Lightning rapid identification method based on image sequence brightness change information

Abstract

The invention provides a lightning rapid identification method based on image sequence brightness change information, and the method comprises the steps: obtaining an image at the current time, and converting the image into a first grayscale image; obtaining continuous N frames of comparison images within a preset period of time before the current time, and converting the N frames of comparison images into N frames of second gray level images; wherein the N frames of second grayscale images comprise a second grayscale image corresponding to a previous frame of image of the image at the current time, and the N frames of second grayscale images are recorded as third grayscale images; obtaining a candidate image according to the brightness entropy change value between the first gray level image and the N frames of second gray level images and the standard deviation of the brightness entropy change value; and determining whether there is a lightning channel in the candidate image based on the form of the highlight area. The method has the advantages that the occurrence of the lightning event can be quickly and accurately identified, automatic and quick screening of the lightning event is realized, the problem of false triggering easily occurring in lightning optical observation is solved, and the observation efficiency and the data quality are effectively improved.

Description

Technical Field

[0001] This application relates to the field of meteorological detection. Specifically, it relates to a lightning recognition method based on an image sequence. Background Art

[0002] Lightning often occurs along with severe convective weather (such as thunderstorms, hailstorms, typhoons, squall lines, etc.). Real-time monitoring and early warning of lightning and taking protective measures can effectively reduce casualties and property losses. Lightning generates physical signals such as sound, light, electricity, and magnetism. In the prior art, the widely used method for automatic observation of lightning events is the acquisition, analysis, and processing of electromagnetic signals. However, the observation of electromagnetic signals is easily interfered, and the requirement for the time synchronization accuracy of multiple stations is also very high. There are systematic and random deviations in the positioning results. With the continuous progress of various technologies and the continuous upgrading of application requirements, the accuracy requirement for lightning detection results is getting higher and higher. In some application scenarios, the detection results based on electromagnetic signals can no longer meet the accuracy requirements.

[0003] Another method for lightning observation is optical observation, which is the direct capture of the optical radiation signal of the lightning channel. It can intuitively provide accurate and reliable lightning channel information and lightning position information. It is a very important lightning observation means, and many important discoveries in lightning physics research come from the analysis of optical observation results. When verifying and evaluating the quality of lightning electromagnetic detection results, optical data is an important evaluation basis.

[0004] Lightning is an instantaneous and rapidly changing discharge event, and the duration of some lightning is even only a few milliseconds. Therefore, high-quality optical observation of lightning requires the use of high-speed shooting methods. The emergence of commercial high-speed cameras has solved the technical bottleneck of high-speed photography. However, the difficulty of automatic optical observation of lightning is still very high. The main reason is that it is limited by the instantaneousness and occasionality of lightning. The applicable detection method is trigger recording, that is, recording only when lightning occurs, rather than continuous recording. This requires reliable and accurate trigger conditions.

[0005] At present, most lightning analysis studies based on optical observations use semi-automatic or manual triggering methods to obtain data. Automatic triggering mainly relies on electromagnetic or light intensity signals, often resulting in frequent false triggers, and the data contains a large number of images without lightning. At the same time, high frame rates bring extremely high data volumes, and a large amount of work is required to screen out lightning-containing images before use, resulting in very low observation efficiency and data acquisition rates. Existing traditional algorithms for lightning optical image recognition are all based on image morphology algorithms, with large computational amounts and difficult to meet the requirements of fast and real-time recognition. Among them, the invention patent with patent number CN116797823A discloses a lightning channel image recognition method, which uses an edge detection algorithm to obtain the lightning contour, and then realizes the recognition of the lightning channel through methods such as threshold segmentation and morphological processing. This type of lightning recognition method based on image morphological features is for single images, can achieve pixel-level recognition accuracy, and the goal is to identify all lightning channels in the image. Due to the complex algorithm and large computational amount, it is suitable for application scenarios with low requirements for operation time. Therefore, it is only suitable for accurately identifying lightning channels in images after recording lightning images, but not suitable as a method for real-time discrimination of whether a lightning event occurs.

[0006] In summary, there is a need in the art to provide an accurate and fast image-based lightning event recognition method to overcome the deficiencies of the prior art. Summary of the Invention

[0007] The present application provides a lightning recognition method based on an image sequence. This method is not targeted at single-frame images but is based on consecutive frame images obtained over a period of time, and it can solve the problems existing in the prior art. The objectives of the present application are achieved through the following technical solutions.

