Corona detection method, device, computer equipment, storage medium and program product

Abstract

The present application relates to a corona detection method, device, computer equipment, storage medium and program product. The method comprises: obtaining a continuous multi-frame solar-blind ultraviolet image; determining the number of times the pixel value of each pixel in the multi-frame solar-blind ultraviolet image is equal to zero; constructing a Poisson probability map of the multi-frame solar-blind ultraviolet image according to the probability function of the Poisson distribution and the number of times the pixel value of each pixel in the multi-frame solar-blind ultraviolet image is equal to zero; constructing a Gaussian intensity map of the multi-frame solar-blind ultraviolet image according to the Gaussian model and the pixel value of each pixel in each frame solar-blind ultraviolet image; determining the corona detection results of the multi-frame solar-blind ultraviolet image according to the Poisson probability map and the Gaussian intensity map. The present method can obtain accurate corona detection results.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a corona detection method, device, computer equipment, storage medium and program product. Background Art

[0002] With the development of solar-blind UV detectors, the application of solar-blind UV imaging technology in the field of power fault detection has also received more and more attention. Compared with traditional detection methods (such as infrared imaging detection, pulse current detection, acoustic detection, and UV pulse detection, etc.), solar-blind UV corona detection has the characteristics of high sensitivity and high detection rate, so it has irreplaceable advantages in the field of power fault detection.

[0003] However, due to the large scattering of the ultraviolet band and the pulsed characteristics of corona discharge, the ultraviolet corona signal will be distributed discretely in the image and discontinuous in the time domain. Therefore, the ultraviolet sequence image will contain a large number of bright spots with discrete distribution, continuous flashing and constantly changing positions, making it difficult to quickly and accurately locate the ultraviolet corona target and judge the discharge intensity. The current detection methods are all based on image morphology and other methods for ultraviolet corona target detection, which will result in low accuracy of corona detection results. Summary of the invention

[0004] Based on this, it is necessary to provide a corona detection method, device, computer equipment, storage medium and program product to address the above technical problems, so as to obtain accurate corona detection results.

[0005] In a first aspect, the present application provides a corona detection method, the method comprising:

[0006] Acquire continuous multi-frame solar-blind UV images;

[0007] Determine the number of times the pixel value of each pixel in multiple frames of solar-blind ultraviolet images is equal to zero;

[0008] According to the probability function of Poisson distribution and the number of times that the pixel value of each pixel point in the multi-frame solar-blind ultraviolet image is equal to zero, a Poisson probability map of the multi-frame solar-blind ultraviolet image is constructed;

[0009] According to the Gaussian model and the pixel value of each pixel point in each frame of the solar-blind ultraviolet image, a Gaussian intensity mapping diagram of multiple frames of solar-blind ultraviolet images is constructed;

[0010] The corona detection results of multiple frames of solar-blind UV images are determined based on the Poisson probability map and the Gaussian intensity map.

[0011] In one embodiment, a Poisson probability map of multiple frames of solar-blind ultraviolet images is constructed based on a probability function of a Poisson distribution and the number of times that the pixel value of each pixel in the multiple frames of solar-blind ultraviolet images is equal to zero, including:

[0012] According to the number of times the pixel value of each pixel in the multi-frame solar-blind ultraviolet image is equal to zero and the total number of frames of the multi-frame solar-blind ultraviolet image, the probability that the pixel value of each pixel is equal to zero is determined; according to the probability that the pixel value of each pixel is equal to zero, a probability statistical graph is constructed; according to the probability statistical graph and the probability function of the Poisson distribution, a Poisson probability mapping graph of the multi-frame solar-blind ultraviolet image is constructed.

[0013] In one embodiment, a Gaussian intensity map of multiple frames of solar-blind ultraviolet images is constructed according to a Gaussian model and a pixel value of each pixel in each frame of solar-blind ultraviolet images, including:

[0014] According to the Gaussian model and the pixel value of each pixel point in each frame of the day-blind ultraviolet image, the Gaussian intensity mapping map corresponding to each frame of the day-blind ultraviolet image is determined; the Gaussian intensity mapping maps corresponding to each frame of the day-blind ultraviolet image are accumulated to obtain the Gaussian intensity mapping maps of multiple frames of the day-blind ultraviolet image.

[0015] In one embodiment, determining the corona detection results of multiple frames of solar-blind ultraviolet images according to the Poisson probability map and the Gaussian intensity map includes:

[0016] According to the Poisson probability map and the Gaussian intensity map, the saliency map corresponding to the multi-frame solar-blind ultraviolet image is constructed; the maximum inter-class variance method is used to binarize the saliency map; according to the binarized saliency map, the corona detection results of the multi-frame solar-blind ultraviolet image are determined.

[0017] In one embodiment, constructing a saliency map corresponding to multiple frames of solar-blind ultraviolet images according to a Poisson probability map and a Gaussian intensity map includes:

[0018] The product of the Poisson probability map and the Gaussian intensity map is used as the saliency map corresponding to multiple frames of solar-blind ultraviolet images.

[0019] In one embodiment, acquiring a continuous plurality of frames of solar-blind ultraviolet images includes:

[0020] The continuous multi-frame original images extracted from the solar-blind ultraviolet video stream are normalized to obtain continuous multi-frame solar-blind ultraviolet images.

