A method, device, electronic device and storage medium for hot spot detection

Abstract

The present application discloses a hot spot detection method, device, electronic device and storage medium. After acquiring an image including a photovoltaic panel and determining the photovoltaic panel area in the image, the second number of pixel points included in a single photovoltaic module in the photovoltaic panel area is determined based on the photovoltaic panel area. The first number of pixel points included in the hot spot area and the contour information of the hot spot area are determined. According to the first number, the second number and the contour information of the hot spot area, the target hot spot category corresponding to the hot spot area is determined. After determining the hot spot area, the present application combines the hot spot area, the number of pixel points included in a single photovoltaic module, and the contour information of the hot spot area to determine the target hot spot category corresponding to the hot spot area. Thus, the target classification of the hot spot area is realized. For maintenance personnel, according to the target hot spot category corresponding to the hot spot area obtained by the present application, a corresponding solution can be determined for hot spot treatment, and the reference and practicability are better.

Description

Technical Field

[0001] The present application relates to the field of image processing technologies, and in particular, to a hot spot detection method, apparatus, electronic device, and storage medium. Background Art

[0002] In recent years, more and more attention has been paid to the development and investment in renewable energy. Solar energy has the advantages of universality, harmlessness, large reserves, etc., and plays an important role in the energy strategy.

[0003] A solar photovoltaic panel power generation system is composed of a series of photovoltaic module batteries connected in series. During the operation of a photovoltaic power station, it is inevitable that there will be bird droppings, fallen leaves, floating dust and other obstructions covering the photovoltaic modules. These obstructions form local shadows on the photovoltaic modules, resulting in changes in the current and voltage of some individual cells in the photovoltaic modules, and causing the local temperature of the photovoltaic modules to rise. This phenomenon is called the hot spot effect.

[0004] The hot spot effect has a greater impact on a photovoltaic power station. It not only affects the power generation efficiency of the photovoltaic modules, but also may cause a fire, posing a greater threat to the safety of the photovoltaic power station. The occurrence of the hot spot effect is somewhat damaging to the photovoltaic modules. Therefore, it is necessary to detect in time the photovoltaic modules that generate the hot spot effect through inspection, that is, to perform hot spot detection on the photovoltaic modules.

[0005] In the related art, generally, a drone is used to photograph the photovoltaic modules. After obtaining an image or video, it is then analyzed through manual analysis or image recognition to detect whether there is a hot spot in the photovoltaic modules in the image. The related art only detects whether there is a hot spot in the photovoltaic modules in the image. For maintenance personnel, generally different solutions need to be adopted according to different hot spots for processing. Therefore, in the related art, after obtaining the hot spot detection result through manual analysis or image recognition, the maintenance personnel still need to view the hot spot image by themselves and then specify a processing solution. Therefore, the hot spot detection solution in the related art has a relatively large reference limitation for maintenance personnel. Summary of the Invention

[0006] Embodiments of the present application provide a hot spot detection method, apparatus, electronic device, and storage medium, which are used to solve the problem that the existing hot spot detection solution cannot classify hot spots and the hot spot detection result has a relatively large reference limitation for maintenance personnel.

[0007] The present application provides a hot spot detection method, and the method includes:

[0008] Obtain an image including a photovoltaic panel, and determine the photovoltaic panel area in the image;

[0009] Detect whether there is a hot spot area in the photovoltaic panel area;

[0010] In response to the presence of a hot spot area in the photovoltaic panel image, determine the first quantity of pixel points included in the hot spot area, the contour information of the hot spot area, and the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area;

[0011] According to the magnitude relationship between the first quantity and the second quantity, and in combination with the contour information of the hot spot area, determine the target hot spot category corresponding to the hot spot area.

[0012] Further, the determining the target hot spot category corresponding to the hot spot area according to the magnitude relationship between the first quantity and the second quantity, and in combination with the contour information of the hot spot area includes:

[0013] According to the magnitude relationship between the first quantity and the second quantity, determine the respective first scores of each candidate hot spot category;

[0014] According to the contour information of the hot spot area, determine the respective second scores of each candidate hot spot category;

[0015] According to the respective first scores and second scores of each candidate hot spot category, determine the target hot spot category corresponding to the hot spot area from each candidate hot spot category.

[0016] Further, the determining the target hot spot category corresponding to the hot spot area from each candidate hot spot category according to the respective first scores and second scores of each candidate hot spot category includes:

[0017] According to the respective first scores and second scores of each candidate hot spot category, determine the respective target scores of each candidate hot spot category; and determine the candidate hot spot category corresponding to the maximum value of the determined respective target scores as the target hot spot category corresponding to the hot spot area.

[0018] Further, the candidate hot spot categories include one or more of string hot spots, planar hot spots, strip hot spots, and dot hot spots.

[0019] Further, the determining the respective first scores of each candidate hot spot category according to the magnitude relationship between the first quantity and the second quantity includes:

[0020] Determine the first reference value of the first quantity and the second quantity;

[0021] According to the preset reference value ranges corresponding to each candidate hot spot category, determine the reference value range to which the first reference value belongs;

[0022] Determine that the first score of the candidate hot spot category corresponding to the reference value range to which the first reference value belongs is higher than the first score of the candidate hot spot category corresponding to the reference value range that does not include the first reference value;

[0023] Among them, the candidate hot spot categories are sorted in descending order of the corresponding reference value ranges as string hot spots, planar hot spots, strip hot spots, and dot hot spots.

[0024] Further, the determining the second score of each candidate hot spot category according to the contour information of the hot spot area includes:

[0025] According to the contour information of the hot spot area, determine the rectangularity and circularity of the hot spot area;

[0026] If the rectangularity is greater than the circularity, determine that the second scores of the string hot spots, planar hot spots, and strip hot spots are greater than the second score of the dot hot spot;

[0027] If the rectangularity is less than the circularity, determine that the second scores of the string hot spots, planar hot spots, and strip hot spots are less than the second score of the dot hot spot.