[0008] In a first aspect, an embodiment of the present application provides a lightning recognition method based on an image sequence, which uses real-time acquired image information to quickly determine whether a lightning event has occurred and provides a reliable trigger signal for the optical observation of lightning. It includes multiple steps:

[0009] Step 1: Obtain an image at the current time, convert the image into a first grayscale image.

[0010] Step 2: Obtain N consecutive comparison images within a preset period of time before the current time, and convert the N comparison images into N second grayscale images; among them, the N second grayscale images include the second grayscale image corresponding to the previous frame image of the image at the current time, denoted as the third grayscale image.

[0011] Step 3: Obtain candidate images based on the brightness entropy change value and its standard deviation between the first grayscale image and the N second grayscale images; and

[0012] Step 4: Determine whether there is a lightning channel in the candidate image based on the morphology of the highlighted region of the candidate image.

[0013] According to the lightning recognition method based on an image sequence provided by the above-mentioned embodiment of the present application, wherein Step 3: Obtaining a candidate image according to the brightness entropy change value and its standard deviation between the first grayscale image and N frames of second grayscale images includes the following steps:

[0014] Step 31: Calculate the brightness entropy of the first grayscale image and each frame of the second grayscale image;

[0015] Step 32: Divide the N frames of second grayscale images into M groups in the order of shooting time, the number of second grayscale images in each group is n, and calculate the average change value V of the brightness entropy of each group of second grayscale images;

[0016] Step 33: Calculate the standard deviation σ of the average change value V of the M groups of second grayscale images according to the average change value V of the brightness entropy of each group of second grayscale images;

[0017] Step 34: Calculate the brightness entropy change value Vi between the first grayscale image and the third grayscale image; and

[0018] Step 35: Determine whether Vi is greater than or equal to a preset first threshold. If "yes", execute Step 4; if "no", the process ends.

[0019] According to the lightning recognition method based on an image sequence provided by the above-mentioned embodiment of the present application, wherein Step 4: Determining whether there is a lightning channel in the candidate image based on the morphology of the highlighted region includes the following steps;

[0020] Step 41: Obtain each mutation pixel point in the first grayscale image whose brightness change exceeds a preset second threshold compared with the same position in the third grayscale image;

[0021] Step 42: Set the mutation pixel points with connected positions as the area of interest; among them, the mutation pixel points may form multiple independent areas of interest;

[0022] Step 43: Select the area of interest with a large area as the target area;

[0023] Step 44: Determine whether the target area conforms to the linear feature. If "yes", execute Step 45; if "no", execute Step 46;

[0024] Step 45: Determine that the image at the current time includes lightning, and then the process ends; and

[0025] Step 46: Determine that there is no lightning in the image at the current time, and then the process ends.

[0026] The lightning recognition method based on an image sequence provided by one of the above - mentioned embodiments of the present application, wherein the calculation formula for the brightness entropy of each grayscale image frame is:

[0027] , where ,

[0028] where E is the brightness entropy of the image, x(i, j) refers to the brightness value of the pixel at the position (i, j) in the image, and the range of the brightness value is [0, 255].

[0029] The lightning recognition method based on an image sequence provided by one of the above - mentioned embodiments of the present application, wherein the calculation formula for the average change value V of the brightness entropy of each group of second grayscale images is: , where Ei is the brightness entropy of the i - th image.

[0030] The lightning recognition method based on an image sequence provided by one of the above - mentioned embodiments of the present application, wherein the calculation formula for the standard deviation σ of the average change value V of the brightness entropy of M groups of second grayscale images calculated according to the average change value V of the brightness entropy of each group of second grayscale images is:

[0031] σ = , where , is the average change value of entropy of the i - th group in M groups.

[0032] The lightning recognition method based on an image sequence provided by one of the above - mentioned embodiments of the present application, wherein step 44: determining whether the target area conforms to the linear feature includes the following steps:

[0033] Step 441: Taking the upper, lower, left, and right of the target area as vertices, forming a circumscribed quadrilateral of the target area, and obtaining the aspect ratio D of the circumscribed quadrilateral; and

[0034] Step 442: Judging whether the aspect ratio D is greater than a preset aspect ratio d. If "yes", execute step 45; if "no", execute step 46.

[0035] The lightning recognition method based on an image sequence provided by one of the above - mentioned embodiments of the present application, wherein the first threshold is Aσ, where A is a preset coefficient.

