Flame region division method and device and storage medium

Through the image segmentation algorithm and the division method of RGB values ​​and gray values, the flame area and the air smoke area are automatically divided, which solves the problem of low manual division efficiency in the existing technology and achieves efficient and accurate flame area division.

CN119338793APending Publication Date: 2025-01-21GUANGDONG POWER GRID CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411460728.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-18
Publication Date
2025-01-21

AI Technical Summary

Technical Problem

The existing flame zone division method relies on manual identification and division, resulting in low accuracy, long-term and low efficiency.

Method used

The image segmentation algorithm is used to determine the flame area and air smoke area, and the flame area and air smoke area are divided according to the RGB value and gray value to achieve automatic division.

Benefits of technology

There is no need for manual review and manual division, which significantly reduces the flame division time and improves the efficiency and accuracy of flame area division.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119338793A_ABST
    Figure CN119338793A_ABST
Patent Text Reader

Abstract

The invention discloses a flame region division method and device and a storage medium. Acquiring a plurality of flame images to be processed; determining a flame region and an air smoke region in the flame image to be processed by adopting an image segmentation algorithm; determining a center line of the flame image to be processed, and extracting an RGB value on the center line of the flame area and a gray value on the center line of the air smoke area; the flame area is divided into a discontinuous flame area and a continuous flame area according to the RGB value, and the air smoke area is divided into an air area and a smoke area according to the gray value. According to the embodiment of the invention, the flame region and the air smoke region in the flame image to be processed are determined by adopting the image segmentation algorithm, and the flame region is divided according to the RGB value and the gray value, so that manual checking and manual flame region division are not needed, the flame division duration can be effectively shortened, and the flame region division efficiency can be effectively improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a flame region division method, device and storage medium. Background Art

[0002] Wildfires are common natural disasters in nature. During the operation of power transmission lines, the high conductivity of wildfires, as well as the high temperature and smoke particles generated by combustion, will cause the air insulation level of the line to decrease, thus causing the transmission line to trip. In addition, the probability of reclosing failure is high, which seriously threatens the safe and reliable operation of the transmission line.

[0003] According to the different effects of flame morphology characteristics, combustion products and other factors in the regional discharge process, the region is often divided into different sections in the study of air regional breakdown characteristics and discharge mechanism under the action of flame.

[0004] The existing flame area division method usually first reduces the interference of the background and highlights the subject through image preprocessing, and then manually identifies and divides the flame area. However, the manual division method has low accuracy and is time-consuming, resulting in low efficiency of the existing flame area division. Summary of the invention

[0005] The present invention provides a flame region division method, device and storage medium to solve the technical problem that the existing flame region division method first reduces background interference and highlights the main body through image preprocessing, and then manually performs flame region identification and division, but the manual division method has low accuracy and is time-consuming, resulting in low efficiency of the existing flame region division.

[0006] The present invention provides a flame region division method, comprising:

[0007] Acquire multiple flame images to be processed;

[0008] Using image segmentation algorithm, the flame area and air smoke area in the flame image to be processed are determined;

[0009] Determine the center line of the flame image to be processed, extract the RGB value on the center line of the flame area, and the gray value on the center line of the air smoke area;

[0010] The flame region is divided into a discontinuous flame region and a continuous flame region according to the RGB value, and the air and smoke region is divided into an air region and a smoke region according to the grayscale value.

[0011] Further, determining the center line of the flame image to be processed includes:

[0012] Using an edge detection algorithm to determine the edge of the flame area in the flame image to be processed;

[0013] According to determining the center point of the edge of the flame area;

[0014] Extending from the central point to the other side of the flame image to be processed, the central line of the flame image to be processed is determined.

[0015] Furthermore, after determining the center line of the flame image to be processed, the method further includes:

[0016] The center line is smoothed.

[0017] Further, dividing the flame area into a discontinuous flame area and a continuous flame area according to the RGB value includes:

[0018] The area where the difference of the RGB values ​​of adjacent positions on the center line exceeds the preset value is used as the first dividing line for dividing the continuous flame area and the discontinuous flame area;

[0019] According to the first dividing line, the flame area is divided into a discontinuous flame area and a continuous flame area.

[0020] Further, dividing the air smoke area into an air area and a smoke area according to the grayscale value includes:

[0021] The area where the gray value difference between adjacent positions on the center line exceeds a preset value is used as the second dividing line for dividing the air area and the smoke area;

[0022] According to the second dividing line, the air-smoke area is divided into an air area and a smoke area.

[0023] Furthermore, the image segmentation algorithm includes at least one of a threshold segmentation algorithm and an edge detection algorithm.

