Method and device for visual fusion of ultraviolet image and visible light image, computer equipment, readable storage medium and program product

Abstract

The application relates to a method and device for visualizing fusion of ultraviolet images and visible light images, equipment, a storage medium and a program product, and relates to the technical field of power safety detection. The method can improve the accuracy of image registration. The method comprises the following steps: extracting an ultraviolet discharge corona region from an ultraviolet image, and calculating the pixel area of the ultraviolet discharge corona region; inputting a detector gain, a detection distance and the pixel area into a trained neural network model to obtain a discharge pulse current intensity and determine an ultraviolet discharge intensity grade; according to an imaging field of view offset, performing registration on the ultraviolet image and the visible light image, and performing pixel-level image fusion based on local content weighting on the registered ultraviolet image and visible light image to obtain an initial fusion image; superimposing the detector gain, the detection distance, the discharge pulse current intensity and the ultraviolet discharge intensity grade on the initial fusion image to obtain a target fusion image, and visually displaying the target fusion image.

Description

Technical Field

[0001] This application relates to the field of power safety detection technology, and in particular to a visualization fusion method, apparatus, computer equipment, computer-readable storage medium, and computer program product for ultraviolet and visible light images. Background Technology

[0002] In the discharge detection of insulators in power systems, ultraviolet (UV) detection using discharge corona is a common method. Since the arc or corona caused by insulator discharge generates UV light during the discharge process, UV detection can identify whether a discharge has occurred in the insulator, thus achieving non-contact safety detection of the insulator.

[0003] Traditional techniques primarily utilize dual-channel ultraviolet / visible light detection systems to detect corona discharge. One channel detects the visible light signal for imaging, while the other detects the ultraviolet light signal to image the corona discharge region. The image of the discharge region is then superimposed on the visible light channel image to obtain a fused ultraviolet image. Subsequent image processing is then used to assess the severity of the corona discharge. However, during image registration between the ultraviolet and visible light detectors, the different spatial resolutions of these detectors lead to differences in detail between the two images, making direct image registration difficult. Inaccurate alignment of image details and contour areas results in low registration accuracy. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium, and computer program product for the visualization fusion of ultraviolet and visible light images, addressing the aforementioned technical problems.

[0005] Firstly, this application provides a visualization fusion method for ultraviolet and visible light images, including:

[0006] Acquire ultraviolet and visible light images detected by a preset dual-channel detector, extract the ultraviolet discharge corona region from the ultraviolet image, and calculate the pixel area of ​​the ultraviolet discharge corona region;

[0007] The detector gain, detection distance, and pixel area of ​​the dual-channel detector are input into a trained neural network model to obtain the discharge pulse current intensity output by the neural network model, and the ultraviolet discharge intensity level is determined based on the discharge pulse current intensity.

[0008] According to the preset imaging field of view offset, the ultraviolet image and the visible light image are registered, and the registered ultraviolet image and the visible light image are fused at the pixel level based on local content weighting to obtain an initial fused image;

[0009] The detector gain, the detection distance, the discharge pulse current intensity, and the ultraviolet discharge intensity level are superimposed on the initial fused image to obtain the target fused image, which is then visualized.

[0010] In one embodiment, the step of extracting the ultraviolet discharge corona region from the ultraviolet image and calculating the pixel area of ​​the ultraviolet discharge corona region includes:

[0011] According to a preset edge detection algorithm, the coordinate points of the bright spot edge contour in the ultraviolet image are extracted by gradient intensity and direction; the coordinate points of the bright spot edge contour are connected to obtain the edge contour of the bright spot image; the number of target pixels within the range of the edge contour of the bright spot image is counted to obtain the pixel area.

[0012] In one embodiment, before registering the ultraviolet image and the visible light image according to a preset imaging field of view offset, the method further includes:

[0013] The imaging array parameters of the visible light sensor and the ultraviolet imaging sensor are obtained, and the target parameters of the observed object are obtained. Based on the imaging array parameters and the target parameters, the imaging area of ​​the observed object on the visible light sensor and the ultraviolet imaging sensor is determined. The distance baseline between the visible light camera and the ultraviolet camera is determined. Based on the distance baseline and with the field of view center of the ultraviolet camera as the origin, the imaging field of view offset of the visible light camera is calculated as the preset imaging field of view offset.

[0014] In one embodiment, registering the ultraviolet image and the visible light image according to a preset imaging field of view offset includes:

[0015] Based on the preset imaging field of view offset, the ultraviolet image and the visible light image are offset calibrated; according to the imaging area, the offset calibrated ultraviolet image and the visible light image are registered and aligned to obtain the registered ultraviolet image and the visible light image.

