Exposure parameter adjustment methods, devices, electronic equipment and storage media

Abstract

This application provides an exposure parameter adjustment method, apparatus, electronic device, and storage medium. The method includes: acquiring a monitoring image of the furnace mouth area of ​​a smelting furnace, and extracting a mask image of the furnace mouth flame from the monitoring image. The monitoring image is acquired by an industrial camera. Based on the monitoring image and the mask image, the method calculates a first-image brightness of the flame area and a second-image brightness of the effective area. Based on the first-image brightness and the second-image brightness, the method calculates the current image brightness of the flame area. The effective area is the region in the monitoring image whose grayscale value is greater than or equal to a preset grayscale threshold. The method calculates the brightness deviation between the current image brightness and a preset target image brightness, and adjusts the exposure parameters of the industrial camera based on the brightness deviation. By combining the brightness characteristics of the flame area in the monitoring image and the brightness characteristics of the overall effective area, the exposure parameters of the industrial camera are dynamically adjusted, ensuring the quality stability of the video image of the flame in the furnace mouth flame monitoring.

Description

Technical Field

[0001] This application relates to the field of computer vision technology, and in particular to an exposure parameter adjustment method, apparatus, electronic device and storage medium. Background Technology

[0002] In smelting operations, the visual characteristics of the furnace flame, such as its shape, brightness, color, and flicker frequency, directly reflect the intensity of the chemical reaction inside the furnace, the temperature changes in the molten pool, and the decarburization process. Real-time, clear video monitoring and image recognition of the furnace flame are crucial for guiding operators to determine the blowing endpoint, optimizing the smelting process, and achieving automated control of the smelting process. However, during smelting, the furnace flame is extremely bright, with significant and rapid changes in local brightness. Furthermore, the presence of smoke, accumulated debris, or mechanical interference often leads to overexposure or underexposure of the overall image, resulting in unstable video image quality.

[0003] In related technologies, exposure parameter control strategies have been developed for industrial cameras or monitoring equipment to ensure video image quality. However, these strategies typically adjust exposure parameters based on the overall brightness of the image or the brightness of a fixed area, performing well in natural environments with gentle lighting changes and uniform brightness distribution. But in the scenario of a smelting furnace, the position, shape, and proportion of the flame area in the image are highly random and uncertain, and the brightness distribution is extremely uneven. It is difficult to simultaneously capture the flame feature details and the overall visual effect, resulting in significant fluctuations in video image quality and limiting the reliability of flame monitoring results. Summary of the Invention

[0004] This application discloses an exposure parameter adjustment method, device, electronic device, and storage medium to solve the technical problem that it is difficult to balance the flame feature details and the overall visual effect in furnace flame monitoring, resulting in unstable video image quality of the flame.

[0005] This application provides an exposure parameter adjustment method, the method comprising: acquiring a monitoring image of a furnace opening area of ​​a smelting furnace, and extracting a mask image of the furnace opening flame from the monitoring image, wherein the monitoring image is acquired by an industrial camera; calculating a first image brightness of the flame area and a second image brightness of an effective area based on the monitoring image and the mask image, and calculating a current image brightness of the flame area based on the first image brightness and the second image brightness, wherein the effective area is an area in the monitoring image whose grayscale value is greater than or equal to a preset grayscale threshold; calculating a brightness deviation between the current image brightness and a preset target image brightness, and adjusting the exposure parameters of the industrial camera based on the brightness deviation.

[0006] In one embodiment of this application, calculating the first image brightness of the flame region and the second image brightness of the effective region based on the monitoring image and the mask image includes: performing pixel-by-pixel mask screening on the monitoring image according to the mask image to obtain a flame region image; and selecting pixels from the monitoring image whose grayscale values ​​are greater than or equal to the grayscale threshold to form an effective region image; calculating the average brightness of all pixels in the flame region image to obtain the first image brightness; and calculating the average brightness of all pixels in the effective region image to obtain the second image brightness.

[0007] In one embodiment of this application, calculating the current screen brightness of the flame region based on the first screen brightness and the second screen brightness includes: calculating the ratio of the number of pixels in the flame region to the number of pixels in the effective region to obtain the flame region proportion; if the flame region proportion is greater than or equal to a preset proportion threshold, then using a preset weight threshold as the fusion weight of the first screen brightness; if the flame region proportion is less than the proportion threshold, then calculating the fusion weight of the first screen brightness based on the flame region proportion, the weight threshold, and the proportion threshold, wherein the weight threshold is the upper limit of the fusion weight corresponding to the first screen brightness; determining the fusion weight of the second screen brightness based on the fusion weight of the first screen brightness; and performing a weighted fusion of the first screen brightness and the second screen brightness based on the fusion weight of the first screen brightness and the fusion weight of the second screen brightness to obtain the current screen brightness.

[0008] In one embodiment of this application, the exposure parameters include exposure time. Adjusting the exposure parameters of the industrial camera according to the brightness deviation includes: obtaining the current exposure time of the industrial camera and mapping the current exposure time to the logarithmic domain to obtain a current logarithmic exposure time; using a proportional-integral-derivative (PID) control algorithm, calculating an initial logarithmic adjustment amount of the exposure time based on the brightness deviation, and selecting the smaller value between the initial logarithmic adjustment amount and a preset upper limit value of the logarithmic adjustment amount as the target logarithmic adjustment amount of the exposure time; calculating the sum of the current logarithmic exposure time and the target logarithmic adjustment amount to obtain the target logarithmic exposure time, and converting the target logarithmic exposure time back to the linear domain through logarithmic inverse operation to obtain a candidate exposure time; determining the target exposure time based on the candidate exposure time and a preset exposure time boundary; and adjusting the exposure time of the industrial camera based on the target exposure time and the current exposure time.

[0009] In one embodiment of this application, a proportional-integral-derivative (PID) control algorithm is used to calculate the initial logarithmic adjustment of the exposure time based on the brightness deviation. This includes: obtaining the brightness of the previous image corresponding to the flame region, the previous brightness deviation, and the cumulative historical deviation value; if the brightness deviation is less than a preset first deviation threshold, setting the preset threshold as the proportional component output value; if the brightness deviation is greater than or equal to the first deviation threshold, setting the brightness deviation as the proportional component output value, thereby obtaining the proportional component; calculating the change between the current image brightness and the previous image brightness; if the change is less than a preset change threshold, adding the brightness deviation to the cumulative historical deviation value. In the process, the smaller value between the accumulated deviation value and the preset upper limit value of the integral component is selected as the output value of the integral component. If the change value is greater than or equal to the change threshold, the historical accumulated deviation value is attenuated according to the preset attenuation factor, and the attenuated accumulated deviation value is set as the output value of the integral component to obtain the integral component. The difference between the brightness deviation and the previous brightness deviation is calculated, and the difference is set as the output value of the differential component to obtain the differential component. According to the preset proportional gain coefficient, integral gain coefficient and differential gain coefficient, the proportional component, the integral component and the differential component are weighted and fused to obtain the logarithmic value of the adjustment amount.