[0028] Further, if the rectangularity is greater than the circularity, the method further includes:

[0029] Determine the minimum circumscribed rotated rectangle of the hot spot area, and determine the second reference values of the long side and the short side of the minimum circumscribed rotated rectangle;

[0030] If the second reference value is greater than a preset first reference threshold, determine that the second score of the planar hot spot is less than the second score of the strip hot spot;

[0031] If the second reference value is not greater than the preset first reference threshold, determine that the second score of the planar hot spot is greater than the second score of the strip hot spot.

[0032] Further, the determining the target score of each candidate hot spot category according to the first score and the second score of each candidate hot spot category includes:

[0033] For each candidate hot spot category, determine the target score of the candidate hot spot category according to the first score of the candidate hot spot category, the quantity weight value corresponding to the first score, the second score, and the contour weight value corresponding to the second score.

[0034] Further, after determining the first reference value of the first quantity and the second quantity, the method further includes:

[0035] If the first reference value is greater than a preset second reference threshold, determine that the target hot spot category corresponding to the hot spot area is a string hot spot.

[0036] Further, determining the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area includes:

[0037] Determine a reference edge of the photovoltaic panel area according to the position or movement trajectory of the drone that acquires the image;

[0038] Determine the quantity of pixel points included in the photovoltaic panel area according to the quantity of pixel points included in the reference edge and the aspect ratio of the photovoltaic panel area determined in advance;

[0039] Determine the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area according to the quantity of pixel points included in the photovoltaic panel area and the quantity of photovoltaic modules included in the photovoltaic panel area determined in advance.

[0040] Further, determining the photovoltaic panel area in the image includes:

[0041] Input the image including the photovoltaic panel into a pre-trained image segmentation model, and based on the image segmentation model, determine the photovoltaic panel area in the image;

[0042] Wherein, the image segmentation model is trained based on the position information of the sample images including the photovoltaic panel and the sample photovoltaic panel areas annotated in the sample images in the sample set.

[0043] On the other hand, the present application provides a hot spot detection device, and the device includes:

[0044] An acquisition module, configured to acquire an image including a photovoltaic panel and determine the photovoltaic panel area in the image;

[0045] A detection module, configured to detect whether there is a hot spot area in the photovoltaic panel area;

[0046] A first determination module, configured to, in response to the existence of a hot spot area in the photovoltaic panel image, determine the first quantity of pixel points included in the hot spot area, the contour information of the hot spot area, and the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area;

[0047] A second determination module, configured to determine the target hot spot category corresponding to the hot spot area according to the magnitude relationship between the first quantity and the second quantity, in combination with the contour information of the hot spot area.

[0048] The second determination module is specifically configured to determine the respective first scores of each candidate hot spot category according to the magnitude relationship between the first quantity and the second quantity; determine the respective second scores of each candidate hot spot category according to the contour information of the hot spot region; and determine the target hot spot category corresponding to the hot spot region from each candidate hot spot category according to the respective first scores and second scores of each candidate hot spot category.

[0049] The second determination module is specifically configured to determine the respective target scores of each candidate hot spot category according to the respective first scores and second scores of each candidate hot spot category; and determine the candidate hot spot category corresponding to the maximum value of the determined respective target scores as the target hot spot category corresponding to the hot spot region.

[0050] The candidate hot spot categories include one or more of string hot spots, planar hot spots, strip hot spots, and dot hot spots.

[0051] The second determination module is specifically configured to determine a first reference value of the first quantity and the second quantity; determine the reference value range to which the first reference value belongs according to the preset reference value ranges corresponding to each candidate hot spot category; and determine that the first scores of the candidate hot spot categories corresponding to the reference value range to which the first reference value belongs are higher than the first scores of the candidate hot spot categories corresponding to the reference value ranges not including the first reference value; wherein, the candidate hot spot categories are sorted in descending order of the corresponding reference value ranges as string hot spots, planar hot spots, strip hot spots, and dot hot spots.

[0052] The second determination module is specifically configured to determine the rectangularity and circularity of the hot spot region according to the contour information of the hot spot region; if the rectangularity is greater than the circularity, determine that the respective second scores of the string hot spot, planar hot spot, and strip hot spot are greater than the second score of the dot hot spot; if the rectangularity is less than the circularity, determine that the respective second scores of the string hot spot, planar hot spot, and strip hot spot are less than the second score of the dot hot spot.

[0053] The second determination module is further configured to determine the minimum circumscribed rotated rectangle of the hot spot region and determine a second reference value of the long side and the short side of the minimum circumscribed rotated rectangle; if the second reference value is greater than a preset first reference threshold, determine that the second score of the planar hot spot is less than the second score of the strip hot spot; if the second reference value is not greater than the preset first reference threshold, determine that the second score of the planar hot spot is greater than the second score of the strip hot spot.

[0054] The second determination module is specifically configured to determine the target score of each candidate hot spot category according to the first score of the candidate hot spot category, the quantity weight value corresponding to the first score, the second score, and the contour weight value corresponding to the second score.

[0055] The second determination module is further configured to determine a first reference value of the first quantity and the second quantity. If the first reference value is greater than a preset second reference threshold, it is determined that the target hot spot category corresponding to the hot spot area is a string hot spot.

[0056] The first determination module is specifically configured to determine a reference edge of the photovoltaic panel area according to the position or movement trajectory of the drone that captures the image; determine the number of pixel points included in the photovoltaic panel area according to the number of pixel points included in the reference edge and the aspect ratio of the photovoltaic panel area determined in advance; and determine a second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area according to the number of pixel points included in the photovoltaic panel area and the number of photovoltaic modules included in the photovoltaic panel area determined in advance.

[0057] The acquisition module is specifically configured to input the image including the photovoltaic panel into a pre-trained image segmentation model, and based on the image segmentation model, determine the photovoltaic panel area in the image; wherein, the image segmentation model is trained based on the sample images including the photovoltaic panel in the sample set and the position information of the sample photovoltaic panel areas annotated in the sample images.

[0058] On the other hand, the present application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus;

[0059] The memory is used to store a computer program;

[0060] The processor is configured to implement the method steps described in any one of the above when executing the program stored on the memory.

