision device; adjusting the night vision parameters of the night vision device according to reference information; acquiring a current image through the night vision device after adjusting the night vision parameters; when the current image achieves a target image effect, associating the initial ambient lighting parameters with the night vision parameters corresponding to the current image; and storing the associated initial ambient lighting parameters and the night vision parameters.

[0019] In the above implementation process, in some specific environments, calibrating the parameters of the night vision device can improve the accuracy of image acquisition by the night vision device.

[0020] In the second aspect, an embodiment of the present application also provides a night vision parameter adjustment device, including: an analysis module, used to analyze the acquired ambient lighting parameters of the current environment to determine the lighting conditions of the current environment; a determination module, used to determine the parameter adjustment range of each night vision parameter in the current environment according to the lighting conditions; an adjustment module, used to adjust the corresponding night vision parameters of the night vision device based on the parameter adjustment range of each night vision parameter.

[0021] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the machine-readable instructions are executed by the processor to perform the steps of the method in the above-mentioned first aspect, or any possible implementation of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the night vision parameter adjustment method in the above-mentioned first aspect, or any possible implementation manner of the first aspect are executed.

[0023] In order to make the above-mentioned objects, features and advantages of the present application more obvious and understandable, embodiments are given below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 A schematic diagram of the interaction between a night vision device and an electronic device provided in an embodiment of the present application;

[0026] Figure 2 A block diagram of an electronic device provided in an embodiment of the present application;

[0027] Figure 3 A flowchart of a method for adjusting night vision parameters provided in an embodiment of the present application;

[0028] Figure 4 A schematic diagram of the functional modules of the night vision parameter adjustment device provided in an embodiment of the present application.

[0029] Description of the marks in the accompanying drawings: 100 - electronic device, 200 - night vision device, 111 - memory, 113 - processor, 301 - analysis module, 302 - determination module, 303 - adjustment module. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings in the embodiments of the present application.

[0031] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0032] Night vision devices play a vital role in modern night vision technology, both in the military and civilian fields. They enable users to observe and operate in low-light or no-light environments. However, the effectiveness of these devices depends largely on the accuracy of their parameter settings, which usually requires manual adjustment.

[0033] The inventor of the present application has found through long-term research that manually adjusting night vision parameters is a time-consuming and cumbersome process. Operators need to constantly try and error to find the best parameter settings based on changes in ambient light and personal visual perception. This "trial and error method" not only increases the operational burden, but may also lead to the loss of key information in emergency or rapidly changing environments. In addition, for application scenarios that require long-term monitoring or frequent switching of observation scenes, the inefficiency of manually adjusting parameters is particularly prominent.

[0034] Moreover, manual adjustments often fail to achieve optimal results. Due to differences in visual perception among individuals and complex and changing ambient light conditions, it is difficult to accurately control the various parameters of the night vision system to achieve the best visual effect based on manual judgment alone. This may lead to problems such as overexposure, darkening, lack of contrast, or loss of details, which in turn affects the accuracy and reliability of observation.

[0035] In view of this, the present application proposes a night vision parameter adjustment method, which analyzes the acquired ambient lighting parameters to determine the lighting conditions of the current environment, and then determines the parameter adjustment range of each night vision parameter in the current environment based on the lighting conditions, thereby realizing automatic adjustment of the night vision parameters and improving the efficiency and accuracy of the night vision parameter adjustment.

[0036] To facilitate understanding of this embodiment, the operating environment of a night vision parameter adjustment method disclosed in an embodiment of the present application is first introduced in detail.

[0037] like Figure 1FIG. 1 is a schematic diagram of the interaction between the night vision device 200 and the electronic device 100 provided in the embodiment of the present application. The electronic device 100 is connected to one or more night vision devices 200 through a network for data communication or interaction.

[0038] Optionally, the electronic device 100 may be a network server, a database server, a personal computer (PC), a tablet computer, a smart phone, a personal digital assistant (PDA), etc. The electronic device 100 may be selected according to actual conditions.

[0039] The above-mentioned night vision device 200 can be a camera, a night vision device, a thermal imager, a laser night vision device, etc. The night vision device 200 can be selected according to actual conditions.

[0040] The night vision device 200 here is used to obtain an environmental image and send the obtained environmental image to the electronic device 100.

[0041] In one embodiment, an ambient light parameter acquisition element is provided in the night vision device 200. The ambient light parameter acquisition element is used to acquire ambient light parameters in the environment where the night vision device 200 is located, and send the ambient light parameters to the electronic device 100.

[0042] The electronic device 100 is used to determine the illumination conditions of the current environment according to the ambient illumination parameters, and to determine the parameter adjustment ranges of the corresponding night vision parameters according to the illumination conditions. The electronic device 100 can also be used to adjust the corresponding night vision parameters of the night vision device 200 according to the parameter adjustment ranges of the night vision parameters.

[0043] In one embodiment, the electronic device 100 may also optimize the preset model according to the image effect of the environmental image, and the function of the electronic device 100 may be selected according to actual conditions.

