A fire extinguishing monitoring system based on image processing

Abstract

This invention relates to the technical field of fire extinguishing monitoring, and more particularly to a fire extinguishing monitoring system based on image processing. The system acquires smoke concentration and images within a space through a smoke acquisition unit and an image acquisition unit, respectively. An image preprocessing unit preprocesses the acquired images, making them more effective. Simultaneously, a YOLOv7 model in the fire area contour recognition unit identifies the fire area, and a threshold method in the fire area contour segmentation unit segments the identified fire area. This allows for a more accurate determination of the actual area ratio of the fire area to the entire image. The system then uses this actual area ratio to determine whether the monitored fire area can be accurately identified, and based on the determination results, identifies the reasons for non-compliance, thereby providing corresponding fire extinguishing plans and improving fire extinguishing efficiency.

Description

Technical Field

[0001] This invention relates to the technical field of fire extinguishing monitoring, and in particular to a fire extinguishing monitoring system based on image processing. Background Technology

[0002] A fire suppression monitoring system based on image processing is a system that uses image processing technology to detect flames and smoke in order to achieve fire early warning and automatic fire suppression. This system can monitor the monitored area in real time, promptly detect fire hazards, improve fire suppression efficiency, and accurately identify fire characteristics such as flames and smoke through image processing technology, reducing false alarms and missed alarms. Furthermore, the system has intelligent analysis capabilities, enabling it to automatically determine the fire situation based on image processing results and take corresponding fire suppression measures.

[0003] Chinese Patent Publication No. CN116939165A discloses a fire protection maintenance monitoring method and system. The method includes: receiving alarm information through video monitoring equipment and recording the fire alarm status; collecting scene information of the monitored area through the video monitoring equipment and sending it to a server for processing in the form of image data; optimizing the frame rate of the image data of the monitored area scene information and processing it using monitoring image blur restoration technology; and controlling the opening and closing of fire extinguishers based on the scene information of the monitored area.

[0004] However, existing technologies still have the following problems: due to the inability to accurately identify the fire area, corresponding fire extinguishing plans cannot be provided, thus reducing fire extinguishing efficiency. Summary of the Invention

[0005] To address this issue, the present invention provides a fire extinguishing monitoring system based on image processing, which overcomes the problem in the prior art that it cannot accurately identify fire areas, thus failing to provide corresponding fire extinguishing plans and reducing fire extinguishing efficiency.

[0006] To achieve the above objectives, the present invention provides a fire extinguishing monitoring system based on image processing, comprising:

[0007] A smoke collection unit, used to collect the smoke concentration in the space;

[0008] An image acquisition unit is used to acquire image information within a space.

[0009] An image preprocessing unit, connected to the image acquisition unit, is used to preprocess the acquired image information;

[0010] A fire area contour recognition unit, which is connected to the image preprocessing unit, is used to recognize the fire feature area in the image information based on the trained YOLOv7 model.

[0011] A fire area contour segmentation unit, which is connected to the fire area contour recognition unit, is used to segment the fire feature region in the image information based on a threshold method, and to obtain the ratio of the area of ​​the segmented part to the actual area of ​​the whole image.

[0012] An analysis unit, which is connected to the smoke collection unit and the fire area contour segmentation unit, is used to determine whether the fire area meets the standard based on the comparison result of the actual area ratio and the preset area ratio determined according to the smoke concentration.

[0013] A cause determination unit, connected to the analysis unit, is used to generate a corresponding processing method based on the non-compliance cause determined by the judgment result obtained by the analysis unit. The preset area ratio is the ratio of the area of ​​the expected fire feature region in the acquired image to the total area of ​​the image. The processing method includes determining the actual area ratio and adjusting the preset area ratio.

[0014] A control unit, connected to the cause determination unit, is used to generate corresponding processing instructions based on the processing method, and to determine the operating parameters of the corresponding component based on the generated processing instructions.

[0015] Furthermore, the analysis unit is also used to determine whether the fire area meets the standard based on the absolute value of the difference between the actual area ratio and the preset area ratio and the preset absolute value, and to analyze the reasons why the fire area identification does not meet the standard based on the smoke concentration or the absolute value of the difference between the actual area ratio and the preset area ratio.