[0024] The present invention provides a flame area division device, comprising:

[0025] A flame image acquisition module to be processed, used to acquire multiple flame images to be processed;

[0026] An image region determination module is used to determine the flame region and the air smoke region in the flame image to be processed by using an image segmentation algorithm;

[0027] A value extraction module is used to determine the center line of the flame image to be processed, extract the RGB value on the center line of the flame area, and the gray value on the center line of the air smoke area;

[0028] The flame area division module is used to divide the flame area into a discontinuous flame area and a continuous flame area according to the RGB value, and to divide the air smoke area into an air area and a smoke area according to the gray value.

[0029] Furthermore, the numerical extraction module is also used for:

[0030] Using an edge detection algorithm to determine the edge of the flame area in the flame image to be processed;

[0031] According to determining the center point of the edge of the flame area;

[0032] Extending from the central point to the other side of the flame image to be processed, the central line of the flame image to be processed is determined.

[0033] The present invention provides a terminal device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the flame area division method as described above is implemented.

[0034] The present invention provides a computer-readable storage medium, which includes a stored computer program; wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the flame area division method as described above.

[0035] The embodiment of the present invention determines the flame area and the air smoke area in the flame image to be processed by adopting an image segmentation algorithm, and divides the flame area into a discontinuous flame area and a continuous flame area according to the RGB value, and divides the air smoke area into an air area and a smoke area according to the grayscale value. There is no need for manual review and manual division of the flame area, which can effectively reduce the flame division time and effectively improve the efficiency of flame area division.

[0036] Furthermore, the embodiment of the present invention can accurately determine the center line of the flame image to be processed, and further determine its RGB value and grayscale value based on the center line to perform flame region division, thereby effectively improving the accuracy of flame region division. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic diagram of the flow of the flame area division method provided by an embodiment of the present invention;

[0038] Figure 2 It is a schematic diagram of the flame area division effect provided by an embodiment of the present invention.

[0039] Figure 3 This is a schematic diagram of the structure of the flame area division device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0041] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0042] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0043] See also Figure 1 The present invention provides a flame region division method, comprising:

[0044] S1, obtaining multiple flame images to be processed;

[0045] In the embodiment of the present invention, the flame image to be processed can be obtained by photographing. To obtain a better segmentation effect, the photographing device needs to maintain a sufficient distance from the flame image.

[0046] S2, using an image segmentation algorithm to determine the flame area and the air smoke area in the flame image to be processed;

[0047] In the embodiment of the present invention, before step S2, the flame image to be processed may be preprocessed, including denoising, reducing brightness, increasing contrast, etc., wherein the contrast and brightness only need to be slightly adjusted to highlight the subject, and avoid excessive adjustment that is not conducive to gap division. By preprocessing the flame image to be processed, the embodiment of the present invention can effectively eliminate interference factors and weaken the background to highlight the flame subject, thereby effectively improving the accuracy of flame area division.

[0048] In an embodiment of the present invention, the flame image to be processed includes a flame area and an air smoke area, wherein the air smoke area is a non-flame area, and there is a relatively obvious edge between the non-flame area and the flame area. The flame area and the air smoke area can be determined based on an image segmentation algorithm combined with an edge detection algorithm.

[0049] S3, determining the center line of the flame image to be processed, extracting the RGB value on the center line of the flame area, and the gray value on the center line of the air smoke area;

[0050] In the embodiment of the present invention, the RGB value and the gray value on the center line may be determined, so as to further divide the flame into various regions.

[0051] S4. Divide the flame area into a discontinuous flame area and a continuous flame area according to the RGB value, and divide the air smoke area into an air area and a smoke area according to the gray value.

[0052] In the embodiment of the present invention, both the discontinuous flame area and the continuous flame area are flame areas, and the two are mainly different in color, that is, different in RGB values, and the continuous flame area and the discontinuous flame area can be accurately divided according to the difference in RGB values. The air area and the smoke area are mainly different in grayscale values, and the air area and the smoke area can be accurately divided according to the grayscale values.

[0053] The embodiment of the present invention determines the flame area and the air smoke area in the flame image to be processed by adopting an image segmentation algorithm, and divides the flame area into a discontinuous flame area and a continuous flame area according to the RGB value, and divides the air smoke area into an air area and a smoke area according to the grayscale value. There is no need for manual review and manual division of the flame area, which can effectively reduce the flame division time and effectively improve the efficiency of flame area division.

[0054] In one embodiment, determining the center line of the flame image to be processed includes:

[0055] Using edge detection algorithm to determine the edge of the flame area in the flame image to be processed;

[0056] According to the center point of the edge of the flame area is determined;

[0057] Extend from the center point to the other side of the flame image to be processed to determine the center line of the flame image to be processed.

[0058] In the embodiment of the present invention, after the center point of the flame edge is determined, a line may be extended to the other side of the flame image to be processed based on the center point based on Hough transform, thereby determining the center line of the flame image to be processed.

