A flame detection method, device and storage medium for a pre-oxidation furnace

Abstract

The present invention relates to the field of digital image processing technology, and in particular to a flame detection method, device and storage medium for a pre-oxidation furnace, the method comprising the following steps: taking an image of a pre-oxidation furnace with a certain resolution; extracting features from the pre-processed image to find a suspected flame area S1; performing corresponding interception according to the suspected flame area S1 to generate a second image with a lower resolution; performing secondary segmentation on the suspected flame area S1 to filter out the white area S2; if the white area S2 is a subset of the suspected flame area S1, then the remaining part S3, that is, S3=S1-S2; performing RGB feature extraction on the remaining part S3, if the conditions are met, it is determined that a fire has occurred and an alarm is issued. The present invention collects images and performs segmentation and interception operations on the images, thereby ensuring that image data is reduced when collecting images, filtering is performed on the suspected areas, filtering out the white areas, reducing pixel processing, saving time, and improving detection efficiency and accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of digital image processing, and in particular to a flame detection method, device and storage medium for 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 in the pre-oxidation furnace is high, once the furnace catches fire, it will explode. The flame can spread to the entire oxidation furnace within a few seconds. In order to improve the speed of flame recognition in the oxidation furnace, the flame can be recognized by visual detection, but the detection accuracy is very high. Once the flame appears, it must be identified and subsequent fire extinguishing measures must be taken. High-precision detection often leads to a high false detection rate. Once a false detection is made and subsequent fire extinguishing measures are taken, it will have a great impact on the operation of the production line and greatly increase production costs.

[0004] 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

[0005] The technical problem to be solved by the present invention is to provide a pre-oxidation furnace flame detection method, equipment and storage medium to effectively solve the problems in the background technology.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is: a flame detection method for a pre-oxidation furnace, comprising the following steps:

[0007] Take an image of the pre-oxidation furnace with a certain resolution;

[0008] Perform feature extraction on the preprocessed image to find the suspected flame area S1;

[0009] A second image with a smaller resolution is generated by performing corresponding interception according to the suspected flame area S1;

[0010] Perform secondary segmentation on the suspected flame area S1 and filter out the white area, which is recorded as S2;

[0011] If the white area S2 is a subset of the suspected flame area S1, the remaining part is recorded as S3, that is, S3 = S1-S2;

[0012] The remaining part S3 is subjected to RGB feature extraction. If the conditions are met, it is determined that a fire has occurred and an alarm is issued.

[0013] Furthermore, when taking the second image, the suspected area S1 should be correspondingly intercepted to generate an image with a smaller resolution. The interception principle is as follows:

[0014] Assume that the resolution of the original image is m×n, and the flame area captured in the first image is S1. Then the interception principle is length: (m×n / S1) / m, width (m×n / S1) / n (rounded to set the size of the second captured image), and so on. After determining the suspected area of ​​the flame, the collected image data will become less, that is, the center of the flame area is taken as the midpoint of the new image, and the length and width are calculated to generate the image.

[0015] Furthermore, when performing secondary segmentation on the suspected flame area S1, first find the white area in the image (i.e., filter out the area with a brightness value greater than 240), and record the area at this time as S2. It is necessary to determine whether S2 at this time is inside the area, that is, a subset of the suspected flame area S1.

[0016] Furthermore, the method for judging whether S2 at this time is inside the region, that is, a subset of the suspected flame region S1 is as follows:

[0017] Assume that the center of region S1 is (x1, y1), and the maximum distance from the center of region S1 is the diameter of the circle. The equation of the circumscribed circle of S1 is:

[0018] (x-x1) 2 +(y-y1) 2 =r 2

[0019] Assume that the center of region S2 is (x0, y0), and the maximum distance from the center of region S2 is the diameter of the circle. The equation of the circumscribed circle of S2 is:

[0020] (x-x0) 2 +(y-y0) 2 =d 2

[0021] If d<r, that is

[0022] (x0-x1) 2 +(y0-y1) 2 <r 2

[0023] It can be determined that S2 is a subset of S1.

[0024] Furthermore, if S2 is determined to be a subset of S1, S2 is filtered out and the remaining part is recorded as S3. If the area of ​​S2 exceeds S1, the intersection of the two areas is calculated, that is, the equation of the circumscribed circle of S2 is calculated.

[0025] (x-x0) 2 +(y-y0) 2 =d 2

[0026] Subtracting the two equations means the area of ​​the intersection is recorded as S3, then calculate the complement of area S3 in S1 and cut out this part.

[0027] Furthermore, in the feature extraction of the remaining area S3, the R, G, and B values ​​of the pixels in the image are extracted, and G / R, B / R, and (G+B) / R are calculated respectively to determine the red feature value of the pixel. When the red feature value exceeds the set threshold, it is marked as meeting the conditions and confirming that a fire has occurred.