[0010] In one embodiment of this application, adjusting the exposure time of the industrial camera based on the target exposure time and the current exposure time includes: determining an adjustment type for the exposure time based on the target exposure time and the current exposure time, wherein the adjustment type includes increasing the exposure time and decreasing the exposure time; if the adjustment type is increasing the exposure time, then generating a first smoothing adjustment command for the exposure time based on a preset first smoothing coefficient, the target exposure time, and the current exposure time, and adjusting the exposure time in response to the first smoothing adjustment command; if the adjustment type is decreasing the exposure time, then generating a second smoothing adjustment command for the exposure time based on a preset second smoothing coefficient, the target exposure time, and the current exposure time, and adjusting the exposure time in response to the second smoothing adjustment command, wherein the second smoothing coefficient is less than the first smoothing coefficient.

[0011] In one embodiment of this application, before adjusting the exposure parameters of the industrial camera according to the brightness deviation, the method further includes: obtaining the number of frames of the monitoring image acquired after the last exposure time adjustment; if the number of frames is less than a preset first quantity threshold, then terminating the adjustment operation of the exposure parameters; or, if the number of frames is greater than or equal to the first quantity threshold, and the number of consecutive frames of the monitoring image with a brightness deviation greater than or equal to a preset second deviation threshold is less than a preset second quantity threshold, then terminating the adjustment operation of the exposure parameters; if the number of frames is greater than or equal to the first quantity threshold, and the number of consecutive frames of the monitoring image with a brightness deviation greater than or equal to the second deviation threshold is greater than or equal to the second quantity threshold, then proceeding to the adjustment operation of the exposure parameters.

[0012] This application also provides an exposure parameter adjustment device, the device comprising: an acquisition module for acquiring a monitoring image of a furnace opening area of ​​a smelting furnace and extracting a mask image of the furnace opening flame from the monitoring image, wherein the monitoring image is acquired by an industrial camera; a calculation module for calculating a first image brightness of the flame area and a second image brightness of an effective area based on the monitoring image and the mask image, and calculating the current image brightness of the flame area based on the first image brightness and the second image brightness, wherein the effective area is an area in the monitoring image whose grayscale value is greater than or equal to a preset grayscale threshold; and an adjustment module for calculating the brightness deviation between the current image brightness and a preset target image brightness, and adjusting the exposure parameters of the industrial camera based on the brightness deviation.

[0013] This application also provides an electronic device, including: a processor; and a storage device for storing a program, which, when executed by the processor, causes the electronic device to implement the exposure parameter adjustment method described above.

[0014] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a computer's processor, causes the computer to perform the exposure parameter adjustment method as described above.

[0015] The beneficial effects of this application are as follows: The exposure parameter adjustment method, device, electronic device, and storage medium provided by this application first acquire a monitoring image of the furnace mouth area of ​​a smelting furnace, and then extract a mask image of the furnace mouth flame from the monitoring image. The monitoring image is acquired by an industrial camera. Then, based on the monitoring image and the mask image, the brightness of the first image of the flame area and the brightness of the second image of the effective area are calculated. Based on the brightness of the first image and the second image, the current image brightness of the flame area is calculated. The effective area is the area in the monitoring image whose gray value is greater than or equal to a preset gray value threshold. Finally, the brightness deviation between the current image brightness and the preset target image brightness is calculated, and the exposure parameters of the industrial camera are adjusted according to the brightness deviation. This allows for dynamic adjustment of the exposure parameters of the industrial camera by combining the brightness characteristics of the flame area in the monitoring image and the brightness characteristics of the overall effective area. This achieves adaptive adjustment of the brightness of the furnace mouth flame image during the smelting process, taking into account both flame details and overall visual effects. It can effectively cope with complex situations such as extremely high flame brightness, significant local brightness differences, and rapid changes in the smelting furnace mouth scene, reducing the problem of overexposure or underexposure of the flame image in the monitoring image, improving the quality of the video image of the furnace mouth flame, and providing reliable input for operator observation and flame recognition. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0017] In the attached diagram: Figure 1 This is a schematic diagram illustrating the implementation environment of an exposure parameter adjustment device according to an exemplary embodiment of this application; Figure 2 This is a schematic flowchart illustrating an exposure parameter adjustment method according to an exemplary embodiment of this application; Figure 3 This is a schematic flowchart illustrating a specific exposure parameter adjustment method in an exemplary embodiment of this application; Figure 4 This is a block diagram illustrating an exposure parameter adjustment device according to an exemplary embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this application. Detailed Implementation

[0018] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0019] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. The drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the shape, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0020] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the present application. However, it will be apparent to those skilled in the art that embodiments of the present application may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the present application.

[0021] In smelting operations, the visual characteristics of the flame at the furnace opening, such as its shape, brightness, color, and flicker frequency, directly reflect the intensity of the chemical reaction within the furnace, changes in the molten pool temperature, and the decarburization process. To ensure the quality of video images of the flame in flame monitoring, strategies for controlling exposure parameters for industrial cameras or monitoring equipment have emerged. However, the inventors of this application have found that these strategies typically adjust exposure parameters based on the overall brightness of the image or the brightness of a fixed area, such as controlling the overall brightness of the image to approach the target brightness, or adjusting exposure parameters based on the brightness of the central area. These strategies perform well in natural environments with gentle lighting changes and uniform brightness distribution. However, in the furnace opening scenario of smelting, the position, shape, and proportion of the flame area in the image are highly random and uncertain, and the brightness distribution is extremely uneven, making it difficult to simultaneously capture the flame feature details and the overall visual effect. This results in significant fluctuations in video image quality, limiting the reliability of flame monitoring results. Therefore, there is an urgent need for a dynamic adaptive exposure adjustment method for industrial smelting flame scenarios that balances flame feature details and the overall visual effect, thereby improving the reliability of flame monitoring results.