[0059] The embodiment of the present invention can accurately determine the center line of the flame image to be processed, and further determine its RGB value and grayscale value based on the center line to perform flame area division, thereby effectively improving the accuracy of flame area division.

[0060] In one embodiment, after determining the center line of the flame image to be processed, the method further includes:

[0061] Smooth the center line.

[0062] The embodiment of the present invention performs smoothing processing on the center line to eliminate small fluctuations caused by noise or inaccurate edge detection, thereby effectively and accurately obtaining the center line.

[0063] In one embodiment, the flame area is divided into a discontinuous flame area and a continuous flame area according to the RGB value, including:

[0064] The area where the difference of the RGB values ​​of adjacent positions on the center line exceeds the preset value is used as the first dividing line for dividing the continuous flame area and the discontinuous flame area;

[0065] According to the first dividing line, the flame area is divided into a discontinuous flame area and a continuous flame area.

[0066] In the embodiment of the present invention, the principle of dividing the flame area into a discontinuous flame area and a continuous flame area is:

[0067] The flame continuous zone burns most fully and has the highest temperature, and its flame is bright red; the flame discontinuous zone is located above the flame continuous zone, a certain distance away from the fuel, and its temperature is lower than the temperature of the continuous zone, and the flame is dull orange-yellow. The embodiment of the present invention extracts the RGB value on the center line, the RGB value of the flame continuous zone is greater than the RGB value of the discontinuous zone, and the difference in RGB values ​​between adjacent positions on the center line exceeds the preset value, that is, the RGB value on the center line shows a more obvious segmentation characteristic, and the segmentation point at this position is used as the first dividing line between the continuous flame zone and the discontinuous flame zone, so that the continuous flame zone and the discontinuous flame zone can be accurately divided.

[0068] In one embodiment, dividing the air smoke area into an air area and a smoke area according to the gray value includes:

[0069] The area where the gray value difference between adjacent positions on the center line exceeds a preset value is used as the second dividing line for dividing the air area and the smoke area;

[0070] According to the second dividing line, the air smoke area is divided into an air area and a smoke area.

[0071] In the embodiment of the present invention, the principle of dividing the air smoke area into the air area and the smoke area according to the gray value is:

[0072] The smoke area has a distinct gray-black color, while the air area is relatively transparent. The embodiment of the present invention extracts the grayscale value of the smoke air area, the grayscale value of the smoke area is greater than the grayscale value of the air area, and has a relatively obvious segmentation characteristic, that is, the grayscale value difference between adjacent positions on the center line exceeds the preset value, and the segmentation point here is used as the second dividing line between the smoke area and the air area, which can effectively improve the accuracy of the division of the air area and the smoke area.

[0073] See also Figure 2 , is a schematic diagram of a flame area division effect provided by an embodiment of the present invention.

[0074] In one embodiment, the image segmentation algorithm includes at least one of a threshold segmentation algorithm and an edge detection algorithm.

[0075] The implementation of the embodiments of the present invention has the following beneficial effects:

[0076] The embodiment of the present invention determines the flame area and the air smoke area in the flame image to be processed by adopting an image segmentation algorithm, and divides the flame area into a discontinuous flame area and a continuous flame area according to the RGB value, and divides the air smoke area into an air area and a smoke area according to the grayscale value. There is no need for manual review and manual division of the flame area, which can effectively reduce the flame division time and effectively improve the efficiency of flame area division.

[0077] Furthermore, the embodiment of the present invention can accurately determine the center line of the flame image to be processed, and further determine its RGB value and grayscale value based on the center line to perform flame region division, thereby effectively improving the accuracy of flame region division.

[0078] See also Figure 3 Based on the same inventive concept as the above embodiment, the present invention provides a flame area division device, comprising:

[0079] The flame image acquisition module 10 is used to acquire multiple flame images to be processed;

[0080] An image region determination module 20 is used to determine the flame region and the air smoke region in the flame image to be processed by using an image segmentation algorithm;

[0081] The value extraction module 30 is used to determine the center line of the flame image to be processed, extract the RGB value on the center line of the flame area, and the gray value on the center line of the air smoke area;

[0082] The flame region division module 40 is used to divide the flame region into a discontinuous flame region and a continuous flame region according to the RGB value, and to divide the air and smoke region into an air region and a smoke region according to the gray value.

[0083] In one embodiment, the value extraction module 30 is further used for:

[0084] Using edge detection algorithm to determine the edge of the flame area in the flame image to be processed;

[0085] According to the center point of the edge of the flame area is determined;

[0086] Extend from the center point to the other side of the flame image to be processed to determine the center line of the flame image to be processed.