[0061] On the other hand, the present application provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the method steps described in any one of the above are implemented.

[0062] The present application provides a hot spot detection method, device, electronic device and storage medium. The method includes: obtaining an image including a photovoltaic panel, and determining the photovoltaic panel area in the image; detecting whether there is a hot spot area in the photovoltaic panel area; in response to the existence of a hot spot area in the photovoltaic panel image, determining a first number of pixel points included in the hot spot area, contour information of the hot spot area, and a second number of pixel points included in a single photovoltaic module in the photovoltaic panel area; and determining a target hot spot category corresponding to the hot spot area according to the magnitude relationship between the first number and the second number, in combination with the contour information of the hot spot area.

[0063] The above technical solution has the following advantages or beneficial effects:

[0064] In the present application, after obtaining an image including a photovoltaic panel and determining the photovoltaic panel area in the image, a second number of pixel points included in a single photovoltaic module in the photovoltaic panel area is determined based on the photovoltaic panel area. And it is detected whether there is a hot spot area in the photovoltaic panel area. If there is, a first number of pixel points included in the hot spot area and contour information of the hot spot area are determined. According to the first number of pixel points included in the hot spot area, the second number of pixel points included in a single photovoltaic module, and the contour information of the hot spot area, a target hot spot category corresponding to the hot spot area is determined. After determining the hot spot area in the present application, a target hot spot category corresponding to the hot spot area is determined by combining the hot spot area, the number of pixel points included in a single photovoltaic module, and the contour information of the hot spot area. Thus, target classification of the hot spot area is achieved. For maintenance personnel, according to the target hot spot category corresponding to the hot spot area obtained in the present application, a corresponding solution can be determined for hot spot processing, and the reference and practicality are better. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0066] Figure 1 It is a schematic diagram of the hot spot detection process provided by the present application;

[0067] Figure 2 It is a schematic diagram of an image including a photovoltaic panel provided by the present application;

[0068] Figure 3 It is a schematic diagram of a segmentation mask provided by the present application;

[0069] Figure 4 It is a schematic diagram of a mask of one of the photovoltaic panel areas provided by the present application;

[0070] Figure 5 Schematic diagram of one of the photovoltaic panel areas in the originally acquired image including photovoltaic panels provided for this application;

[0071] Figure 6 Schematic diagram of the photovoltaic panel area after grayscale processing and binarization processing provided for this application;

[0072] Figure 7 Schematic diagram of series string hot spot provided for this application;

[0073] Figure 8 Schematic diagram of planar hot spot provided for this application;

[0074] Figure 9 Schematic diagram of strip hot spot provided for this application;

[0075] Figure 10 Schematic diagram of dot hot spot provided for this application;

[0076] Figure 11 Schematic diagram of determining the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area provided for this application;

[0077] Figure 12 Schematic diagram of the structure of the hot spot detection device provided for this application;

[0078] Figure 13 Schematic diagram of the structure of the electronic device provided for this application. Detailed implementation manners

[0079] The following will further describe this application in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the protection scope of this application.

[0080] Figure 1 Schematic diagram of the hot spot detection process provided for this application. This process includes the following steps:

[0081] S101: Acquire an image including a photovoltaic panel, and determine the photovoltaic panel area in the image.

[0082] S102: Detect whether there is a hot spot area in the photovoltaic panel area. If so, proceed to S103. If not, end the process.

[0083] S103: In response to the existence of a hot spot area in the photovoltaic panel image, determine the first quantity of pixel points included in the hot spot area, the contour information of the hot spot area, and the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area.

[0084] S104: Determine a target hot spot category corresponding to the hot spot region based on the magnitude relationship between the first quantity and the second quantity and in combination with the contour information of the hot spot region.

[0085] The hot spot detection method provided in this application is applied to an electronic device. The electronic device can be a device such as a PC, a tablet computer, a server, etc., or an intelligent image acquisition device. If the electronic device is an intelligent image acquisition device, after the intelligent image acquisition device acquires an image including a photovoltaic panel, it determines the photovoltaic panel region in the image, and then proceeds with the process of detecting the hot spot region and determining the target hot spot category corresponding to the hot spot region. If the electronic device is a device such as a PC, a tablet computer, a server, etc., after the image acquisition device acquires an image including a photovoltaic panel, it sends the image including the photovoltaic panel to the electronic device. After the electronic device obtains the image including the photovoltaic panel, it determines the photovoltaic panel region in the image, and then proceeds with the process of detecting the hot spot region and determining the target hot spot category corresponding to the hot spot region.

[0086] The electronic device stores a pre-trained image segmentation model. After obtaining an image including a photovoltaic panel, it inputs the image into the image segmentation model and determines the photovoltaic panel region in the image based on the image segmentation model. Among them, the image segmentation model is trained based on the sample images including photovoltaic panels in the sample set and the position information of the sample photovoltaic panel regions annotated in the sample images.

[0087] After the electronic device determines the photovoltaic panel region in the image, it detects whether there is a hot spot region in the photovoltaic panel region. Specifically, it first performs gray processing and binary processing on the photovoltaic panel region, and determines the hot spot region based on the processed photovoltaic panel region. Specifically, it extracts the contour of the processed photovoltaic panel region. If no contour is extracted, it means that there is no hot spot region in the photovoltaic panel region, and the hot spot detection process ends. If a contour is extracted, the contour region is the hot spot region. It should be noted that the number of extracted contour regions may be multiple. If multiple contour regions are extracted, it means that there are multiple hot spot regions in the photovoltaic panel region. For each hot spot region, its corresponding target hot spot category is determined.