[0036] The lightning recognition method based on image sequences disclosed in this application can be used in conjunction with existing lightning channel observation systems. The lightning channel observation system includes a photographing unit and a control component. The control component is electrically connected to the photographing unit. The photographing unit takes pictures and transmits the images to the control component. When the control component uses the lightning recognition method based on image sequences in an embodiment of this application to analyze the images of the photographing unit and determines that a lightning event has occurred, the control component records the time of the lightning event and stores the images taken by the photographing unit. The control component includes a chassis, a processor, a GPS antenna, a GPS timing unit, and a power supply. The processor is arranged inside the chassis and is electrically connected to the photographing unit. The GPS antenna is installed outside the chassis, the GPS timing unit is installed inside the chassis, the GPS antenna is electrically connected to the GPS timing unit, and the GPS timing unit is electrically connected to the processor. The power supply is arranged inside the chassis and is connected to the processor.

[0037] In a second aspect, an embodiment of this application provides an electronic device, including: a memory, a processor; wherein, the memory is used to store one or more computer instructions, and when the one or more computer instructions are executed by the processor, the lightning recognition method based on image sequences shown in the above first aspect is implemented.

[0038] In a third aspect, an embodiment of this application provides a computer storage medium for storing a computer program, and when the computer program is executed by a computer, the lightning recognition method based on image sequences shown in the above first aspect is implemented.

[0039] In a fourth aspect, an embodiment of this application provides a computer program product, including: a computer-readable storage medium storing computer instructions, and when the computer instructions are executed by one or more processors, the one or more processors are caused to execute the steps in the lightning recognition method based on image sequences in the above first aspect.

[0040] The advantages of the lightning recognition method based on image sequences according to the embodiments of this application are as follows: It can quickly and accurately identify the occurrence of lightning events, avoiding the multi-level convolution and matrix algorithms that are necessary for image morphology with a huge amount of computation (the basic calculation method of the convolution algorithm is to slide pixel matrices of different sizes on the image for calculation, and the amount of computation increases exponentially with the increase of image pixels). The amount of computation is only one-thousandth of the morphology algorithm. It can identify lightning events within milliseconds, solve the problem of false triggering that is prone to occur in lightning optical observations, realize the automatic and rapid screening of lightning events, improve the acquisition efficiency and observation quality of lightning optical data, and truly realize the full-automatic optical observation of lightning; it is not only beneficial to lightning scientific research, but also has high application value in aspects such as lightning accident investigation and lightning activity warning. Description of the Drawings

[0041] Other features, objectives, and advantages of the present application will become more apparent through the following detailed description of non - restrictive embodiments of the present application with reference to the accompanying drawings.

[0042] Figure 1 The flowchart of the lightning recognition method based on an image sequence according to an embodiment of the present application is shown.

[0043] Figure 2 Shown as Figure 1 The flowchart of determining whether a target area conforms to a linear feature in the lightning recognition method based on an image sequence according to an embodiment of the present application as shown.

[0044] Figure 3 The lightning channel observation system of the lightning recognition method based on an image sequence according to an embodiment of the present application is shown.

[0045] Figure 4 The third grayscale image converted from the previous - frame image at the current moment is shown.

[0046] Figure 5 The first grayscale image converted from the image at the current moment is shown. Detailed implementation manners

[0047] The following describes the specific implementation manners of the present application in conjunction with the accompanying drawings and embodiments. Through the content recorded in this specification, those skilled in the art can clearly and completely understand the technical solution of the present application, the technical problems solved, and the technical effects produced. It can be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. In addition, for the convenience of description, only the parts related to the present application are shown in the drawings.

[0048] It should be noted that the structures, ratios, sizes, etc. shown in the drawings of the specification are only used to cooperate with the content recorded in the specification for those skilled in the art to understand and read, and are not used to limit the conditions under which the present application can be implemented. Therefore, they do not have technical essential significance. Any modification of the structure, change of the proportional relationship, or adjustment of the size, without affecting the efficacy that the present application can produce and the purpose that can be achieved, should fall within the scope covered by the technical content disclosed in the present application.

[0049] The terms such as "first", "second", "said", etc. as referred to do not indicate a limitation in quantity and may indicate singular or plural. The terms "comprising", "including", "having" and any variations thereof involved in the present application are intended to cover non-exclusive inclusion; for example, a process, method, system, product or device comprising a series of steps or modules is not limited to the listed steps or units, but may further include steps or units not listed, or may further include other steps or units inherent to these processes, methods, products or devices. The terms "connected", "coupled", etc. similar to those involved in the present application are not limited only to physical or mechanical connections, but may also include direct or indirect electrical connections.