[0016] In one embodiment, the step of performing pixel-level image fusion based on local content weighting on the registered ultraviolet image and visible light image to obtain an initial fused image includes:

[0017] Edge detection is performed on the ultraviolet image and the visible light image respectively to obtain corresponding edge maps; based on the edge maps, the current pixel value and the corresponding pixel weighting coefficient of each pixel are determined, and a weighted calculation is performed according to the pixel weighting coefficient and the current pixel value to obtain the fused target pixel value; the initial fused image is determined according to the target pixel value.

[0018] In one embodiment, determining the current pixel value and corresponding pixel weighting coefficient of each pixel based on the edge map includes:

[0019] The local mean of each pixel is obtained, and the local standard deviation is determined based on the local mean. A local contrast map is calculated for the edge map using the local standard deviation. The edge map and the local contrast map are combined to obtain a fusion weight map corresponding to the ultraviolet image and the visible light image. In the fusion weight map, the current pixel value of each pixel and the corresponding pixel weighting coefficient are determined.

[0020] Secondly, this application also provides a visualization fusion device for ultraviolet images and visible light images, comprising:

[0021] The image acquisition module is used to acquire ultraviolet images and visible light images detected by a preset dual-channel detector, extract the ultraviolet discharge corona region from the ultraviolet image, and calculate the pixel area of ​​the ultraviolet discharge corona region.

[0022] The model processing module is used to input the detector gain, detection distance and pixel area of ​​the dual-channel detector into the trained neural network model to obtain the discharge pulse current intensity output by the neural network model, and determine the ultraviolet discharge intensity level based on the discharge pulse current intensity.

[0023] The image registration module is used to register the ultraviolet image and the visible light image according to a preset imaging field offset, and to perform pixel-level image fusion based on local content weighting on the registered ultraviolet image and the visible light image to obtain an initial fused image.

[0024] The image display module is used to overlay the detector gain, the detection distance, the discharge pulse current intensity, and the ultraviolet discharge intensity level onto the initial fused image to obtain a target fused image, and to visualize the target fused image.

[0025] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0026] A preset dual-channel detector acquires ultraviolet (UV) and visible light images. The UV discharge corona region is extracted from the UV image, and its pixel area is calculated. The detector gain, detection distance, and pixel area of ​​the dual-channel detector are input into a trained neural network model to obtain the discharge pulse current intensity output by the neural network model. Based on the discharge pulse current intensity, the UV discharge intensity level is determined. The UV and visible light images are registered according to a preset imaging field of view offset. The registered UV and visible light images are then fused using pixel-level image fusion based on local content weighting to obtain an initial fused image. The detector gain, detection distance, discharge pulse current intensity, and UV discharge intensity level are superimposed on the initial fused image to obtain a target fused image, which is then visualized.

[0027] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0028] A preset dual-channel detector acquires ultraviolet (UV) and visible light images. The UV discharge corona region is extracted from the UV image, and its pixel area is calculated. The detector gain, detection distance, and pixel area of ​​the dual-channel detector are input into a trained neural network model to obtain the discharge pulse current intensity output by the neural network model. Based on the discharge pulse current intensity, the UV discharge intensity level is determined. The UV and visible light images are registered according to a preset imaging field of view offset. The registered UV and visible light images are then fused using pixel-level image fusion based on local content weighting to obtain an initial fused image. The detector gain, detection distance, discharge pulse current intensity, and UV discharge intensity level are superimposed on the initial fused image to obtain a target fused image, which is then visualized.

[0029] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0030] A preset dual-channel detector acquires ultraviolet (UV) and visible light images. The UV discharge corona region is extracted from the UV image, and its pixel area is calculated. The detector gain, detection distance, and pixel area of ​​the dual-channel detector are input into a trained neural network model to obtain the discharge pulse current intensity output by the neural network model. Based on the discharge pulse current intensity, the UV discharge intensity level is determined. The UV and visible light images are registered according to a preset imaging field of view offset. The registered UV and visible light images are then fused using pixel-level image fusion based on local content weighting to obtain an initial fused image. The detector gain, detection distance, discharge pulse current intensity, and UV discharge intensity level are superimposed on the initial fused image to obtain a target fused image, which is then visualized.

[0031] The aforementioned visualization fusion method, apparatus, computer equipment, computer-readable storage medium, and computer program product for ultraviolet and visible light images extract the ultraviolet discharge corona region from the detected ultraviolet image, calculate the pixel area of ​​the ultraviolet discharge corona region, and then determine the discharge pulse current intensity and ultraviolet discharge intensity level by combining detector gain, detection distance, and pixel area. Then, based on a preset imaging field of view offset, the visible light and ultraviolet images are rapidly registered. An initial fused image is obtained through pixel-level image fusion based on local content weighting. Finally, relevant parameter information is superimposed on the initial fused image to obtain the target fused image. This simultaneously achieves the effect of visually displaying the target fused image, thereby reasonably eliminating the differences between the visible light and ultraviolet images, reducing the error generated during registration, and thus improving the accuracy of image registration.

