Pre-oxidation furnace fire extinguishing and explosion suppression flame detection method and system

Abstract

The present invention relates to the technical field of carbon fiber production, and in particular to a method and system for detecting fire extinguishing and explosion suppression in a pre-oxidation furnace. The method comprises: acquiring RGB images in the pre-oxidation furnace through a plurality of cameras; identifying a bright light area in the pre-oxidation furnace through threshold segmentation, and judging whether the bright light area is a small area or a large area through the area of ​​the bright light area; if the bright light area is a small area, judging the color proportion in the bright light area, and if the proportion of blue pixels and / or green pixels in the bright light area exceeds a set value, judging it as edge light; if it does not exceed the set value, judging whether the red pixels in the bright light area exceed the set value, and if so, judging it as a flame, and if not, judging whether there is a bright yellow area in the bright light area, and if so, judging it as a flame; if the bright light area is a large area, judging whether the bright light area is a white area, and if so, judging whether white areas also appear in other cameras, and if so, judging it as a flame.

Description

Technical Field

[0001] The invention relates to the technical field of carbon fiber production, and in particular to a method and system for detecting fire extinguishing and explosion suppressing flames in a pre-oxidation furnace. Background Art

[0002] The oxidation and carbonization process of PAN-based carbon fibers includes pre-oxidation, low-temperature carbonization, high-temperature carbonization, surface treatment, sizing and drying, etc. Among them, pre-oxidation is an important intermediate process. The linear molecular chain of PAN precursor gradually forms a heat-resistant ladder structure in this process. PAN precursor needs to pass through multiple pre-oxidation furnaces with increasing temperatures in the oxidation furnace cluster. The main reactions of the pre-oxidation process are cyclization, oxidation and dehydrogenation, which are all exothermic reactions, which will cause heat storage and overheating inside the fiber. The temperature in the pre-oxidation furnace is high, and it is easy to catch fire due to excessive local temperature.

[0003] Since the temperature inside the pre-oxidation furnace is relatively high, once the furnace catches fire, deflagration will occur, and the flame can spread to the entire oxidation furnace within a few seconds. In order to increase the speed of flame recognition in the oxidation furnace, the flame can be identified by visual detection, but the detection accuracy is very high. As soon as a flame appears, it must be identified and subsequent fire extinguishing measures must be taken.

[0004] Sometimes there is edge light in the pre-oxidation furnace, which will interfere with flame detection. If the edge light is identified as flame and subsequent fire extinguishing and shutdown steps are performed, it will cause great losses. Therefore, the flame detection in the pre-oxidation furnace needs to have a detection rate of percentage and a false detection rate of 0, which requires high reliability and high stability of flame detection.

[0005] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present invention, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art already known to those skilled in the art. Summary of the invention

[0006] The present invention provides a method and system for detecting fire extinguishing and explosion suppressing flames in a pre-oxidation furnace, thereby effectively solving the problems in the background technology.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is: a method and system for detecting flames in a pre-oxidation furnace for extinguishing and suppressing explosions, comprising:

[0008] Acquire RGB images in the pre-oxidation furnace through several cameras;

[0009] Identifying the bright light area in the pre-oxidation furnace by threshold segmentation, and judging whether the bright light area is small or large by the area of ​​the bright light area;

[0010] If the bright light area is a small area, determine the color ratio in the bright light area, and if the ratio of blue pixels and / or green pixels in the bright light area exceeds a set value, determine that it is edge light;

[0011] If it does not exceed the set value, then determine whether the red pixel in the bright light area exceeds the set value, if so, determine it is a flame, if not, determine whether there is a bright yellow area in the bright light area, if so, determine it is a flame;

[0012] If the bright light area is a large area, determine whether the bright light area is a white area. If so, determine whether white areas also appear in other cameras. If so, determine that it is a flame.