[0021] In a second aspect, the present application also provides a corona detection device, the device comprising:

[0022] An image acquisition module, used for acquiring continuous multi-frame solar-blind ultraviolet images;

[0023] A number determination module is used to determine the number of times the pixel value of each pixel point in multiple frames of solar-blind ultraviolet images is equal to zero;

[0024] The first construction module is used to construct a Poisson probability map of the multiple frames of solar-blind ultraviolet images according to a probability function of Poisson distribution and the number of times that the pixel value of each pixel point in the multiple frames of solar-blind ultraviolet images is equal to zero;

[0025] The second construction module is used to construct a Gaussian intensity map of multiple frames of solar-blind ultraviolet images according to the Gaussian model and the pixel value of each pixel point in each frame of solar-blind ultraviolet image;

[0026] The result determination module is used to determine the corona detection results of multiple frames of solar-blind ultraviolet images according to the Poisson probability map and the Gaussian intensity map.

[0027] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0028] Acquire continuous multi-frame solar-blind UV images;

[0029] Determine the number of times the pixel value of each pixel in multiple frames of solar-blind ultraviolet images is equal to zero;

[0030] According to the probability function of Poisson distribution and the number of times that the pixel value of each pixel point in the multi-frame solar-blind ultraviolet image is equal to zero, a Poisson probability map of the multi-frame solar-blind ultraviolet image is constructed;

[0031] According to the Gaussian model and the pixel value of each pixel point in each frame of the solar-blind ultraviolet image, a Gaussian intensity mapping diagram of multiple frames of solar-blind ultraviolet images is constructed;

[0032] The corona detection results of multiple frames of solar-blind UV images are determined based on the Poisson probability map and the Gaussian intensity map.

[0033] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0034] Acquire continuous multi-frame solar-blind UV images;

[0035] Determine the number of times the pixel value of each pixel in multiple frames of solar-blind ultraviolet images is equal to zero;

[0036] According to the probability function of Poisson distribution and the number of times that the pixel value of each pixel point in the multi-frame solar-blind ultraviolet image is equal to zero, a Poisson probability map of the multi-frame solar-blind ultraviolet image is constructed;

[0037] According to the Gaussian model and the pixel value of each pixel point in each frame of the solar-blind ultraviolet image, a Gaussian intensity mapping diagram of multiple frames of solar-blind ultraviolet images is constructed;

[0038] The corona detection results of multiple frames of solar-blind UV images are determined based on the Poisson probability map and the Gaussian intensity map.

[0039] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0040] Acquire continuous multi-frame solar-blind UV images;

[0041] Determine the number of times the pixel value of each pixel in multiple frames of solar-blind ultraviolet images is equal to zero;

[0042] According to the probability function of Poisson distribution and the number of times that the pixel value of each pixel point in the multi-frame solar-blind ultraviolet image is equal to zero, a Poisson probability map of the multi-frame solar-blind ultraviolet image is constructed;

[0043] According to the Gaussian model and the pixel value of each pixel point in each frame of the solar-blind ultraviolet image, a Gaussian intensity mapping diagram of multiple frames of solar-blind ultraviolet images is constructed;

[0044] The corona detection results of multiple frames of solar-blind UV images are determined based on the Poisson probability map and the Gaussian intensity map.

[0045] The above-mentioned corona detection method, device, computer equipment, storage medium and program product, by combining the number of times the pixel value of each pixel point in multiple frames of day-blind ultraviolet images is equal to zero with the probability function of Poisson distribution, constructs a Poisson probability map of multiple frames of day-blind ultraviolet images; further, by combining the Gaussian model with the pixel value of each pixel point in each frame of day-blind ultraviolet images, constructs a Gaussian intensity map of multiple frames of day-blind ultraviolet images; then, based on the Poisson probability map and the Gaussian intensity map, realizes multi-dimensional analysis of multiple frames of day-blind ultraviolet images, and obtains the corona detection results of multiple frames of day-blind ultraviolet images. The above-mentioned scheme, by introducing Poisson distribution and Gaussian model, realizes ultraviolet corona target detection from two dimensions of signal frequency and signal intensity, making the ultraviolet corona target clearer and ensuring the accuracy of the corona detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1This is an application environment diagram of a corona detection method provided in an embodiment of the present application;

[0048] Figure 2 A schematic diagram of a corona detection method provided in an embodiment of the present application;

[0049] Figure 3 A schematic diagram of a process for constructing a Poisson probability map provided in an embodiment of the present application;

[0050] Figure 4 A schematic diagram of a process for constructing a Gaussian intensity map provided in an embodiment of the present application;

[0051] Figure 5 A schematic diagram of a process for determining a corona detection result provided in an embodiment of the present application;

[0052] Figure 6 This is a comparison diagram of the effects of binarization provided in an embodiment of the present application;

[0053] Figure 7 A schematic diagram of a process of another corona detection method provided in an embodiment of the present application;

[0054] Figure 8 A structural block diagram of a corona detection device provided in an embodiment of the present application;

[0055] Fig. 9 It is a structural block diagram of another corona detection device provided in an embodiment of the present application;

[0056] Fig.10 This is a diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] The corona detection method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The terminal 102 conducts an inspection on site, captures images and videos of the site during the inspection, and sends the images and videos to the server 104; then, the server 104 can process the received images and videos, and obtain continuous multi-frame day-blind ultraviolet images; further, the server 104 can analyze and process the continuous multi-frame day-blind ultraviolet images, and finally obtain the corresponding corona detection results. Among them, the terminal 102 can be, but is not limited to, various ultraviolet cameras, day-blind ultraviolet detectors, and smart devices. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0059] In an exemplary embodiment, Figure 2 As shown, a corona detection method is provided, which is applied to Figure 1 Taking the server 104 in the example as an example, the following steps may be included:

[0060] S201, acquiring multiple frames of continuous solar-blind ultraviolet images.