[0022] Therefore, please see Figure 1 , Figure 1 This is a schematic diagram illustrating an implementation environment of an exposure parameter adjustment device, as shown in an exemplary embodiment of this application. Figure 1As shown, the implementation environment may include an exposure parameter adjustment device 110 and a computer device 120. The exposure parameter adjustment device 110 can be installed within the computer device 120 to adjust the exposure parameters. The computer device 120 can be at least one of a desktop graphics processing unit (GPU) computer, a GPU computing cluster, or a neural network computer. This exposure parameter adjustment device 110 can dynamically adjust the exposure parameters of the industrial camera by combining the brightness characteristics of the flame area in the monitored image with the brightness characteristics of the overall effective area. This enables adaptive adjustment of the brightness of the furnace flame image during the smelting process, balancing flame details and overall visual effects. It can effectively handle complex situations in smelting furnace scenes such as extremely high flame brightness, significant local brightness differences, and rapid changes, reducing overexposure or underexposure of the flame image in the monitored image, improving the quality of the furnace flame video image, and providing reliable input for operator observation and flame recognition.

[0023] Please see Figure 2 , Figure 2 This is a schematic flowchart illustrating an exposure parameter adjustment method according to an exemplary embodiment of this application. This method can be applied to... Figure 1 The implementation environment is shown, and the method is specifically executed by the exposure parameter adjustment device 110 in that implementation environment. It should be understood that the method can also be applied to other exemplary implementation environments and executed by devices in other implementation environments. This embodiment does not limit the implementation environment to which the method is applicable.

[0024] like Figure 2 As shown, in an exemplary embodiment, the exposure parameter adjustment method includes at least steps S210 to S230, which are described in detail below: Step S210: Acquire a monitoring image of the furnace mouth area of ​​the smelting furnace, and extract a mask image of the furnace mouth flame from the monitoring image, wherein the monitoring image is acquired by an industrial camera.

[0025] Among these, the monitoring image refers to image data obtained in real time by using an industrial camera to capture images of the furnace opening area during smelting operations. This monitoring image includes various targets such as furnace opening flames, flue gas, and slag. The furnace opening flame mask image refers to a binary image containing only the furnace opening flame area, precisely segmented from the monitoring image using image processing technology, used to accurately define the range of the flame. An industrial camera refers to equipment used in industrial production environments for image or video acquisition. Furthermore, smelting furnaces include, but are not limited to, converters, and smelting operations include, but are not limited to, converter steelmaking operations.

[0026] For example, extracting a mask image of the furnace opening flame from a monitoring image includes: inputting the monitoring image into a pre-built flame segmentation model, extracting the flame region contour using the flame segmentation model, and obtaining a mask image of the furnace opening flame.

[0027] The type of flame segmentation model is not limited, including but not limited to convolutional neural networks, transformer networks, or other models suitable for image segmentation.

[0028] For example, the training method of the flame segmentation model includes: acquiring multiple labeled furnace opening monitoring image samples, each sample including the original monitoring image and its corresponding flame region mask label; inputting the original monitoring image into the flame segmentation model to be trained to obtain the predicted flame mask; calculating the loss value based on the difference between the predicted flame mask and the corresponding flame region mask label; iteratively optimizing the parameters of the flame segmentation model to be trained based on the loss value until the convergence condition is met to obtain the final flame segmentation model.

[0029] Step S220: Calculate the first image brightness of the flame region and the second image brightness of the effective region based on the monitoring image and the mask image, and calculate the current image brightness of the flame region based on the first image brightness and the second image brightness. The effective region is the region in the monitoring image whose gray value is greater than or equal to a preset gray value threshold.

[0030] The first image brightness refers to the comprehensive measurement of the brightness information of all pixels within the flame area defined by the masked image of the furnace flame; the second image brightness refers to the comprehensive measurement of the brightness information of all pixels within the monitored image where the grayscale value is greater than or equal to a preset grayscale threshold; the grayscale value of each pixel in the effective area is greater than or equal to the preset grayscale threshold, i.e., it does not include excessively dark or meaningless parts in the monitored image; the current image brightness refers to the brightness value that represents the current visual effect of the furnace flame after comprehensively considering the first image brightness of the flame area and the second image brightness of the effective area; the grayscale threshold can be set according to actual conditions and experience to exclude excessively dark areas in the image.

[0031] In one embodiment, calculating the first screen brightness of the flame region and the second screen brightness of the effective region based on the monitoring image and the mask image includes: calculating the first screen brightness of the flame region based on the monitoring image and the mask image; and calculating the second screen brightness of the effective region based on the monitoring image.

[0032] In one embodiment, calculating the first image brightness of the flame region and the second image brightness of the effective region based on the monitoring image and the mask image includes: performing pixel-by-pixel mask screening on the monitoring image based on the mask image to obtain the flame region image; and selecting pixels with gray values ​​greater than or equal to a gray value threshold from the monitoring image to form the effective region image; calculating the average brightness of all pixels in the flame region image to obtain the first image brightness; and calculating the average brightness of all pixels in the effective region image to obtain the second image brightness.

[0033] In this embodiment, applying the mask image pixel-by-pixel to the original monitoring image allows for the filtering of the flame region, determining the flame region image, and thus accurately determining the brightness information of all pixels in the flame region. This ensures that the calculated brightness of the first image accurately reflects the brightness of the flame in the monitoring image. Simultaneously, by traversing all pixels in the monitoring image, pixels with grayscale values ​​greater than or equal to a grayscale threshold are identified and filtered to determine the effective region image. This accurately determines the brightness information of all pixels in the effective region, ensuring that the calculated brightness of the first image accurately reflects the overall brightness of the monitoring image. This provides a reliable data foundation for subsequent calculations of the current image brightness and adjustments to exposure parameters.

[0034] It should be noted that the brightness mentioned in this embodiment can be the grayscale value of a pixel, or the brightness component after a specific conversion, such as converting the monitoring image from the RGB (Red-Green-Blue) color space to the YUV (Luminance-Bandwidth-Chrominance) color space and extracting its brightness component.

[0035] In one possible embodiment, the method for determining the flame region image further includes: if a user-defined region of interest is detected, then the region of interest is acquired, and the monitoring image is subjected to pixel-by-pixel masking based on the region of interest to obtain the flame region image.

[0036] As one possible implementation, in flame monitoring, users can set the ROI (Region of Interest) through the system's open interface. If the user has pre-set the ROI, the final flame area image is determined using the ROI, so that the brightness calculation of the subsequent first image can be performed within the ROI. This enhances flexibility and allows users to customize the monitoring range according to the actual scene, so as to adjust the brightness for different on-site conditions and observation needs.