[0016] Furthermore, the analysis unit is also used to generate a corresponding processing method based on the comparison result of the smoke concentration and the preset smoke concentration, including analyzing the reasons why the fire area does not meet the standard based on the ratio of the absolute value of the difference between the actual area ratio and the preset area ratio to the preset absolute value, or adjusting the threshold of the fire area contour segmentation unit based on the difference between the smoke concentration and the preset smoke concentration.

[0017] Furthermore, the analysis unit is also used to reduce the threshold based on the difference between the smoke concentration and the preset smoke concentration, and the difference is proportional to the reduction of the threshold.

[0018] Furthermore, the analysis unit is also used to increase the noise reduction ratio in image preprocessing based on the threshold, and the decrease in the threshold is proportional to the increase in the noise reduction ratio.

[0019] Furthermore, the analysis unit is also used to generate corresponding processing methods based on the comparison results of the absolute value of the difference between the actual area ratio and the preset area ratio and the ratio of the preset absolute value to the preset ratio. These methods include adjusting the preset area ratio based on the collected wind speed, or determining the reason why the fire area does not meet the standard based on historical smoke and fog density, or adjusting the preset area ratio based on the height of the smoke concentration collector of the smoke collection unit.

[0020] Furthermore, the analysis unit is also used to generate a corresponding processing method based on the comparison result of the ratio of the wind speed to the preset wind speed and the preset ratio, wherein: when the ratio is greater than or equal to the preset ratio, the preset area ratio is increased based on the absolute value of the difference between the ratio and the preset ratio, and the absolute value is proportional to the increase of the preset area ratio; when the ratio is less than the preset ratio, the preset area ratio is decreased based on the absolute value of the difference between the ratio and the preset ratio, and the absolute value is proportional to the decrease of the preset area ratio.

[0021] Furthermore, the analysis unit is also used to generate a corresponding processing method based on the comparison result of the slope of the plotted time-smoke concentration curve at the current time node and the corresponding preset slope, including adjusting the preset area ratio based on the collected wind speed, or adjusting the obtained actual area ratio based on the amount of combustibles.

[0022] Furthermore, the analysis unit is also used to increase the actual area ratio based on the difference between the quantity of combustibles and the preset quantity, and the difference is proportional to the increase in the actual area ratio.

[0023] Furthermore, the analysis unit is also used to reduce the preset area ratio based on the difference between the height of the image acquisition unit's image acquisition device and the preset height, and the difference is proportional to the reduction of the preset area ratio.

[0024] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention collects smoke concentration and images in the space through a smoke collection unit and an image collection unit, respectively, and preprocesses the collected images through an image preprocessing unit, making the collected images more effective. At the same time, the fire area is identified by the YOLOv7 model in the fire area contour recognition unit, and the identified fire area is segmented by the threshold method of the fire area contour segmentation unit. This allows for a more accurate determination of the actual area ratio of the fire area to the entire image, and the determination of whether the monitored fire area can be accurately identified based on the actual area ratio. Based on the determination result, the reasons for non-compliance with the standards are identified, thereby providing corresponding fire extinguishing plans and improving fire extinguishing efficiency.

[0025] Furthermore, the present invention also determines whether the identification of fire areas meets the standard based on the comparison result of the absolute value of the difference between the actual area ratio and the preset area ratio and the preset absolute value. This can quickly determine whether the identification of fire areas meets the standard, thereby enabling the rapid construction of fire prevention plans and further improving the efficiency of fire fighting.

[0026] Furthermore, the present invention also performs a secondary judgment on the identification of fire areas based on smoke concentration, which can more accurately determine whether the identification of fire areas meets the standards, thereby more effectively improving the subsequent fire extinguishing monitoring system, making the fire extinguishing monitoring system more accurate in identifying fire areas, and further improving the efficiency of fire extinguishing.

[0027] Furthermore, the present invention adjusts the image segmentation threshold based on the difference between the smoke concentration and the preset smoke concentration, which can more accurately segment the fire area, thereby making the obtained actual area ratio more accurate and further improving the efficiency of fire fighting.