[0061] The solar-blind ultraviolet image may be an image captured by a solar-blind ultraviolet camera or a solar-blind ultraviolet detector. The embodiment of the present application does not specifically limit the device for capturing the solar-blind ultraviolet image.

[0062] Exemplarily, the original solar-blind ultraviolet image or video taken by a solar-blind ultraviolet camera or a solar-blind ultraviolet detector or other equipment is intercepted and processed to obtain continuous multi-frame solar-blind ultraviolet images.

[0063] S202, determining the number of times the pixel value of each pixel point in multiple frames of solar-blind ultraviolet images is equal to zero.

[0064] Exemplarily, each pixel in multiple frames of day-blind ultraviolet images may be statistically analyzed independently. For example, pixel (1, 1) may be statistically analyzed independently, that is, pixel (1, 1) in each frame of day-blind ultraviolet images may be analyzed to determine whether the pixel value of pixel (1, 1) in each frame of day-blind ultraviolet images is equal to 0; after the pixel (1, 1) in all frames of day-blind ultraviolet images is analyzed, the number of times the pixel value of pixel (1, 1) in multiple frames of day-blind ultraviolet images is equal to zero may be determined.

[0065] S203, constructing a Poisson probability map of the multiple frames of solar-blind ultraviolet images according to a probability function of Poisson distribution and the number of times that the pixel value of each pixel in the multiple frames of solar-blind ultraviolet images is equal to zero.

[0066] Among them, the Poisson probability map can reflect the UV corona signal in multiple frames of solar-blind UV images in terms of frequency.

[0067] Exemplarily, based on the number of times the pixel value of each pixel in multiple frames of day-blind ultraviolet images is equal to zero, the probability that the pixel value of each pixel in multiple frames of day-blind ultraviolet images is equal to zero can be determined; further, by combining and deforming the probability that the pixel value of each pixel in multiple frames of day-blind ultraviolet images is equal to zero and the probability function of the Poisson distribution, a Poisson probability mapping diagram of the frame day-blind ultraviolet images can be obtained.

[0068] S204, constructing a Gaussian intensity map of multiple frames of solar-blind ultraviolet images according to the Gaussian model and the pixel value of each pixel point in each frame of solar-blind ultraviolet image.

[0069] Among them, the Gaussian model can classify the data. In the embodiment of the present application, the Gaussian model can effectively classify the valid signals and invalid noise signals in the solar-blind ultraviolet image, so that the constructed Gaussian intensity map can well highlight the ultraviolet corona signal; the Gaussian intensity map can reflect the ultraviolet corona signal in multiple frames of solar-blind ultraviolet images in terms of intensity.

[0070] Exemplarily, the Gaussian scale coefficient in the Gaussian model is adjusted to the optimal value; further, the pixel value of each pixel in each frame of the day-blind ultraviolet image is input into the Gaussian model, and the Gaussian model analyzes and processes the pixel value of each pixel in the day-blind ultraviolet image to obtain a Gaussian intensity mapping map of multiple frames of day-blind ultraviolet images.

[0071] S205, determining the corona detection results of the multiple frames of solar-blind ultraviolet images according to the Poisson probability map and the Gaussian intensity map.

[0072] The corona detection result may include but is not limited to information such as the number of ultraviolet corona signals, the location of ultraviolet corona signals, and the intensity of ultraviolet corona signals.

[0073] Exemplarily, the Poisson probability map and the Gaussian intensity map can be and / or operated; further, based on the result after the operation, the solar-blind ultraviolet discharge signal is extracted, and the corona detection results of multiple frames of solar-blind ultraviolet images are generated. It should be noted that, by combining the Poisson probability map and the Gaussian intensity map, multiple frames of solar-blind ultraviolet images can be analyzed from two dimensions of frequency and intensity, thereby ensuring the accuracy of the corona detection results.

[0074] The above corona detection method constructs a Poisson probability map of multiple frames of solar-blind ultraviolet images by combining the number of times the pixel value of each pixel in multiple frames of solar-blind ultraviolet images is equal to zero with the probability function of Poisson distribution; further, the Gaussian model is combined with the pixel value of each pixel in each frame of solar-blind ultraviolet images to construct a Gaussian intensity map of multiple frames of solar-blind ultraviolet images; then, based on the Poisson probability map and the Gaussian intensity map, a multi-dimensional analysis of multiple frames of solar-blind ultraviolet images is realized, and the corona detection results of multiple frames of solar-blind ultraviolet images are obtained. The above scheme realizes ultraviolet corona target detection from two dimensions of signal frequency and signal intensity by introducing Poisson distribution and Gaussian model, making the ultraviolet corona target clearer and ensuring the accuracy of the corona detection results.

[0075] Based on the above embodiment, the present application embodiment explains the above S203 in detail. Specifically, the present application embodiment involves the process of constructing a Poisson probability map of multiple frames of solar blind ultraviolet images, such as Figure 3 As shown, the specific steps include:

[0076] S301, determining the probability that the pixel value of each pixel point is equal to zero according to the number of times the pixel value of each pixel point in the multiple frames of solar-blind ultraviolet images is equal to zero and the total number of frames of the multiple frames of solar-blind ultraviolet images.