[0037] In one embodiment, calculating the current screen brightness of the flame region based on the first screen brightness and the second screen brightness includes: calculating the ratio of the number of pixels in the flame region to the number of effective pixels to obtain the flame region proportion; if the flame region proportion is greater than or equal to a preset proportion threshold, then the preset weight threshold is used as the fusion weight of the first screen brightness; if the flame region proportion is less than the proportion threshold, then the fusion weight of the first screen brightness is calculated based on the flame region proportion, the weight threshold, and the proportion threshold, wherein the weight threshold is the upper limit of the fusion weight corresponding to the first screen brightness; determining the fusion weight of the second screen brightness based on the fusion weight of the first screen brightness; and performing weighted fusion of the first screen brightness and the second screen brightness based on the fusion weight of the first screen brightness and the fusion weight of the second screen brightness to obtain the current screen brightness.

[0038] The percentage threshold and weight threshold can be set according to actual conditions and experience.

[0039] In this embodiment, considering that directly merging or averaging these two brightness levels in a fixed ratio may not accurately reflect the true brightness of the furnace flame, especially when the proportion of the flame area fluctuates greatly, it may easily lead to distortion in the current image brightness calculation, thereby affecting the accuracy of subsequent exposure parameter adjustments. Therefore, the weighted fusion of the first image brightness and the second image brightness is dynamically determined based on the proportion of the flame area. The proportion of the flame area can intuitively reflect the degree of flame coverage in the image, thereby obtaining the current image brightness with the flame area as the center.

[0040] In this embodiment, when the proportion of the flame area reaches or exceeds the proportion threshold, it indicates that the flame occupies a sufficiently large proportion in the overall effective image. At this time, the brightness of the first image is given a higher fusion weight. When the proportion of the flame area is less than the proportion threshold, it indicates that the flame occupies a small proportion in the overall effective image. At this time, the fusion weight of the brightness of the first image will be reduced accordingly. This ensures that when the flame is strong, the flame area is used as the main exposure reference, and when the flame is weak or blocked, the overall effective area is used as a supplement, thus avoiding drastic fluctuations in exposure parameters.

[0041] For example, the fusion weight of the brightness of the first image is calculated based on the proportion of the flame area, the weight threshold, and the proportion threshold, including: calculating the ratio of the proportion of the flame area to the proportion threshold; and calculating the product of the weight threshold and the ratio to obtain the fusion weight of the brightness of the first image.

[0042] In this exemplary embodiment, the formula for calculating the fusion weight of the first image brightness is: Equation (1) in, This indicates the blending weight of the brightness of the first frame; This represents the weight threshold, which is the upper limit of the fusion weight corresponding to the brightness of the first frame; Indicates the percentage of the flame area; Indicates the percentage threshold; The formula for calculating the proportion of the flame area is: Equation (2) in, Indicates the percentage of the flame area; This indicates the number of pixels in the flame area; Indicates the number of pixels in the valid region; when At that time, the blending weight of the first frame brightness Blending weights for brightness in the second frame ,when At this time, the blending weight of the brightness of the first frame decreases linearly with the proportion of the flame area. Blending weights for brightness in the second frame .

[0043] For example, the formula for calculating the current screen brightness is: Equation (3) in, Indicates the current screen brightness; Indicates the brightness of the first screen; Indicates the brightness of the second screen; This indicates the blending weight of the brightness of the first frame; This indicates the blending weight of the second image's brightness.

[0044] Step S230: Calculate the brightness deviation between the current image brightness and the preset target image brightness, and adjust the exposure parameters of the industrial camera according to the brightness deviation.

[0045] Among them, target image brightness refers to the pre-set brightness that the image of the desired furnace flame area needs to achieve; brightness deviation represents the degree of deviation between the current image brightness and the target image brightness, and is the amount that drives the adjustment of exposure parameters; exposure parameters refer to the parameters that affect the total amount of light received by the industrial camera image sensor, including but not limited to exposure time, gain, and aperture.

[0046] For example, setting the target screen brightness includes: if a user sets a brightness preference coefficient, then the brightness preference coefficient is obtained, and the target screen brightness is determined according to the brightness preference coefficient and a preset mapping relationship, wherein the mapping relationship represents the correspondence between each brightness preference coefficient and different screen brightness; if no user sets a brightness preference coefficient, then a preset brightness threshold is set as the target screen brightness.

[0047] In this exemplary embodiment, the user can set a brightness preference coefficient through the system's open interface. The system queries the mapping relationship based on this coefficient to dynamically determine the target screen brightness that conforms to the user's visual habits, the current ambient light, or different visual sensitivities. If the user does not set a brightness preference coefficient, the preset brightness threshold is used by default. This not only reduces the problem of overexposure or loss of detail caused by fixed target screen brightness, but also enhances the system's personalized adaptation capabilities and user experience.

[0048] For example, the formula for calculating brightness deviation is: Equation (4) in, Indicates brightness deviation; Indicates the brightness of the target image; This indicates the current screen brightness.

[0049] In one embodiment, the exposure parameters include exposure time. Adjusting the exposure parameters of the industrial camera based on the brightness deviation includes: acquiring the current exposure time of the industrial camera and mapping the current exposure time to the logarithmic domain to obtain the current logarithmic exposure time; using a proportional-integral-derivative (PID) control algorithm to calculate an initial logarithmic adjustment amount of the exposure time based on the brightness deviation, and selecting the smaller value between the initial logarithmic adjustment amount and a preset upper limit value of the logarithmic adjustment amount as the target logarithmic adjustment amount of the exposure time; calculating the sum of the current logarithmic exposure time and the target logarithmic adjustment amount to obtain the target logarithmic exposure time, and converting the target logarithmic exposure time back to the linear domain through logarithmic inverse operation to obtain a candidate exposure time; determining the target exposure time based on the candidate exposure time and a preset exposure time boundary; and adjusting the exposure time of the industrial camera based on the target exposure time and the current exposure time.

[0050] The upper limit of the logarithmic adjustment is used to limit the initial logarithmic adjustment of the output. This upper limit can be set according to the actual situation and experience. The exposure time boundary is the minimum and maximum exposure time limit of the industrial camera or the minimum and maximum exposure time limit set by the user through the system open interface. The minimum exposure time set by the user is greater than or equal to the minimum exposure time of the industrial camera, and the maximum exposure time set by the user is less than or equal to the maximum exposure time of the industrial camera.