[0032] Compared with the prior art, the implementation scheme of this application has the following significant advantages:

[0033] (1) In view of the shortcomings of traditional algorithms such as wavelet transformation, SIFT feature matching, and mutual information matching used for registration and alignment of visible light and ultraviolet channel imaging data, which consume large amounts of computational resources and take a long time, this application proposes to quickly align the imaging area based on the imaging field offset moment. The alignment operation can be directly applied in the image fusion process without the need for complex iterative calculations or feature extraction and matching processes. The amount of computation is greatly reduced, the efficiency is improved, and the image alignment can be completed quickly to achieve real-time detection and output.

[0034] (2) To address the shortcomings of fixed fusion coefficients (such as 0.5) in traditional pixel fusion and the computational complexity and speed issues caused by the fusion rules of high-frequency subbands, a pixel-level image fusion based on local content weighting is proposed to obtain the fused image. On the one hand, it reduces the computational complexity of traditional transform domain-based image fusion and the distortion problem caused by fixed threshold spatial domain fusion algorithms (such as pixel arithmetic mean). On the other hand, it preserves local details that are highly sensitive to human vision, maintains key information in the original image, improves the accuracy and quality of image fusion, and is conducive to more accurate analysis of the target through subsequent image processing. Attached Figure Description

[0035] 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.

[0036] Figure 1 This is an application environment diagram of a visualization fusion method for ultraviolet and visible light images in one embodiment;

[0037] Figure 2 This is a flowchart illustrating a visualization fusion method for ultraviolet and visible light images in one embodiment;

[0038] Figure 3 This is a flowchart illustrating the pixel area calculation steps in one embodiment;

[0039] Figure 4 This is a flowchart illustrating the image fusion steps in one embodiment;

[0040] Figure 5 This is a flowchart illustrating a visualization fusion method for ultraviolet and visible light images in a specific embodiment.

[0041] Figure 6 This is a structural block diagram of a visualization fusion device for ultraviolet and visible light images in one embodiment;

[0042] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0043] 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.

[0044] The visualization fusion method for ultraviolet and visible light images provided in this application embodiment can be applied to, for example... Figure 1 The application environment shown depicts a scenario where the terminal communicates with the server via a network. The data storage system stores the data that the server needs to process. This data storage system can be integrated onto the server, or it can be hosted in the cloud or on other network servers.

[0045] Specifically, the visualization fusion method for ultraviolet and visible light images provided in this application embodiment can be executed by a terminal.

[0046] For example, the terminal acquires ultraviolet and visible light images detected by a preset dual-channel detector, extracts the ultraviolet discharge corona region from the ultraviolet image, and calculates the pixel area of ​​the ultraviolet discharge corona region; the terminal inputs the detector gain, detection distance, and pixel area of ​​the dual-channel detector into a trained neural network model to obtain the discharge pulse current intensity output by the neural network model, and determines the ultraviolet discharge intensity level based on the discharge pulse current intensity; the terminal registers the ultraviolet and visible light images according to a preset imaging field of view offset, and performs pixel-level image fusion based on local content weighting on the registered ultraviolet and visible light images to obtain an initial fused image; the terminal superimposes the detector gain, detection distance, discharge pulse current intensity, and ultraviolet discharge intensity level onto the initial fused image to obtain a target fused image, and visualizes the target fused image.

[0047] In such Figure 1 In the application environment shown, the terminal can be, but is not limited to, various personal computers, laptops, smartphones, and tablets. The server can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0048] In one embodiment, such as Figure 2 As shown, a visualization fusion method for ultraviolet and visible light images is provided, which can be applied to... Figure 1 Taking the terminal in the example, the explanation includes the following steps:

[0049] Step S201: Obtain the ultraviolet image and visible light image detected by the preset dual-channel detector, extract the ultraviolet discharge corona region from the ultraviolet image, and calculate the pixel area of ​​the ultraviolet discharge corona region.

[0050] The dual-channel detector can be a detector with a visible light imaging channel and an ultraviolet imaging channel, and the ultraviolet discharge corona region can be a bright spot region of corona or arc discharge in the ultraviolet image.

[0051] It should be noted that the preset dual-channel detector can be installed at a predetermined distance d from the insulator being detected, and can determine an equivalent triangular relationship based on the height h of the insulator.

[0052] Specifically, the terminal detects insulator discharge by controlling the visible light imaging channel and ultraviolet imaging channel of the dual-channel detector, and acquires visible light images and ultraviolet images respectively; the visible light image has a first resolution and the ultraviolet image has a second resolution; then the ultraviolet image is preprocessed (grayscale conversion and noise reduction), and then the ultraviolet discharge corona region is extracted and the pixel area of ​​the ultraviolet discharge corona region is calculated.

[0053] Step S202: Input the detector gain, detection distance and pixel area of ​​the dual-channel detector into the trained neural network model to obtain the discharge pulse current intensity output by the neural network model, and determine the ultraviolet discharge intensity level based on the discharge pulse current intensity.