[0088] Figure 2 For the schematic diagram of the image including a photovoltaic panel provided in this application, Figure 2 input the shown image into the pre-trained image segmentation model. Based on the image segmentation model, determine the segmentation mask map mask of the photovoltaic panel region in the image. Figure 3 For the schematic diagram of the segmentation mask provided in this application. The segmentation mask map includes multiple photovoltaic panel region mask maps. Figure 4One of the schematic diagrams of the photovoltaic panel area mask provided by this application. The photovoltaic panel area mask is used to indicate the position information of the photovoltaic panel area in the image. The photovoltaic panel area in the originally acquired image including the photovoltaic panel is determined according to the photovoltaic panel area mask. Figure 5 One of the schematic diagrams of the photovoltaic panel area in the originally acquired image including the photovoltaic panel provided by this application. Figure 5 The image shown is subjected to grayscale processing and binaryzation processing using the adaptive threshold OTSU algorithm to obtain Figure 6 the image shown. Figure 6 One of the schematic diagrams of the photovoltaic panel area after grayscale processing and binaryzation processing provided by this application. Based on Figure 6 contour extraction is performed to detect whether there is a hot spot area in the photovoltaic panel area.

[0089] In this application, if it is detected that there is a hot spot area in the photovoltaic panel area, in response to the existence of the hot spot area in the photovoltaic panel image, the first quantity of the pixel points included in the hot spot area, the contour information of the hot spot area, and the second quantity of the pixel points included in a single photovoltaic module in the photovoltaic panel area are determined. According to the magnitude relationship between the first quantity and the second quantity, combined with the contour information of the hot spot area, the target hot spot category corresponding to the hot spot area is determined.

[0090] Among them, the hot spot categories include string hot spots, planar hot spots, strip hot spots, and dot hot spots. Among them, the overall hot spot existing in at least two photovoltaic modules is called a string hot spot. Figure 7 One of the schematic diagrams of the string hot spot provided by this application. The planar hot spot in a single photovoltaic module is called a planar hot spot. Figure 8 One of the schematic diagrams of the planar hot spot provided by this application. The strip hot spot parallel to the short border or the long border of the photovoltaic module is called a strip hot spot. Figure 9 One of the schematic diagrams of the strip hot spot provided by this application. The dot hot spot distributed in a single or multiple dot shapes is called a dot hot spot. Figure 10 One of the schematic diagrams of the dot hot spot provided by this application.

[0091] The electronic device can pre-determine the size relationship of the number of pixel points corresponding to series hot spots, planar hot spots, strip hot spots, and dot hot spots respectively, and the contour information of the hot spot area. For example, for a series hot spot, the size relationship of the number of pixel points is that the first quantity is greater than the second quantity, and the contour information is a quasi-rectangular contour; for a planar hot spot, the size relationship of the number of pixel points is that the first quantity is not greater than the second quantity, and the ratio of the first quantity to the second quantity is greater than a set threshold, and the contour information is a quasi-rectangular contour; for a strip hot spot, the size relationship of the number of pixel points is that the first quantity is not greater than the second quantity, and the ratio of the first quantity to the second quantity is not greater than the set threshold, and the contour information is a quasi-rectangular contour; for a dot hot spot, the size relationship of the number of pixel points is that the first quantity is not greater than the second quantity, and the ratio of the first quantity to the second quantity is not greater than the set threshold, and the contour information is a quasi-circular contour. Among them, the quasi-rectangular contour means that the rectangularity of the hot spot area is greater than the circularity, and the quasi-circular contour means that the rectangularity of the hot spot area is less than the circularity.

[0092] Among them, the rectangularity reflects the degree of filling of the hot spot area with its minimum bounding rectangle, and is a parameter reflecting the similarity degree of a hot spot area to a rectangle, which is the rectangular fitting factor. Its calculation formula is:

[0093] R = S0 / S M E R ;

[0094] Among them, S0 represents the area of the hot spot area, and S M E R represents the area of the minimum bounding rectangle of the hot spot area. The rectangularity R takes values between 0 and 1.

[0095] The calculation formula for circularity is:

[0096] C = F / (π * max 2 );

[0097] Among them, C represents circularity, F represents the area of the hot spot area, and max represents the maximum distance from the central pixel point of the hot spot area to all contour pixel points.

[0098] The electronic device determines the target hot spot category of the hot spot area based on the pre-determined size relationship of the number of pixel points corresponding to series hot spots, planar hot spots, strip hot spots, and dot hot spots respectively, the contour information of the hot spot area, the size relationship between the first quantity of pixel points included in the hot spot area in the image including the photovoltaic panel determined, and the second quantity of pixel points included in a single photovoltaic module, and the contour information of the hot spot area.

[0099] For example, in an image including a photovoltaic panel, the number of pixels in the hot spot area is no greater than the number of pixels in a single photovoltaic module, and the ratio of the number of pixels in the hot spot area to the number of pixels in a single photovoltaic module is no greater than a set threshold. If the contour information is a rectangular-like contour, the target hot spot category corresponding to the hot spot area is determined to be a strip-shaped hot spot. Another example is that in an image including a photovoltaic panel, the number of pixels in the hot spot area is no greater than the number of pixels in a single photovoltaic module, and the ratio of the number of pixels in the hot spot area to the number of pixels in a single photovoltaic module is no greater than a set threshold. If the contour information is a circular-like contour, the target hot spot category corresponding to the hot spot area is determined to be a dot-shaped hot spot.

[0100] In this application, after obtaining an image including a photovoltaic panel and determining the photovoltaic panel area in the image, the number of pixels in a single photovoltaic module in the photovoltaic panel area is determined based on the photovoltaic panel area. And it is detected whether there is a hot spot area in the photovoltaic panel area. If there is, the number of pixels in the hot spot area, i.e., the first quantity, and the contour information of the hot spot area are determined. According to the first quantity of pixels in the hot spot area, the second quantity of pixels in a single photovoltaic module, and the contour information of the hot spot area, the target hot spot category corresponding to the hot spot area is determined. After determining the hot spot area in this application, the target hot spot category corresponding to the hot spot area is determined by combining the hot spot area, the number of pixels in a single photovoltaic module, and the contour information of the hot spot area. Thus, the target classification of the hot spot area is realized. For maintenance personnel, according to the target hot spot category corresponding to the hot spot area obtained in this application, the corresponding solution for hot spot treatment can be determined, which has better reference and practicality.