[0051] In this embodiment, considering the large range of brightness variation in the flame during the smelting process, the exposure time is mapped to the logarithmic domain for adjustment. That is, by equating addition in the logarithmic domain with multiplication in the linear domain, the relative physical effect of the control increment remains constant regardless of the current exposure time. In other words, whether the current exposure is dark or bright, the control quantity has a relatively consistent adjustment sensitivity in different exposure ranges, ensuring relative consistency of control. This better conforms to the law of the influence of exposure time on brightness, making the adjustment process smoother and more stable.

[0052] Furthermore, considering the high-frequency flickering and rapid brightness changes of the flame during the smelting process, an improved PID (Proportional-Integral-Differential) control algorithm is adopted. This algorithm calculates the initial logarithmic adjustment of the exposure time based on the brightness deviation in the logarithmic domain. It also comprehensively considers the current brightness deviation, historical cumulative deviation, and deviation trend of the flame image to determine the candidate exposure time. This allows for rapid response based on brightness deviation and effectively eliminates steady-state errors, reducing potential issues such as response hysteresis, overshoot, or oscillation that may occur with linear adjustment. Simultaneously, by limiting the upper limit of the adjustment amount and considering the exposure time boundary, it not only effectively limits the amplitude of a single adjustment, preventing excessive adjustment from causing instability in the flame image, but also ensures that the final set exposure time is within the allowable range, improving the stability and safety of the adjustment and resulting in a good flame image effect after exposure time adjustment.

[0053] For example, the formula for calculating the initial logarithmic adjustment is: Equation (5) in, This represents the initial logarithmic adjustment amount for the exposure time; This represents the proportional component determined based on the brightness deviation; This represents the integral component determined based on the brightness deviation; This represents the differential component determined based on the brightness deviation; , , These represent the preset proportional gain coefficient, integral gain coefficient, and differential gain coefficient, respectively.

[0054] For example, let the upper limit of the logarithmic adjustment be _____. ,like Then the target logarithmic adjustment is ;like Then the target logarithmic adjustment is ;like Then the target logarithmic adjustment is and Any one of them.

[0055] For example, the formula for calculating the candidate exposure time is: Equation (6) in, Indicates the candidate's exposure time. (•) indicates exponential function operation; Indicates the current logarithmic exposure time; This represents the target logarithmic adjustment.

[0056] For example, determining the target exposure time based on the candidate exposure time and the preset exposure time boundary includes: comparing the candidate exposure time with the upper limit of exposure time and the lower limit of exposure time respectively; if the candidate exposure time is less than the lower limit of exposure time, then the lower limit of exposure time is determined as the target exposure time; if the candidate exposure time is greater than the upper limit of exposure time, then the upper limit of exposure time is determined as the target exposure time; if the candidate exposure time is greater than or equal to the lower limit of exposure time and less than or equal to the upper limit of exposure time, then the candidate exposure time is determined as the target exposure time.

[0057] Let the target exposure time be The minimum exposure time is The maximum exposure time is ,when hour, ,when hour, ,when hour, .

[0058] In one embodiment, a proportional-integral-derivative (PID) control algorithm is used to calculate the initial logarithmic adjustment of the exposure time based on the brightness deviation. This includes: obtaining the brightness of the previous image corresponding to the flame area, the previous brightness deviation, and the cumulative historical deviation value; if the brightness deviation is less than a preset first deviation threshold, setting the preset threshold as the proportional component output value; if the brightness deviation is greater than or equal to the first deviation threshold, setting the brightness deviation as the proportional component output value, thereby obtaining the proportional component; calculating the change in brightness between the current image and the previous image; if the change is less than a preset change threshold, adding the brightness deviation to the cumulative historical deviation value, and... The smaller of the accumulated deviation value and the preset upper limit of the integral component is selected as the output value of the integral component. If the change value is greater than or equal to the change threshold, the historical accumulated deviation value is attenuated according to the preset attenuation factor, and the attenuated accumulated deviation value is set as the output value of the integral component to obtain the integral component. The difference between the brightness deviation and the previous brightness deviation is calculated, and the difference is set as the output value of the differential component to obtain the differential component. According to the preset proportional gain coefficient, integral gain coefficient and differential gain coefficient, the proportional component, integral component and differential component are weighted and fused to obtain the logarithmic value of the adjustment amount.

[0059] Among them, the first deviation threshold, change threshold, upper limit of integral component, attenuation factor, proportional gain coefficient, integral gain coefficient and differential gain coefficient can be set according to actual situation and experience; the current image brightness refers to the brightness of the flame in the current frame of the monitored image; the previous brightness deviation refers to the deviation between the image brightness of the flame in the previous frame of the monitored image and the brightness of the target image; the historical deviation cumulative value refers to the sum of the deviations between the image brightness of the flame in the previous frame and all previous monitored images and the brightness of the target image.

[0060] It should be noted that the preset threshold is used to suppress frequent or unnecessary exposure time adjustments caused by minor deviations. Preferably, the preset threshold is 0.

[0061] In this embodiment, considering that the furnace flame has the characteristics of high-frequency flickering, drastic and complex brightness changes, directly applying the PID control algorithm may lead to problems such as over-response, oscillation or sensitivity to noise in the adjustment process, making it difficult to ensure the stability and accuracy of exposure time adjustment. Therefore, the PID control algorithm is further improved to ensure the reliability of flame monitoring results.

[0062] In this embodiment, a dead zone threshold is set when obtaining the proportional component. Specifically, a first deviation threshold is set for each brightness deviation. When the brightness deviation is less than the first deviation threshold, the preset threshold is set as the proportional component output value. When the brightness deviation is greater than or equal to the first deviation threshold, the brightness deviation is directly set as the proportional component output value. This avoids frequent adjustments to the exposure time due to small brightness deviations, ensuring adjustment stability. Conversely, it enables a rapid response when the brightness deviation is large, ensuring timely adjustment.

[0063] When obtaining the integral component, adaptive attenuation and limiting are performed. Specifically, when the change in brightness between the current screen and the previous screen is less than the change threshold, it indicates that the screen brightness change is relatively stable. At this time, the brightness deviation is accumulated into the historical deviation accumulation value, and the smaller of the accumulated deviation value and the upper limit value of the integral component is used as the integral component output value to eliminate long-term steady-state errors and prevent integral saturation. If the change value is greater than or equal to the change threshold, it indicates that the screen brightness has changed drastically. At this time, the historical deviation accumulation value is attenuated according to the attenuation factor, and the attenuated deviation accumulation value is used as the integral component output value to quickly adapt to the new brightness change and avoid excessive influence of historical errors on the current control.