[0087] In one embodiment, after determining the center line of the flame image to be processed, the method further includes:

[0088] Smooth the center line.

[0089] In one embodiment, the flame region division module 40 is further used to:

[0090] The area where the difference of the RGB values ​​of adjacent positions on the center line exceeds the preset value is used as the first dividing line for dividing the continuous flame area and the discontinuous flame area;

[0091] According to the first dividing line, the flame area is divided into a discontinuous flame area and a continuous flame area.

[0092] In one embodiment, the flame region division module 40 is further used to:

[0093] The area where the gray value difference between adjacent positions on the center line exceeds a preset value is used as the second dividing line for dividing the air area and the smoke area;

[0094] According to the second dividing line, the air smoke area is divided into an air area and a smoke area.

[0095] In one embodiment, the image segmentation algorithm includes at least one of a threshold segmentation algorithm and an edge detection algorithm.

[0096] Accordingly, an embodiment of the present invention further provides a terminal device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the flame area division method of any one of the above embodiments when executing the computer program.

[0097] The terminal device of this embodiment includes: a processor, a memory, and a computer program and computer instructions stored in the memory and executable on the processor. When the processor executes the computer program, each step in the above embodiment 1 is implemented, for example Figure 1 Alternatively, when the processor executes the computer program, the functions of each module / unit in the above device embodiment, such as the flame region division module 40, are implemented.

[0098] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in a memory and executed by a processor to complete the present invention. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device. For example, the flame region division module 40 is used to divide the flame region into a discontinuous flame region and a continuous flame region according to RGB values, and to divide the air smoke region into an air region and a smoke region according to grayscale values.

[0099] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the diagram, or may combine certain components, or different components. For example, the terminal device may also include an input / output device, a network access device, a bus, etc.

[0100] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0101] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile terminal, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0102] Among them, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0103] Accordingly, an embodiment of the present invention further provides a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the flame area division method of any one of the above embodiments.

[0104] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A flame area division method, characterized in that: include: Acquire multiple flame images to be processed; Using image segmentation algorithm, the flame area and air smoke area in the flame image to be processed are determined; Determine the center line of the flame image to be processed, extract the RGB value on the center line of the flame area, and the gray value on the center line of the air smoke area; The flame region is divided into a discontinuous flame region and a continuous flame region according to the RGB value, and the air and smoke region is divided into an air region and a smoke region according to the grayscale value.

2. The flame area division method according to claim 1, characterized in that: Determining the center line of the flame image to be processed includes: Using an edge detection algorithm to determine the edge of the flame area in the flame image to be processed; According to determining the center point of the edge of the flame area; Extending from the central point to the other side of the flame image to be processed, the central line of the flame image to be processed is determined.

3. The flame area division method according to claim 2, characterized in that: After determining the center line of the flame image to be processed, the method further includes: The center line is smoothed.

4. The flame area division method according to claim 1, characterized in that: Dividing the flame area into a discontinuous flame area and a continuous flame area according to the RGB value, including: The area where the difference of the RGB values ​​of adjacent positions on the center line exceeds the preset value is used as the first dividing line for dividing the continuous flame area and the discontinuous flame area; According to the first dividing line, the flame area is divided into a discontinuous flame area and a continuous flame area.

5. The flame area division method according to claim 1, characterized in that: Dividing the air smoke area into an air area and a smoke area according to the grayscale value includes: The area where the gray value difference between adjacent positions on the center line exceeds a preset value is used as the second dividing line for dividing the air area and the smoke area; According to the second dividing line, the air-smoke area is divided into an air area and a smoke area.

6. The flame area division method according to claim 1, characterized in that: The image segmentation algorithm includes at least one of a threshold segmentation algorithm and an edge detection algorithm.

7. A flame area division device, characterized in that: include: A flame image acquisition module to be processed, used to acquire multiple flame images to be processed; An image region determination module is used to determine the flame region and the air smoke region in the flame image to be processed by using an image segmentation algorithm; A value extraction module is used to determine the center line of the flame image to be processed, extract the RGB value on the center line of the flame area, and the gray value on the center line of the air smoke area; The flame area division module is used to divide the flame area into a discontinuous flame area and a continuous flame area according to the RGB value, and to divide the air and smoke area into an air area and a smoke area according to the gray value.

8. The flame area dividing device according to claim 7, characterized in that: The value extraction module is also used to: Using an edge detection algorithm to determine the edge of the flame area in the flame image to be processed; According to determining the center point of the edge of the flame area; Extending from the central point to the other side of the flame image to be processed, the central line of the flame image to be processed is determined.

9. A terminal device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the flame area division method according to any one of claims 1 to 6 is implemented when the processor executes the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program; wherein, when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the flame area division method according to any one of claims 1 to 6.