[0050] In a first aspect, Figure 1 A flowchart of a lightning recognition method based on an image sequence according to an embodiment of the present application is shown. As Figure 1 shown, the lightning recognition method based on an image sequence includes multiple steps:

[0051] Step 1: Obtain an image at the current time and convert the image into a first grayscale image; wherein, the method of converting the image into a grayscale image includes but is not limited to: average method, weighted method or maximum / minimum method; for example: Figure 5 A first grayscale image of the image conversion at the current moment is shown;

[0052] Step 2: Obtain N consecutive comparison images within a preset period of time before the current time, and convert the N comparison images into N second grayscale images; wherein, the N second grayscale images include the second grayscale image corresponding to the previous frame image of the image at the current time, denoted as the third grayscale image; for example: Figure 4 A third grayscale image of the conversion of the previous frame image at the current moment is shown;

[0053] Step 3: Obtain candidate images according to the brightness entropy change value and its standard deviation between the first grayscale image and the N second grayscale images; and

[0054] Step 4: Determine whether there is a lightning channel in the candidate images based on the morphology of the highlighted area.

[0055] According to the lightning recognition method based on an image sequence provided by the above embodiment of the present application, wherein Step 3: Obtaining candidate images according to the brightness entropy change value and its standard deviation between the first grayscale image and the N second grayscale images includes the following steps:

[0056] Step 31: Calculate the brightness entropy of the first grayscale image and each second grayscale image;

[0057] Step 32: Divide the N second grayscale images into M groups in the chronological order of shooting. The number of second grayscale images in each group is n, and calculate the average change value V of the brightness entropy of the second grayscale images in each group;

[0058] Step 33: Calculate the standard deviation σ of the average change value V of the M groups of second grayscale images based on the average change value V of the brightness entropy of the second grayscale images in each group;

[0059] Step 34: Calculate the brightness entropy change value Vi between the first grayscale image and the third grayscale image; and

[0060] Step 35: Determine whether Vi is greater than or equal to a preset first threshold. If "yes", execute Step 4; if "no", the process ends.

[0061] According to the lightning recognition method based on an image sequence provided by the above-mentioned one embodiment of the present application, wherein Step 4: Judging whether there is a lightning channel in the candidate image based on the morphology of the highlighted area includes the following steps;

[0062] Step 41: Obtain the mutation pixel points in the first grayscale image where the brightness change exceeds a preset second threshold compared with the same position in the third grayscale image;

[0063] Step 42: Set the mutation pixel points with connected positions as the areas of interest; among them, the mutation pixel points may form multiple independent areas of interest;

[0064] Step 43: Select the area of interest with a large area as the target area;

[0065] Step 44: Judge whether the target area conforms to the linear feature. If "yes", execute Step 45; if "no", execute Step 46;

[0066] Step 45: Determine that the image at the current time includes lightning, and then the process ends; and

[0067] Step 46: Determine that there is no lightning in the image at the current time, and then the process ends.

[0068] According to the lightning recognition method based on an image sequence provided by the above-mentioned one embodiment of the present application, wherein the brightness entropy calculation formula of each grayscale image is:

[0069] , where ,

[0070] where E is the brightness entropy of the image, x(i,j) refers to the brightness value of the pixel at the position (i,j) in the image, and the range of the brightness value is [0, 255].

[0071] The lightning recognition method based on an image sequence provided by the above-mentioned one embodiment of the present application, wherein the calculation formula for the average change value V of the brightness entropy of each group of second grayscale images is:

[0072] , where Ei is the brightness entropy of the i-th image.

[0073] The lightning recognition method based on an image sequence provided by the above-mentioned one embodiment of the present application, wherein the calculation formula for calculating the standard deviation σ of M groups of second grayscale images according to the average change value V of the brightness entropy of each group of second grayscale images is:

[0074] σ = , where , is the average change value of entropy of the i-th group among M groups.

[0075] The lightning recognition method based on an image sequence provided by the above-mentioned one embodiment of the present application, wherein the first threshold is Aσ, where A is a preset coefficient, for example: positive integers such as 2, 3...; the second threshold is 2 times the brightness of the pixel point of the third grayscale image, and the maximum value is 255.