[0101] In this application, in order to make the determination of the target hot spot category corresponding to the hot spot area more accurate, the step of determining the target hot spot category corresponding to the hot spot area according to the magnitude relationship between the first quantity and the second quantity and in combination with the contour information of the hot spot area includes:

[0102] According to the magnitude relationship between the first quantity and the second quantity, the first score of each candidate hot spot category is determined;

[0103] According to the contour information of the hot spot area, the second score of each candidate hot spot category is determined;

[0104] According to the first score and the second score of each candidate hot spot category, the target hot spot category corresponding to the hot spot area is determined from each candidate hot spot category.

[0105] In this application, after determining the first quantity of pixel points included in the hot spot area, the contour information of the hot spot area, and the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area, the first score of each candidate hot spot category is determined according to the magnitude relationship between the first quantity and the second quantity. The candidate hot spot categories include string hot spots, planar hot spots, strip hot spots, and dot hot spots.

[0106] Optionally, if the first quantity is greater than the second quantity, it is determined that the first score of the string hot spot is higher than the first scores of the planar hot spot, the strip hot spot, and the dot hot spot respectively; for the planar hot spot, the strip hot spot, and the dot hot spot, the order from largest to smallest of the first scores is, for example, the planar hot spot, the strip hot spot, and the dot hot spot. If the first quantity is not greater than the second quantity, and the ratio of the first quantity to the second quantity is greater than a set threshold, it is determined that the first score of the planar hot spot is higher than the first scores of the string hot spot, the strip hot spot, and the dot hot spot respectively; for the string hot spot, the strip hot spot, and the dot hot spot, the order from largest to smallest of the first scores is, for example, the strip hot spot, the dot hot spot, and the string hot spot. If the first quantity is not greater than the second quantity, and the ratio of the first quantity to the second quantity is not greater than the set threshold, it is determined that the first scores of the strip hot spot and the dot hot spot are higher than the first scores of the string hot spot and the planar hot spot.

[0107] In this application, after determining the contour information of the hot spot area, the second score of each candidate hot spot category is determined according to the contour information of the hot spot area. The contour information of the hot spot area is determined according to the rectangularity and circularity of the hot spot area. If the rectangularity of the hot spot area is greater than the circularity, the contour information of the hot spot area is determined to be a quasi-rectangular contour. If the rectangularity of the hot spot area is less than the circularity, the contour information of the hot spot area is determined to be a quasi-circular contour.

[0108] Optionally, if it is determined that the contour information of the hot spot area is a quasi-rectangular contour, it is determined that the second score of the dot hot spot is lower than the second scores of the string hot spot, the planar hot spot, and the strip hot spot respectively; for the string hot spot, the planar hot spot, and the strip hot spot, the order from largest to smallest of the second scores is, for example, the strip hot spot, the planar hot spot, and the string hot spot. If it is determined that the contour information of the hot spot area is a quasi-circular contour, it is determined that the second score of the dot hot spot is higher than the second scores of the string hot spot, the planar hot spot, and the strip hot spot respectively; for the string hot spot, the planar hot spot, and the strip hot spot, the order from largest to smallest of the second scores is, for example, the string hot spot, the planar hot spot, and the strip hot spot.

[0109] After determining the first score and the second score for each candidate hot spot category, the target hot spot category corresponding to the hot spot area is determined from each candidate hot spot category according to the first score and the second score of each candidate hot spot category. Specifically, according to the first score and the second score of each candidate hot spot category, the target score of each candidate hot spot category is determined; and the candidate hot spot category corresponding to the maximum value of the determined target scores is determined as the target hot spot category corresponding to the hot spot area. Among them, for each candidate hot spot category, the first score and the second score of the candidate hot spot category can be added to obtain the target score of the candidate hot spot category. Alternatively, for each candidate hot spot category, according to the first score of the candidate hot spot category, the quantity weight value corresponding to the first score, the second score, and the contour weight value corresponding to the second score, the target score of the candidate hot spot category is determined. The quantity weight value is configured for the first score, and the contour weight value is configured for the second score according to the actual scenario. If more attention is paid to the influence of the number of pixel points on the hot spot classification, the quantity weight value is greater than the contour weight value. For example, the quantity weight value is 0.8 and the contour weight value is 0.2. If more attention is paid to the influence of the contour of the hot plate area on the hot spot classification, the quantity weight value is less than the contour weight value. For example, the quantity weight value is 0.2 and the contour weight value is 0.8, and so on. For each candidate hot spot category, the first score of the candidate hot spot category, the quantity weight value corresponding to the first score, the second score, and the contour weight value corresponding to the second score are weighted and summed to obtain the target score of the candidate hot spot category. Then, the candidate hot spot category corresponding to the maximum value of each target score is selected and determined as the target hot spot category corresponding to the hot spot area.

[0110] In this application, in order to make the determination of the first score for each candidate hot spot category more accurate, the determination of the first score for each candidate hot spot category according to the magnitude relationship between the first quantity and the second quantity includes:

[0111] Determine a first reference value of the first quantity and the second quantity;

[0112] According to the preset reference value ranges corresponding to each candidate hot spot category, determine the reference value range to which the first reference value belongs;

[0113] Determine that the first score of the candidate hot spot category corresponding to the reference value range to which the first reference value belongs is higher than the first score of the candidate hot spot category corresponding to the reference value range that does not include the first reference value;

[0114] Among them, the candidate hot spot categories are sorted as string hot spots, planar hot spots, strip hot spots, and dot hot spots in descending order of the corresponding reference value ranges.

[0115] Determine a first reference value for the first quantity and the second quantity. The first reference value can be the difference between the first quantity and the second quantity. Preferably, the first reference value can be the ratio of the first quantity to the second quantity. The electronic device stores a preset reference value range corresponding to each candidate hot spot category. Sort the candidate hot spot categories in descending order according to the corresponding reference value ranges as series hot spots, planar hot spots, strip hot spots, and dot hot spots. Taking the first reference value being the ratio of the first quantity to the second quantity as an example, for instance, the reference value range corresponding to series hot spots is >1; the reference value range corresponding to planar hot spots is from 0.5 to 1, excluding 0.5 and including 1; the reference value range corresponding to strip hot spots is from 0.2 to 0.5, excluding 0.2 and including 0.5; the reference value range corresponding to dot hot spots is from 0 to 0.2, including 0.2.

