Visual adjustment method and device, computer device, readable storage medium and program product

Abstract

The application relates to a visual adjustment method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring a plurality of frames of sampling information collected for a cable area; based on the sampling information, extracting comprehensive feature information of the cable area; for each frame of sampling information, based on the sampling information, performing visual feature analysis on the cable area to obtain visual feature information corresponding to the sampling information of the cable area; in the case that an information difference between the visual feature information and the comprehensive feature information does not satisfy an information difference condition, determining visual adjustment information of the cable area according to the information difference; based on the visual adjustment information, performing visual adjustment on the cable area, and returning to the step of acquiring the plurality of frames of sampling information collected for the cable area until the information differences between the visual feature information and the comprehensive feature information all satisfy the information difference condition. The method can improve the cable state detection accuracy.

Description

Technical Field

[0001] This application relates to the field of utility tunnel inspection technology, and in particular to a visual adjustment method, device, computer equipment, readable storage medium, and program product. Background Technology

[0002] With the development of technology in the field of utility tunnel inspection, advanced inspection methods such as drones and intelligent monitoring equipment have emerged. These technologies are characterized by high efficiency, flexibility, and wide coverage, enabling them to conduct detailed inspections of cables and other facilities deep inside the utility tunnel, greatly improving the efficiency and quality of utility tunnel inspections. This leads to the discussion of supplementary lighting control methods during the image acquisition process of drones or monitoring equipment used in utility tunnel inspections.

[0003] Traditional technologies mainly employ global metering and fixed brightness threshold-driven supplementary lighting. This involves measuring the overall light intensity of the entire inspection scene and determining whether to activate supplementary lighting and the intensity of the supplementary lighting based on a pre-set fixed brightness threshold.

[0004] However, the current supplementary lighting control method has obvious problems. The internal environment of the utility tunnel is complex, and the cable area is unevenly distributed. The cables in different locations are affected by factors such as lighting conditions and shading, resulting in significant differences. Global metering cannot accurately reflect the actual lighting requirements of the cable area, and fixed brightness thresholds cannot flexibly adjust the supplementary lighting strategy according to the dynamic changes of the cable area. This can lead to situations where the acquired cable images are too bright, too dark, or have unclear local details, resulting in inaccurate cable status detection. Summary of the Invention

[0005] Therefore, it is necessary to provide a visual adjustment method, apparatus, computer equipment, readable storage medium, and program product that can improve the accuracy of cable status detection in response to the above-mentioned technical problems.

[0006] In a first aspect, this application provides a visual adjustment method, including:

[0007] Acquire multi-frame sampling information for the cable area;

[0008] Based on the sampling information, extract the comprehensive feature information of the cable region;

[0009] For each frame of the sampling information, visual feature analysis is performed on the cable region based on the sampling information to obtain visual feature information of the cable region corresponding to the sampling information;

[0010] If the information difference between the visual feature information and the comprehensive feature information does not meet the information difference condition, the visual adjustment information of the cable area is determined according to the information difference.

[0011] Based on the visual adjustment information, the cable area is visually adjusted, and the process returns to the step of obtaining multi-frame sampling information collected for the cable area, until the information difference between each visual feature information and the comprehensive feature information satisfies the information difference condition.

[0012] In one embodiment, the comprehensive feature information includes a first brightness and an average brightness variance; the first brightness is less than the second brightness; the visual feature information includes the average brightness and brightness variance of the sampled information; the information difference includes the brightness information difference and the brightness variance difference value; the visual accommodation information includes supplemental lighting enhancement information;

[0013] When the information difference between visual feature information and the comprehensive feature information does not meet the information difference condition, determining the visual adjustment information of the cable area according to the information difference includes:

[0014] If the difference between the average brightness of the sampled information and the brightness of the first brightness is negative, and the difference between the brightness variance and the average brightness variance is negative, then it is determined that the difference between the brightness information and the difference between the brightness variance do not satisfy the information difference condition.

[0015] The supplementary lighting enhancement information for the cable area is determined based on the brightness information difference; the brightness information difference is positively correlated with the supplementary lighting enhancement information.

[0016] In one embodiment, the integrated feature information includes a second brightness, wherein the first brightness is less than the second brightness; the visual accommodation information includes supplemental lighting reduction information;

[0017] When the information difference between the visual feature information and the comprehensive feature information does not meet the information difference condition, determining the visual adjustment information of the cable region according to the information difference includes:

[0018] If the difference between the average brightness of the sampled information and the brightness of the second brightness is positive, and the difference between the brightness variance and the average brightness variance is negative, then it is determined that the difference between the brightness information and the difference between the brightness variance do not satisfy the information difference condition.

[0019] The supplementary lighting reduction information for the cable area is determined based on the brightness information difference; the brightness information difference is inversely correlated with the supplementary lighting reduction information.

[0020] In one embodiment, the comprehensive feature information includes a texture threshold, the visual feature information includes texture feature values, and the visual adjustment information includes light ratio adjustment information.

[0021] When the information difference between visual feature information and the comprehensive feature information does not meet the information difference condition, determining the visual adjustment information of the cable area according to the information difference includes:

[0022] If the information difference between the texture feature value of the sampled information and the texture threshold is negative, then it is determined that the information difference does not satisfy the information difference condition.

[0023] Based on the texture feature values, the light ratio adjustment information of the cable area is determined.

[0024] In one embodiment, the comprehensive feature information further includes the texture median; determining the light proportion adjustment information of the cable region based on the texture feature value includes:

[0025] The texture missing ratio of the sampled information is determined based on the ratio of the texture feature value to the texture median; the ratio is inversely correlated with the texture missing ratio.