[0076] Figure 2 shows the Figure 1 flowchart of judging whether the target area conforms to the linear feature in the lightning recognition method based on an image sequence according to one embodiment of the present application as shown. As Figure 2 shown, step 44: Judging whether the target area conforms to the linear feature includes the following steps:

[0077] Step 441: Taking the upper, lower, left, and right of the target area as vertices, forming a circumscribed quadrilateral of the target area, and obtaining the aspect ratio D of the circumscribed quadrilateral; and

[0078] Step 442: Judging whether the aspect ratio D is greater than a preset aspect ratio d. Preferably, d is greater than 10; if "yes", execute step 45; if "no", execute step 46.

[0079] The lightning recognition method based on an image sequence provided by the above-mentioned one embodiment of the present application, wherein judging whether the target area conforms to the linear feature means judging whether the shape of the target area is linear. Commonly used methods are edge detection (based on algorithms such as Canny and Sobel) and Hough Transform, but the computational complexity of such algorithms will increase exponentially severely with the improvement of image resolution and the increase of edge complexity. Therefore, it is not suitable for the scenario of quickly judging whether lightning occurs in the present application; while the judgment of the linear feature based on the aspect ratio can greatly improve the judgment speed. When the aspect ratio value is very large, the target area can be determined to be linear.

[0080] The lightning recognition method based on an image sequence provided by the above-described embodiment of the present application, wherein the value range of the preset aspect ratio d is 20 - 50, and preferably, the value of the aspect ratio d is 20.

[0081] The lightning recognition method based on an image sequence disclosed in the present application can be used in cooperation with an existing lightning channel observation system. Figure 3 Fig. shows a lightning channel observation system for the lightning recognition method based on an image sequence according to an embodiment of the present application. Figure 3 As shown, the lightning channel observation system includes a photographing unit 901 and a control component 902. The control component 902 is electrically connected to the photographing unit 901. The photographing unit 901 takes a photograph and transmits the image to the control component 902. The control component 902 scrolls and pre-stores a continuous frame image sequence for a certain period of time, and uses the lightning recognition method based on an image sequence according to an embodiment of the present application to analyze the received image sequence. When it is determined that a lightning event occurs, the control component 902 records the time of the lightning event and officially stores the image sequence photographed by the photographing unit 901. The control component 902 includes a chassis 9021, a processor 9022, a GPS antenna 9023, a GPS time service unit 9024, and a power supply 9025. The processor 9022 is disposed in the chassis 9021, and the processor 9022 is electrically connected to the photographing unit 901. The GPS antenna 9023 is installed outside the chassis 9021, the GPS time service unit 9024 is installed in the chassis 9021, the GPS antenna 9023 is electrically connected to the GPS time service unit 9024, and the GPS time service unit 9024 is electrically connected to the processor 9022. The power supply 9025 is disposed in the chassis 9021 and is connected to the processor 9022.

[0082] In a second aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor; wherein, the memory is used for storing one or more computer instructions, and when the one or more computer instructions are executed by the processor, the lightning recognition method based on an image sequence shown in the above first aspect is implemented.

[0083] In a third aspect, an embodiment of the present application provides a computer storage medium for storing a computer program, and when the computer program is executed by a computer, the lightning recognition method based on an image sequence shown in the above first aspect is implemented.

[0084] In a fourth aspect, an embodiment of the present application provides a computer program product, including: a computer-readable storage medium storing computer instructions, and when the computer instructions are executed by one or more processors, the one or more processors are caused to execute the steps in the lightning recognition method based on an image sequence in the above first aspect.

[0085] The advantages of the lightning recognition method based on an image sequence according to an embodiment of the present application are as follows: it can recognize the occurrence of lightning events in real time, quickly (millisecond level), and accurately, solves the reliable triggering problem of optical lightning observations and the automatic and rapid discrimination of lightning events, improves the acquisition efficiency of lightning optical data, and truly realizes the full-automatic optical observation of lightning; it is not only beneficial to lightning scientific research, but also has high application value in aspects such as lightning accident investigation and lightning activity warning.