[0044] To facilitate understanding of this embodiment, the electronic device 100 that executes the night vision parameter adjustment method disclosed in the embodiment of the present application is introduced in detail below.

[0045] like Figure 2 , which is a block diagram of an electronic device. The electronic device 100 may include a memory 111 and a processor 113. A person skilled in the art may understand that Figure 2 The structure shown is only for illustration and does not limit the structure of the electronic device 100. For example, the electronic device 100 may further include Figure 2 More or fewer components as shown, or with Figure 2 Different configurations are shown.

[0046] The memory 111 and the processor 113 are directly or indirectly electrically connected to each other to achieve data transmission or interaction. For example, these elements can be electrically connected to each other via one or more communication buses or signal lines. The processor 113 is used to execute the executable module stored in the memory.

[0047] The memory 111 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc. The memory 111 is used to store programs, and the processor 113 executes the program after receiving an execution instruction. The method executed by the electronic device 100 defined by the process disclosed in any embodiment of the present application can be applied to the processor 113, or implemented by the processor 113.

[0048] The processor 113 may be an integrated circuit chip with signal processing capability. The processor 113 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0049] The electronic device 100 in this embodiment can be used to execute each step in each method provided in the embodiments of the present application. The implementation process of the night vision parameter adjustment method is described in detail below through several embodiments.

[0050] See also Figure 3, is a flow chart of a method for adjusting night vision parameters provided in an embodiment of the present application. Figure 3 The specific process shown is described in detail.

[0051] Step 201, analyzing the acquired ambient lighting parameters of the current environment to determine the lighting conditions of the current environment.

[0052] The ambient lighting parameters here may include: light intensity parameters, spectrum characteristics, etc. The ambient lighting parameters can be selected according to actual conditions.

[0053] The above-mentioned lighting conditions may include: lighting intensity, lighting uniformity, light source type, etc. The lighting conditions can be selected according to actual conditions.

[0054] Optionally, the ambient lighting parameter can be acquired in real time, at preset time intervals, or when the current environment changes. The acquisition of the ambient lighting parameter can be selected according to actual conditions.

[0055] It should be understood that after obtaining the ambient lighting parameters, the ambient lighting parameters can be analyzed in real time to determine the lighting conditions of the current environment. It is also possible to analyze the ambient lighting parameters when the ambient lighting parameters change to determine the lighting conditions of the current environment. The method for determining the lighting conditions can be selected according to actual conditions.

[0056] The analysis method of the ambient lighting parameters here may include data statistical analysis, spectrum analysis, spatial distribution analysis, etc. The analysis method of the ambient lighting parameters may be selected according to actual conditions.

[0057] Step 202, determining the parameter adjustment range of each night vision parameter in the current environment according to the lighting conditions.

[0058] Optionally, the correlation between the lighting conditions and the parameter adjustment ranges of various night vision parameters can be set in advance. After the lighting conditions are determined, the corresponding parameter adjustment ranges can be matched directly according to the lighting conditions. It is also possible to establish a preset model, input the determined lighting conditions into the preset model, and determine the parameter adjustment ranges of various night vision parameters in the current environment based on the preset model. The method for determining the parameter adjustment ranges of various night vision parameters in the current environment can be selected according to actual conditions.

[0059] The night vision parameters here refer to the device parameters used by the night vision device to acquire images. The parameter adjustment range of the night vision parameters may include parameter adjustment ranges of multiple parameters. For example, the adjustment range of brightness, the adjustment range of contrast, the adjustment range of sharpness, etc. The type of the parameter adjustment range can be selected according to actual conditions.

[0060] Specifically, step 202 may include: calculating night vision parameters matching the current environment according to the illumination conditions obtained by real-time analysis, wherein the night vision parameters include but are not limited to: gain value, exposure time, sensitivity, contrast adjustment value, sharpness, white balance parameter, noise reduction intensity, dynamic range adjustment parameter, etc.

[0061] The gain value here is used to control the degree of signal amplification, which affects the brightness and contrast of the image; the exposure time is used to determine the length of time the sensor receives light, which has an important impact on the brightness and noise level of the image; the sensitivity is used to adjust the image sensor's sensitivity to light; the contrast adjustment value is used to change the degree of difference between light and dark areas in the image; the sharpening level: used to enhance the edge and detail clarity of the image. The white balance parameter is used to correct color deviation under different light sources; the noise reduction intensity is used to control the level of noise when increasing the image brightness; the dynamic range adjustment parameter is used to ensure that the details of both bright and dark areas are captured in a high-contrast environment.

[0062] In one embodiment, the initial range of the gain may be determined according to the light intensity in the following manner:

[0063] First, divide the light intensity into several intervals, for example, very weak light (less than 10 lux), weak light (10-50 lux), medium light (50-200 lux), and strong light (more than 200 lux).

[0064] For extremely low light environments, the initial range of gain can be set to a higher value, such as 50-100 times, because under such extremely low light conditions, a significant signal enhancement is required to obtain a resolvable image.