[0026] Based on the texture loss ratio, determine the light ratio adjustment information for the cable area.

[0027] In one embodiment, acquiring multi-frame sampling information collected for the cable area includes:

[0028] Perform area detection on the cable area to determine the sampling range for sampling the cable area;

[0029] Sampling is performed according to the sampling range to obtain multiple frames of sampling information collected for the cable area.

[0030] Secondly, this application also provides a visual adjustment device, comprising:

[0031] The sampling information acquisition module is used to acquire multi-frame sampling information collected from the cable area;

[0032] The feature information extraction module is used to extract comprehensive feature information of the cable region based on the sampling information.

[0033] The information analysis module is used to perform visual feature analysis on the cable region based on the sampling information for each frame, and obtain visual feature information of the cable region corresponding to the sampling information;

[0034] The visual accommodation information determination module is used to determine the visual accommodation information of the cable area according to the information difference when the information difference between the visual feature information and the comprehensive feature information does not meet the information difference condition.

[0035] The visual adjustment module is used to perform visual adjustment on the cable area based on the visual adjustment information, and return to the step of obtaining multi-frame sampling information collected for the cable area until the information difference between each visual feature information and the comprehensive feature information satisfies the information difference condition.

[0036] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described above.

[0037] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method described above.

[0038] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described above.

[0039] The aforementioned visual adjustment method, device, computer equipment, readable storage medium, and program product, by acquiring multi-frame sampling information of the cable area, can comprehensively capture the image features of the cable area at different times and under different conditions, providing rich data for subsequent analysis; by analyzing the information of multi-frame sampling information and determining the comprehensive feature information and the visual feature information of each frame of sampling information, the overall condition and individual differences of the cable area can be accurately grasped; when the information difference between the visual feature information and the comprehensive feature information does not meet the conditions, the visual adjustment information is determined according to the information difference, realizing the dynamic adjustment of visual parameters according to the actual state of the cable area, rather than using a fixed mode; the visual adjustment of the cable area is performed based on the visual adjustment information, and this process is repeated until the information difference meets the conditions, ensuring that the acquired cable image is always in the best visual effect, effectively solving the image quality problem caused by the inability of traditional supplementary lighting control methods to accurately adapt to the complex and changing conditions of the cable area, and greatly improving the accuracy of judging the cable status. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a diagram illustrating the application environment of the visual adjustment method in one embodiment;

[0042] Figure 2 This is a flowchart illustrating a visual adjustment method in one embodiment;

[0043] Figure 3 This is a flowchart illustrating the visual adjustment method in another embodiment;

[0044] Figure 4 This is a structural block diagram of the visual adjustment device in one embodiment;

[0045] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0047] The visual adjustment method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, server 102 communicates with sampling device 104 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be integrated onto server 102, or it can be located on a cloud or other network server. Server 102 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. It is a device used to acquire relevant data and information from a specific object or environment and transform it into a form that can be processed, stored, and analyzed. In this embodiment, sampling device 104 can focus on image acquisition, that is, it is a device capable of capturing visual information of a target object, converting light signals into electrical signals, and then generating digital images for subsequent viewing, analysis, and other purposes. Specifically, during the visual adjustment process, server 102 acquires multiple frames of sampling information for the cable area from sampling device 104; extracts comprehensive feature information of the cable area based on each sampling information; performs visual feature analysis on the cable area based on each frame of sampling information to obtain visual feature information of the cable area corresponding to the sampling information; if the information difference between the visual feature information and the comprehensive feature information does not meet the information difference condition, the visual adjustment information of the cable area is determined according to the information difference; the cable area is visually adjusted based on the visual adjustment information, and the process returns to the step of acquiring multiple frames of sampling information for the cable area, until the information difference between each visual feature information and the comprehensive feature information meets the information difference condition.

[0048] In one exemplary embodiment, such as Figure 2As shown, a visual adjustment method is provided, which is applied to... Figure 1 Taking server 102 as an example, the explanation includes the following steps S202 to S210. Wherein:

[0049] Step S202: Obtain multi-frame sampling information collected for the cable area.

[0050] In this context, the cable area refers to a specific spatial range within scenarios such as utility tunnels and power facilities where cables are concentrated and require focused monitoring and image acquisition. It could be a fixed-length cable laying area or a critical area containing multiple cable connection points and equipment. Multi-frame sampling information consists of multiple sets of image data continuously collected over a period of time using sampling equipment (such as cameras) targeting the cable area. Each set of image data constitutes one frame of sampling information, and multi-frame information can more comprehensively reflect the state and characteristics of the cable area at different times.

[0051] Specifically, in practice, sampling devices installed in suitable locations can be used to sample the cable area, obtaining multiple frames of sampling information. For example, the sampling device can be a high-definition camera or an industrial camera, capable of clearly capturing images of the cable area. Exemplarily, the sampling device can be fixed to the wall or support of the pipe gallery, or carried by a mobile inspection device, continuously capturing images of the cable area at pre-set time intervals or sampling frequencies. For example, capturing one image every 2 seconds, continuously capturing 60 times, yields 60 frames of sampling information for the cable area, ensuring the presence of ideal information in the collected samples. During the acquisition process, it is crucial to ensure the sampling device's position is stable to avoid blurry or inaccurate images due to device movement.

[0052] Optionally, the server can directly obtain the sampling range of the cable area and acquire multi-frame sampling information of the cable area within the sampling range. Alternatively, it can perform area detection on the cable area to determine the sampling range for sampling the cable area, and then perform sampling according to the sampling range to obtain multi-frame sampling information of the cable area.