[0013] Furthermore, the identifying the bright light area in the pre-oxidation furnace by threshold segmentation comprises the following steps:

[0014] Perform image segmentation on an image and divide it into three channels: R, G, and B;

[0015] Perform threshold segmentation on the three channels respectively, filter out the area where R is greater than the first threshold, and filter out the area where G and B are greater than the second threshold;

[0016] The filtered areas are combined to obtain the bright area.

[0017] Furthermore, the first threshold is greater than the second threshold.

[0018] Furthermore, if the proportion of blue pixels and / or green pixels in the bright light area exceeds a set value, it is determined to be edge light, including:

[0019] Determine the color of each pixel in the bright light area;

[0020] Determine whether the ratio of blue pixels in the bright light area to the pixels in the entire area exceeds P1, and if so, determine that it is edge light;

[0021] It is determined whether the ratio of green pixels in the bright light area to the pixels in the entire area exceeds P2. If so, it is determined to be edge light.

[0022] Furthermore, determining the color of each pixel in the bright light area includes:

[0023] The three channel components of pixel Q are Q (R, G, B);

[0024] If B>R, B>G, and B / (G+B+R)>P3, then the pixel is a blue pixel;

[0025] If G>B, G>R, and G / (G+B+R)>P3, then the pixel is a green pixel;

[0026] If R>B, R>G, and R / (G+B+R)>P3, the pixel is a red pixel.

[0027] Furthermore, the step of judging whether the red pixel in the bright light area exceeds a set value G1, and if so, judging that it is a flame, further comprises:

[0028] It is determined whether the maximum grayscale value of the red pixels in the bright light area exceeds a set value, and if so, it is determined to be a flame.

[0029] Further, the determining whether there is a bright yellow area in the bright light area, and if so, determining it as a flame, further includes:

[0030] Determine whether there are any pixels with R>240 and G>240 among the pixels in the bright light area;

[0031] If yes, these pixels are selected and recorded as area A2;

[0032] Calculate the complement A3 of the area A2 in the bright area A1;

[0033] The proportion of red pixels in the complement A3 is calculated. If it exceeds the set value P4 and the maximum grayscale value of the red pixels in the bright light area exceeds the set value G1, it is determined to be a flame.

[0034] The present invention also includes a pre-oxidation furnace fire extinguishing and explosion suppression flame detection system, using the above method, including:

[0035] An acquisition unit, used for acquiring RGB images in the pre-oxidation furnace through a plurality of cameras;

[0036] An area judgment unit, used for identifying a bright light area in the pre-oxidation furnace by threshold segmentation, and judging whether the bright light area is a small area or a large area by the area of ​​the bright light area;

[0037] The flame judgment unit is used to judge the flame, including:

[0038] If the bright light area is a small area, determine the color ratio in the bright light area, and if the ratio of blue pixels and / or green pixels in the bright light area exceeds a set value, determine that it is edge light;

[0039] If it does not exceed the set value, then determine whether the red pixel in the bright light area exceeds the set value, if so, determine it is a flame, if not, determine whether there is a bright yellow area in the bright light area, if so, determine it is a flame;

[0040] If the bright light area is a large area, determine whether the bright light area is a white area. If so, determine whether white areas also appear in other cameras. If so, determine that it is a flame.

[0041] The present invention also includes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described above is implemented.

[0042] The present invention also includes a storage medium on which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.