[0065] In low-light environments, the initial range of gain can be appropriately reduced, such as 20-50 times, to avoid excessive enhancement resulting in obvious noise.

[0066] In a medium light environment, the initial gain range may be 5-20 times, because the environment has a certain amount of natural light and does not require excessively high gain.

[0067] In strong light environments, the initial range of gain should be set at a lower level, such as 1-5 times, or even the gain function can be turned off to prevent image overexposure and distortion.

[0068] The gain can be fine-tuned as follows:

[0069] Observe the real-time output image effect. If the image is too dark or too bright, increase or decrease the gain value accordingly. You can set a certain step size, for example, fine-tune the gain value by 5% or 10% each time.

[0070] Calculate the gradient of image quality evaluation indicators (such as contrast, clarity, etc.) relative to the gain value, and then fine-tune the gain according to the direction and magnitude of the gradient. When the gradient is positive, reduce the gain, and when the gradient is negative, increase the gain.

[0071] The gain is taken as the control quantity, and the deviation between the image quality index and the expected index is taken as the input, and the gain adjustment amount is calculated by the PID controller.

[0072] Record the gain adjustment and corresponding image effects under different lighting conditions. When encountering similar lighting conditions again, refer to the historical data for fine-tuning.

[0073] If the light intensity changes quickly, the gain can be fine-tuned to a larger extent; if the light intensity changes slowly, the fine-tuning amplitude should be reduced accordingly to avoid frequent and large adjustments that may cause image instability.

[0074] Divide the image into multiple regions, evaluate the image quality of each region separately, and fine-tune the gain independently according to the lighting conditions and image requirements of the region. For example, when adjusting the gain, appropriately adjust parameters such as exposure time or sensitivity to achieve a more ideal image effect.

[0075] The contrast ratio can be calculated as follows:

[0076] Calculate the grayscale histogram, which shows the frequency of different gray levels in the image. The shape of the histogram can give you a preliminary understanding of the grayscale distribution characteristics of the image. If the histogram is narrow and concentrated in a small grayscale value range, it usually means that the image has low contrast. If the histogram covers a wide grayscale range, it means that the image may have high contrast.

[0077] Calculate the grayscale mean and standard deviation; the mean is used to reflect the average grayscale level of the image, and the standard deviation indicates the degree of dispersion of the grayscale value. The larger the standard deviation, the larger the range of grayscale value variation and the higher the contrast may be.

[0078] Observe the bimodal or multimodal distribution of grayscale; if there are multiple obvious peaks, it means that there are areas of different brightness in the image, which may be related to the contrast characteristics of the image.

[0079] Local contrast analysis: Divide the image into multiple small areas and calculate the grayscale statistical characteristics of each area to understand the changes in the local contrast of the image.

[0080] According to the lighting conditions and preset algorithm rules, the appropriate contrast adjustment value is calculated, taking into account the image detail retention and overall visual effect to avoid excessive enhancement or reduction of contrast.

[0081] The contrast adjustment value can be calculated as follows:

[0082] First, the lighting conditions are quantitatively evaluated; for example, the light intensity is divided into several intervals, and each interval corresponds to a numerical value representing the light intensity level.

[0083] Set a series of basic contrast adjustment coefficients based on light intensity; the lower the light intensity, the larger the basic contrast adjustment coefficient may be, in order to enhance the contrast of the image and make it clearer in low light environments; the higher the light intensity, the smaller the basic contrast adjustment coefficient may be, in order to avoid excessive contrast enhancement in strong light and cause image distortion.

[0084] Analyze the original contrast of the image; the original contrast can be quantified by calculating the grayscale standard deviation of the image or other contrast evaluation indicators.

[0085] The calculation is performed according to the preset algorithm rules, combining the basic contrast adjustment coefficient and the original contrast.

[0086] The brightness can be calculated as follows:

[0087] The light intensity data is quantified and graded. For example, it is divided into several intensity intervals, each of which corresponds to a specific level.

[0088] Set a corresponding brightness weight for each brightness level. The lower the light intensity level, the higher the corresponding brightness weight; the higher the light intensity level, the lower the brightness weight.

[0089] Determine the preset brightness ranges for the night vision device, for example, minimum and maximum values.

[0090] In addition, the overall brightness level of the environment, the brightness characteristics of the target object, and the visual adaptability of the human eye are considered. The brightness can be calculated as follows:

[0091] Assuming the light intensity is Indicates that the range of light intensity is divided into The intervals are Each interval corresponds to a brightness coefficient , ... .

[0092] The initial brightness value can be calculated by the following formula:

[0093]

[0094] in, is the current light intensity, is the initial brightness value, is the minimum brightness value, is the maximum brightness value, For the The brightness coefficient corresponding to each interval.