[0064] When obtaining the differential component, since the differential component can reflect the trend and rate of change of brightness deviation, the difference between the brightness deviation and the previous brightness deviation is set as the output value of the differential component. Adjustment is made in advance before the deviation increases or decreases significantly, which effectively suppresses the rapid change of deviation and makes the adjustment of exposure time smoother and more stable.

[0065] In this embodiment, the improved PID control strategy can dynamically determine the exposure time adjustment based on the flame flicker characteristics, namely the degree of flame fluctuation and the trend of brightness change. This significantly improves the robustness and dynamic response capability of the exposure time adjustment, ensuring that the brightness of the furnace flame in the monitoring image captured by the industrial camera remains within a better brightness range.

[0066] In one possible embodiment, when the brightness deviation is determined, the average deviation value corresponding to the monitored image sequence is determined as the final brightness deviation to avoid the impact of single-frame brightness anomalies on control.

[0067] In one possible embodiment, when adding the brightness deviation to the historical deviation accumulation value, it is necessary to satisfy the condition that the change value between the brightness of multiple consecutive current frames and the brightness of the previous frame is less than the change threshold. When attenuating the historical deviation accumulation value according to the attenuation factor, it is necessary to satisfy the condition that the change value between the brightness of multiple consecutive current frames and the brightness of the previous frame is greater than or equal to the change threshold, so as to avoid the impact of single-frame brightness abnormality on control.

[0068] In one possible embodiment, before calculating the difference between the brightness deviation and the previous brightness deviation, the brightness deviation and the previous brightness deviation are respectively low-pass filtered to suppress high-frequency noise interference in the brightness signal.

[0069] Specifically, the exposure time of the industrial camera is adjusted based on the target exposure time and the current exposure time, including: determining the adjustment type of the exposure time based on the target exposure time and the current exposure time, where the adjustment type includes increasing the exposure time and decreasing the exposure time; if the adjustment type is to increase the exposure time, a first smoothing adjustment command for the exposure time is generated based on a preset first smoothing coefficient, the target exposure time, and the current exposure time, and the exposure time is adjusted in response to the first smoothing adjustment command; if the adjustment type is to decrease the exposure time, a second smoothing adjustment command for the exposure time is generated based on a preset second smoothing coefficient, the target exposure time, and the current exposure time, and the exposure time is adjusted in response to the second smoothing adjustment command, wherein the second smoothing coefficient is smaller than the first smoothing coefficient.

[0070] The first smoothing coefficient and the second smoothing coefficient can be set according to actual conditions and experience. They are used to determine the degree to which the actual exposure time approaches the target exposure time each time an adjustment is made.

[0071] For example, the adjustment type of the exposure time is determined based on the target exposure time and the current exposure time, including: if the target exposure time is greater than the current exposure time, the adjustment type is determined to be to increase the exposure time; if the target exposure time is less than the current exposure time, the adjustment type is determined to be to decrease the exposure time.

[0072] In this embodiment, considering that directly applying the calculated target exposure time to an industrial camera may cause frequent and drastic changes in the exposure time in a dynamically changing environment, it is necessary to achieve a smooth transition of image brightness visually after determining the target exposure time.

[0073] In this embodiment, in the smoothing process of the exposure time output stage, an asymmetric smoothing coefficient is used. When the exposure time is increased, a relatively large first smoothing coefficient is used to ensure a certain response speed and ensure that the image is clear. When the exposure time is shortened, a relatively small second smoothing coefficient is used, so that the exposure time adjustment process is more stable and gradual, ensuring that the image is visually smoother.

[0074] For example, in the smoothing process, time-weighted averaging, sliding window filtering, or exponential decay smoothing can be used to suppress short-term brightness fluctuations caused by natural flame flicker.

[0075] For example, a first-order exponential smoothing filter strategy is used to generate the first smoothing adjustment command and the second smoothing adjustment command.

[0076] In this exemplary embodiment, the expression for the first-order exponential smoothing filter is: Equation (7) in, Indicates the output exposure time; Indicates the smoothing coefficient; Indicates the current exposure time; This represents the target exposure time; for the smoothing coefficient, the first smoothing coefficient is used when the exposure time is increased. When shortening the exposure time, a second smoothing coefficient is used. .

[0077] In one embodiment, before adjusting the exposure parameters of the industrial camera according to the brightness deviation, the method further includes: acquiring the number of frames of the monitoring image acquired after the last exposure time adjustment; if the number of frames is less than a preset first quantity threshold, then terminating the exposure parameter adjustment operation; or, if the number of frames is greater than or equal to the first quantity threshold, and the number of consecutive frames of the monitoring image with a brightness deviation greater than or equal to a preset second deviation threshold is less than the preset second quantity threshold, then terminating the exposure parameter adjustment operation; if the number of frames is greater than or equal to the first quantity threshold, and the number of consecutive frames of the monitoring image with a brightness deviation greater than or equal to the second deviation threshold is greater than or equal to the second quantity threshold, then proceeding with the exposure parameter adjustment operation.

[0078] The first quantity threshold, the second quantity threshold, and the second deviation threshold can be set according to actual conditions and experience. In addition, this embodiment does not limit the relationship between the first quantity threshold and the second quantity threshold, or the relationship between the second deviation threshold and the aforementioned first deviation threshold.

[0079] In this embodiment, considering that immediately adjusting the exposure parameters every time a brightness deviation is detected would lead to frequent fluctuations in the exposure parameters, thus affecting the quality of the monitored image, an adjustment timing judgment mechanism is introduced. Specifically, no further adjustments are made within a preset number of frames since the last adjustment, or even after reaching the preset number of frames, if the significant brightness deviation is not persistent but may only be a momentary fluctuation, no further adjustments are made. Only after reaching the preset number of frames, if the significant brightness deviation persists, will subsequent exposure parameter adjustment operations be initiated. This avoids an immediate response to every detected brightness deviation, effectively preventing frequent parameter fluctuations.