[0054] The neural network model can be a CNN (Convolutional Neural Network) model, which uses detector gain, detection distance, corona discharge image features (such as pixel area), and discharge pulse current intensity as feature variables, detector gain, detection distance, and pixel area as input features (x1, x2, ..., xn), and discharge pulse current intensity as output (y). By training the CNN network, a prediction model is obtained, and in subsequent use, the discharge pulse current intensity (such as pulse current peak value) can be determined using known detection parameters.

[0055] Specifically, the discharge level intensity can be determined based on the correspondence between the discharge pulse current intensity and the ultraviolet discharge intensity level (indicating the degree of danger of partial discharge) established by the power system or enterprise. That is, based on the impact of the corona and arc generated by the insulator discharge on the safety of the insulator electrical equipment, the peak value of the pulse current at the corresponding stage is divided into different danger levels, which correspond to the ultraviolet discharge intensity level.

[0056] For example, when the peak value of the pulse current is within the first set range [Int1~Int2), corona discharge begins to occur, corresponding to danger level 1, and the ultraviolet discharge intensity level output is level 1; when the peak value of the pulse current is within the second set range [Int1~Int2), the ultraviolet discharge intensity level output is level 2; if it exceeds the Int2 standard, it is defined as level 3 (the highest level).

[0057] Step S203: Register the ultraviolet image and the visible light image according to the preset imaging field offset, and perform pixel-level image fusion based on local content weighting on the registered ultraviolet image and the visible light image to obtain the initial fused image.

[0058] Among them, the imaging field of view offset can be used to represent the deviation between the field of view and the actual imaging system.

[0059] Specifically, the terminal performs offset calibration on the ultraviolet and visible light images based on a preset imaging field offset, and registers and aligns the offset-calibrated ultraviolet and visible light images according to the imaging area to obtain registered ultraviolet and visible light images. Then, based on the rapidly registered visible light image, the corresponding bright spot of the discharge region in the ultraviolet image is fused with it, and the initial fused image is obtained through pixel-level image fusion based on local content weighting.

[0060] Step S204: The detector gain, detection distance, discharge pulse current intensity and ultraviolet discharge intensity level are superimposed on the initial fused image to obtain the target fused image, and the target fused image is visualized.

[0061] Specifically, the terminal overlays parameters such as detector gain, detection distance, discharge pulse current intensity, and ultraviolet discharge intensity level onto the initial fused image to obtain the final target fused image, and then visualizes and displays the target fused image.

[0062] In the aforementioned visualization fusion method for ultraviolet and visible light images, the ultraviolet discharge corona region is extracted from the detected ultraviolet image, the pixel area of ​​the ultraviolet discharge corona region is calculated, and then the discharge pulse current intensity and ultraviolet discharge intensity level are determined by combining the detector gain, detection distance, and pixel area. Then, the visible light image and ultraviolet image are quickly registered according to the preset imaging field offset. An initial fused image is obtained by pixel-level image fusion based on local content weighting. Finally, relevant parameter information is superimposed on the initial fused image to obtain the target fused image. At the same time, the effect of visually displaying the target fused image is achieved, thereby reasonably eliminating the differences between the visible light image and the ultraviolet image, reducing the error generated by the two images during registration, and thus improving the accuracy of image registration.

[0063] In one embodiment, such as Figure 3 As shown, in step S201 above, the ultraviolet discharge corona region is extracted from the ultraviolet image, and the pixel area of ​​the ultraviolet discharge corona region is calculated. Specifically, this includes the following steps:

[0064] Step S301: According to the preset edge detection algorithm, the coordinate points of the bright spot edge contour in the ultraviolet image are extracted by gradient intensity and direction.

[0065] Step S302: Connect the coordinate points of the bright spot edge contour to obtain the bright spot image edge contour.

[0066] Step S303: Count the number of target pixels within the range of the edge contour of the bright spot image to obtain the pixel area.

[0067] Specifically, the terminal extracts the ultraviolet discharge corona region (i.e., the bright spot region of corona or arc discharge in the ultraviolet image) using the Canny algorithm. This includes: extracting the coordinate points of the bright spot edge contour of the discharge region through gradient intensity and direction; then refining the edge contour (e.g., through non-maximum suppression); and finally, further suppressing noise using a double threshold method to filter out noisy lines, resulting in a continuous and clear edge contour of the discharge bright spot image. The pixel area of ​​the ultraviolet discharge corona region is calculated by counting the number of pixels with a value of 1 within the contour area. Furthermore, the terminal combines detector gain, detection distance, and pixel area in a trained neural network model to determine the discharge pulse current intensity and the ultraviolet discharge level intensity.