[0116] After determining the first reference value for the first quantity and the second quantity, according to the preset reference value range corresponding to each candidate hot spot category, determine the reference value range to which the first reference value belongs, and then determine that the first score of the candidate hot spot category corresponding to the reference value range to which the first reference value belongs is higher than the first score of the candidate hot spot category corresponding to the reference value range that does not include the first reference value. For example, if the first reference value for the first quantity and the second quantity is determined to be 0.7, and the reference value range to which it belongs is from 0.5 to 1, and 0.5 to 1 is the reference value range corresponding to planar hot spots, then determine that the first score of planar hot spots is higher than the first scores of series hot spots, strip hot plates, and dot hot spots. For example, if the first reference value for the first quantity and the second quantity is determined to be 0.3, and the reference value range to which it belongs is from 0.2 to 0.5, and 0.2 to 0.5 is the reference value range corresponding to strip hot spots, then determine that the first score of strip hot spots is higher than the first scores of series hot spots, planar hot plates, and dot hot spots.

[0117] In this application, in order to make the determination of the second score of each candidate hot spot category more accurate, the step of determining the second score of each candidate hot spot category according to the contour information of the hot spot area includes:

[0118] According to the contour information of the hot spot area, determine the rectangularity and circularity of the hot spot area;

[0119] If the rectangularity is greater than the circularity, determine that the second scores of the series hot spots, planar hot spots, and strip hot spots are greater than the second score of the dot hot spot;

[0120] If the rectangularity is less than the circularity, determine that the second scores of the series hot spots, planar hot spots, and strip hot spots are less than the second score of the dot hot spot.

[0121] In this application, after determining the contour information of the hot spot area, according to the contour information of the hot spot area, the rectangularity and circularity of the hot spot area are determined respectively. If the rectangularity is greater than the circularity, it is determined that the contour of the hot spot area is a quasi-rectangular contour. At this time, it is determined that the second scores of the series hot spot, the planar hot spot, and the strip hot spot are each greater than the second score of the dot hot spot. If the rectangularity is less than the circularity, it is determined that the contour of the hot spot area is a quasi-circular contour. At this time, it is determined that the second scores of the series hot spot, the planar hot spot, and the strip hot spot are each less than the second score of the dot hot spot.

[0122] In addition, in order to accurately determine the second scores of the planar hot spot and the strip hot spot, if the rectangularity is greater than the circularity, the method further includes:

[0123] Determine the minimum circumscribed rotated rectangle of the hot spot area, and determine the second reference values of the long side and the short side of the minimum circumscribed rotated rectangle;

[0124] If the second reference value is greater than a preset first reference threshold, it is determined that the second score of the planar hot spot is less than the second score of the strip hot spot;

[0125] If the second reference value is not greater than the preset first reference threshold, it is determined that the second score of the planar hot spot is greater than the second score of the strip hot spot.

[0126] If the rectangularity of the hot spot area is greater than the circularity, at this time, the minimum circumscribed rotated rectangle of the hot spot area is determined, and the second reference values of the long side and the short side of the minimum circumscribed rotated rectangle are determined. The second reference value can be the difference between the long side and the short side of the minimum circumscribed rotated rectangle. Preferably, the second reference value can be the ratio of the long side to the short side of the minimum circumscribed rotated rectangle. Taking the second reference value as the ratio of the long side to the short side of the minimum circumscribed rotated rectangle as an example, the electronic device stores a preset first reference threshold, and the preset first reference threshold is, for example, 1.5, 2, 2.5, etc. If the second reference value is greater than the preset first reference threshold, it is determined that the second score of the planar hot spot is less than the second score of the strip hot spot; if the second reference value is not greater than the preset first reference threshold, it is determined that the second score of the planar hot spot is greater than the second score of the strip hot spot.

[0127] In this application, in order to make the determination of the target hot spot category as the series hot spot more accurate and improve the efficiency of determining the target hot spot category of the hot spot area, after determining the first reference value of the first quantity and the second quantity, the method further includes:

[0128] If the first reference value is greater than a preset second reference threshold, it is determined that the target hot spot category corresponding to the hot spot area is the series hot spot.

[0129] Taking the ratio of the first quantity to the second quantity as the first reference value as an example, the preset second reference threshold saved by the electronic device is, for example, 1. If the first reference value is greater than the preset second reference threshold, it indicates that there is a hot spot area in at least two photovoltaic modules at this time. At this time, there is no need to determine the second score corresponding to each candidate hot spot category according to the contour information, and directly determine that the target hot spot category corresponding to the hot spot area is the string hot spot.

[0130] In this application, images including photovoltaic panels are collected by a drone. Specifically, an image acquisition device is installed on the drone. During the flight of the drone, images including photovoltaic panels are collected through the image acquisition device. The distance between the drone and the photovoltaic panel cannot be fixed, and the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area is related to the distance between the drone and the photovoltaic panel. For example, if the distance between the drone and the photovoltaic panel is far, the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area is small; if the distance between the drone and the photovoltaic panel is close, the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area is large. To make the determination of the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area more accurate, determining the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area includes:

[0131] Determine the reference side of the photovoltaic panel area according to the position or movement trajectory of the drone that collects the image;

[0132] Determine the number of pixel points included in the photovoltaic panel area according to the number of pixel points included in the reference side and the aspect ratio of the photovoltaic panel area determined in advance;

[0133] Determine the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area according to the number of pixel points included in the photovoltaic panel area and the number of photovoltaic modules included in the photovoltaic panel area determined in advance.

[0134] In this application, first, the reference side of the photovoltaic panel area is determined according to the position or movement trajectory of the drone that collects the image. Figure 11 This is a schematic diagram of determining the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area provided by this application. Taking Figure 11 as an example, if the position or movement trajectory of the drone is from Figure 11 moving upward from the lower direction, the short side W of the obtained photovoltaic panel area is complete, while the long side H of the photovoltaic panel area may be truncated. At this time, the reference side of the photovoltaic panel area is determined as the short side W.