[0043] The beneficial effects of the present invention are as follows: the present invention performs characteristic analysis on flames and edge light. Generally, in the area with edge light, there are blue and green areas in addition to red and yellow. According to this characteristic, edge light and flame are distinguished. In a small fire, after the camera is generally imaged, the color of the pixels is basically red and yellow, with a part being bright red and a part being yellow. As the flame burns, the image of the flame in the camera will become bright yellow in the middle and red at the edge. As the flame burns, the white part of the image of the flame in the camera will become larger and larger. The bright light area is extracted from the image by the threshold segmentation method, and it is judged whether it is a flame or edge light according to the color characteristics of the bright light area A1. When the detected flame has the characteristics of a medium fire, the center of the flame is bright yellow and the edge is red. It is judged whether there is bright yellow. When the area is large, a large fire detection process is performed to detect whether multiple cameras capture the white area at the same time. Therefore, by combining image processing and color analysis, through multi-step and multi-stage logical judgment, the flame in the pre-oxidation furnace can be effectively identified and the edge light can be distinguished, thereby improving the accuracy and reliability of flame detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 is a flow chart of the method of the present invention;

[0046] Figure 2 It is a structural schematic diagram of the device of the present invention;

[0047] Figure 3 Pixel images of different flame states;

[0048] Figure 4 Several pixel maps for edge light;

[0049] Figure 5 A schematic diagram of the structure of a computer device. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0051] Embodiment 1:

[0052] like Figure 1 As shown: A method for detecting flames in a pre-oxidation furnace to extinguish and suppress explosions, comprising the following steps:

[0053] Acquire RGB images in the pre-oxidation furnace through several cameras;

[0054] The bright light area in the pre-oxidation furnace is identified by threshold segmentation, and the area of ​​the bright light area is used to determine whether the bright light area is small or large;

[0055] If the bright light area is a small area, determine the color ratio in the bright light area. If the ratio of blue pixels and / or green pixels in the bright light area exceeds the set value, it is determined to be edge light.

[0056] If it does not exceed the set value, then determine whether the red pixel in the bright light area exceeds the set value. If so, it is determined to be a flame. If not, determine whether there is a bright yellow area in the bright light area. If so, it is determined to be a flame.

[0057] If the bright light area is a large area, determine whether the bright light area is a white area. If so, determine whether white areas also appear in other cameras. If so, determine that it is a flame.

[0058] By analyzing the characteristics of flames and edge light, it is found that in general, the edge light area contains blue and green areas in addition to red and yellow. According to this characteristic, edge light and flame are distinguished. In a small fire, after the camera is generally imaged, the color of the pixels is basically red and yellow, some are bright red, and some are yellow. As the flame burns, the image of the flame in the camera will become bright yellow in the middle and red at the edge. As the flame burns, the white part of the flame image in the camera will become larger and larger. The bright light area is extracted from the image by the threshold segmentation method. According to the color characteristics of the bright light area A1, it is judged whether it is a flame or edge light. When the detected flame has the characteristics of a medium fire, the center of the flame is bright yellow and the edge is red. It is judged whether there is bright yellow. When the area is large, the large fire detection process is carried out to detect whether multiple cameras capture the white area at the same time. Therefore, by combining image processing and color analysis, through multi-step and multi-stage logical judgment, the flame in the pre-oxidation furnace can be effectively identified and the edge light can be distinguished, thereby improving the accuracy and reliability of flame detection.

[0059] In this embodiment, the bright light area in the pre-oxidation furnace is identified by threshold segmentation, including the following steps:

[0060] Perform image segmentation on an image and divide it into three channels: R, G, and B;

[0061] Perform threshold segmentation on the three channels respectively, filter out the area where R is greater than the first threshold, and filter out the area where G and B are greater than the second threshold;

[0062] The filtered areas are combined to obtain the bright area.

[0063] Because the flame is usually brighter, the brightness value of the first threshold is set to 30, and sometimes the edge light is darker, so the brightness value of the second threshold is set to 25. Therefore, the first threshold is set larger than the second threshold.

[0064] If the proportion of blue pixels and / or green pixels in the bright light area exceeds a set value, it is judged as edge light, including:

[0065] Determine the color of each pixel in the bright light area;

[0066] Determine whether the ratio of blue pixels in the bright light area to the pixels in the entire area exceeds P1. If so, it is determined to be edge light;

[0067] It is determined whether the ratio of green pixels in the bright light area to the pixels in the entire area exceeds P2. If so, it is determined to be edge light.