[0068] In one embodiment, before registering the ultraviolet image and the visible light image according to a preset imaging field offset, the following steps are also included:

[0069] The imaging array parameters of the visible light sensor and the ultraviolet imaging sensor are obtained, and the target parameters of the observed object are obtained. Based on the imaging array parameters and the target parameters, the imaging area of ​​the observed object on the visible light sensor and the ultraviolet imaging sensor is determined. The distance baseline between the visible light camera and the ultraviolet camera is determined. Based on the distance baseline and with the field of view center of the ultraviolet camera as the origin, the imaging field of view offset of the visible light camera is calculated as the preset imaging field of view offset.

[0070] Specifically, the terminal acquires the image array parameters of the photosensitive surfaces of two visible light sensors and an ultraviolet imaging sensor, including the imaging array mu*nu (representing the number of rows and columns of the pixel array of the ultraviolet sensor, respectively) and mr*nr (representing the number of rows and columns of the pixel array of the visible light sensor, respectively), in pixels; the pixel pitch I, in μm; and the focal length f, in mm; then, it determines the relevant parameters of the observed object, including the target distance d, in meters, and the area length L*width W of the observed object; then, based on the imaging array parameters of the ultraviolet and visible light sensors and the relevant parameters of the observed object, it determines the imaging areas Su and Sr of the observed object on the ultraviolet and visible light sensors. The formula for calculating the imaging area is as follows:

[0071] Su1=fu / (Iu*10 -3 )*(L / d); Su2=fu / (Iu*10 -3 )*(W / d)

[0072] Sr1=fr / (Ir*10 -3)*(L / d); Sr2=fr / (Ir*10 -3 )*(W / d)

[0073] Finally, based on the baseline dl between the ultraviolet camera and the visible light camera, and taking the center of the ultraviolet camera's field of view as the origin, the imaging field of view offset of the visible light camera is calculated. The specific calculation formula is as follows:

[0074] ΔF=fr*(dl / 2)*(d / Ir)

[0075] In the above formula, ΔF is the imaging field of view offset, f is the focal length, d is the target distance, and I is the pixel spacing.

[0076] In one embodiment, step S203 above involves registering the ultraviolet image and the visible light image according to a preset imaging field of view offset, specifically including the following steps:

[0077] Based on a preset imaging field of view offset, the ultraviolet and visible light images are offset calibrated; according to the imaging area, the offset calibrated ultraviolet and visible light images are registered and aligned to obtain registered ultraviolet and visible light images.

[0078] Specifically, the terminal obtains a visible light image registered with the ultraviolet image by using the imaging field of view offset of the visible light camera. In the specific registration process, since both sensors are based on parallel light, the terminal first performs offset calibration on the two imaging images based on the imaging field of view offset before registration, and then performs registration and alignment according to the imaging areas Su and Sr of the observed object on the ultraviolet sensor and the visible light sensor, respectively.

[0079] In one embodiment, such as Figure 4 As shown, in step S203 above, pixel-level image fusion based on local content weighting is performed on the registered ultraviolet image and visible light image to obtain an initial fused image. Specifically, this includes the following steps:

[0080] Step S401: Perform edge detection on the ultraviolet image and the visible light image respectively to obtain the corresponding edge maps.

[0081] Step S402: Based on the edge map, determine the current pixel value and the corresponding pixel weighting coefficient of each pixel point, and perform weighted calculation based on the pixel weighting coefficient and the current pixel value to obtain the fused target pixel value.

[0082] Step S403: Determine the initial fused image based on the target pixel value.

[0083] In step S402 above, based on the edge map, the current pixel value and the corresponding pixel weighting coefficient of each pixel are determined, which specifically includes the following steps:

[0084] The local mean of each pixel is obtained, and the local standard deviation is determined based on the local mean. The local contrast map is calculated for the edge map using the local standard deviation. The edge map and the local contrast map are combined to obtain the fusion weight map corresponding to the ultraviolet image and the visible light image. In the fusion weight map, the current pixel value of each pixel and the corresponding pixel weighting coefficient are determined.

[0085] Specifically, based on the rapidly registered visible light image, the terminal performs pixel-level image fusion on the ultraviolet and visible light images. This involves weighting the pixels of the two images to obtain the fused pixel values, thereby determining the fused image. The specific calculation method is as follows:

[0086] IF(x,y)=α*rgb(x,y)+β*uv(x,y)

[0087] In the above formula, α and β represent the pixel weighting coefficients of the visible light image and the ultraviolet image, respectively, and rgb(x,y) and uv(x,y) represent the current pixel value of the corresponding pixel point (x,y) in the visible light image and the ultraviolet image, respectively.

[0088] In this embodiment, to address the shortcomings of fixed fusion coefficients (e.g., a value of 0.5) in traditional pixel fusion and the computational complexity and speed issues caused by fusion rules using high-frequency subbands, a pixel-level image fusion based on local content weighting is proposed to obtain the fused image. On the one hand, this reduces the computational complexity of traditional transform domain-based image fusion and the distortion problems caused by fixed threshold spatial domain fusion algorithms (e.g., pixel arithmetic mean). On the other hand, it preserves local details that are highly sensitive to human vision, maintains key information in the original image, and improves the accuracy and quality of image fusion, which is beneficial for more accurate analysis of the target through subsequent image processing.