[0028] Furthermore, the present invention adjusts the noise reduction ratio during image preprocessing based on the reduction magnitude of the threshold, which makes the obtained image clearer, thereby making the fire area contour recognition and segmentation more accurate, and further improving the efficiency of fire fighting.

[0029] Furthermore, the present invention also determines whether the identification of the fire area meets the standard based on the comparison result of the absolute value of the difference between the actual area ratio and the preset area ratio and the ratio of the preset absolute value and the preset ratio. This can more quickly determine the reason why the identification of the fire area does not meet the label, thereby further improving the efficiency of fire fighting.

[0030] Furthermore, the present invention adjusts the preset area ratio based on the wind speed in the space, which can more accurately adjust the preset area ratio, thereby more accurately determining whether the identification of the fire area meets the standard, and further improving the accuracy of the fire extinguishing plan and the efficiency of fire extinguishing.

[0031] Furthermore, the present invention also determines the reasons why the identification of the fire area does not meet the standards based on the slope of the plotted time-smoke concentration curve, which can more accurately determine the reasons for non-compliance with the standards, thereby further improving the accuracy of subsequent treatment methods for the causes, and further improving the efficiency of fire extinguishing.

[0032] Furthermore, the present invention adjusts the actual area ratio obtained based on the quantity of combustibles, which makes the actual area ratio more accurate, thereby further improving the accuracy of determining whether the fire area meets the standard, and thus further improving the efficiency of fire extinguishing.

[0033] Furthermore, the present invention also adjusts the preset area ratio based on the height of the smoke concentration collector, which can more accurately adjust the preset area ratio, thereby more accurately determining whether the identification of the fire area meets the standard, and further improving the efficiency of fire extinguishing. Attached Figure Description

[0034] Figure 1 This is a schematic diagram of the structure of a fire extinguishing monitoring system based on image processing according to an embodiment of the present invention;

[0035] Figure 2 This is a flowchart illustrating the fire extinguishing monitoring method based on image processing according to an embodiment of the present invention;

[0036] Figure 3 This is a flowchart illustrating the steps of determining whether the identification of a fire zone conforms to the standard based on the absolute value of the difference between the actual area ratio and the preset area ratio, according to an embodiment of the present invention.

[0037] Figure 4 This is a flowchart illustrating the steps of determining the ratio of the absolute value of the difference between the actual area ratio and the preset area ratio, according to an embodiment of the present invention. Detailed Implementation

[0038] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0039] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0040] It should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0041] Please see Figure 1 As shown, it is a structural schematic diagram of the fire extinguishing monitoring system based on image processing according to an embodiment of the present invention.

[0042] The system includes a smoke acquisition unit, an image acquisition unit, an image preprocessing unit, a fire area contour recognition unit, a fire area contour segmentation unit, an analysis unit, a cause determination unit, and a control unit.

[0043] The smoke collection unit is used to collect the smoke concentration in the space;

[0044] The image acquisition unit is used to acquire image information within the space;

[0045] The image preprocessing unit is connected to the image acquisition unit and is used to preprocess the acquired image information.

[0046] The fire area contour recognition unit is connected to the image preprocessing unit and is used to recognize the fire area in the image information based on the trained YOLOv7 model. The fire area includes smoke area and flame burning area.

[0047] The fire area contour segmentation unit is connected to the fire area contour recognition unit. It is used to segment the fire feature region in the image information based on a threshold method, and to obtain the ratio of the area of ​​the segmented part to the actual area of ​​the whole image.

[0048] The analysis unit is connected to the smoke collection unit and the fire area contour segmentation unit, and is used to determine whether the fire area meets the standard based on the comparison result of the actual area ratio and the preset area ratio determined according to the smoke concentration.

[0049] The cause determination unit is connected to the analysis unit and is used to generate a corresponding processing method based on the non-standard cause determined by the judgment result obtained by the analysis unit. The preset area ratio is the ratio of the area of ​​the expected fire feature area in the acquired image to the total area of ​​the image. The processing method includes determining the actual area ratio and adjusting the preset area ratio.