[0053] Step S204: Extract comprehensive feature information of the cable area based on the sampling information.

[0054] Among them, the comprehensive feature information is information that represents the overall characteristics of the cable area after the overall analysis and processing of multi-frame sampling information. It covers comprehensive information such as the average brightness and average brightness variance of the cable area.

[0055] Specifically, the server can process the acquired multi-frame sampling information using image analysis algorithms or software. For example, it can integrate multiple frames to calculate the average brightness of all frames, reflecting the overall brightness of the cable area. It can also calculate the average brightness variance of all frames, or analyze the color distribution to determine the main colors present in the cable area and their proportions. Furthermore, it can analyze the overall texture details of all frames. Combining this information yields comprehensive feature information that represents the overall characteristics of the cable area.

[0056] Step S206: For each frame of sampling information, perform visual feature analysis on the cable area based on the sampling information to obtain the visual feature information of the cable area corresponding to the sampling information.

[0057] Among them, visual feature information is obtained from the sampled information of each frame through specific analysis methods, reflecting the specific visual characteristics of the cable region in that frame of image. For example, the brightness and texture of the cable in a certain frame.

[0058] Specifically, for each frame of sampled information, the server needs to analyze it individually, focusing on the visual features represented in the sampled information to determine the visual feature information corresponding to the cable region in the sampled information. For example, the visual feature information may include average brightness, brightness variance, texture feature values, etc., and the specific calculation method is similar to that of existing technologies, so it will not be elaborated here.

[0059] Step S208: If the information difference between visual feature information and comprehensive feature information does not meet the information difference condition, determine the visual adjustment information of the cable area according to the information difference.

[0060] Information difference refers to the degree of difference between visual feature information and comprehensive feature information. It can be measured by specific algorithms or indicators, such as brightness difference, texture difference, sharpness difference ratio, and color deviation. The information difference condition is a pre-defined criterion used to determine whether the difference between visual feature information and comprehensive feature information is within an acceptable range. When the information difference meets this condition, it indicates that the quality of the currently acquired image meets the requirements. Visual accommodation information, calculated based on the information difference, is used to adjust the image acquisition parameters in the cable area, such as fill light intensity, light ratio adjustment information, camera focal length, exposure time, and image contrast, with the aim of making subsequently acquired images more compliant with requirements.

[0061] Specifically, after information analysis is complete, the server compares the visual feature information of each frame of sampled information with the comprehensive feature information, calculating the information difference between them. For example, if the preset first brightness of the cable area in the comprehensive feature information is 120, while the average brightness of that area in the visual feature information of a certain frame of sampled information is 90, then the brightness difference between the visual feature information and the comprehensive feature information is -30. The preset information difference condition is that the information difference is positive, so this information difference does not meet the preset information difference condition. At this time, the server will determine the visual adjustment information based on this information difference. If the brightness is too low, it determines that the supplementary light intensity needs to be increased; if the brightness is too high, it determines that the supplementary light intensity needs to be decreased.

[0062] Optionally, the comprehensive feature information includes a first brightness and an average brightness variance; the first brightness is less than a second brightness; the visual feature information includes the average brightness and brightness variance of the sampled information; the information difference includes the brightness information difference and the difference in brightness variance; and the visual accommodation information includes supplementary lighting enhancement information. In this embodiment, if the brightness information difference between the average brightness and the first brightness of the sampled information is negative, and the difference in brightness variance between the brightness variance and the average brightness variance is also negative, then it is determined that the brightness information difference and the difference in brightness variance do not meet the information difference condition, and supplementary lighting enhancement information for the cable area is determined based on the brightness information difference; the brightness information difference is positively correlated with the supplementary lighting enhancement information.

[0063] Optionally, the comprehensive feature information includes a second brightness, where the first brightness is less than the second brightness; the visual accommodation information includes supplemental lighting reduction information. In this embodiment, if the difference between the average brightness and the second brightness of the sampled information is positive, and the difference between the brightness variance and the average brightness variance is negative, then it is determined that the brightness difference and the difference in brightness variance do not meet the information difference condition, and supplemental lighting reduction information for the cable area is determined based on the brightness difference; the brightness difference and the supplemental lighting reduction information are inversely correlated.

[0064] Step S210: Visually adjust the cable area based on the visual adjustment information, and return to the step of obtaining multi-frame sampling information collected for the cable area until the information difference between each visual feature information and the comprehensive feature information satisfies the information difference condition.

[0065] Specifically, the server can adjust the sampling device accordingly based on the visual adjustment information determined in step S208. If it is necessary to increase the supplementary light intensity, the supplementary light is controlled to increase the brightness; if it is necessary to adjust the camera focal length, the camera lens is driven by a motor to perform focusing operations; if it is necessary to adjust the exposure time, it is modified in the settings of the sampling device. After completing the visual adjustment, the system returns to step S202 to reacquire multi-frame sampling information collected for the cable area. Then, steps S204, S206, and S208 are repeated to continuously analyze, compare, and adjust the information until the information difference between the visual feature information and the comprehensive feature information of each frame of sampling information meets the preset information difference condition. At this point, it indicates that the quality of the currently acquired image has met the requirements, and the adjustment can be stopped for subsequent processing or analysis.