[0077] Exemplarily, each pixel in multiple frames (n+1 frames) of day-blind ultraviolet images is independently counted to determine the number of times that the pixel value of each pixel in the n+1 frame of day-blind ultraviolet images is equal to zero, for example, s （x，y） is the number of times the pixel value of the pixel point (x, y) is equal to zero in the n+1 frame day-blind ultraviolet image; further, based on the total number of frames n+1 of the multi-frame day-blind ultraviolet image, the probability P that the pixel value of the pixel point (x, y) is equal to zero can be determined （x，y） =s （x，y） / (n+1), where (x, y) is any pixel in the solar-blind ultraviolet image.

[0078] S302: construct a probability statistics graph according to the probability that the pixel value of each pixel point is equal to zero.

[0079] As shown in the above example, based on the position of each pixel in the solar-blind ultraviolet image, the probability P of each pixel value being equal to zero is （x，y） By performing statistics, we can obtain the probability statistics graph P corresponding to multiple frames of solar-blind ultraviolet images. 0 .

[0080] S303, constructing a Poisson probability map of multiple frames of solar-blind ultraviolet images according to the probability statistics map and the probability function of the Poisson distribution.

[0081] It should be noted that the probability function of the Poisson distribution is defined as follows:

[0082] (1)

[0083] in, represents the number of independent events that occur. represents the average rate at which events occur. That is, if the average rate at which events occur is known , we can calculate the number of The probability of an event If Substituting into formula (1), we get:

[0084] (2)

[0085] By transforming formula (2), we can get:

[0086] (3)

[0087] From equation (3), we can see that if we can calculate the probability of no event occurring per unit time, we can calculate the average rate at which events occur.

[0088] Optionally, without considering the influence of dark noise, for any pixel in the day-blind ultraviolet image, in a certain frame of the day-blind ultraviolet image, if the pixel value of the pixel is greater than zero, it is regarded as an event occurring; if the pixel value of the pixel is equal to zero, it is regarded as no event occurring.

[0089] Furthermore, the probability that the pixel value of each pixel in the multi-frame solar-blind ultraviolet image is equal to zero is known, and the corresponding probability statistical map is constructed. Combined with the above formula, the average rate map of each pixel receiving the corona signal can be determined, that is, the Poisson probability map :

[0090] (4)

[0091] in, It is the probability statistics graph corresponding to multiple frames of solar-blind ultraviolet images; is a tuning parameter, which can be a positive real number very close to 0, used to avoid division by zero errors and to adjust Dynamic range of Poisson probability map It can be used to characterize the frequency of corona discharge at the discharge point in the detection field of view, and reflect the distribution of ultraviolet corona targets in the airspace from the perspective of frequency.

[0092] In an embodiment of the present application, by combining the probability statistics graph of the pixel value of each pixel equal to zero with the Poisson distribution probability function, a Poisson probability mapping graph that can reflect the frequency of the solar-blind ultraviolet discharge signal is obtained, laying the foundation for accurately obtaining corona detection results.

[0093] Based on the above embodiment, the present application embodiment explains the above S204 in detail. Specifically, the present application embodiment involves the process of constructing a Gaussian intensity map of multiple frames of solar-blind ultraviolet images, such as Figure 4 As shown, the specific steps include:

[0094] S401, determining a Gaussian intensity map corresponding to each frame of the solar-blind ultraviolet image according to a Gaussian model and the pixel value of each pixel point in each frame of the solar-blind ultraviolet image.

[0095] Exemplarily, for any frame of solar-blind ultraviolet image, based on the pixel value of each pixel point in the frame of solar-blind ultraviolet image and the Gaussian model, a Gaussian intensity map corresponding to the frame of solar-blind ultraviolet image is constructed. , which can be specifically expressed as:

[0096] (5)

[0097] in, Indicates Frame solar-blind UV images, Indicates The pixel value of the pixel point (x, y) in the frame solar-blind UV image, , is the Gaussian scaling factor, .

[0098] S402, accumulating the Gaussian intensity mapping images corresponding to each frame of the solar-blind ultraviolet image to obtain Gaussian intensity mapping images of multiple frames of the solar-blind ultraviolet image.

[0099] For example, the Gaussian intensity map corresponding to each frame of the solar-blind ultraviolet image is By accumulating, we can get the Gaussian intensity mapping diagram of multiple frames of solar-blind ultraviolet images. Specifically, it can be expressed as:

[0100] (6)

[0101] in, Indicates continuous The serial number of the first frame in the solar-blind UV image. Indicates continuous The sequence number of the last frame in the solar-blind UV image.

[0102] In an embodiment of the present application, by accumulating the Gaussian intensity mapping diagrams corresponding to each frame of the day-blind ultraviolet image, the high-frequency effective signal in the day-blind ultraviolet image can be enhanced, that is, the high-frequency effective signal is amplified in intensity, laying the foundation for accurately obtaining corona detection results.

[0103] Based on the above embodiment, the present application embodiment explains the above embodiment S205 in detail. Specifically, the present application embodiment involves a process of determining the corona detection results of multiple frames of solar-blind ultraviolet images, such as Figure 5 As shown, the specific steps include:

[0104] S501, constructing saliency maps corresponding to multiple frames of solar-blind ultraviolet images according to the Poisson probability map and the Gaussian intensity map.