[0086] Although the present application has been described and illustrated with reference to specific embodiments of the present application, such descriptions and illustrations are not intended to limit the present application. Those skilled in the art can clearly understand that various changes can be made, and equivalent elements can be substituted within the embodiments without departing from the protection scope of the present application as defined by the claims. Due to variables in the manufacturing process, etc., there may be differences between the technical reproduction in the present application and the actual device. There may be other embodiments of the present application that are not specifically described. The specification and the drawings should be regarded as illustrative rather than restrictive, and modifications can be made in accordance with the purpose and spirit of the present application, and all such modifications are within the protection scope of the claims. Although the methods disclosed herein have been described with reference to specific operations performed in a specific order, it should be understood that these operations can be recombined, subdivided, or arranged to form equivalent methods without departing from the disclosure of the present application. Therefore, unless specifically indicated herein, the order and grouping of operations do not limit the present application.

Claims

1. A lightning recognition method based on an image sequence, characterized in that, It includes multiple steps: Step 1: Obtain an image of the current time and convert the image into a first grayscale image; Step 2: Obtain N consecutive comparison images within a preset period of time before the current time, and convert the N comparison images into N second grayscale images; among them, the second grayscale image corresponding to the previous frame image of the image at the current time is included in the N second grayscale images, denoted as the third grayscale image; Step 3: Obtain a candidate image according to the brightness entropy change value and its standard deviation between the first grayscale image and the N second grayscale images; and Step 4: Judge whether there is a lightning channel in the candidate image based on the morphology of the highlighted area.

2. The lightning recognition method based on an image sequence according to claim 1, wherein Step 3: Obtain a candidate image according to the brightness entropy change value and its standard deviation between the first grayscale image and the N second grayscale images, including the following steps: Step 31: Calculate the brightness entropy of the first grayscale image and each second grayscale image; Step 32: Divide the N second grayscale images into M groups in the order of shooting time, with the number of second grayscale images in each group being n, and calculate the average change value V of the brightness entropy of each group of second grayscale images; Step 33: Calculate the standard deviation σ of the average change value V of the M groups of second grayscale images according to the average change value V of the brightness entropy of each group of second grayscale images; Step 34: Calculate the brightness entropy change value Vi between the first grayscale image and the third grayscale image; And Step 35: Judge whether Vi is greater than or equal to a preset first threshold. If "yes", execute Step 4; if "no", the process ends.

3. The lightning recognition method based on an image sequence according to any one of claims 1 or 2, characterized in that Step 4: Judging whether there is a lightning channel in the candidate image based on the morphology of the highlighted area includes the following steps; Step 41: Obtain each mutation pixel point in the first grayscale image whose brightness change compared to the same position in the third grayscale image exceeds a preset second threshold; Step 42: Set the mutation pixel points with connected positions as the area of concern; among them, the mutation pixel points may form multiple independent areas of concern; Step 43: Select the area of concern with a large area as the target area; Step 44: Judge whether the target area conforms to the linear feature. If "yes", execute Step 45; if "no", execute Step 46; Step 45: Determine that the image at the current time includes lightning, and then the process ends; and Step 46: Determine that there is no lightning in the image at the current time, and then the process ends.

4. The lightning recognition method based on an image sequence according to claim 2, characterized in that The calculation formula for the brightness entropy of each frame of grayscale image is: , where , where E is the brightness entropy of the image, x(i,j) refers to the brightness value of the pixel at the position (i,j) in the image, and the range of the brightness value is [0, 255].

5. The lightning recognition method based on an image sequence according to claim 4, characterized in that The calculation formula for the average change value V of the brightness entropy of each group of second grayscale images is: , where Ei is the luminance entropy of the i-th image.

6. The lightning recognition method based on an image sequence according to claim 5, wherein The calculation formula for calculating the standard deviation σ of the M groups of second grayscale images according to the average change value V of the brightness entropy of each group of second grayscale images is: σ = , where , is the entropy average change value of the i-th group in the M groups.

7. The lightning recognition method based on an image sequence according to claim 3, wherein, Step 44: Judging whether the target area conforms to the linear feature includes the following steps: Step 441: Take the upper, lower, left, and right vertices of the target area to form a circumscribed quadrilateral of the target area, and obtain the aspect ratio D of the circumscribed quadrilateral; And Step 442: Judge whether the aspect ratio D is greater than a preset aspect ratio d. If "yes", execute Step 45; if "no", execute Step 46.

8. The lightning recognition method based on an image sequence according to claim 7, wherein, The value range of the preset aspect ratio d is 20 - 50.

9. The lightning recognition method based on an image sequence according to claim 7, characterized in that The first threshold is Aσ, where A is a preset coefficient.

Images