[0066] The aforementioned visual adjustment method, by acquiring multi-frame sampling information of the cable area, can comprehensively capture the image features of the cable area at different times and under different conditions, providing rich data for subsequent analysis. Information analysis of the multi-frame sampling information determines the comprehensive feature information and the visual feature information of each frame, accurately grasping the overall condition and individual differences of the cable area. When the information difference between the visual feature information and the comprehensive feature information does not meet the conditions, visual adjustment information is determined according to the information difference, realizing dynamic adjustment of visual parameters based on the actual state of the cable area, rather than using a fixed mode. Visual adjustment of the cable area is performed based on the visual adjustment information, and this process is repeated until the information difference meets the conditions, ensuring that the acquired cable image is always in the best visual effect. This effectively solves the image quality problem caused by the inability of traditional supplementary lighting control methods to accurately adapt to the complex and changing conditions of the cable area, greatly improving the accuracy of cable condition judgment.

[0067] In an exemplary embodiment, the comprehensive feature information includes a first luminance and an average luminance variance; the visual feature information includes the average luminance and luminance variance of the sampled information; the information difference includes the luminance information difference and the difference in luminance variance; the visual accommodation information includes supplementary lighting enhancement information; when the information difference between the visual feature information and the comprehensive feature information does not meet the information difference condition, the visual accommodation information of the cable area is determined according to the information difference, including: if the luminance information difference between the average luminance and the first luminance of the sampled information is negative, and the difference in luminance variance between the luminance variance and the average luminance variance is negative, then it is determined that the luminance information difference and the difference in luminance variance do not meet the information difference condition; supplementary lighting enhancement information of the cable area is determined according to the luminance information difference; the luminance information difference is positively correlated with the supplementary lighting enhancement information.

[0068] Here, "first brightness" is a specific parameter value related to brightness in the comprehensive feature information. For example, the first brightness could be the brightness value located at the 25th percentile after statistically analyzing the average brightness of each frame of sampled information. "Average brightness variance" is a parameter in the comprehensive feature information reflecting the dispersion of brightness distribution in the cable area. "Brightness variance" is a parameter in the visual feature information reflecting the dispersion of brightness distribution in the cable area within a specific frame of sampled information. "Supplemental lighting enhancement information" refers to information used to enhance supplemental lighting, such as increasing light intensity.

[0069] Specifically, in this embodiment, firstly, multi-frame sampling information of the cable area is analyzed to obtain the first brightness and average brightness variance in the comprehensive feature information, as well as the average brightness and brightness variance in the visual feature information of each frame of sampling information. Next, the difference between the average brightness and the first brightness of the sampling information, and the difference between the brightness variance and the average brightness variance of the sampling information are calculated. When the brightness information difference is negative, it indicates that the average brightness of the sampling information is lower than the first brightness. Simultaneously, a negative brightness variance difference means that the brightness distribution of the sampling information is more concentrated than in the comprehensive feature information, indicating it is too dark and details are compressed. In this case, the information difference is deemed not to meet the condition. Then, supplementary lighting enhancement information is determined based on the brightness information difference. Since the brightness information difference is positively correlated with the supplementary lighting enhancement information—that is, the more negative the brightness information difference—the stronger the supplementary lighting enhancement information, thereby increasing the brightness of the cable area.

[0070] In this embodiment, the supplementary lighting can be precisely adjusted according to the difference in brightness information to achieve a suitable brightness level in the cable area, thereby improving the image acquisition quality and facilitating subsequent analysis and processing of the cable area.

[0071] In an exemplary embodiment, the comprehensive feature information includes a second brightness, where the first brightness is less than the second brightness; the visual accommodation information includes supplemental lighting reduction information; when the information difference between the visual feature information and the comprehensive feature information does not meet the information difference condition, the visual accommodation information of the cable area is determined according to the information difference, including: if the brightness information difference between the average brightness of the sampled information and the second brightness is positive, and the difference between the brightness variance and the average brightness variance is negative, then it is determined that the brightness information difference and the difference in brightness variance do not meet the information difference condition; supplemental lighting reduction information of the cable area is determined according to the brightness information difference; the brightness information difference and the supplemental lighting reduction information are inversely correlated.

[0072] The second brightness is another specific parameter value of brightness in the comprehensive feature information, which is greater than the first brightness. For example, the second brightness can be the brightness value located at the 75th percentile after statistically analyzing the average brightness of each frame's sampled information.

[0073] Specifically, in this embodiment, the second brightness is first obtained from the comprehensive feature information, and the average brightness in the visual feature information of each frame of sampled information is also obtained. The difference between the average brightness of the sampled information and the second brightness, and the difference between the variance of the sampled information brightness and the variance of the average brightness are calculated. When the brightness information difference is positive, it indicates that the average brightness of the sampled information is higher than the second brightness, and when the difference in brightness variance is negative, it indicates that the brightness distribution of the sampled information is more concentrated, and it is determined that the brightness is too bright and the details are overexposed and compressed. At this time, it is determined that the information difference does not meet the condition. Then, the supplementary lighting reduction information is determined based on the brightness information difference, because the brightness information difference and the supplementary lighting reduction information are inversely correlated, that is, the more positive the brightness information difference, the weaker the supplementary lighting reduction information. In this way, the excessive brightness in the cable area is reduced.

[0074] In this embodiment, the supplementary lighting can be effectively adjusted according to the brightness, avoiding excessive brightness in the cable area that could lead to overexposure of the image, thus ensuring image quality and providing clear and accurate image data for subsequent analysis.

[0075] In an exemplary embodiment, the comprehensive feature information includes a texture threshold, the visual feature information includes texture feature values, and the visual adjustment information includes light ratio adjustment information. When there is an information difference between the visual feature information and the comprehensive feature information that does not meet the information difference condition, the visual adjustment information of the cable area is determined according to the information difference, including: if the information difference between the texture feature value of the sampled information and the texture threshold is negative, then it is determined that the information difference does not meet the information difference condition; and the light ratio adjustment information of the cable area is determined based on the texture feature value.