[0050] The control unit is connected to the cause determination unit to generate corresponding processing instructions based on the processing method, and to determine the operating parameters of the corresponding component based on the generated processing instructions.

[0051] Specifically, in this embodiment, the smoke concentration in the space is collected by the smoke concentration collector of the smoke collection unit, so as to determine whether the smoke concentration affects the identification of the fire area. The image collection unit collects images in the space by the image collector. The image preprocessing unit performs image filtering on the images collected by the image collection unit to remove the influence of noise in the image. Then, the YOLOv7 model trained in the fire area contour recognition unit is used to recognize the contour of the fire area to obtain the contour of the fire area. The fire area contour segmentation unit uses a threshold method to segment the fire area contour recognized by the fire area recognition unit to obtain a more accurate fire area contour image. The ratio of the area of ​​the segmented fire area contour image to the total area of ​​the image is calculated to obtain the actual area ratio. Finally, the analysis unit determines the actual area ratio based on the obtained smoke concentration. The preset area ratio is obtained based on the relationship between historical smoke concentration and historical preset area ratios. The comparison between the obtained actual area ratio and the preset area ratio determines whether the fire area identification meets the standards. If it does not meet the standards, a corresponding processing method is generated based on the reasons for non-compliance. This allows subsequent processing and control of the fire extinguishing monitoring system components based on the reasons for non-compliance. These components include: an adjustment component for the segmentation threshold in the fire area contour segmentation unit, whose adjustment trend is controlled by the smoke acquisition unit; an adjustment component for the image noise reduction ratio in the image preprocessing unit, whose adjustment trend is determined based on the segmentation threshold adjustment trend; and an adjustment component for the preset area ratio within the area, which primarily adjusts the preset area ratio based on the changing trend of wind speed within the space, and also adjusts it based on the height of the image acquisition device within the space.

[0052] Please see Figure 2 The diagram shown is a flowchart illustrating the fire suppression monitoring method based on image processing according to an embodiment of the present invention. The process includes:

[0053] S1, the smoke concentration in the space is collected through the smoke collection unit;

[0054] S2, acquires image information within the space through the image acquisition unit;

[0055] S3, the acquired image information is preprocessed by the image preprocessing unit connected to the image acquisition unit;

[0056] S4, the fire area contour recognition unit connected to the image preprocessing unit identifies the fire feature area in the image information based on the trained YOLOv7 model;

[0057] S5, the fire feature region in the image information is segmented based on a threshold method by the fire region contour segmentation unit connected to the fire region contour recognition unit, and the ratio of the area of ​​the segmented part to the actual area of ​​the whole image is obtained.

[0058] S6, the analysis unit, which is connected to the smoke collection unit and the fire area outline segmentation unit respectively, determines whether the fire area meets the standard based on the comparison result between the actual area ratio and the preset area ratio determined according to the smoke concentration;

[0059] S7, the cause determination unit connected to the analysis unit generates a corresponding processing method based on the non-compliance cause determined by the judgment result obtained by the analysis unit. The preset area ratio is the ratio of the area of ​​the expected fire feature area in the acquired image to the total area of ​​the image. The processing method includes determining the actual area ratio and adjusting the preset area ratio.

[0060] S8, the corresponding processing instruction is generated by the processing method of the control unit connected to the cause determination unit, and the operating parameters of the corresponding component are determined based on the generated processing instruction.

[0061] Specifically, in this embodiment, the trained YOLOv7 model is input into the preprocessed image and the training iterations, batch size and learning rate of the model are adaptively modified to obtain the optimal fire area recognition model.

[0062] Specifically, in this embodiment, the single threshold method is used to segment the feature region based on the threshold. This method selects a global threshold T, where the segmentation formula is output = {255, if pixel value ≥ T; 0 otherwise}. The pixels are divided into two categories based on the threshold, namely foreground and background. Finally, contour extraction is performed to segment the fire feature region.

[0063] Specifically, in this embodiment, a preset area ratio corresponding to each historical smoke concentration is summarized based on the historical smoke concentration, so that the currently collected smoke concentration can also determine the corresponding preset area ratio.