[0068] As a preferred embodiment of the above, determining the color of each pixel in the bright light area includes:

[0069] The three channel components of pixel Q are Q (R, G, B);

[0070] If B>R, B>G, and B / (G+B+R)>P3, then the pixel is a blue pixel;

[0071] If G>B, G>R, and G / (G+B+R)>P3, then the pixel is a green pixel;

[0072] If R>B, R>G, and R / (G+B+R)>P3, the pixel is a red pixel.

[0073] In this embodiment, it is determined whether the red pixel in the bright light area exceeds the set value G1, and if so, it is determined to be a flame, and the following further includes:

[0074] Determine whether the maximum grayscale value of the red pixel in the bright light area exceeds the set value. If so, it is determined to be a flame.

[0075] Determine whether there is a bright yellow area in the bright light area, and if so, determine it as a flame, and also include:

[0076] Determine whether there are pixels with R>240 and G>240 in the bright light area;

[0077] If yes, these pixels are selected and recorded as area A2;

[0078] Calculate the complement A3 of area A2 in bright area A1;

[0079] The proportion of red pixels in the complement set A3 is calculated. If it exceeds the set value P4 and the maximum grayscale value of the red pixels in the bright area exceeds the set value G1, it is determined to be a flame.

[0080] like Figure 2 As shown, this embodiment also includes a pre-oxidation furnace fire extinguishing and explosion suppression flame detection system, using the above method, including:

[0081] An acquisition unit, used for acquiring RGB images in the pre-oxidation furnace through a plurality of cameras;

[0082] An area judgment unit is used to identify the bright light area in the pre-oxidation furnace by threshold segmentation, and judge whether the bright light area is a small area or a large area according to the area of ​​the bright light area;

[0083] The flame judging unit is used to judge the flame, comprising:

[0084] If the bright light area is a small area, determine the color ratio in the bright light area. If the ratio of blue pixels and / or green pixels in the bright light area exceeds the set value, it is determined to be edge light.

[0085] If it does not exceed the set value, then determine whether the red pixel in the bright light area exceeds the set value. If so, it is determined to be a flame. If not, determine whether there is a bright yellow area in the bright light area. If so, it is determined to be a flame.

[0086] If the bright light area is a large area, determine whether the bright light area is a white area. If so, determine whether white areas also appear in other cameras. If so, determine that it is a flame.

[0087] Embodiment 2:

[0088] In this embodiment, the overall detection idea is divided into two parts:

[0089] S1: First identify the bright light area A1 in the furnace;

[0090] S2: Perform feature judgment (such as shape, state, color, etc.) on the bright light area A1 to distinguish whether it is flame or edge light.

[0091] 1. Small fire detection process:

[0092] S1: First identify the bright light area A1 in the furnace;

[0093] First of all, when processing the image, we need to find the bright area in the furnace. How to find the bright area?

[0094] 1) Perform image segmentation on an image and divide it into three channels. Perform corresponding threshold segmentation on each image and find out R>30 (the flame area needs to be screened out, because the flame is generally brighter, so the brightness value is set to 30). The screened area is recorded as R1;

[0095] G>25, B>25 (the edge light area needs to be screened out, because sometimes the edge light is darker, so the brightness value is set to 25) The screened area is recorded as G1, B1;

[0096] Find the union of the filtered areas, and set area A1=R1UG1UB1;

[0097] S2: Perform color feature judgment on the A1 area to determine whether it is flame or edge light.

[0098] Generally, the edge light area contains blue and green areas in addition to red and yellow. Based on this feature, edge light and flame are distinguished.