[0076] The texture threshold is a standard value set in the comprehensive feature information to determine the texture of the cable area. The texture feature value is a parameter value in the visual feature information that reflects the texture features of the cable area in a certain frame of sampled information.

[0077] Specifically, the server can first determine the texture threshold in the comprehensive feature information and the texture feature value in the visual feature information of each frame's sampled information. The information difference between the two is calculated. When the information difference is negative, it indicates that the texture feature value of the sampled information is lower than the texture threshold, meaning the texture performance of the cable area is poor, and the information difference is deemed insufficient. Then, the server determines the light ratio adjustment information for the cable area based on the texture feature value, improving the texture display effect of the cable area by adjusting the light ratio.

[0078] In this embodiment, the light ratio can be adjusted to address situations where the texture of the cable area is unclear, thereby optimizing the texture display of the cable area in the image, making the image more accurately reflect the actual state of the cable, and improving the accuracy of image analysis.

[0079] In an exemplary embodiment, the comprehensive feature information further includes the texture median; based on the texture feature value, determining the light proportion adjustment information of the cable region includes: determining the texture missing ratio of the sampling information based on the ratio of the texture feature value and the texture median; the ratio is inversely correlated with the texture missing ratio; and determining the light proportion adjustment information of the cable region according to the texture missing ratio.

[0080] Among them, the texture median is the value that is in the middle position after sorting the texture feature values ​​of the cable area in the comprehensive feature information.

[0081] Specifically, in this embodiment, in addition to the texture threshold in the comprehensive feature information, the texture median is also considered. First, the ratio of the texture feature value to the texture median of each frame's sampled information is calculated. Since this ratio is inversely correlated with the texture loss ratio—that is, the smaller the ratio, the greater the texture loss ratio—the light ratio adjustment information for the cable region is determined based on the calculated texture loss ratio. By reasonably adjusting the light ratio, texture loss is compensated for, and image quality is improved. For example, For texture feature values, The median of the texture, the percentage of missing textures. If texture loss is triggered, appropriately reduce the main light's PWM (Pulse Width Modulation) to avoid overexposure and further texture loss; at the same time, adjust the ratio of cool / warm light, with the cool light ratio... warm light ratio The proportion of cool light is adjusted to enhance texture details. Here, k is an adjustment coefficient.

[0082] In this embodiment, by combining the median of the texture, the texture loss situation can be determined more accurately, and then the light ratio can be adjusted in a targeted manner. This can better optimize the texture display of the cable area image, improve the image quality, and provide a reliable basis for subsequent monitoring and analysis of the cable.

[0083] In one exemplary embodiment, obtaining multi-frame sampling information for a cable region includes: performing region detection on the cable region to determine the sampling range for sampling the cable region; and performing sampling according to the sampling range to obtain multi-frame sampling information for the cable region.

[0084] The sampling range is the specific area range determined when acquiring images of the cable area.

[0085] Specifically, in this embodiment, image detection algorithms or sensors are first used to perform region detection on the cable area. By analyzing features in the image or information fed back by the sensors, the position and range of the cable area in the image are accurately determined, thereby clarifying the sampling range. Then, according to this determined sampling range, a sampling device is used to perform multiple samplings at a set time interval or frequency to obtain multiple frames of sampling information for the cable area.

[0086] In this embodiment, the sampling range of the cable area can be accurately determined, avoiding the collection of information from irrelevant areas, improving sampling efficiency and targeting, and ensuring that the acquired multi-frame sampling information can accurately reflect the state of the cable area, providing a high-quality data foundation for subsequent analysis and processing.

[0087] In one specific embodiment, the visual adjustment method may consist of the following system structure: a drone platform, a sampling device (gimbal camera), a fill light module (main light, cool / warm dual-color LED (Light Emitting Diode), driver board), and a server (outputting PWM / switching signals).

[0088] Specifically, the PTZ camera can first sample the cable area, and the server's YOLO module outputs the cable boundary box in real time to determine the sampling range of the cable area. Initial sampling of 60 frames ensures that ideal values ​​are present within the window. Then, the average brightness of the pixels in the ROI (Region of Interest) of the collected sampling information is calculated, and the brightness window of the ROI in the most recent N frames is maintained. The system calculates the median L_med, 25th percentile Q25, 75th percentile Q75, and average brightness variance σ_roi in real time. σ_roi represents the dispersion of pixel grayscale within the ROI; the more dispersed and different the pixel values, the larger the variance; the more concentrated the pixel values ​​are at the same grayscale, the smaller the variance. When there are details, the cable surface has bumps, scratches, edges, and shadows, with smaller areas being brighter and darker, resulting in a more scattered pixel distribution and higher variance. When details are suppressed (too dark / too bright / blurred), the grayscale of the entire area becomes very similar (almost the same brightness), such as a "gray patch" or a "white patch," and the pixel distribution is squeezed together, significantly reducing the variance. Additionally, the server needs to perform Laplacian energy calculations on the sampled information, maintain the texture scoring window W_T for the most recent N frames, and calculate the 10th percentile threshold in real time. Real-time frames sequentially undergo valid frame judgment → window update → brightness judgment → texture judgment → supplementary lighting control.