[0095] The brightness adjustment amount is calculated in the above manner, and the brightness adjustment amount is combined with the initial brightness value to obtain the final brightness value. If the brightness adjustment amount is a positive value, the final brightness value will increase; if the brightness adjustment amount is a negative value, the final brightness value will decrease.

[0096] Color saturation can be calculated as follows:

[0097] Assuming the color The values ​​are (red component), (green component), (blue component).

[0098] First, calculate the brightness (or lightness) of the color :

[0099]

[0100] Then, calculate the chromaticity component of the color :

[0101]

[0102] Finally, color saturation It can be calculated as:

[0103]

[0104] An adjustment amount for the color saturation is calculated, and the adjustment amount is applied to the current color saturation setting to obtain a new color saturation value.

[0105] The above-mentioned calculation method of the parameter adjustment range of the night vision parameter is only exemplary, and the parameter adjustment range of the night vision parameter can be set according to actual conditions.

[0106] Step 203: adjusting the corresponding night vision parameters of the night vision device based on the parameter adjustment range of each night vision parameter.

[0107] In the above implementation process, the acquired ambient lighting parameters are analyzed to determine the lighting conditions of the current environment, and then the parameter adjustment range of each night vision parameter in the current environment is determined based on the lighting conditions, so as to realize automatic adjustment of the night vision parameters and improve the efficiency and accuracy of the night vision parameter adjustment.

[0108] In a possible implementation, step 201 includes: obtaining statistics on the light intensity parameters of the current environment to determine the light intensity of the current environment; calculating the light difference values ​​of the light intensity parameters between various regions, and determining the light uniformity of the current environment based on the light difference values; and determining the spectrum type of the current environment based on the spectrum characteristics.

[0109] Among them, the statistically obtained light intensity parameters of the current environment are used to understand the central trend and discrete degree of the light intensity.

[0110] Optionally, the statistical method of the light intensity parameter may include: calculating the mean value, the median, the standard deviation, etc. The statistical method of the light intensity parameter may be selected according to actual conditions.

[0111] The illumination intensity determined based on the above illumination intensity parameters may include: maximum value, minimum value, average value, frequency and amplitude of change of illumination intensity, etc. The parameter value used to represent the illumination intensity may be selected according to actual conditions.

[0112] The illumination uniformity here refers to the illumination difference value between regions, uniformity and other indicators (such as the ratio of maximum to minimum illumination intensity), etc. The illumination uniformity can be determined through spatial distribution analysis, that is, the illumination distribution is determined based on the illumination difference between different regions. The illumination uniformity can be used to determine whether there are areas that are too bright or too dark, and can also be used to determine the stability of the illumination intensity.

[0113] The above-mentioned determination of the spectrum type of the current environment according to the spectrum characteristics may include: analyzing the spectrum characteristics of the light, determining the spectrum composition of the light source, and judging the spectrum type. The spectrum characteristics may include the color temperature, color rendering index, luminous efficiency, etc. of the light source, and the spectrum type may be natural light, incandescent lamp, fluorescent lamp, LED lamp, etc. The spectrum characteristics and / or spectrum type may be adjusted according to actual conditions.

[0114] Optionally, the illumination intensity, illumination uniformity and spectrum type can be determined in real time, at set time intervals, or when corresponding illumination intensity parameters and / or spectrum characteristics change. The illumination intensity, illumination uniformity and spectrum type can be determined in a manner selected according to actual conditions.

[0115] In the above implementation process, by analyzing multiple parameters in the ambient lighting parameters separately, various lighting conditions such as light brightness, uniformity and spectrum type are determined, thereby improving the accuracy of ambient lighting parameter analysis and further improving the accuracy of lighting conditions.

[0116] In a possible implementation, before step 202, the method further includes: establishing a preset model according to lighting conditions and device parameters of the night vision device.

[0117] Among them, the preset model is configured to determine the ideal adjustment range of each night vision parameter under various ambient lighting parameters.

[0118] In one embodiment, step 202 includes: inputting the lighting conditions into a preset model to obtain a parameter adjustment range of each night vision parameter under the ambient lighting parameters.

[0119] Specifically, step 202 may include the following steps:

[0120] Step 1: Determine the range of values ​​that each variable in the preset model can take. For example, the gain coefficient May be in Changes in range, aperture size exist Between, exposure time exist Between, light intensity exist between.

[0121] Step 2: Set different light intensity values, where different light intensity values ​​are used to represent different light conditions.

[0122] Step 3: For each given light intensity value, use numerical optimization methods to find the parameter combination that optimizes the imaging quality within the range of possible values ​​of each parameter. The imaging quality can be measured by evaluation indicators, such as image clarity, contrast, signal-to-noise ratio, etc.

[0123] Optionally, the numerical optimization method may include a gradient descent method, a genetic algorithm, etc. The numerical optimization method may be selected according to actual conditions.

[0124] Step 3 here can be implemented in the following ways:

[0125] First, an objective function is defined, through which the evaluation index of imaging quality is associated with the parameters in the model so as to maximize or minimize the objective function (depending on the nature of the evaluation index).