[0099] According to the characteristics of small fire and edge light:

[0100] 1) There will be blue pixels in the edge light, so calculate the blue pixel ratio of each pixel in area A1. When the blue pixel ratio exceeds P, it is recorded as edge light. P = A (number of blue pixels) / A1 (area of ​​area A1);

[0101] Definition of blue pixel (a pixel Q(R,G,B) is defined as meeting two conditions: 1. B>G and B>R; 2. B / (G+B+R)>P1, indicating that the pixel is a blue pixel.

[0102] 2) If there are no blue pixels in area A1, then we need to find the corresponding green pixels. There will be green pixels in edge light, so calculate the green pixel ratio of each pixel in area A1. When the ratio of green pixels exceeds P2, it is recorded as edge light. P2=A2 (number of green pixels) / A1 (area of ​​area A1);

[0103] Definition of green pixel (set pixel Q(R,G,B) to meet two conditions: 1. G>B and G>R; 2. G / (G+B+R)>P2 indicates that the pixel is a green pixel.

[0104] 3) If there are neither blue pixels nor green pixels in area A1, it is necessary to determine whether it is a flame area. Because in a small fire, the colors of the pixels are basically red and yellow after the camera images, some are bright red, and some are yellow. Therefore, the red pixel ratio of each pixel is defined. If the red pixel ratio in an area A1 exceeds P3, and the maximum grayscale value of the red pixels in the area must exceed G1, it means that the area A1 is a flame area.

[0105] Definition of red pixel (set pixel Q(R,G,B) to meet two conditions: 1. R>B and R>G; 2. R / (G+B+R)>P4 indicates that the pixel is a green pixel.

[0106] If the image does not meet the three conditions, enter the following judgment logic:

[0107] 2. Middle fire detection process:

[0108] As the flame burns, the image of the flame in the camera will become bright yellow in the middle and red at the edges. Once the middle is bright yellow, the overall red proportion of the flame will become less than this, and the following judgment logic needs to be entered:

[0109] S3: Check whether there is a bright yellow area in the image captured by the camera (R>240 and G>240, the value of B can be unlimited, because if the B value is very small, it will appear yellow, and if the B value is very large, it will appear white. These all meet the characteristics of medium to large fires). So first filter out this area and record it as A3, calculate the complement of A3 in A1 A4; then study the regional characteristics of A4. Calculate the red pixel ratio of each pixel in A4. If the red pixel ratio in A4 exceeds P5 and the maximum red pixel grayscale exceeds a certain grayscale value, it means that this area is a flame area.

[0110] If the image still does not meet the above characteristics, it will enter the following logic:

[0111] 3. Fire detection process:

[0112] As the flame burns, the white part of the flame image in the camera will become larger and larger. Due to the camera installation angle, it is impossible for multiple cameras to detect white at the same time. At this time, if multiple cameras simultaneously monitor the white (R>240, G>240, B>240) area in the picture, it is determined that a flame has appeared.

[0113] See also Figure 3A computer device 400 provided in an embodiment of the present application includes: a processor 410 and a memory 420, wherein the memory 420 stores a computer program executable by the processor 410, and when the computer program is executed by the processor 410, the above method is executed.

[0114] The embodiment of the present application further provides a storage medium 430 on which a computer program is stored. When the computer program is run by the processor 410, the above method is executed.

[0115] Among them, the storage medium 430 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, disk or optical disk.

[0116] In the description of the present invention, 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 the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0117] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like 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 an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0118] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0119] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0120] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0121] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0122] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0123] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A flame detection method for fire extinguishing and explosion suppression in a pre-oxidation furnace, characterized in that: The steps include: Acquire RGB images in the pre-oxidation furnace through several cameras; Identifying the bright light area in the pre-oxidation furnace by threshold segmentation, and judging whether the bright light area is small or large by the area of ​​the bright light area; If the bright light area is a small area, determine the color ratio in the bright light area, and if the ratio of blue pixels and / or green pixels in the bright light area exceeds a set value, determine that it is edge light; If it does not exceed the set value, then determine whether the red pixel in the bright light area exceeds the set value, if so, determine it is a flame, if not, determine whether there is a bright yellow area in the bright light area, if so, determine it is a flame; If the bright light area is a large area, determine whether the bright light area is a white area. If so, determine whether white areas also appear in other cameras. If so, determine that it is a flame.