[0028] 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.

[0029] 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.

[0030] The beneficial effects of the present invention are as follows: the present invention collects images and performs segmentation and interception operations on the images, thereby ensuring that image data is reduced when collecting images, and performs filtering processing on suspected areas to filter out white areas, reduce pixel processing, save time, and improve detection efficiency and detection accuracy. After removing the white areas, RGB feature extraction is performed on the remaining areas, with higher detection accuracy, reducing the processing of redundant pixels, and avoiding false detections. This detection method can not only improve the rate of acquiring images, but also improve the efficiency in regional processing, making the area more stable, and detecting flames more efficiently and stably. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] 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.

[0032] Figure 1Flow chart of the flame detection method of the pre-oxidation furnace in the embodiment of the present invention;

[0033] Figure 2 Schematic diagram of the structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] 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.

[0035] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only and do not represent the only implementation method.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0037] In the flame detection process of the pre-oxidation furnace, the detection rate needs to reach 100% and the false detection rate needs to be 0. This requires the overall device to have high reliability and high stability. Therefore, based on the above principles, some research has been conducted on the flame detection in the pre-oxidation furnace. The following high reliability and stable detection method is proposed.

[0038] like Figure 1 As shown, a flame detection method for a pre-oxidation furnace comprises the following steps:

[0039] Take an image of the pre-oxidation furnace with a certain resolution;

[0040] Perform feature extraction on the preprocessed image to find the suspected flame area S1;

[0041] A second image with a smaller resolution is generated by performing corresponding interception according to the suspected flame area S1;

[0042] Perform secondary segmentation on the suspected flame area S1 and filter out the white area S2;

[0043] If the white area S2 is a subset of the suspected flame area S1, then the remaining part S3, that is, S3 = S1-S2;

[0044] The remaining part S3 is subjected to RGB feature extraction. If the conditions are met, it is determined that a fire has occurred and an alarm is issued.

[0045] When detecting the flame as a whole, it is necessary to consider the specific situation in the pre-oxidation furnace, so it is not possible to detect whether there is a flame in the oxidation furnace in real time according to the original static model. By collecting images in the pre-oxidation furnace, the suspected flame area in the image is found. This can be achieved through sensors or visual tracking. The second image is intercepted according to the suspected flame area, and the suspected flame area in the second image is screened. After removing the white area, the remaining part is subjected to RGB feature extraction. If the conditions are met, it is determined that a fire has occurred and an alarm is triggered. It reduces pixel processing, saves time, and improves detection efficiency. At the same time, it also improves efficiency in regional processing, making the area more stable. More efficient and stable flame detection.

[0046] In this embodiment, when taking the second image, the suspected area S1 should be intercepted accordingly to generate an image with a lower resolution. If an image with the same resolution is still taken, it will inevitably cause a waste of image acquisition. Therefore, when taking the image, the resolution of the first image cannot be used, which will cause a waste of time. The interception principles are as follows:

[0047] Assume that the original image resolution is m×n, and the first intercepted flame area is S1, then the interception principle is length: (m×n / S1) / m, width (m×n / S1) / n, (rounded, so as to set the size of the second captured image), and so on. After determining the suspected flame area, the collected image data will be less, that is, the center of the flame area is taken as the midpoint of the new image, and the length and width are calculated to generate the image. This can ensure that the image data is reduced when collecting images.

[0048] In an embodiment of the present invention, when performing secondary segmentation on the suspected flame area S1, first find the white area in the image (that is, filter out the area with a brightness value greater than 240), and record the area at this time as S2. It is necessary to determine whether S2 at this time is inside the area, that is, a subset of the suspected flame area S1.

[0049] As a preferred embodiment of the above, the method for judging whether S2 at this time is inside the area, that is, a subset of the suspected flame area S1 is:

[0050] Assume that the center of region S1 is (x1, y1), and the maximum distance from the center of region S1 is the diameter of the circle. The equation of the circumscribed circle of S1 is:

[0051] (x-x1) 2 +(y-y1) 2 =r2

[0052] Assume that the center of region S2 is (x0, y0), and the maximum distance from the center of region S2 is the diameter of the circle. The equation of the circumscribed circle of S2 is:

[0053] (x-x0) 2 +(y-y0) 2 =d 2

[0054] If d<r, that is

[0055] (x0-x1) 2 +(y0-y1) 2 <r 2

[0056] It can be determined that S2 is a subset of S1.

[0057] As a preferred embodiment of the above, if it is determined that S2 is a subset of S1, S2 is filtered out and the remaining part is recorded as S3. If the area of ​​S2 exceeds S1, the intersection of the two areas is calculated, that is, the equation of the circumscribed circle of S2 is calculated.