[0064] Please see Figure 3 The diagram illustrates the steps of determining whether a fire zone meets the standard based on the absolute value of the difference between the actual area ratio and the preset area ratio, according to an embodiment of the present invention. In this embodiment, the analysis unit is further used to determine whether a fire zone meets the standard based on the absolute value of the difference between the actual area ratio and the preset area ratio, and to analyze the reasons why a fire zone does not meet the standard based on the smoke concentration or the absolute value of the difference between the actual area ratio and the preset area ratio.

[0065] Specifically, in this embodiment, the absolute value L0 can be divided into a first preset absolute value L1 and a second preset absolute value L2. The first preset absolute value L1 is set to 0.9, and the second preset absolute value L2 is set to 1.5. It should be noted that in other embodiments, the values ​​of L1 and L2 can also be determined based on the corresponding fire extinguishing requirements. The comparison process between the absolute value L and L1 and L2 is as follows:

[0066] If the absolute value L is less than or equal to the first preset absolute value L1, the fire zone is determined to be accurately identified, and a fire prevention plan based on the acquired area component is then implemented.

[0067] If the absolute value L is greater than the first preset absolute value L1 and less than the second preset absolute value L2, it means that it cannot be determined whether the judgment result is caused by other factors. Then, the judgment result is judged a second time based on the smoke concentration P.

[0068] If the absolute value L is greater than or equal to the second preset absolute value L2, it is determined that the identification of the fire area does not meet the standard. Then, the reason why the identification of the fire area does not meet the standard is analyzed based on the ratio Q of the absolute value of the difference between the actual area ratio and the preset area ratio and the preset absolute value.

[0069] Specifically, in this embodiment of the invention, the analysis unit is also used to generate a corresponding processing method based on the comparison result between the smoke concentration and the preset smoke concentration, including analyzing the reasons why the fire area does not meet the standard based on the ratio of the absolute value of the difference between the actual area ratio and the preset area ratio to the preset absolute value, or adjusting the threshold of the fire area contour segmentation unit based on the difference between the smoke concentration and the preset smoke concentration.

[0070] Specifically, in this embodiment, the preset smoke concentration P0 = 0.8% obs / m, and the comparison process between the smoke concentration P and the preset smoke concentration P0 is as follows:

[0071] If the smoke concentration P is less than or equal to the preset smoke concentration P0, it means that the identification of the fire area is not affected by the smoke. Then, the reason why the identification of the fire area does not meet the standard is analyzed based on the ratio Q of the absolute value of the difference between the actual area ratio and the preset area ratio and the preset absolute value.

[0072] If the smoke concentration P is greater than the preset smoke concentration P0, it indicates that the identification of the fire area is greatly affected by the smoke. Then, the threshold of the fire area contour segmentation unit is adjusted based on the difference R between the smoke concentration and the preset smoke concentration.

[0073] Specifically, in this embodiment of the invention, the analysis unit is also used to reduce the threshold based on the difference between the smoke concentration and the preset smoke concentration, and the difference is proportional to the reduction of the threshold.

[0074] Specifically, in this embodiment, the preset difference R0 = 0.1% obs / m, and the comparison process between the difference R and the preset difference R0 is as follows:

[0075] If the difference R is less than or equal to the preset difference R0, then the threshold is adjusted to 0.9 times the original threshold.

[0076] If the difference R is greater than the preset difference R0, then the threshold is adjusted to 0.6 times the original threshold.

[0077] Specifically, in this embodiment of the invention, the analysis unit is also used to increase the noise reduction ratio in image preprocessing based on the threshold, and the decrease in the threshold is proportional to the increase in the noise reduction ratio.

[0078] Specifically, in this embodiment of the invention, the preset reduction magnitude M0 of the threshold is 9, and the comparison process between the reduction threshold M and the preset reduction threshold M0 is as follows:

[0079] If the reduction threshold M is less than or equal to the preset reduction threshold M0, then the noise reduction ratio is adjusted to 1.4 times the original noise reduction ratio;

[0080] If the reduction threshold M is greater than the preset reduction threshold M0, then the noise reduction ratio is adjusted to 2.1 times the original noise reduction ratio.