[0126] Then, by continuously iteratively calculating and comparing the objective function values ​​under different parameter combinations, the ideal range of each night vision parameter under a specific light intensity can be finally determined.

[0127] For example, if image clarity is used as the evaluation index, clarity can be expressed as a parameter , , and Function , then the goal is to find a set of parameters such that Reached maximum value.

[0128] In the above implementation process, by creating a preset model in advance, when determining the parameter adjustment range of each night vision parameter, the lighting conditions can be directly input into the preset model, and then the parameter adjustment range of each night vision parameter under the ambient lighting parameters can be obtained, thereby realizing the automatic determination of the parameter adjustment range of each night vision parameter, and improving the efficiency and accuracy of determining the parameter adjustment range of each night vision parameter.

[0129] In one possible implementation, a preset model is established according to lighting conditions and equipment parameters of a night vision device, including: establishing an initial preset model according to lighting conditions and equipment parameters of a night vision device; continuously acquiring ambient lighting parameters; when the ambient lighting parameters change, comparing the ambient lighting parameters with corresponding multiple set threshold ranges to determine the set threshold range to which the ambient lighting parameters belong; determining a corresponding adjustment strategy according to the set threshold range to which the ambient lighting parameters belong; adjusting model parameters of the initial preset model based on the adjustment strategy; inputting the lighting conditions into the initial preset model after adjusting the model parameters to obtain a corresponding imaging effect; and when the imaging effect reaches the expected effect, stopping adjusting the model parameters to obtain the preset model.

[0130] The initial preset model here can be a basic model framework, and the model parameters in the initial preset model are set initial parameters. The initial preset model can be trained and optimized to obtain a preset model.

[0131] In one embodiment, a real-time monitoring system may be established first to continuously obtain ambient light parameters.

[0132] The above-mentioned set thresholds are one or more thresholds set in advance. The set thresholds may be multiple different threshold ranges corresponding to parameters such as light intensity, and each threshold range may correspond to a set of preset parameter adjustment strategies.

[0133] After setting the set threshold in advance, the monitored ambient light parameters are compared with the corresponding multiple set threshold ranges to determine the set threshold range to which the current ambient light parameters belong. Then, the corresponding model parameters are adjusted based on the adjustment strategy associated with the set threshold range to which the current ambient light parameters belong. For example, if the light intensity is reduced, the gain factor can be increased and the exposure time can be extended.

[0134] It should be understood that after adjusting the parameters of the initial preset model, the lighting conditions are input into the initial preset model after the parameters are adjusted to output the corresponding imaging effect. When the imaging effect reaches the expected result, it is determined that the optimization of the initial preset model is completed, the adjustment of the model parameters is stopped, and the current initial preset model is used as the preset model. When the imaging effect does not reach the expected result, starting from obtaining the ambient lighting parameters, the above steps are repeated to continuously correct and optimize the initial preset model until the imaging effect reaches the expected result.

[0135] In one embodiment, since the adjustment of parameters is not completed instantly but changes gradually over a certain period of time, in order to avoid image instability caused by excessive parameter adjustment and to ensure image continuity, a smooth transition mechanism can also be introduced in the process of determining the preset model.

[0136] In the above implementation process, taking into account the changes in light, an initial preset model is established according to the lighting conditions and the equipment parameters of the night vision device, and the model parameters in the initial preset model are adjusted based on the ambient lighting parameters. The obtained preset model has the ability to adaptively adjust the parameter range according to changes in lighting conditions, thereby improving the accuracy of the preset model.

[0137] In one possible implementation, after stopping adjusting the model parameters, the method also includes: combining multiple parameters in the ambient lighting parameters respectively to obtain multiple parameter combinations; predicting the corresponding image effects under each parameter combination through a preset model; determining the parameter range corresponding to the image effect that meets the expected effect; and optimizing the parameters within the parameter range based on the image effect and the expected effect.

[0138] The parameter types in each parameter combination may be the same or different, and the parameter values ​​of each parameter in each parameter combination may be the same or different. The parameter combination may be adjusted according to actual needs.

[0139] The image effect here may include: image clarity, image contrast, image noise level, image color accuracy, etc. The image effect can be selected according to actual conditions.

[0140] It should be understood that after determining multiple parameter combinations, the corresponding image effects under each parameter combination are predicted by a preset model to obtain the corresponding image effect of each parameter combination. The parameter combination whose image effect meets the expected effect is selected, and the parameters in the parameter combination whose image effect meets the expected effect are optimized.

[0141] In one embodiment, the specific implementation method of optimizing the parameters in the parameter combination whose image effect satisfies the preset effect may be as follows:

[0142] Continuously collect environmental images under actual environmental lighting, and iteratively adjust the parameters in the parameter combination according to the difference between the actual imaging effect of the environmental image and the expected effect. Then predict the image effect corresponding to the adjusted parameter combination through the preset model, and stop the iteration when the difference between the image effect and the preset effect is less than the difference threshold. When the difference between the image effect and the preset effect is greater than or equal to the difference threshold, continue to iteratively adjust the parameters in the parameter combination until the difference between the image effect and the preset effect is less than the difference threshold.