[0058] (x-x0) 2 +(y-y0) 2 =d 2

[0059] Subtracting the two equations means the area of ​​the intersection is recorded as S3, then calculate the complement of area S3 in S1 and cut out this part.

[0060] In this embodiment, when extracting features from the remaining area S3, the R, G, and B values ​​of the pixels in the image are extracted, and G / R, B / R, and (G+B) / R are calculated respectively to determine the red feature value of the pixel. When the red feature value exceeds the set threshold, it is marked as meeting the conditions and confirming that a fire has occurred.

[0061] Among them, mainly include:

[0062] Set the flame size to be detected;

[0063] According to the size of image pixels, the flame size to be detected is converted into a range whose diameter is determined by the number of pixels;

[0064] The area is demarcated with the predicted center point coordinates as the center of the circle.

[0065] According to the expected flame size, the flame diameter or radius to be detected is set, and according to the size and resolution of the image pixels, the flame size to be detected is converted into the corresponding number of pixels. This can be calculated by a simple scale or pixel density. With the predicted center point coordinates as the center of the circle and the calculated number of pixels as the radius, a circular area is drawn. This circular area is determined to be the area where the flame center appears, realizing dynamic recognition.

[0066] By collecting images and performing image segmentation and interception operations, it is ensured that image data is reduced when collecting images, and filtering is performed on suspected areas to filter out white areas, reduce pixel processing, save time, and improve detection efficiency. After removing the white area, RGB feature extraction is performed on the remaining area, with higher detection accuracy, reducing the processing of redundant pixels and avoiding false detection. This detection method can not only improve the rate of image acquisition, but also improve the efficiency of regional processing, making the area more stable. More efficient and stable detection of flames.

[0067] See also Figure 2 A 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.

[0068] 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.

[0069] 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.

[0070] 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.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] 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, a "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 of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), 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), a fiber optic 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.

[0075] 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, a plurality of 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.

[0076] 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.

[0077] 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 a pre-oxidation furnace, characterized in that: The steps include: Take an image of the pre-oxidation furnace with a certain resolution; Perform feature extraction on the preprocessed image to find the suspected flame area S1; A second image with a smaller resolution is generated by performing corresponding interception according to the suspected flame area S1; Perform secondary segmentation on the second image, filter out the white area S2, find the white area in the image, record the area at this time as S2, and then determine whether S2 at this time is a subset of the suspected flame area S1 inside the area; the method for determining whether S2 at this time is a subset of the suspected flame area S1 inside the area is: Assume that the center of region S1 is (x1, y1), and the maximum distance from the center of region S1 is the diameter of the circle. The equation of the circumscribed circle of S1 is: (x-x1) 2 +(y-y1) 2 =r 2 Assume that the center of region S2 is (x0, y0), and the maximum distance from the center of region S2 is the diameter of the circle. The equation of the circumscribed circle of S2 is: (x-x0) 2 +(y-y0) 2 =d 2 If d<r, (x0-x1) 2 +(y0-y1) 2 <r 2 It can be determined that S2 is a subset of S1; If the white area S2 is a subset of the suspected flame area S1, then the remaining part S3 = S1-S2; Perform RGB feature extraction on the remaining part S3. If the conditions are met, it is determined that a fire has occurred and an alarm is issued. During feature extraction of the remaining area S3, the R, G, and B values ​​of the pixels in the image are extracted, and G / R, B / R, and (G+B) / R are calculated respectively to determine the red feature value of the pixel. When the red feature value exceeds the set threshold, it is marked as meeting the conditions and confirming that a fire has occurred.

2. The pre-oxidation furnace flame detection method according to claim 1, characterized in that: When taking the second image, a corresponding interception of the suspected area S1 is performed to generate an image with a smaller resolution. The interception principle is as follows: Assume that the resolution of the original image is m×n, the first captured flame area is S1, and the capture principle is length: (m×n / S1) / m, width (m×n / S1) / n. After the suspected flame area is determined, the collected image data will become less, that is, the image is generated with the length and width calculated with the center of the flame area as the midpoint of the new image.

3. The pre-oxidation furnace flame detection method according to claim 1, characterized in that: If S2 is determined to be a subset of S1, S2 is filtered out and the remaining part is recorded as S3. If the area of ​​S2 exceeds S1, the intersection of the two areas is calculated to calculate the equation of the circumscribed circle of S2. (x-x0) 2 +(y-y0) 2 =d 2 Subtracting the two equations is to get the area of ​​the intersection, which is recorded as S3. Then calculate the complement of area S3 in S1 and remove the complement.

4. 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 3 is implemented.

5. 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 3 is implemented.

Images