[0089] When the average brightness of a sampled frame falls below Q25 and the brightness variance is lower than a set percentage of the average brightness variance, it is determined to be too dark and subject to detail compression. The server then determines the brightness gap accordingly. Calculate the PWM increment of the main fill light based on the variance attenuation amount to increase the fill light intensity; when the average brightness of a certain frame of sampling information is higher than Q75 and the average brightness variance decreases synchronously, it is determined that the over-brightness and over-exposure cause the loss of details, and the server calculates according to the over-brightness amplitude Calculate the PWM decrement based on the variance attenuation amount to reduce the fill light intensity; when the brightness falls within the [Q25, Q75] confidence interval, keep the current PWM value unchanged. If the texture is insufficient, calculate the texture missing ratio and adjust the current ratio of the cold / warm light LEDs accordingly.

[0090] Collect the sampling information again after fill light and return to the step of obtaining multiple frames of sampling information collected for the cable area until the brightness falls back within the [Q25, Q75] confidence interval and the texture score recovers above the threshold; continuously execute this closed-loop during the inspection to ensure that the cable images at different positions and different backgrounds are all kept clear.

[0091] Specifically, the server can use the YOLOv11 detection model to locate the cable, and the ROI only covers the cable area; avoid sacrificing the cable brightness for the overall picture in the global exposure method, and make the fill light logic focus on the target area. When the drone enters the target section, keep the gimbal stable and shoot for 2-3 seconds (about 60-90 frames), calculate the average brightness L_roi and texture feature value T_roi of each frame of ROI, fill the sliding windows W_L and W_T, and form an initial statistic including the ideal state to ensure that there are ideal values in the window. If the ROI is missing, the confidence is low, the occlusion exceeds the threshold, the exposure is saturated, or the noise is abnormal, it is determined as an invalid frame, skip the window update and maintain the fill light output. For valid frames, write L_roi and T_roi into W_L and W_T in sequence, the window length N≈30–60, and adopt the first-in-first-out strategy to only retain the data in the most recent period, so that the statistic is updated in real time according to the environment. The server can obtain Q25, Q75 and the average brightness variance σ_mean from W_L. The brightness control is divided into two cases:

[0092] ① Increase the brightness (supplementary fill light): If the average brightness L_roi of the current frame < Q25 and the brightness variance of this frame , it is determined that both the brightness and details decline. Calculate the brightness gap , and map it to the main light adjustment amount according to to increase the fill light intensity. Where k_L is the brightness adjustment coefficient (for example, 0.5), α is the variance attenuation weight coefficient (for example, 0.3), η is the variance attenuation threshold ratio (for example, 0.2), and clip(·) is the clipping function, which constrains the PWM value within the reasonable interval [PWMmin, PWMmax].

[0093] ② Decrease the brightness (reduce the fill light): If the average brightness L_roi of the current frame > Q75 and the brightness variance of this frame If the brightness is too high and the details are overexposed and compressed, then it is determined that the brightness is too high and the details are overexposed and compressed. Calculate the degree of overexposure. , and according to This is mapped to the main light adjustment, reducing the supplementary light intensity. Here, k_H is the overbrightness adjustment coefficient (e.g., 0.4, usually slightly less than k_L to maintain a smooth dimming curve), and the other parameters have the same meaning as above. When the brightness falls within the [Q25, Q75] confidence range, the current PWM value is maintained to avoid flickering caused by frequent small adjustments.

[0094] Additionally, the server can use W_T to calculate the 10th percentile T_10 of the texture score and the texture median T_target; the texture threshold is set to T_10, and texture is considered missing only when the current texture feature value falls into the historical worst 10%. Texture missing ratio. If texture loss is triggered, reduce the main light PWM appropriately to avoid overexposure and further texture loss; at the same time, adjust the ratio of cool / warm light, with the cool light ratio... warm light ratio Increase the proportion of cool light to enhance texture details.

[0095] After the fill light operation, the next frame is acquired, and the above steps are repeated until the brightness and texture indicators return to the normal range of the window, achieving closed-loop convergence. If window statistics are abnormal, a safe mode can be entered, using a preset absolute threshold until the window stabilizes. The fill light hardware requirements are as follows: the main fill light group supports 0-100% PWM duty cycle adjustment; independent channels for cool and warm LEDs, allowing for separate PWM control and adjustable color temperature; and the MCU (Microcontroller Unit) / flight controller outputs at least three PWM channels for the main light, cool light, and warm light.

[0096] For example, taking a sliding window length of N=10 as an example, the complete process of increasing and decreasing brightness is illustrated:

[0097] Initial state: The ROI brightness sequence (unit: grayscale / 255) within the window is: 92, 90, 93, 91, 95, 89, 94, 92, 91, 93. At this time, Q25≈91, Q75≈93, L_med≈92, σ_mean≈2.5, and PWM_current=30%.

[0098] Scene 1: Increase brightness (to trigger fill light when it's too dark)

[0099] Frame 11: L_roi(11) = 80 (lower than Q25 = 91), σ_roi(11) = 1.5 (lower than σ_mean·0.8 = 2.0), indicating abnormally dark conditions and compressed details. Calculation Assuming k_L = 0.5 and α = 0.3, then After the supplemental lighting, the brightness gradually recovered in frames 12-14: L_roi(12)=88, L_roi(13)=90, L_roi(14)=92, the window was updated, Q25 returned to around 91, and the brightness fell back into the reliable range.

[0100] Scene 2: Reduce brightness (too bright triggers dimming)

[0101] Assume the window is updated to the following values ​​after illumination: 88, 90, 92, 93, 92, 91, 94, 92, 91, 93, Q25≈91, Q75≈93, σ_mean≈2.2, PWM_current=35.9%.