[0143] In the above implementation process, when creating the preset model, the relationship between various night vision parameters is comprehensively considered, and the overall optimization of the parameters is achieved, so that relatively satisfactory image effects can be obtained in different environments. In addition, by allowing the algorithm to interact with the environment, a better parameter adjustment strategy can be obtained, thereby improving the preset model's ability to adapt to complex and changing lighting conditions.

[0144] In a possible implementation, after stopping adjusting the model parameters, the method further includes: determining the sensitivity of each night vision parameter to the image effect; and determining the weight of each night vision parameter in the preset model optimization according to the sensitivity of the night vision parameter to the image quality.

[0145] The greater the sensitivity of the parameter to the image quality, the higher the weight given to the parameter in the preset model optimization process. That is, the weight of the parameter is proportional to the sensitivity of the parameter to the image quality.

[0146] In one embodiment, the weight of the image quality index may be dynamically adjusted according to different lighting environments and application requirements, for example, improving clarity and brightness in low-light environments, and improving color accuracy and contrast in conditions with certain ambient light.

[0147] In another embodiment, the parameters can be optimized in combination with the perception characteristics of the human eye to the image. For example, according to the sensitivity difference of the human eye to different brightness and contrast, the parameters can be optimized so that the final image better meets the visual needs of the human eye, thereby providing a more "satisfactory" image effect.

[0148] In the above implementation process, the influence of night vision parameters on image effects can be increased by determining the weight of each parameter in the preset model optimization according to the sensitivity of the parameter to the image effect.

[0149] In a possible implementation, the preset model is:

[0150]

[0151] in, is the light intensity, is the gain factor of the night vision device, is the aperture size of the night vision device, is the exposure time, is the pixel position The original image brightness value at is the pixel position The adjusted image brightness value at The differential of .

[0152] The gain coefficient here is used to adjust the degree of light amplification of the night vision device. The aperture size and exposure time jointly control the brightness of the light entering the device. The integral part represents the cumulative calculation of the image brightness within the original light intensity range.

[0153] In one embodiment, considering the hardware limitations of the night vision device and the requirements of the actual application scenario, parameter constraints can also be set. For example, the gain coefficient is limited to not exceed the maximum value allowed by the device to avoid excessive amplification of noise; the exposure time can also be limited according to the battery life requirements. The constraints can be adjusted according to the actual situation.

[0154] In a possible implementation, the method also includes: measuring initial ambient lighting parameters of a specific environment through a night vision device; adjusting the night vision parameters of the night vision device according to reference information; acquiring a current image through the night vision device after adjusting the night vision parameters; when the current image achieves a target image effect, associating the initial ambient lighting parameters with the night vision parameters corresponding to the current image; and storing the associated initial ambient lighting parameters and night vision parameters.

[0155] The specific environment here refers to some special environments. For example, extremely low light environment (such as the suburbs at night without moonlight, deep caves, etc.), complex light pollution environment (such as areas with staggered lights and flashing neon lights), high humidity environment (such as rain forests, rivers, etc.), extreme temperature environment (such as extremely cold snowy mountains or hot deserts, etc.), environment with strong electromagnetic interference (such as areas near high-voltage power lines, communication base stations, etc.), dusty environment (such as construction sites, areas with strong winds and sand, etc.), underwater environment, high altitude environment, chemical pollution environment (such as places with corrosive gases or liquids), etc. The specific environment can be adjusted according to actual conditions.

[0156] The reference information mentioned above refers to the information parameters of the standard equipment or reference object used for calibration under specific circumstances, for example, the light intensity and color temperature provided by a standard light source, or a calibration pattern or target object with specific characteristics.

[0157] In one embodiment, before calibration is performed, a night vision device is used to measure the calibration environment, and current parameter values ​​and image effects are recorded, which can be used as reference information.

[0158] The above-mentioned adjusting the night vision parameters of the night vision device according to the reference information may include: gradually adjusting the gain, contrast, brightness, color saturation and other parameters of the night vision device according to the reference information, so that the difference between the adjusted parameters and the reference information becomes smaller, and during the adjustment process, observing the changes in the image effect so that the image quality gradually improves and reaches a better state.

[0159] In one embodiment, after adjusting to a good image effect, further fine-tuning can be performed. For example, the gain and contrast can be fine-tuned to ensure that details in the image are clearly visible while avoiding over-enhancing or weakening certain parts. The color saturation can be fine-tuned to make the colors look natural and realistic.

[0160] It should be understood that when the current image achieves the target image effect, it means that the current night vision parameters are better, and the night vision parameters are associated with the initial ambient light parameters and stored. When facing the same initial ambient light parameters again, the night vision parameters can be directly used.

[0161] Since environmental conditions may change, night vision equipment can be calibrated regularly to ensure that the performance and image effects of the night vision equipment are always maintained at the best condition.