[0135] The electronic device stores the aspect ratio of the length and width of a pre-determined photovoltaic panel area, determines the number of pixel points included in the reference side, i.e., the short side, and then multiplies the number of pixel points included in the short side by the aspect ratio of the length and width of the photovoltaic panel area to obtain the actual number of pixel points included in the long side of the photovoltaic panel area. Then, the product of the number of pixel points included in the short side and the actual number of pixel points included in the long side is determined as the number of pixel points included in the photovoltaic panel area. The electronic device stores the number of photovoltaic modules included in the pre-determined photovoltaic panel area, and determines the ratio of the number of pixel points included in the photovoltaic panel area to the number of photovoltaic modules included in the photovoltaic panel area as the second number of pixel points included in a single photovoltaic module in the photovoltaic panel area.

[0136] In this application, according to the position or movement trajectory of the drone that captures the image, the reference side of the photovoltaic panel area is determined. The reference side is a complete and accurate side. Based on the number of pixel points included in the reference side, the number of pixel points included in the photovoltaic panel area is determined. Even if the photovoltaic panel area in the image is truncated, the number of pixel points included in the photovoltaic panel area can be accurately determined. Furthermore, according to the number of pixel points included in the photovoltaic panel area and the pre-determined number of photovoltaic modules included in the photovoltaic panel area, the second number of pixel points included in a single photovoltaic module in the photovoltaic panel area is determined. This makes the determined second number of pixel points included in a single photovoltaic module accurate.

[0137] Figure 12 It is a schematic structural diagram of the hot spot detection device provided by this application. The device includes:

[0138] An acquisition module 121, configured to acquire an image including a photovoltaic panel and determine the photovoltaic panel area in the image;

[0139] A detection module 122, configured to detect whether there is a hot spot area in the photovoltaic panel area;

[0140] A first determination module 123, configured to, in response to the existence of a hot spot area in the photovoltaic panel image, determine the first number of pixel points included in the hot spot area, the contour information of the hot spot area, and the second number of pixel points included in a single photovoltaic module in the photovoltaic panel area;

[0141] A second determination module 124, configured to determine the target hot spot category corresponding to the hot spot area according to the magnitude relationship between the first number and the second number, in combination with the contour information of the hot spot area.

[0142] The second determination module 124 is specifically configured to determine the first score of each candidate hot spot category according to the magnitude relationship between the first quantity and the second quantity; determine the second score of each candidate hot spot category according to the contour information of the hot spot area; and determine the target hot spot category corresponding to the hot spot area from each candidate hot spot category according to the first score and the second score of each candidate hot spot category.

[0143] The second determination module 124 is specifically configured to determine the target score of each candidate hot spot category according to the first score and the second score of each candidate hot spot category; and determine the candidate hot spot category corresponding to the maximum value of the determined target scores as the target hot spot category corresponding to the hot spot area.

[0144] The candidate hot spot categories include one or more of string hot spots, planar hot spots, strip hot spots, and dot hot spots.

[0145] The second determination module 124 is specifically configured to determine a first reference value of the first quantity and the second quantity; determine the reference value range to which the first reference value belongs according to the preset reference value ranges corresponding to each candidate hot spot category; and determine that the first score of the candidate hot spot category corresponding to the reference value range to which the first reference value belongs is higher than the first score of the candidate hot spot category corresponding to the reference value range that does not include the first reference value; wherein, the candidate hot spot categories are sorted in descending order of the corresponding reference value ranges as string hot spots, planar hot spots, strip hot spots, and dot hot spots.

[0146] The second determination module 124 is specifically configured to determine the rectangularity and circularity of the hot spot area according to the contour information of the hot spot area; if the rectangularity is greater than the circularity, determine that the second scores of the string hot spot, the planar hot spot, and the strip hot spot are greater than the second score of the dot hot spot; if the rectangularity is less than the circularity, determine that the second scores of the string hot spot, the planar hot spot, and the strip hot spot are less than the second score of the dot hot spot.

[0147] The second determination module 124 is further configured to determine the minimum circumscribed rotated rectangle of the hot spot area and determine a second reference value of the long side and the short side of the minimum circumscribed rotated rectangle; if the second reference value is greater than a preset first reference threshold, determine that the second score of the planar hot spot is less than the second score of the strip hot spot; if the second reference value is not greater than the preset first reference threshold, determine that the second score of the planar hot spot is greater than the second score of the strip hot spot.

[0148] The second determination module 124 is specifically configured to determine the target score of each candidate hot spot category according to the first score of the candidate hot spot category, the quantity weight value corresponding to the first score, the second score, and the contour weight value corresponding to the second score.

[0149] The second determination module 124 is further configured to determine a first reference value of the first quantity and the second quantity. If the first reference value is greater than a preset second reference threshold, it is determined that the target hot spot category corresponding to the hot spot area is a string hot spot.

[0150] The first determination module 123 is specifically configured to determine a reference edge of the photovoltaic panel area according to the position or movement trajectory of the drone that acquires the image; determine the number of pixel points included in the photovoltaic panel area according to the number of pixel points included in the reference edge and the aspect ratio of the length and width of the photovoltaic panel area determined in advance; and determine a second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area according to the number of pixel points included in the photovoltaic panel area and the number of photovoltaic modules included in the photovoltaic panel area determined in advance.

[0151] The acquisition module 121 is specifically configured to input the image including the photovoltaic panel into a pre-trained image segmentation model, and determine the photovoltaic panel area in the image based on the image segmentation model; wherein, the image segmentation model is trained based on the sample images including the photovoltaic panel in the sample set and the position information of the sample photovoltaic panel areas annotated in the sample images.

[0152] This application also provides an electronic device, as Figure 13 shown, including: a processor 301, a communication interface 302, a memory 303, and a communication bus 304. Among them, the processor 301, the communication interface 302, and the memory 303 complete mutual communication through the communication bus 304;

[0153] A computer program is stored in the memory 303. When the program is executed by the processor 301, the processor 301 is caused to execute any of the above method steps.