[0080] The aforementioned exposure parameter adjustment method first acquires a monitoring image of the furnace mouth area and extracts a mask image of the furnace mouth flame from the monitoring image. This monitoring image is acquired by an industrial camera. Then, based on the monitoring image and the mask image, the first image brightness of the flame area and the second image brightness of the effective area are calculated. Based on the first image brightness and the second image brightness, the current image brightness of the flame area is calculated. The effective area is the area in the monitoring image whose gray value is greater than or equal to a preset gray value threshold. Finally, the brightness deviation between the current image brightness and the preset target image brightness is calculated, and the exposure parameters of the industrial camera are adjusted according to the brightness deviation. This method can dynamically adjust the exposure parameters of the industrial camera by combining the brightness characteristics of the flame area in the monitoring image and the brightness characteristics of the overall effective area, thus achieving adaptive adjustment of the furnace mouth flame image brightness during the smelting process. It takes into account both flame details and overall visual effects, and can effectively cope with complex situations such as extremely high flame brightness, significant local brightness differences, and rapid changes in the smelting furnace mouth scene. It reduces the problem of overexposure or underexposure of the flame image in the monitoring image, improves the quality of the video image of the furnace mouth flame, and provides reliable input for operator observation and flame recognition.

[0081] Please see Figure 3 , Figure 3 This is a schematic flowchart illustrating a specific exposure parameter adjustment method as shown in an exemplary embodiment of this application. Figure 3 As shown, the specific exposure parameter adjustment method includes at least steps S310 to S311, which are detailed below: Step S301: Obtain monitoring images of the furnace mouth area of ​​the smelting furnace; Step S302: Using the flame segmentation model, extract the mask image of the furnace flame from the monitoring image; Step S303: Determine the regions in the monitored image whose grayscale values ​​are greater than or equal to the grayscale threshold as valid regions; Step S304: Calculate the first image brightness of the flame area and the second image brightness of the effective area based on the monitoring image and the mask image; Step S305: Determine the brightness fusion weight based on the ratio of the flame area to the effective area, and perform weighted fusion of the brightness of the first screen and the brightness of the second screen based on the brightness fusion weight to obtain the current screen brightness; Step S306: Calculate the brightness deviation between the current screen brightness and the target screen brightness; Step S307: In the logarithmic domain, a proportional-integral-derivative control algorithm is used to determine the candidate exposure time based on the brightness deviation. Step S308: Limit the candidate exposure time according to the exposure time boundary to determine the target exposure time; Step S309: Using a first-order exponential smoothing filter, the real-time output exposure time is determined based on the current exposure time and the target exposure time. Step S310: Continuously send the real-time output exposure time to the industrial camera; Step S311: Perform continuous closed-loop control on the exposure time of the industrial camera.

[0082] This specific exposure parameter adjustment method achieves visual smoothness and stability of overall image brightness while preserving flame details. It is highly targeted, specifically designed for smelting scenarios, and can adapt to flickering, obstructed, and extreme brightness conditions at the furnace opening. It exhibits high robustness by evaluating exposure based on the flame area, reducing overexposure or underexposure. It demonstrates excellent smoothness through a combination of time filtering and adaptive control, achieving smooth visual brightness and avoiding frequent parameter fluctuations. It is highly customizable, supporting user settings for brightness preference coefficients, regions of interest, and exposure time boundaries. Furthermore, it offers good real-time performance due to its lightweight algorithm, allowing it to run in real-time on industrial cameras or edge computing devices.

[0083] Please see Figure 4 , Figure 4 This is a block diagram illustrating an exposure parameter adjustment device according to an exemplary embodiment of this application. The device can be applied to… Figure 1 The implementation environment shown is intended to illustrate an application of this device in other exemplary environments. This embodiment does not limit the application environment to which the device is applicable.

[0084] like Figure 4 As shown, in an exemplary embodiment, the exposure parameter adjustment device 400 includes at least a data acquisition module 410, a calculation module 420, and an adjustment module 430, which are described in detail below: The acquisition module 410 is used to acquire monitoring images of the furnace mouth area of ​​the smelting furnace and extract mask images of the furnace mouth flames from the monitoring images. The monitoring images are acquired by an industrial camera. The calculation module 420 is used to calculate the first screen brightness of the flame area and the second screen brightness of the effective area based on the monitoring image and the mask image, and to calculate the current screen brightness of the flame area based on the first screen brightness and the second screen brightness, wherein the effective area is the area in the monitoring image whose gray value is greater than or equal to a preset gray value threshold. The adjustment module 430 is used to calculate the brightness deviation between the current image brightness and the preset target image brightness, and to adjust the exposure parameters of the industrial camera according to the brightness deviation.

[0085] It should be noted that the exposure parameter adjustment device provided in the above embodiments and the exposure parameter adjustment method provided in the above embodiments belong to the same concept. The content of the operation performed by each module has been described in detail in the method embodiments, and will not be repeated here.

[0086] This application also provides an exposure parameter adjustment system, including the aforementioned exposure parameter adjustment device. The exposure parameter adjustment device is equipped with a user interface and a display screen. The user interface allows the user to set the region of interest, brightness preference coefficient, and exposure time boundary. The display screen is used to visualize the exposure parameter adjustment process. The exposure parameter adjustment device is connected to a programmable industrial camera and is used to dynamically update the exposure parameters of the industrial camera based on the brightness characteristics of the flame area and the brightness characteristics of the overall effective area in the monitored image.

[0087] It should be noted that the exposure parameter adjustment system provided in the above embodiments and the exposure parameter adjustment method provided in the above embodiments belong to the same concept. The content of the device operation has been described in detail in the method embodiments, and will not be repeated here.

[0088] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this application. Figure 5 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 5 The computer system 500 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0089] like Figure 5 As shown, the computer system 500 includes a Central Processing Unit (CPU) 501, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, based on programs stored in Read-Only Memory (ROM) 502 or programs loaded from storage portion 508 into Random Access Memory (RAM) 503. The RAM 503 also stores various programs and data required for system operation. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An Input / Output (I / O) interface 505 is also connected to the bus 504.

[0090] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. Removable media 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 510 as needed so that computer programs read from them can be installed into storage section 508 as needed.

[0091] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by central processing unit (CPU) 501, it performs various functions defined in the system of this application.

[0092] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a computer's processor, causes the computer to perform the exposure parameter adjustment method as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not deployed within that electronic device.

[0093] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0094] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. An exposure parameter adjustment method characterized by, The method includes: Acquire monitoring images of the furnace mouth area of ​​a smelting furnace, and extract masked images of the furnace mouth flames from the monitoring images, wherein the monitoring images are acquired by an industrial camera; Based on the monitoring image and the mask image, the first image brightness of the flame region and the second image brightness of the effective region are calculated, and the current image brightness of the flame region is calculated based on the first image brightness and the second image brightness, wherein the effective region is the region in the monitoring image whose gray value is greater than or equal to a preset gray value threshold. Calculate the brightness deviation between the current image brightness and the preset target image brightness, and adjust the exposure parameters of the industrial camera according to the brightness deviation.