[0081] Please see Figure 4 The diagram illustrates the steps of determining the area ratio based on the absolute value of the difference between the actual area ratio and the preset area ratio, and the ratio of the preset absolute value to the preset ratio, according to an embodiment of the present invention. In this embodiment, the analysis unit is further used to generate corresponding processing methods based on the comparison results of the absolute value of the difference between the actual area ratio and the preset area ratio, and the ratio of the preset absolute value to the preset ratio. These methods include adjusting the preset area ratio based on the collected wind speed, determining the reason why the fire area does not meet the standard based on historical smoke and fog density, or adjusting the preset area ratio based on the height of the smoke concentration collector of the smoke collection unit.

[0082] Specifically, in this embodiment, the ratio Q0 can be divided into a first preset ratio Q1 and a second preset ratio Q2. The first preset ratio Q1 is set to 1.1, and the second preset ratio Q2 is set to 1.8. It should be noted that in other embodiments, the values ​​of Q1 and Q2 can also be determined based on the corresponding fire extinguishing requirements. The comparison process between the ratio Q and Q1 and Q2 is as follows:

[0083] If the ratio Q is less than or equal to the first preset ratio Q1, it is determined that there is a problem with ventilation in the space, and the preset area ratio is adjusted based on the wind speed collected by the anemometer.

[0084] If the ratio Q is greater than the first preset ratio Q1 and less than the second preset ratio Q2, it means that the reason why the fire area identification does not meet the standard cannot be determined temporarily. Then, the reason why the fire area identification does not meet the standard is determined based on the historical smoke and fog.

[0085] If the ratio Q is greater than or equal to the second preset ratio Q2, it is determined that there is a problem with the smoke collection unit, and the preset area ratio is adjusted based on the height of the smoke concentration collector of the smoke collection unit.

[0086] Specifically, in this embodiment of the invention, the analysis unit is further used to generate a corresponding processing method based on the comparison result of the ratio of the wind speed to the preset wind speed and the preset ratio, wherein: when the ratio is greater than or equal to the preset ratio, the preset area ratio is increased based on the absolute value of the difference between the ratio and the preset ratio, and the absolute value is proportional to the increase of the preset area ratio; when the ratio is less than the preset ratio, the preset area ratio is decreased based on the absolute value of the difference between the ratio and the preset ratio, and the absolute value is proportional to the decrease of the preset area ratio.

[0087] Specifically, in this embodiment, the preset ratio U0=1, and the comparison process between the ratio of wind speed to preset wind speed and the preset ratio is as follows:

[0088] If the ratio U is greater than or equal to the preset ratio U0, it indicates that the high air velocity results in a low smoke concentration. Therefore, the preset area ratio is increased based on the absolute value of the difference between the ratio and the preset ratio, and the preset absolute value W0 = 0.2. The comparison process based on the absolute value W of the difference between the ratio and the preset ratio and the preset absolute value W0 is as follows:

[0089] If the absolute value W is less than or equal to the preset absolute value W0, then the preset area ratio is adjusted to 1.2 times the original preset area ratio;

[0090] If the absolute value W is greater than the preset absolute value W0, then the preset area ratio is adjusted to 1.9 times the original preset area ratio.

[0091] If the ratio U is less than the preset ratio U0, it indicates that the low air velocity leads to a higher smoke concentration. Therefore, the preset area ratio is reduced based on the absolute value of the difference between the ratio and the preset ratio, and the preset absolute value W0 = 0.3. The comparison process based on the absolute value W of the difference between the ratio and the preset ratio and the preset absolute value W0 is as follows:

[0092] If the absolute value W is less than or equal to the preset absolute value W0, then the preset area ratio is adjusted to 0.9 times the original preset area ratio;

[0093] If the absolute value W is greater than the preset absolute value W0, then the preset area ratio is adjusted to 0.7 times the original preset area ratio.

[0094] Specifically, in this embodiment of the invention, the analysis unit is also used to generate a corresponding processing method based on the comparison result of the slope of the plotted time-smoke concentration curve at the current time node and the corresponding preset slope, including adjusting the preset area ratio based on the collected wind speed, or adjusting the obtained area ratio based on the amount of combustibles.