[0089] First, the terminal processes the ultraviolet and visible light images using an edge detector to obtain edge maps. For the ultraviolet image, as mentioned above, the bright spots of the discharge region are used as the edge map to determine the edge contour coordinates. For the visible light image, a contour map featuring the insulator surface structure is obtained, and the edge contour coordinates are determined. Then, the edge map (binary image, pixel value 0 or 255) generated by edge detection is normalized to adjust its range to [0, 1]. By highlighting edge regions with higher weights and non-edge regions with lower weights, important structural features are emphasized in the subsequent fusion process.

[0090] In the preprocessed edge map, the terminal calculates the local mean for each pixel using a sliding window, such as 5x5 (or 3x3). The window slides across the entire image, calculating the mean for each pixel, including the pixel and its neighborhood. Then, the local standard deviation is calculated, and the same sliding window is used to calculate the local standard deviation again (including calculating the square of the difference between each pixel and the local mean, and then calculating the local standard deviation). Here, the local standard deviation is a measure of the difference between a pixel value and its local mean. A high standard deviation indicates high contrast around the pixel, related to local detail and edges. Using a local contrast measurement method, a contrast map is calculated for each image using the local standard deviation, and the contrast map is normalized to the range [0, 1].

[0091] Finally, the terminal combines the edge maps and local contrast maps corresponding to the ultraviolet and visible light images, multiplying them to generate the final weight map. This ensures that the weight map values ​​are between [0, 1] and the sum of the weights of the two weight maps is 1 at each pixel location. This results in a fused weight map corresponding to the visible light and ultraviolet images, which is the same size as the original image (the registered visible light image). The value of each pixel represents the importance weight of that pixel location. Therefore, the final weight map is used to weight and calculate each pixel in each image, as described in the formula above. The pixel value at the corresponding location is multiplied by its weight, and the results of the two images are then added together to obtain the final fused image. This achieves the fusion of the bright spot image of the ultraviolet image with the visible light image. After superimposing the detection distance, detection gain, discharge pulse current intensity, and ultraviolet discharge intensity level, a visual output is achieved.

[0092] In one embodiment, such as Figure 5 As shown, a visualization fusion method for ultraviolet and visible light images is provided in a specific embodiment, which includes the following steps:

[0093] Step S501: Obtain the ultraviolet image and visible light image detected by the preset dual-channel detector; extract the coordinate points of the bright spot edge contour in the ultraviolet image by gradient intensity and direction according to the preset edge detection algorithm; connect the coordinate points of the bright spot edge contour to obtain the edge contour of the bright spot image; count the number of target pixels within the range of the edge contour of the bright spot image to obtain the pixel area.

[0094] Step S502: Input the detector gain, detection distance and pixel area of ​​the dual-channel detector into the trained neural network model to obtain the discharge pulse current intensity output by the neural network model, and determine the ultraviolet discharge intensity level based on the discharge pulse current intensity.

[0095] Step S503: Obtain the imaging array parameters of the visible light sensor and the ultraviolet imaging sensor, and obtain the target parameters of the observed object. Based on the imaging array parameters and the target parameters, determine the imaging area of ​​the observed object on the visible light sensor and the ultraviolet imaging sensor. Determine the distance baseline between the visible light camera and the ultraviolet camera. Based on the distance baseline and with the center of the ultraviolet camera's field of view as the origin, calculate the imaging field of view offset of the visible light camera, which is used as the preset imaging field of view offset.

[0096] Step S504: Based on the preset imaging field offset, perform offset calibration on the ultraviolet image and the visible light image; according to the imaging area, register and align the offset-calibrated ultraviolet image and the visible light image to obtain the registered ultraviolet image and the visible light image.

[0097] Step S505: Perform edge detection on the ultraviolet image and the visible light image respectively to obtain the corresponding edge map; obtain the local mean of each pixel, determine the local standard deviation based on the local mean, calculate the local contrast map of the edge map using the local standard deviation; combine the edge map and the local contrast map to obtain the fusion weight map corresponding to the ultraviolet image and the visible light image.

[0098] Step S506: In the fusion weight map, determine the current pixel value and the corresponding pixel weighting coefficient of each pixel. Perform weighted calculation based on the pixel weighting coefficient and the current pixel value to obtain the fused target pixel value; determine the initial fused image based on the target pixel value.

[0099] Step S507: The detector gain, detection distance, discharge pulse current intensity and ultraviolet discharge intensity level are superimposed on the initial fused image to obtain the target fused image, and the target fused image is visualized.