[0154] The communication bus mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, only a thick line is shown in the figure, but it does not mean that there is only one bus or one type of bus.

[0155] The communication interface 302 is used for communication between the above-mentioned electronic device and other devices.

[0156] The memory may include a Random Access Memory (RAM), or may also include a Non-Volatile Memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0157] The above-mentioned processor may be a general-purpose processor, including a central processing unit, a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0158] This application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program executable by an electronic device. When the program runs on the electronic device, it enables the electronic device to implement any of the above method steps when executed.

[0159] Although the preferred embodiments of this application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of this application.

[0160] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to include these changes and modifications.

Claims

1. A hot spot detection method, characterized in that, The method includes: Obtain an image including a photovoltaic panel, and determine the photovoltaic panel area in the image; Detect whether there is a hot spot area in the photovoltaic panel area; In response to the existence of a hot spot area in the photovoltaic panel area, determine a first quantity of pixel points included in the hot spot area, contour information of the hot spot area, and a second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area; Determine respective first scores of each candidate hot spot category according to the magnitude relationship between the first quantity and the second quantity; Determine respective second scores of each candidate hot spot category according to the contour information of the hot spot area; Determine a target hot spot category corresponding to the hot spot area from each candidate hot spot category according to the respective first scores and second scores of each candidate hot spot category; Wherein, the candidate hot spot categories include one or more of string hot spots, planar hot spots, strip hot spots, and dot hot spots.

2. The method according to claim 1, characterized in that, The determining a target hot spot category corresponding to the hot spot area from each candidate hot spot category according to the respective first scores and second scores of each candidate hot spot category includes: Determine respective target scores of each candidate hot spot category according to the respective first scores and second scores of each candidate hot spot category; and determine the candidate hot spot category corresponding to the maximum value of the determined respective target scores as the target hot spot category corresponding to the hot spot area.

3. The method according to claim 1, characterized in that, The determining respective first scores of each candidate hot spot category according to the magnitude relationship between the first quantity and the second quantity includes: Determine a first reference value of the first quantity and the second quantity; Determine the reference value range to which the first reference value belongs according to the preset reference value ranges corresponding to each candidate hot spot category; Determine that the first score of the candidate hot spot category corresponding to the reference value range to which the first reference value belongs is higher than the first score of the candidate hot spot category corresponding to the reference value range not including the first reference value; Wherein, the candidate hot spot categories are sorted as string hot spots, planar hot spots, strip hot spots, and dot hot spots in descending order of the corresponding reference value ranges.

4. The method according to claim 1, characterized in that, The determining respective second scores of each candidate hot spot category according to the contour information of the hot spot area includes: Determine the rectangularity and circularity of the hot spot area according to the contour information of the hot spot area; If the rectangularity is greater than the circularity, determine that the respective second scores of the string hot spots, planar hot spots, and strip hot spots are greater than the second score of the dot hot spots; If the rectangularity is less than the circularity, determine that the respective second scores of the string hot spots, planar hot spots, and strip hot spots are less than the second score of the dot hot spots.

5. The method according to claim 4, wherein If the rectangularity is greater than the circularity, the method further includes: Determine the minimum circumscribed rotated rectangle of the hot spot area, and determine a second reference value of the long side and the short side of the minimum circumscribed rotated rectangle; If the second reference value is greater than a preset first reference threshold, determine that the second score of the planar hot spot is less than the second score of the strip hot spot; If the second reference value is not greater than the preset first reference threshold, determine that the second score of the planar hot spot is greater than the second score of the strip hot spot.

6. The method according to claim 2, wherein The determining the target score of each candidate hot spot category according to the first score and the second score of each candidate hot spot category respectively includes: For each candidate hot spot category, determine the target score of the candidate hot spot category according to the first score of the candidate hot spot category, the quantity weight value corresponding to the first score, the second score, and the contour weight value corresponding to the second score.

7. The method according to claim 3, wherein After determining the first reference value of the first quantity and the second quantity, the method further includes: If the first reference value is greater than a preset second reference threshold, determine that the target hot spot category corresponding to the hot spot area is a string hot spot.

8. The method according to claim 1, wherein Determining the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area includes: Determine the reference edge of the photovoltaic panel area according to the position or movement trajectory of the drone that acquires the image; Determine the number of pixel points included in the photovoltaic panel area according to the number of pixel points included in the reference edge and the aspect ratio of the photovoltaic panel area determined in advance; Determine the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area according to the number of pixel points included in the photovoltaic panel area and the number of photovoltaic modules included in the photovoltaic panel area determined in advance.

9. The method according to claim 1, characterized in that, The determining the photovoltaic panel area in the image includes: Input the image including the photovoltaic panel into a pre-trained image segmentation model, and based on the image segmentation model, determine the photovoltaic panel area in the image; Wherein, the image segmentation model is trained based on the position information of the sample photovoltaic panel area marked in the sample image including the photovoltaic panel in the sample set.

10. A hot spot detection device, characterized in that, The device includes: An acquisition module, configured to acquire an image including a photovoltaic panel and determine the photovoltaic panel area in the image; A detection module, configured to detect whether there is a hot spot area in the photovoltaic panel area; A first determination module, configured to, in response to the existence of a hot spot area in the photovoltaic panel area, determine the first quantity of pixel points included in the hot spot area, the contour information of the hot spot area, and the second quantity of pixel points included in a single photovoltaic module in the photovoltaic panel area; A second determination module, configured to determine the first score of each candidate hot spot category according to the magnitude relationship between the first quantity and the second quantity; Determine the second score of each candidate hot spot category according to the contour information of the hot spot area; Determine the target hot spot category corresponding to the hot spot area from each candidate hot spot category according to the first score and the second score of each candidate hot spot category respectively; Wherein, the candidate hot spot categories include one or more of string hot spots, planar hot spots, strip hot spots, and dot hot spots.

11. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus; The memory is used for storing a computer program; The processor is configured to, when executing the program stored on the memory, implement the method according to any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 1-9 is implemented.

Images