[0102] Frame 21: L_roi(21)=98 (higher than Q75=93), σ_roi(21)=1.2 (lower than σ_mean·0.8=1.76), indicating overexposure and loss of detail. Calculation Assuming k_H = 0.4, then After reducing the brightness, the brightness gradually drops back down in frames 22-24: L_roi(22)=96, L_roi(23)=94, L_roi(24)=93. The window is updated, Q75 returns to around 93, and the brightness falls back into the reliable range.

[0103] Scenario 3: Remain unchanged (brightness within the confidence range)

[0104] When L_roi falls within the range of [Q25, Q75] (e.g., L_roi=92, Q25=91, Q75=93), the current PWM value is maintained regardless of the variance, thus avoiding frequent adjustments and flickering caused by small fluctuations.

[0105] In a specific embodiment, such as Figure 3 As shown, a visual adjustment method is also provided, including:

[0106] Step S301: Perform area detection on the cable area to determine the sampling range for sampling the cable area;

[0107] Step S302: Sample according to the sampling range to obtain multi-frame sampling information collected for the cable area;

[0108] Step S303: Based on the sampling information, extract the comprehensive feature information of the cable area;

[0109] Step S304: For each frame of sampling information, perform visual feature analysis on the cable area based on the sampling information to obtain the visual feature information of the cable area corresponding to the sampling information;

[0110] Step S305: If the difference between the average brightness and the first brightness of the sampled information is negative, and the difference between the brightness variance and the average brightness variance is negative, then it is determined that the difference between the brightness information and the difference between the brightness variance do not meet the information difference condition.

[0111] Step S306: Determine the supplementary lighting enhancement information for the cable area based on the brightness information difference;

[0112] Among them, the difference in brightness information is positively correlated with the information enhanced by supplemental lighting;

[0113] Step S307: If the difference between the average brightness and the second brightness of the sampled information is positive, and the difference between the brightness variance and the average brightness variance is negative, then it is determined that the difference between the brightness information and the difference between the brightness variance do not meet the information difference condition.

[0114] Step S308: Determine the supplementary lighting reduction information for the cable area based on the brightness information difference;

[0115] Among them, the difference in brightness information is inversely correlated with the reduction in information from supplemental lighting;

[0116] Step S309: If the information difference between the texture feature value of the sampled information and the texture threshold is negative, then it is determined that the information difference does not meet the information difference condition.

[0117] Step S310: Determine the proportion of missing texture information based on the ratio of texture feature value to texture median;

[0118] Among them, the ratio is inversely correlated with the proportion of texture loss;

[0119] Step S311: Determine the light ratio adjustment information of the cable area according to the texture loss ratio;

[0120] Step S312: If the information difference between each visual feature information and the comprehensive feature information all meet the information difference condition, no further visual adjustment is performed.

[0121] Step S313: Visually adjust the cable area based on the visual adjustment information, and return to step S302.

[0122] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0123] Based on the same inventive concept, this application also provides a visual adjustment device for implementing the visual adjustment method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more visual adjustment device embodiments provided below can be found in the limitations of the visual adjustment method described above, and will not be repeated here.

[0124] In one exemplary embodiment, such as Figure 4 As shown, a visual adjustment device 400 is provided, including: a sampling information acquisition module 402, a feature information extraction module 404, an information analysis module 406, a visual adjustment information determination module 408, and a visual adjustment module 410, wherein:

[0125] The sampling information acquisition module 402 is used to acquire multi-frame sampling information collected from the cable area.

[0126] The feature information extraction module 404 is used to extract comprehensive feature information of the cable area based on each sampling information;

[0127] The information analysis module 406 is used to perform visual feature analysis on the cable area based on the sampling information for each frame, and to obtain the visual feature information of the cable area corresponding to the sampling information.

[0128] The visual accommodation information determination module 408 is used to determine the visual accommodation information of the cable area according to the information difference when the information difference between visual feature information and comprehensive feature information does not meet the information difference condition.

[0129] The visual adjustment module 410 is used to perform visual adjustment on the cable area based on visual adjustment information and return the steps of acquiring multi-frame sampling information collected for the cable area until the information difference between each visual feature information and the comprehensive feature information meets the information difference condition.

[0130] In an exemplary embodiment, the comprehensive feature information includes a first luminance and an average luminance variance; the visual feature information includes the average luminance and luminance variance of the sampled information; the information difference includes the luminance information difference and the luminance variance difference value; and the visual accommodation information includes supplemental lighting enhancement information. In this embodiment, the visual accommodation information determination module 408 is further configured to:

[0131] If the difference between the average brightness and the first brightness of the sampled information is negative, and the difference between the brightness variance and the average brightness variance is negative, then it is determined that the difference between the brightness information and the difference between the brightness variance do not meet the information difference condition.

[0132] The supplementary lighting enhancement information for the cable area is determined based on the difference in brightness information; the difference in brightness information is positively correlated with the supplementary lighting enhancement information.

[0133] In an exemplary embodiment, the comprehensive feature information includes a second brightness, where the first brightness is less than the second brightness; the visual accommodation information includes supplemental lighting reduction information. In this embodiment, the visual accommodation information determination module 408 is further configured to:

[0134] If the difference between the average brightness and the second brightness of the sampled information is positive, and the difference between the brightness variance and the average brightness variance is negative, then it is determined that the difference between the brightness information and the difference between the brightness variance do not meet the information difference condition.

[0135] The information on reducing supplementary lighting in the cable area is determined based on the difference in brightness information; the difference in brightness information is inversely correlated with the information on reducing supplementary lighting.