[0105] One possible implementation method is to use the product of the Poisson probability map and the Gaussian intensity map as the saliency map corresponding to multiple frames of solar-blind ultraviolet images.

[0106] As in the above example, the Poisson probability map M can be n and the Gaussian intensity map G n The product of is directly used as the saliency map U corresponding to multiple frames of solar-blind ultraviolet images n , that is, the saliency map U corresponding to multiple frames of solar-blind ultraviolet images n It can be expressed as: n =M n *G n .

[0107] Another possible implementation method is to supplement the Gaussian intensity map with the Poisson probability map, that is, to use the Gaussian intensity map as the main map. For example, the pixel value of a certain pixel point (x, y) in the Gaussian intensity map is 0, that is, I 1 (x, y) = 0, and the pixel value of the pixel point (x, y) in the Poisson probability map does not exceed the Poisson pixel value threshold (which can be set in advance), that is, I 2 (x, y) T , then the pixel value of the pixel point (x, y) in the saliency map is 0; and if the pixel value of the pixel point (x, y) in the Poisson probability map exceeds the Poisson pixel value threshold, that is, I 2 (x, y)>I T , then the pixel value of the pixel point (x, y) in the saliency map is I 1 (x, y) + I 2 (x, y).

[0108] ​Of course, the Poisson probability map can also be supplemented according to the Gaussian intensity map, that is, the Poisson probability map is used as the main map. Specifically, the ratio of the Poisson probability map and the Gaussian intensity map in the significance map can be adjusted according to whether the signal frequency is mainly used or the signal intensity is mainly used.

[0109] S502, using the maximum inter-class variance method to perform binarization processing on the saliency map.

[0110] Among them, the maximum inter-class variance method is a method for binary segmentation of an image based on a threshold value, which can distinguish the foreground and background of the image to the greatest extent.

[0111] Exemplarily, all pixels in the saliency map are divided into two categories by the maximum inter-class variance method, which may be ultraviolet corona signal (foreground) and noise (background). Furthermore, based on the pixel values ​​of the two categories of pixels in the saliency map, the optimal segmentation threshold is determined to complete the binarization process of the saliency map.

[0112] S503, determining the corona detection results of the multiple frames of solar-blind ultraviolet images according to the saliency map that has been binarized.

[0113] For example, the saliency map after binary processing can highlight the UV corona signal in the solar-blind UV image, so that the number of UV corona signals, the location of UV corona signals, and the intensity of UV corona signals can be accurately determined, and the corona detection results can be generated for the staff to take emergency measures. The specific effect can be as follows Figure 6 shown.

[0114] In an embodiment of the present application, by constructing a saliency map corresponding to multiple frames of day-blind ultraviolet images and binarizing the saliency map, the ultraviolet corona signal is enhanced and the noise is suppressed, laying a foundation for the accuracy of the corona detection results.

[0115] Based on the above embodiment, the embodiment of the present application explains the above S201 in detail. Specifically, the embodiment of the present application involves a process of obtaining a continuous multi-frame solar-blind ultraviolet image, which may specifically include: normalizing the continuous multi-frame original image extracted from the solar-blind ultraviolet video stream to obtain a continuous multi-frame solar-blind ultraviolet image.

[0116] Exemplarily, multiple frames of continuous original images are captured from the day-blind ultraviolet video acquired by the terminal 102 on site, such as continuous original images from the vth frame to the v+nth frame; wherein v and n are positive integers not equal to 0, and the initial value of v is 1; further, the continuous original images from the vth frame to the v+nth frame are normalized so that the pixel value of each pixel in the image is .

[0117] Optionally, the image acquired by the terminal 102 is an 8-bit grayscale image, such as an 8-bit grayscale image output by a solar-blind ultraviolet detector. Therefore, the process of normalization can be expressed as:

[0118] I(x,y)=I 0 (x, y) / 255 (7)

[0119] Among them, I 0 (x, y) represents the pixel value of any pixel in the original image, and I(x, y) represents the pixel value of any pixel after the original image is normalized.

[0120] In the embodiment of the present application, the original image is normalized to lay the foundation for the subsequent analysis of the solar-blind ultraviolet image.

[0121] Based on the above embodiment, this embodiment provides an optional example of a corona detection method. Figure 7 As shown, the specific implementation process is as follows:

[0122] S701, normalizing the continuous multiple frames of original images extracted from the solar-blind ultraviolet video stream to obtain continuous multiple frames of solar-blind ultraviolet images.

[0123] S702, determining the number of times the pixel value of each pixel in multiple frames of solar-blind ultraviolet images is equal to zero.

[0124] S703, determining the probability that the pixel value of each pixel point is equal to zero according to the number of times the pixel value of each pixel point in the multiple frames of solar-blind ultraviolet images is equal to zero and the total number of frames of the multiple frames of solar-blind ultraviolet images.

[0125] S704: construct a probability statistics graph according to the probability that the pixel value of each pixel point is equal to zero.

[0126] S705, constructing a Poisson probability map of multiple frames of solar-blind ultraviolet images according to the probability statistics map and the probability function of the Poisson distribution.

[0127] S706, determining a Gaussian intensity map corresponding to each frame of the solar-blind ultraviolet image according to the Gaussian model and the pixel value of each pixel point in each frame of the solar-blind ultraviolet image.