2. The method for detecting flames in a pre-oxidation furnace for extinguishing and suppressing explosions according to claim 1, characterized in that: The method of identifying the bright light area in the pre-oxidation furnace by threshold segmentation includes the following steps: Perform image segmentation on an image and divide it into three channels: R, G, and B; Perform threshold segmentation on the three channels respectively, filter out the area where R is greater than the first threshold, and filter out the area where G and B are greater than the second threshold; The filtered areas are combined to obtain the bright area.

3. The method for detecting flames in a pre-oxidation furnace for extinguishing and suppressing explosions according to claim 2, characterized in that: The first threshold is greater than the second threshold.

4. The method for detecting flames in a pre-oxidation furnace for extinguishing and suppressing explosions according to claim 1, characterized in that: If the proportion of blue pixels and / or green pixels in the bright light area exceeds a set value, it is judged as edge light, including: Determine the color of each pixel in the bright light area; Determine whether the ratio of blue pixels in the bright light area to the pixels in the entire area exceeds P1, and if so, determine that it is edge light; It is determined whether the ratio of green pixels in the bright light area to the pixels in the entire area exceeds P2. If so, it is determined to be edge light.

5. The method for detecting flames in a pre-oxidation furnace for extinguishing and suppressing explosions according to claim 4, characterized in that: The determining the color of each pixel in the bright light area includes: The three channel components of pixel Q are Q(R, G, B); If B>R, B>G, and B / (G+B+R)>P3, then the pixel is a blue pixel; If G>B, G>R, and G / (G+B+R)>P3, then the pixel is a green pixel; If R>B, R>G, and R / (G+B+R)>P3, the pixel is a red pixel.

6. The method for detecting flames in a pre-oxidation furnace for extinguishing and suppressing explosions according to claim 4, characterized in that: The step of determining whether the red pixel in the bright light area exceeds a set value G1, and if so, determining that it is a flame, further includes: It is determined whether the maximum grayscale value of the red pixels in the bright light area exceeds a set value, and if so, it is determined to be a flame.

7. The method for detecting flames in a pre-oxidation furnace for extinguishing and suppressing explosions according to claim 1, characterized in that: The step of determining whether there is a bright yellow area in the bright light area, and if so, determining that it is a flame, further includes: Determine whether there are any pixels with R>240 and G>240 among the pixels in the bright light area; If yes, these pixels are selected and recorded as area A2; Calculate the complement A3 of the area A2 in the bright light area; The proportion of red pixels in the complement A3 is calculated. If it exceeds the set value P4 and the maximum grayscale value of the red pixels in the bright light area exceeds the set value G1, it is determined to be a flame.

8. A flame detection system for fire extinguishing and explosion suppression in a pre-oxidation furnace, characterized in that: Use of the method according to any one of claims 1 to 7, comprising: An acquisition unit, used for acquiring RGB images in the pre-oxidation furnace through a plurality of cameras; An area judgment unit, used for identifying a bright light area in the pre-oxidation furnace by threshold segmentation, and judging whether the bright light area is a small area or a large area by the area of ​​the bright light area; The flame judging unit is used to judge the flame, comprising: If the bright light area is a small area, determine the color ratio in the bright light area, and if the ratio of blue pixels and / or green pixels in the bright light area exceeds a set value, determine that it is edge light; If it does not exceed the set value, then determine whether the red pixel in the bright light area exceeds the set value, if so, determine it is a flame, if not, determine whether there is a bright yellow area in the bright light area, if so, determine it is a flame; If the bright light area is a large area, determine whether the bright light area is a white area. If so, determine whether white areas also appear in other cameras. If so, determine that it is a flame.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images