[0136] In an exemplary embodiment, the comprehensive feature information includes a texture threshold, the visual feature information includes texture feature values, and the visual adjustment information includes light ratio adjustment information. In this embodiment, the visual adjustment information determination module 408 further includes:

[0137] The information difference judgment unit is used to determine that the information difference does not meet the information difference condition if the information difference between the texture feature value with sampled information and the texture threshold is negative.

[0138] The light proportion adjustment information determination unit is used to determine the light proportion adjustment information of the cable area based on texture feature values.

[0139] In an exemplary embodiment, the comprehensive feature information further includes the texture median. In this embodiment, the light proportion adjustment information determination unit is specifically used for:

[0140] The ratio of texture feature value to texture median is used to determine the proportion of missing texture information in the sampled information; the ratio is inversely correlated with the proportion of missing texture.

[0141] Based on the proportion of texture loss, determine the light ratio adjustment information for the cable area.

[0142] In an exemplary embodiment, the sampling information acquisition module 402 is specifically used for:

[0143] Perform area detection on the cable area to determine the sampling range for sampling in the cable area;

[0144] Sampling is performed according to the sampling range to obtain multi-frame sampling information collected for the cable area.

[0145] Each module in the aforementioned visual adjustment device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0146] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a visual adjustment method. The display unit of the computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0147] Those skilled in the art will understand that Figure 5The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0148] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0149] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0150] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described above.

[0151] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0152] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0153] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0154] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A visual accommodation method, characterized in that, The method includes: Acquire multi-frame sampling information for the cable area; Based on the sampling information, extract comprehensive feature information of the cable region; For each frame of the sampling information, visual feature analysis is performed on the cable region based on the sampling information to obtain visual feature information of the cable region corresponding to the sampling information; If the information difference between the visual feature information and the comprehensive feature information does not meet the information difference condition, the visual adjustment information of the cable area is determined according to the information difference. Based on the visual adjustment information, the cable area is visually adjusted, and the process returns to the step of obtaining multi-frame sampling information collected for the cable area, until the information difference between each visual feature information and the comprehensive feature information satisfies the information difference condition.

2. The method according to claim 1, characterized in that, The comprehensive feature information includes a first brightness and an average brightness variance; the visual feature information includes the average brightness and brightness variance of the sampled information; the information difference includes the brightness information difference and the brightness variance difference value; the visual accommodation information includes supplemental lighting enhancement information; When the information difference between visual feature information and the comprehensive feature information does not meet the information difference condition, determining the visual adjustment information of the cable area according to the information difference includes: If the difference between the average brightness of the sampled information and the brightness of the first brightness is negative, and the difference between the brightness variance and the average brightness variance is negative, then it is determined that the difference between the brightness information and the difference between the brightness variance do not satisfy the information difference condition. The supplementary lighting enhancement information for the cable area is determined based on the brightness information difference; the brightness information difference is positively correlated with the supplementary lighting enhancement information.

3. The method according to claim 2, characterized in that, The comprehensive feature information includes a second brightness, wherein the first brightness is less than the second brightness; the visual accommodation information includes supplemental lighting reduction information. When the information difference between the visual feature information and the comprehensive feature information does not meet the information difference condition, determining the visual adjustment information of the cable region according to the information difference includes: If the difference between the average brightness of the sampled information and the brightness of the second brightness is positive, and the difference between the brightness variance and the average brightness variance is negative, then it is determined that the difference between the brightness information and the difference between the brightness variance do not satisfy the information difference condition. The supplementary lighting reduction information for the cable area is determined based on the brightness information difference; the brightness information difference is inversely correlated with the supplementary lighting reduction information.

4. The method according to claim 1, characterized in that, The comprehensive feature information includes a texture threshold, and the visual feature information includes texture feature values; the visual adjustment information includes light ratio adjustment information. When the information difference between visual feature information and the comprehensive feature information does not meet the information difference condition, determining the visual adjustment information of the cable area according to the information difference includes: If the information difference between the texture feature value of the sampled information and the texture threshold is negative, then it is determined that the information difference does not satisfy the information difference condition. Based on the texture feature values, the light ratio adjustment information of the cable area is determined.

5. The method according to claim 4, characterized in that, The comprehensive feature information also includes the texture median; the step of determining the light proportion adjustment information of the cable region based on the texture feature value includes: The texture missing ratio of the sampled information is determined based on the ratio of the texture feature value to the texture median; the ratio is inversely correlated with the texture missing ratio. Based on the texture loss ratio, determine the light ratio adjustment information for the cable area.

6. The method according to claim 1, characterized in that, The acquisition of multi-frame sampling information collected for the cable area includes: Perform area detection on the cable area to determine the sampling range for sampling the cable area; Sampling is performed according to the sampling range to obtain multiple frames of sampling information collected for the cable area.

7. A visual adjustment device, characterized in that, The device includes: The sampling information acquisition module is used to acquire multi-frame sampling information collected from the cable area; The feature information extraction module is used to extract comprehensive feature information of the cable region based on the sampling information. The information analysis module is used to perform visual feature analysis on the cable region based on the sampling information for each frame, and obtain visual feature information of the cable region corresponding to the sampling information; The visual accommodation information determination module is used to determine the visual accommodation information of the cable area according to the information difference when the information difference between the visual feature information and the comprehensive feature information does not meet the information difference condition. The visual adjustment module is used to perform visual adjustment on the cable area based on the visual adjustment information, and return to the step of obtaining multi-frame sampling information collected for the cable area until the information difference between each visual feature information and the comprehensive feature information satisfies the information difference condition.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images