[0128] S707, accumulating the Gaussian intensity mapping images corresponding to each frame of the solar-blind ultraviolet image to obtain Gaussian intensity mapping images of multiple frames of the solar-blind ultraviolet image.

[0129] S708: taking the product of the Poisson probability map and the Gaussian intensity map of the multiple frames of solar-blind ultraviolet images as the saliency map corresponding to the multiple frames of solar-blind ultraviolet images.

[0130] S709, using the maximum inter-class variance method to perform binarization processing on the saliency map.

[0131] S710, determining the corona detection results of multiple frames of solar-blind ultraviolet images according to the saliency map that has been binarized.

[0132] The specific process of the above S701-S710 can refer to the description of the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0133] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0134] Based on the same inventive concept, the embodiment of the present application also provides a corona detection device for implementing the above-mentioned corona detection method. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above-mentioned method, so the specific limitations in one or more corona detection device embodiments provided below can refer to the limitations of the corona detection method above, and will not be repeated here.

[0135] In an exemplary embodiment, Figure 8 As shown, a corona detection device 1 is provided, comprising: an image acquisition module 10, a number determination module 20, a first construction module 30, a second construction module 40 and a result determination module 50, wherein:

[0136] The image acquisition module 10 is used to acquire multiple frames of continuous solar-blind ultraviolet images.

[0137] The number determination module 20 is used to determine the number of times the pixel value of each pixel point in multiple frames of solar-blind ultraviolet images is equal to zero.

[0138] The first construction module 30 is used to construct a Poisson probability map of multiple frames of solar-blind ultraviolet images according to a probability function of Poisson distribution and the number of times the pixel value of each pixel in the multiple frames of solar-blind ultraviolet images is equal to zero.

[0139] The second construction module 40 is used to construct Gaussian intensity maps of multiple frames of solar-blind ultraviolet images according to the Gaussian model and the pixel value of each pixel point in each frame of solar-blind ultraviolet image.

[0140] The result determination module 50 is used to determine the corona detection results of multiple frames of solar-blind ultraviolet images according to the Poisson probability map and the Gaussian intensity map.

[0141] In one embodiment, the image acquisition module 10 is specifically used for:

[0142] The continuous multi-frame original images extracted from the solar-blind ultraviolet video stream are normalized to obtain continuous multi-frame solar-blind ultraviolet images.

[0143] In one embodiment, the first building module 30 is specifically used for:

[0144] According to the number of times the pixel value of each pixel in the multi-frame solar-blind ultraviolet image is equal to zero and the total number of frames of the multi-frame solar-blind ultraviolet image, the probability that the pixel value of each pixel is equal to zero is determined; according to the probability that the pixel value of each pixel is equal to zero, a probability statistical graph is constructed; according to the probability statistical graph and the probability function of the Poisson distribution, a Poisson probability mapping graph of the multi-frame solar-blind ultraviolet image is constructed.

[0145] In one embodiment, the second building module 40 is specifically used for:

[0146] According to the Gaussian model and the pixel value of each pixel point in each frame of the day-blind ultraviolet image, the Gaussian intensity mapping map corresponding to each frame of the day-blind ultraviolet image is determined; the Gaussian intensity mapping maps corresponding to each frame of the day-blind ultraviolet image are accumulated to obtain the Gaussian intensity mapping maps of multiple frames of the day-blind ultraviolet image.

[0147] In one embodiment, Fig. 9 As shown, the result determination module 50 specifically includes:

[0148] The construction unit 51 is used to construct a saliency map corresponding to multiple frames of solar-blind ultraviolet images according to the Poisson probability map and the Gaussian intensity map.

[0149] The processing unit 52 is used to perform binarization processing on the saliency map using the maximum inter-class variance method.

[0150] The result determination unit 53 is used to determine the corona detection results of multiple frames of solar-blind ultraviolet images according to the significance map after binarization processing.

[0151] In one embodiment, the construction unit 51 is further configured to:

[0152] The product of the Poisson probability map and the Gaussian intensity map is used as the saliency map corresponding to multiple frames of solar-blind ultraviolet images.

[0153] Each module in the above-mentioned corona detection device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0154] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.10 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store image data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a corona detection method is implemented.

[0155] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0156] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0157] Acquire continuous multi-frame solar-blind UV images;

[0158] Determine the number of times the pixel value of each pixel in multiple frames of solar-blind ultraviolet images is equal to zero;

[0159] According to the probability function of Poisson distribution and the number of times that the pixel value of each pixel point in the multi-frame solar-blind ultraviolet image is equal to zero, a Poisson probability map of the multi-frame solar-blind ultraviolet image is constructed;

[0160] According to the Gaussian model and the pixel value of each pixel point in each frame of the solar-blind ultraviolet image, a Gaussian intensity mapping diagram of multiple frames of solar-blind ultraviolet images is constructed;

[0161] The corona detection results of multiple frames of solar-blind UV images are determined based on the Poisson probability map and the Gaussian intensity map.

[0162] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0163] According to the number of times the pixel value of each pixel in the multi-frame solar-blind ultraviolet image is equal to zero and the total number of frames of the multi-frame solar-blind ultraviolet image, the probability that the pixel value of each pixel is equal to zero is determined; according to the probability that the pixel value of each pixel is equal to zero, a probability statistical graph is constructed; according to the probability statistical graph and the probability function of the Poisson distribution, a Poisson probability mapping graph of the multi-frame solar-blind ultraviolet image is constructed.