[0162] In another embodiment, a user-defined mode may be set to allow the user to personalize the parameter range or strategy of the automatic adjustment according to their own needs.

[0163] In the above implementation process, in some specific environments, calibrating the parameters of the night vision device can improve the accuracy of image acquisition by the night vision device.

[0164] Based on the same application concept, a night vision parameter adjustment device corresponding to the night vision parameter adjustment method is also provided in the embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to that in the aforementioned night vision parameter adjustment method embodiment, the implementation of the device in this embodiment can refer to the description in the embodiment of the above method, and the repeated parts will not be repeated.

[0165] See also Figure 4 , is a functional module diagram of the night vision parameter adjustment device provided in the embodiment of the present application. Each module in the night vision parameter adjustment device in this embodiment is used to execute each step in the above method embodiment. The night vision parameter adjustment device includes an analysis module 301, a determination module 302, and an adjustment module 303; wherein,

[0166] The analysis module 301 is used to analyze the acquired ambient lighting parameters of the current environment to determine the lighting conditions of the current environment.

[0167] The determination module 302 is used to determine the parameter adjustment range of each night vision parameter in the current environment according to the lighting conditions.

[0168] The adjustment module 303 is used to adjust the corresponding night vision parameters of the night vision device based on the parameter adjustment range of each night vision parameter.

[0169] In a possible implementation, the analysis module 301 is also used to: statistically obtain the light intensity parameters of the current environment to determine the light intensity of the current environment; calculate the light difference values ​​of the light intensity parameters between each area, and determine the light uniformity of the current environment based on the light difference values; determine the spectral type of the current environment based on the spectral characteristics.

[0170] In a possible implementation, the night vision parameter adjustment device also includes a model creation module, which is used to: establish a preset model based on lighting conditions and equipment parameters of the night vision device; wherein the preset model is configured to determine an ideal adjustment range of each night vision parameter under various ambient lighting parameters.

[0171] In a possible implementation manner, the determination module 302 is further configured to: input the lighting conditions into a preset model to obtain a parameter adjustment range of each night vision parameter under the ambient lighting parameters.

[0172] In one possible implementation, the model creation module is specifically used to: establish an initial preset model according to lighting conditions and equipment parameters of a night vision device; continuously obtain ambient lighting parameters; when the ambient lighting parameters change, compare the ambient lighting parameters with corresponding multiple set threshold ranges to determine the set threshold range to which the ambient lighting parameters belong; determine a corresponding adjustment strategy according to the set threshold range to which the ambient lighting parameters belong; adjust the model parameters of the initial preset model based on the adjustment strategy; input the lighting conditions into the initial preset model after adjusting the model parameters to obtain the corresponding imaging effect; when the imaging effect reaches the expected effect, stop adjusting the model parameters to obtain the preset model.

[0173] In a possible implementation, the night vision parameter adjustment device also includes a model creation module, which is used to: combine multiple parameters in the ambient lighting parameters respectively to obtain multiple parameter combinations; predict the corresponding image effects under each parameter combination through a preset model; determine the parameter range corresponding to the image effect that meets the expected effect; and optimize the parameters within the parameter range based on the image effect and the expected effect.

[0174] In a possible implementation, the night vision parameter adjustment device also includes a weight determination module, which is used to: determine the sensitivity of each night vision parameter to the image effect; and determine the weight of each night vision parameter in the preset model optimization according to the sensitivity of the night vision parameter to the image quality.

[0175] In a possible implementation, the night vision parameter adjustment device also includes an association module, which is used to: measure the initial ambient lighting parameters of a specific environment through a night vision device; adjust the night vision parameters of the night vision device according to reference information; obtain a current image through the night vision device after adjusting the night vision parameters; when the current image achieves the target image effect, associate the initial ambient lighting parameters with the night vision parameters corresponding to the current image; and store the associated initial ambient lighting parameters and night vision parameters.

[0176] In addition, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the night vision parameter adjustment method described in the above method embodiment are executed.

[0177] The computer program product of the night vision parameter adjustment method provided in the embodiment of the present application includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the steps of the night vision parameter adjustment method described in the above method embodiment. Please refer to the above method embodiment for details, which will not be repeated here.

[0178] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0179] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0180] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes. It should be noted that in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variation thereof are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus that includes a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or apparatus. In the absence of more restrictions, the elements defined by the sentence "includes..." do not exclude the presence of other identical elements in the process, method, article or apparatus that includes the elements.