[0100] The beneficial effects of the above embodiments are as follows:

[0101] This application extracts the ultraviolet discharge corona region from the detected ultraviolet image, calculates the pixel area of ​​the ultraviolet discharge corona region, and then determines the discharge pulse current intensity and ultraviolet discharge intensity level by combining detector gain, detection distance, and pixel area. Then, it performs rapid registration of visible light and ultraviolet images according to a preset imaging field offset, and obtains an initial fused image by pixel-level image fusion based on local content weighting. Finally, relevant parameter information is superimposed on the initial fused image to obtain the target fused image, and the effect of visually displaying the target fused image is achieved. This effectively eliminates the differences between visible light and ultraviolet images, reduces the error generated during the registration of the two images, and thus improves the accuracy of image registration.

[0102] It should be understood that although the steps in the flowcharts of the embodiments described above 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 embodiments described above 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.

[0103] Based on the same inventive concept, this application also provides an ultraviolet and visible light image visualization fusion apparatus for implementing the above-described method for visually fusing ultraviolet and visible light images. The solution provided by this apparatus is similar to the solution described in the above-described method. Therefore, the specific limitations of one or more embodiments of the ultraviolet and visible light image visualization fusion apparatus provided below can be found in the limitations of the ultraviolet and visible light image visualization fusion method described above, and will not be repeated here.

[0104] In one exemplary embodiment, such as Figure 6 As shown, a visualization fusion device for ultraviolet and visible light images is provided, comprising:

[0105] The image acquisition module 601 is used to acquire ultraviolet and visible light images detected by a preset dual-channel detector, extract the ultraviolet discharge corona region from the ultraviolet image, and calculate the pixel area of ​​the ultraviolet discharge corona region.

[0106] The model processing module 602 is used to input the detector gain, detection distance and pixel area of ​​the dual-channel detector into the trained neural network model to obtain the discharge pulse current intensity output by the neural network model, and to determine the ultraviolet discharge intensity level based on the discharge pulse current intensity.

[0107] The image registration module 603 is used to register the ultraviolet image and the visible light image according to the preset imaging field offset, and to perform pixel-level image fusion based on local content weighting on the registered ultraviolet image and the visible light image to obtain an initial fused image.

[0108] The image display module 604 is used to overlay detector gain, detection distance, discharge pulse current intensity and ultraviolet discharge intensity level on the initial fused image to obtain the target fused image and to visualize the target fused image.

[0109] In one embodiment, the image acquisition module 601 is further configured to extract the coordinate points of the bright spot edge contour in the ultraviolet image by gradient intensity and direction according to a preset edge detection algorithm; connect the coordinate points of the bright spot edge contour to obtain the edge contour of the bright spot image; and count the number of target pixels within the range of the edge contour of the bright spot image to obtain the pixel area.

[0110] In one embodiment, the visualization fusion device for ultraviolet and visible light images further includes an information preparation module, used to acquire the imaging array parameters of the visible light sensor and the ultraviolet imaging sensor, and acquire the target parameters of the observed object; determine the imaging area of ​​the observed object on the visible light sensor and the ultraviolet imaging sensor based on the imaging array parameters and the target parameters; determine the distance baseline between the visible light camera and the ultraviolet camera; and calculate the imaging field of view offset of the visible light camera based on the distance baseline and with the center of the field of view of the ultraviolet camera as the origin, as a preset imaging field of view offset.

[0111] In one embodiment, the image registration module 603 is further configured to perform offset calibration on the ultraviolet image and the visible light image based on a preset imaging field offset; and to register and align the offset-calibrated ultraviolet image and the visible light image according to the imaging area to obtain the registered ultraviolet image and the visible light image.

[0112] In one embodiment, the image registration module 603 is further configured to perform edge detection on the ultraviolet image and the visible light image respectively to obtain corresponding edge maps; based on the edge maps, determine the current pixel value of each pixel and the corresponding pixel weighting coefficient; perform weighted calculation based on the pixel weighting coefficient and the current pixel value to obtain the fused target pixel value; and determine the initial fused image based on the target pixel value.

[0113] In one embodiment, the image registration module 603 is further configured to obtain the local mean of each pixel, determine the local standard deviation based on the local mean, calculate the local contrast map of the edge map using the local standard deviation, combine the edge map and the local contrast map to obtain the fusion weight map corresponding to the ultraviolet image and the visible light image, and determine the current pixel value and the corresponding pixel weighting coefficient of each pixel in the fusion weight map.

[0114] The modules in the aforementioned visualization fusion device for ultraviolet and visible light images 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 corresponding operations of each module.

[0115] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7 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 executed by the processor, the computer program implements a visualization fusion method for ultraviolet and visible light images. The display unit is used to form a visually visible image and can be a display screen, projection device, or 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.

[0116] Those skilled in the art will understand that Figure 7 The 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.

[0117] In one embodiment, a computer device is also 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 in the above method embodiments.