2. The exposure parameter adjustment method according to claim 1, wherein Based on the monitored image and the mask image, the brightness of the first image of the flame region and the brightness of the second image of the effective region are calculated, including: The monitoring image is filtered pixel by pixel based on the mask image to obtain a flame area image, and pixels with gray values ​​greater than or equal to the gray value threshold are selected from the monitoring image to form an effective area image. The average brightness of all pixels in the flame area image is calculated to obtain the first image brightness, and the average brightness of all pixels in the effective area image is calculated to obtain the second image brightness.

3. The exposure parameter adjustment method according to claim 1, characterized in that, Calculate the current screen brightness of the flame area based on the first screen brightness and the second screen brightness, including: Calculate the ratio of the number of pixels in the flame region to the number of pixels in the effective region to obtain the proportion of the flame region; If the proportion of the flame area is greater than or equal to a preset proportion threshold, then the preset weight threshold is used as the fusion weight of the first screen brightness. If the proportion of the flame area is less than the proportion threshold, then the fusion weight of the first screen brightness is calculated based on the proportion of the flame area, the weight threshold, and the proportion threshold, wherein the weight threshold is the upper limit of the fusion weight corresponding to the first screen brightness. The fusion weight of the second image brightness is determined based on the fusion weight of the first image brightness; Based on the fusion weight of the first image brightness and the fusion weight of the second image brightness, the first image brightness and the second image brightness are weighted and fused to obtain the current image brightness.

4. The exposure parameter adjustment method according to claim 1, characterized in that, The exposure parameters include exposure time, and adjusting the exposure parameters of the industrial camera according to the brightness deviation includes: Obtain the current exposure time of the industrial camera and map the current exposure time to the logarithmic domain to obtain the current logarithmic exposure time; A proportional-integral-derivative (PID) control algorithm is used to calculate the initial logarithmic adjustment of the exposure time based on the brightness deviation, and the smaller value between the initial logarithmic adjustment and the preset upper limit of the logarithmic adjustment is selected as the target logarithmic adjustment of the exposure time. Calculate the sum of the current logarithmic exposure time and the target logarithmic adjustment amount to obtain the target logarithmic exposure time, and then transform the target logarithmic exposure time back to the linear domain through logarithmic inverse operation to obtain the candidate exposure time; The target exposure time is determined based on the candidate exposure time and the preset exposure time boundary. The exposure time of the industrial camera is adjusted based on the target exposure time and the current exposure time.

5. The exposure parameter adjustment method according to claim 4, characterized in that, Using a proportional-integral-derivative (PID) control algorithm, the initial logarithmic adjustment of the exposure time is calculated based on the brightness deviation, including: Obtain the brightness of the previous image, the brightness deviation of the previous image, and the cumulative value of the historical deviation corresponding to the flame area; If the brightness deviation is less than a preset first deviation threshold, the preset threshold is set as the proportional component output value; if the brightness deviation is greater than or equal to the first deviation threshold, the brightness deviation is set as the proportional component output value, thereby obtaining the proportional component. Calculate the change value between the current screen brightness and the previous screen brightness. If the change value is less than a preset change threshold, the brightness deviation is added to the historical deviation accumulation value, and the smaller value between the accumulated deviation value and the preset upper limit value of the integral component is selected as the integral component output value. If the change value is greater than or equal to the change threshold, the historical deviation accumulation value is attenuated according to a preset attenuation factor, and the attenuated deviation accumulation value is set as the integral component output value to obtain the integral component. Calculate the difference between the brightness deviation and the previous brightness deviation, and set the difference as the differential component output value to obtain the differential component; Based on preset proportional gain coefficient, integral gain coefficient, and differential gain coefficient, the proportional component, the integral component, and the differential component are weighted and fused to obtain the logarithmic value of the adjustment amount.

6. The exposure parameter adjustment method according to claim 4, characterized in that, Adjusting the exposure time of the industrial camera based on the target exposure time and the current exposure time includes: Based on the target exposure time and the current exposure time, the adjustment type of the exposure time is determined, and the adjustment type includes increasing the exposure time and decreasing the exposure time; If the adjustment type is the extended exposure time, then according to the preset first smoothing coefficient, the target exposure time and the current exposure time, a first smoothing adjustment command for the exposure time is generated, and the exposure time is adjusted in response to the first smoothing adjustment command; If the adjustment type is to shorten the exposure time, then a second smoothing adjustment command for the exposure time is generated based on a preset second smoothing coefficient, the target exposure time, and the current exposure time, and the exposure time is adjusted in response to the second smoothing adjustment command, wherein the second smoothing coefficient is less than the first smoothing coefficient.

7. The exposure parameter adjustment method according to any one of claims 1 to 6, characterized in that, Before adjusting the exposure parameters of the industrial camera based on the brightness deviation, the method further includes: Obtain the frame number of the monitoring image acquired after the last exposure time adjustment; If the number of frames is less than a preset first quantity threshold, the adjustment operation of the exposure parameter is terminated; or, if the number of frames is greater than or equal to the first quantity threshold, and the number of consecutive frames of the monitored image with a brightness deviation greater than or equal to a preset second deviation threshold is less than a preset second quantity threshold, the adjustment operation of the exposure parameter is terminated. If the number of frames is greater than or equal to the first quantity threshold, and the number of consecutive frames of the monitored image with a brightness deviation greater than or equal to the second deviation threshold is greater than or equal to the second quantity threshold, then the exposure parameter adjustment operation is initiated.

8. An exposure parameter adjustment device, characterized in that, The device includes: The acquisition module is used to acquire monitoring images of the furnace mouth area during smelting operations and extract mask images of the furnace mouth flames from the monitoring images, wherein the monitoring images are acquired by an industrial camera; The calculation module is used to calculate the first image brightness of the flame region and the second image brightness of the effective region based on the monitoring image and the mask image, and to calculate the current image brightness of the flame region based on the first image brightness and the second image brightness, wherein the effective region is the region in the monitoring image whose gray value is greater than or equal to a preset gray value threshold. The adjustment module is used to calculate the brightness deviation between the current image brightness and the preset target image brightness, and adjust the exposure parameters of the industrial camera according to the brightness deviation.

9. An electronic device, characterized in that, include: processor; A storage device for storing a program that, when executed by the processor, causes the electronic device to implement the exposure parameter adjustment method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by the computer's processor, causes the computer to perform the exposure parameter adjustment method as described in any one of claims 1 to 7.

Images