[0164] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0165] According to the Gaussian model and the pixel value of each pixel point in each frame of the day-blind ultraviolet image, the Gaussian intensity mapping map corresponding to each frame of the day-blind ultraviolet image is determined; the Gaussian intensity mapping maps corresponding to each frame of the day-blind ultraviolet image are accumulated to obtain the Gaussian intensity mapping maps of multiple frames of the day-blind ultraviolet image.

[0166] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0167] According to the Poisson probability map and the Gaussian intensity map, the saliency map corresponding to the multi-frame solar-blind ultraviolet image is constructed; the maximum inter-class variance method is used to binarize the saliency map; according to the binarized saliency map, the corona detection results of the multi-frame solar-blind ultraviolet image are determined.

[0168] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0169] The product of the Poisson probability map and the Gaussian intensity map is used as the saliency map corresponding to multiple frames of solar-blind ultraviolet images.

[0170] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0171] The continuous multi-frame original images extracted from the solar-blind ultraviolet video stream are normalized to obtain continuous multi-frame solar-blind ultraviolet images.

[0172] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0173] Acquire continuous multi-frame solar-blind UV images;

[0174] Determine the number of times the pixel value of each pixel in multiple frames of solar-blind ultraviolet images is equal to zero;

[0175] According to the probability function of Poisson distribution and the number of times that the pixel value of each pixel point in the multi-frame solar-blind ultraviolet image is equal to zero, a Poisson probability map of the multi-frame solar-blind ultraviolet image is constructed;

[0176] According to the Gaussian model and the pixel value of each pixel point in each frame of the solar-blind ultraviolet image, a Gaussian intensity mapping diagram of multiple frames of solar-blind ultraviolet images is constructed;

[0177] The corona detection results of multiple frames of solar-blind UV images are determined based on the Poisson probability map and the Gaussian intensity map.

[0178] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0179] According to the number of times the pixel value of each pixel in the multi-frame solar-blind ultraviolet image is equal to zero and the total number of frames of the multi-frame solar-blind ultraviolet image, the probability that the pixel value of each pixel is equal to zero is determined; according to the probability that the pixel value of each pixel is equal to zero, a probability statistical graph is constructed; according to the probability statistical graph and the probability function of the Poisson distribution, a Poisson probability mapping graph of the multi-frame solar-blind ultraviolet image is constructed.

[0180] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0181] According to the Gaussian model and the pixel value of each pixel point in each frame of the day-blind ultraviolet image, the Gaussian intensity mapping map corresponding to each frame of the day-blind ultraviolet image is determined; the Gaussian intensity mapping maps corresponding to each frame of the day-blind ultraviolet image are accumulated to obtain the Gaussian intensity mapping maps of multiple frames of the day-blind ultraviolet image.

[0182] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0183] According to the Poisson probability map and the Gaussian intensity map, the saliency map corresponding to the multi-frame solar-blind ultraviolet image is constructed; the maximum inter-class variance method is used to binarize the saliency map; according to the binarized saliency map, the corona detection results of the multi-frame solar-blind ultraviolet image are determined.

[0184] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0185] The product of the Poisson probability map and the Gaussian intensity map is used as the saliency map corresponding to multiple frames of solar-blind ultraviolet images.

[0186] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0187] The continuous multi-frame original images extracted from the solar-blind ultraviolet video stream are normalized to obtain continuous multi-frame solar-blind ultraviolet images.

[0188] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0189] Acquire continuous multi-frame solar-blind UV images;

[0190] Determine the number of times the pixel value of each pixel in multiple frames of solar-blind ultraviolet images is equal to zero;

[0191] According to the probability function of Poisson distribution and the number of times that the pixel value of each pixel point in the multi-frame solar-blind ultraviolet image is equal to zero, a Poisson probability map of the multi-frame solar-blind ultraviolet image is constructed;

[0192] According to the Gaussian model and the pixel value of each pixel point in each frame of the solar-blind ultraviolet image, a Gaussian intensity mapping diagram of multiple frames of solar-blind ultraviolet images is constructed;

[0193] The corona detection results of multiple frames of solar-blind UV images are determined based on the Poisson probability map and the Gaussian intensity map.

[0194] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0195] According to the number of times the pixel value of each pixel in the multi-frame solar-blind ultraviolet image is equal to zero and the total number of frames of the multi-frame solar-blind ultraviolet image, the probability that the pixel value of each pixel is equal to zero is determined; according to the probability that the pixel value of each pixel is equal to zero, a probability statistical graph is constructed; according to the probability statistical graph and the probability function of the Poisson distribution, a Poisson probability mapping graph of the multi-frame solar-blind ultraviolet image is constructed.

[0196] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0197] According to the Gaussian model and the pixel value of each pixel point in each frame of the day-blind ultraviolet image, the Gaussian intensity mapping map corresponding to each frame of the day-blind ultraviolet image is determined; the Gaussian intensity mapping maps corresponding to each frame of the day-blind ultraviolet image are accumulated to obtain the Gaussian intensity mapping maps of multiple frames of the day-blind ultraviolet image.

[0198] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0199] According to the Poisson probability map and the Gaussian intensity map, the saliency map corresponding to the multi-frame solar-blind ultraviolet image is constructed; the maximum inter-class variance method is used to binarize the saliency map; according to the binarized saliency map, the corona detection results of the multi-frame solar-blind ultraviolet image are determined.