[0181] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. 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. It should be noted that similar numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0182] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for adjusting night vision parameters, characterized in that: include: Analyze the acquired ambient lighting parameters of the current environment to determine the lighting conditions of the current environment; Determining, according to the lighting conditions, a parameter adjustment range of each night vision parameter in the current environment; Adjusting corresponding night vision parameters of the night vision device based on the parameter adjustment range of each night vision parameter; Before determining the parameter adjustment range of each night vision parameter in the current environment according to the illumination condition, the method further includes: Establishing a preset model according to the lighting conditions and the equipment parameters of the night vision equipment; wherein the preset model is configured to determine an ideal adjustment range of each night vision parameter under various ambient lighting parameters; Determining the parameter adjustment range of each night vision parameter in the current environment according to the illumination condition includes: Inputting the illumination condition into the preset model to obtain the parameter adjustment range of each night vision parameter under the ambient illumination parameter; The step of establishing a preset model according to the illumination conditions and the equipment parameters of the night vision equipment comprises: Establishing an initial preset model according to the lighting conditions and device parameters of the night vision device; Continuously obtain ambient lighting parameters; When the ambient light parameter changes, the ambient light parameter is compared with a plurality of corresponding set threshold ranges to determine the set threshold range to which the ambient light parameter belongs; Determining a corresponding adjustment strategy according to a set threshold range to which the ambient light parameter belongs; Adjusting the model parameters of the initial preset model based on the adjustment strategy; Inputting the illumination condition into the initial preset model after adjusting the model parameters to obtain the corresponding imaging effect; When the imaging effect reaches the expected effect, stop adjusting the model parameters to obtain the preset model; After stopping adjusting the model parameters, the method further includes: Combining various parameters in the ambient lighting parameters respectively to obtain multiple parameter combinations; Predicting the corresponding image effects under various parameter combinations through the preset model; Determine a parameter range corresponding to an image effect that satisfies the expected effect; Optimizing parameters within the parameter range according to the image effect and the expected effect; After stopping adjusting the model parameters, the method further includes: Determining the sensitivity of each of the night vision parameters to the image effect; The weight of each of the night vision parameters in the preset model optimization is determined according to the sensitivity of the night vision parameter to the image quality.

2. The method according to claim 1, characterized in that in, The ambient lighting parameters include lighting intensity parameters and spectrum characteristics; The lighting conditions include: lighting intensity, lighting uniformity and spectrum type; The step of analyzing the obtained ambient lighting parameters of the current environment to determine the lighting conditions of the current environment includes: Counting the obtained light intensity parameters of the current environment to determine the light intensity of the current environment; Calculating illumination difference values ​​of illumination intensity parameters between various regions, and determining the illumination uniformity of the current environment according to the illumination difference values; The spectrum type of the current environment is determined according to the spectrum characteristics.

3. The method according to claim 1, characterized in that in, The preset model is: in, is the light intensity, is the gain factor of the night vision device, is the aperture size of the night vision device, is the exposure time, is the pixel position The original image brightness value at is the pixel position The adjusted image brightness value at The differential of .

4. The method according to claim 1 or 2, characterized in that: The method further comprises: Measuring initial ambient light parameters of a specific environment by means of the night vision device; adjusting night vision parameters of the night vision device according to the reference information; Acquire the current image through the night vision device after adjusting the night vision parameters; When the current image achieves the target image effect, associating the initial ambient lighting parameter with the night vision parameter corresponding to the current image; The associated initial ambient lighting parameters and the night vision parameters are stored.

5. A night vision parameter adjustment device, characterized in that: include: An analysis module is used to analyze the acquired ambient lighting parameters of the current environment to determine the lighting conditions of the current environment; A determination module, used to determine the parameter adjustment range of each night vision parameter in the current environment according to the lighting conditions; An adjustment module, used for adjusting corresponding night vision parameters of a night vision device based on parameter adjustment ranges of various night vision parameters; A model creation module, for: establishing a preset model according to lighting conditions and equipment parameters of a night vision device; wherein the preset model is configured to determine an ideal adjustment range of each night vision parameter under various ambient lighting parameters; The determination module is further used to: input the illumination conditions into a preset model to obtain the parameter adjustment range of each night vision parameter under the ambient illumination parameters; The model creation module is specifically used to: establish an initial preset model according to the lighting conditions and the equipment parameters of the night vision equipment; continuously obtain the ambient lighting parameters; when the ambient lighting parameters change, compare the ambient lighting parameters with the corresponding multiple set threshold ranges respectively to determine the set threshold range to which the ambient lighting parameters belong; determine the corresponding adjustment strategy according to the set threshold range to which the ambient lighting parameters belong; adjust the model parameters of the initial preset model based on the adjustment strategy; input the lighting conditions into the initial preset model after adjusting the model parameters to obtain the corresponding imaging effect; when the imaging effect reaches the expected effect, stop adjusting the model parameters to obtain the preset model; The model creation module is further used to: respectively combine multiple parameters in the ambient lighting parameters to obtain multiple parameter combinations; predict the corresponding image effects under each parameter combination through a preset model; determine the parameter range corresponding to the image effect that meets the expected effect; and optimize the parameters within the parameter range according to the image effect and the expected effect; The weight determination module is used to: determine the sensitivity of each night vision parameter to the image effect; and determine the weight of each night vision parameter in the preset model optimization according to the sensitivity of the night vision parameter to the image quality.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are executed.

Images