[0118] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0119] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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 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 method for visually fusing ultraviolet and visible light images, characterized in that, The method includes: Acquire ultraviolet and visible light images detected by a preset dual-channel detector, extract the ultraviolet discharge corona region from the ultraviolet image, and calculate the pixel area of ​​the ultraviolet discharge corona region; The detector gain, detection distance, and pixel area of ​​the dual-channel detector are input into a trained neural network model to obtain the discharge pulse current intensity output by the neural network model, and the ultraviolet discharge intensity level is determined based on the discharge pulse current intensity. Based on a preset imaging field of view offset, the ultraviolet image and the visible light image are registered. Edge detection is then performed on the registered ultraviolet and visible light images to obtain corresponding edge maps. The edge maps are normalized to adjust their range to [0, 1]. In the preprocessed edge maps, the local mean of each pixel is calculated. The local mean of each pixel is obtained, and the local standard deviation is determined based on the local mean. A local contrast map is calculated on the edge maps using the local standard deviation, and the local contrast map is normalized to [0, 1]. Within the range of [1]; the edge map and the local contrast map are combined, and their product is used to generate the final weight map, ensuring that the value of the weight map is between [0, 1] and the sum of the weights of the two weight maps is 1 at each pixel position, thus obtaining the fused weight map corresponding to the visible light image and the ultraviolet image; in the fused weight map, the current pixel value and the corresponding pixel weighting coefficient of each pixel point are determined; weighted calculation is performed according to the pixel weighting coefficient and the current pixel value to obtain the fused target pixel value; the initial fused image is determined according to the target pixel value; The detector gain, the detection distance, the discharge pulse current intensity, and the ultraviolet discharge intensity level are superimposed on the initial fused image to obtain the target fused image, which is then visualized.

2. The method according to claim 1, characterized in that, The step of extracting the ultraviolet discharge corona region from the ultraviolet image and calculating the pixel area of ​​the ultraviolet discharge corona region includes: According to the preset edge detection algorithm, the coordinate points of the bright spot edge contour in the ultraviolet image are extracted by gradient intensity and direction; Connect the coordinate points of the bright spot edge contour to obtain the bright spot image edge contour; The number of target pixels is counted within the edge contour of the bright spot image to obtain the pixel area.

3. The method according to claim 1, characterized in that, Before registering the ultraviolet image and the visible light image according to a preset imaging field offset, the method further includes: The imaging array parameters of the visible light sensor and the ultraviolet imaging sensor are obtained, and the target parameters of the observed object are obtained. Based on the imaging array parameters and the target parameters, the imaging area of ​​the observed object on the visible light sensor and the ultraviolet imaging sensor is determined. Determine the distance baseline between the visible light camera and the ultraviolet camera. Based on the distance baseline and taking the field of view center of the ultraviolet camera as the origin, calculate the imaging field of view offset of the visible light camera, which is then used as the preset imaging field of view offset.

4. The method according to claim 3, characterized in that, The registration of the ultraviolet image and the visible light image according to a preset imaging field of view offset includes: Based on the preset imaging field of view offset, the ultraviolet image and the visible light image are offset calibrated. Based on the imaging area, the offset-calibrated ultraviolet image and visible light image are registered and aligned to obtain the registered ultraviolet image and visible light image.

5. A visualization fusion device for ultraviolet and visible light images, characterized in that, The device includes: The image acquisition module is used to acquire ultraviolet and visible light images detected by a preset dual-channel detector, extract the ultraviolet discharge corona region from the ultraviolet image, and calculate the pixel area of ​​the ultraviolet discharge corona region. The model processing module is used to input the detector gain, detection distance and pixel area of ​​the dual-channel detector into the trained neural network model to obtain the discharge pulse current intensity output by the neural network model, and determine the ultraviolet discharge intensity level based on the discharge pulse current intensity. The image registration module is used to register the ultraviolet image and the visible light image according to a preset imaging field of view offset; to perform edge detection on the registered ultraviolet image and the visible light image respectively to obtain corresponding edge maps; to normalize the edge maps to adjust their range to [0, 1]; to calculate the local mean of each pixel in the preprocessed edge maps; to obtain the local mean of each pixel; to determine the local standard deviation based on the local mean; to calculate the local contrast map of the edge maps using the local standard deviation; and to normalize the local contrast map to [0, 1]. Within the range of [1]; the edge map and the local contrast map are combined, and their product is used to generate the final weight map, ensuring that the value of the weight map is between [0, 1] and the sum of the weights of the two weight maps is 1 at each pixel position, thus obtaining the fused weight map corresponding to the visible light image and the ultraviolet image; in the fused weight map, the current pixel value and the corresponding pixel weighting coefficient of each pixel point are determined; weighted calculation is performed according to the pixel weighting coefficient and the current pixel value to obtain the fused target pixel value; the initial fused image is determined according to the target pixel value; The image display module is used to overlay the detector gain, the detection distance, the discharge pulse current intensity, and the ultraviolet discharge intensity level onto the initial fused image to obtain a target fused image, and to visualize the target fused image.

6. 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 4.

7. 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 4.

8. 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 4.

Images