[0200] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0201] The product of the Poisson probability map and the Gaussian intensity map is used as the saliency map corresponding to multiple frames of solar-blind ultraviolet images.

[0202] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0203] The continuous multi-frame original images extracted from the solar-blind ultraviolet video stream are normalized to obtain continuous multi-frame solar-blind ultraviolet images.

[0204] It should be noted that the information (including but not limited to image information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0205] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile 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), magnetoresistive 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0206] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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 specification.

[0207] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A corona detection method, characterized in that: The method comprises: Acquire continuous multi-frame solar-blind UV images; Determine the number of times the pixel value of each pixel in multiple frames of solar-blind ultraviolet images is equal to zero; According to the probability function of Poisson distribution and the number of times that the pixel value of each pixel point in the multi-frame solar-blind ultraviolet image is equal to zero, a Poisson probability map of the multi-frame solar-blind ultraviolet image is constructed; Determine a Gaussian intensity map corresponding to each frame of the solar-blind ultraviolet image according to the Gaussian model and the pixel value of each pixel point in each frame of the solar-blind ultraviolet image; Accumulating the Gaussian intensity mapping images corresponding to each frame of the solar-blind ultraviolet image to obtain the Gaussian intensity mapping images of multiple frames of the solar-blind ultraviolet image; Constructing a saliency map corresponding to the multiple frames of solar-blind ultraviolet images according to the Poisson probability map and the Gaussian intensity map; Using the maximum inter-class variance method, binarization processing is performed on the saliency map; The corona detection results of multiple frames of solar-blind ultraviolet images are determined based on the binarized saliency maps.

2. The method according to claim 1, characterized in that The method of constructing a Poisson probability map of multiple frames of solar-blind ultraviolet images according to the probability function of Poisson distribution and the number of times that the pixel value of each pixel point in the multiple frames of solar-blind ultraviolet images is equal to zero comprises: Determine the probability that the pixel value of each pixel point is equal to zero according to the number of times the pixel value of each pixel point in the multiple frames of solar-blind ultraviolet images is equal to zero and the total number of frames of the multiple frames of solar-blind ultraviolet images; Construct a probability statistical graph based on the probability that the pixel value of each pixel is equal to zero; According to the probability statistics diagram and the probability function of Poisson distribution, a Poisson probability mapping diagram of multiple frames of solar-blind ultraviolet images is constructed.

3. The method according to claim 1, characterized in that: The constructing, according to the Poisson probability map and the Gaussian intensity map, saliency maps corresponding to the multiple frames of solar-blind ultraviolet images comprises: The product of the Poisson probability map and the Gaussian intensity map is used as the saliency map corresponding to the multiple frames of solar-blind ultraviolet images.

4. The method according to claim 1, characterized in that The constructing, according to the Poisson probability map and the Gaussian intensity map, saliency maps corresponding to the multiple frames of solar-blind ultraviolet images comprises: According to the Poisson probability map, the Gaussian intensity map is supplemented to obtain the saliency maps corresponding to the multiple frames of solar-blind ultraviolet images; or, The Poisson probability map is supplemented according to the Gaussian intensity map to obtain saliency maps corresponding to the multiple frames of solar-blind ultraviolet images.

5. The method according to claim 1, characterized in that The method of acquiring a continuous plurality of frames of solar-blind ultraviolet images comprises: The continuous multi-frame original images extracted from the solar-blind ultraviolet video stream are normalized to obtain continuous multi-frame solar-blind ultraviolet images.

6. The method according to claim 1, characterized in that The corona detection result includes the number of ultraviolet corona signals, the location of ultraviolet corona signals and the intensity of ultraviolet corona signals.

7. A corona detection device, characterized in that: The device comprises: An image acquisition module, used for acquiring continuous multi-frame solar-blind ultraviolet images; A number determination module is used to determine the number of times the pixel value of each pixel point in multiple frames of solar-blind ultraviolet images is equal to zero; The first construction module is used to construct a Poisson probability map of the multiple frames of solar-blind ultraviolet images according to a probability function of Poisson distribution and the number of times that the pixel value of each pixel point in the multiple frames of solar-blind ultraviolet images is equal to zero; The second construction module is used to construct a Gaussian intensity map of multiple frames of solar-blind ultraviolet images according to the Gaussian model and the pixel value of each pixel point in each frame of solar-blind ultraviolet image; A result determination module, used for determining the corona detection results of multiple frames of solar-blind ultraviolet images according to the Poisson probability map and the Gaussian intensity map; The second construction module is specifically used to determine the Gaussian intensity mapping map corresponding to each frame of the day-blind ultraviolet image according to the Gaussian model and the pixel value of each pixel point in each frame of the day-blind ultraviolet image; accumulate the Gaussian intensity mapping maps corresponding to each frame of the day-blind ultraviolet image to obtain the Gaussian intensity mapping maps of multiple frames of the day-blind ultraviolet image; The result determination module specifically includes: A construction unit, configured to construct a saliency map corresponding to the plurality of frames of solar-blind ultraviolet images according to the Poisson probability map and the Gaussian intensity map; A processing unit, configured to perform binarization processing on the saliency map using a maximum inter-class variance method; The result determination unit is used to determine the corona detection results of multiple frames of solar-blind ultraviolet images according to the significance map after binarization processing.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

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

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

Images