[0095] Specifically, in this embodiment, the preset slope G0=1, and the comparison process between the slope G of the plotted time-smoke concentration curve at the current time node and the corresponding preset slope GO is as follows:

[0096] If the slope G is less than or equal to the preset slope G0, it indicates that the smoke concentration is gradually accumulating, and there is a problem with ventilation in the space. The preset area ratio is adjusted based on the wind speed collected by the anemometer.

[0097] If the slope G is greater than the preset slope G0, it indicates that there is a deviation in the quantity of combustibles indoors, and the area ratio obtained is adjusted based on the quantity of combustibles.

[0098] Specifically, in this embodiment of the invention, the analysis unit is also used to increase the actual area ratio based on the difference between the quantity of combustible material and the preset quantity, and the difference is proportional to the increase in the actual area ratio.

[0099] Specifically, in this embodiment, the preset difference K0 = 3, and the comparison process between the difference K between the quantity of combustible material and the preset quantity and the preset difference K0 is as follows:

[0100] If the difference K is less than or equal to the preset difference K0, the obtained actual area ratio will be adjusted to 1.5 times the original actual area ratio;

[0101] If the difference K is greater than the preset difference K0, the obtained actual area ratio will be adjusted to 1.9 times the original actual area ratio.

[0102] Specifically, in this embodiment of the invention, the analysis unit is further used to reduce the preset area ratio based on the difference between the height of the image acquisition unit's image acquisition device and the preset height, and the difference is proportional to the reduction of the preset area ratio.

[0103] Specifically, in this embodiment, the preset difference V0 = 0.5m, and the comparison process between the difference between the height of the smoke concentration collector of the smoke collection unit and the preset height is as follows:

[0104] If the difference V is less than or equal to the preset difference V0, the preset area ratio is adjusted to 0.8 times the original preset area ratio;

[0105] If the difference V is greater than the preset difference V0, the preset area ratio is adjusted to 0.6 times the original preset area ratio.

[0106] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0107] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A fire extinguishing monitoring system based on image processing, characterized in that, include: smoke The collection unit is used to collect the smoke concentration in the space; An image acquisition unit is used to acquire image information within a space. An image preprocessing unit, connected to the image acquisition unit, is used to preprocess the acquired image information; A fire area contour recognition unit, which is connected to the image preprocessing unit, is used to identify fire feature areas in the image information based on a trained YOLOv7 model. A fire area contour segmentation unit, which is connected to the fire area contour recognition unit, is used to segment the fire feature region in the image information based on a threshold method, and to obtain the ratio of the area of ​​the segmented part to the actual area of ​​the whole image. An analysis unit, which is connected to the smoke collection unit and the fire area contour segmentation unit respectively, is used to determine whether the fire area meets the standard based on the comparison result of the actual area ratio and the preset area ratio determined according to the smoke concentration. A cause determination unit, connected to the analysis unit, is used to generate a corresponding processing method based on the non-compliance cause determined by the judgment result obtained by the analysis unit. The preset area ratio is the ratio of the area of ​​the expected fire feature region in the acquired image to the total area of ​​the image. The processing method includes determining the actual area ratio and adjusting the preset area ratio. A control unit, connected to the cause determination unit, is used to generate corresponding processing instructions based on the processing method, and to determine the operating parameters of the corresponding component based on the generated processing instructions; The analysis unit is also used to determine whether the fire area meets the standard based on the absolute value of the difference between the actual area ratio and the preset area ratio, and to analyze the reasons why the fire area does not meet the standard based on the absolute value of the difference between the smoke concentration or the actual area ratio and the preset area ratio.

2. The fire extinguishing monitoring system based on image processing according to claim 1, characterized in that, The analysis unit is also used to generate a corresponding processing method based on the comparison result of the smoke concentration and the preset smoke concentration, including analyzing the reasons why the fire area does not meet the standard based on the ratio of the absolute value of the difference between the actual area ratio and the preset area ratio to the preset absolute value, or adjusting the threshold of the fire area contour segmentation unit based on the difference between the smoke concentration and the preset smoke concentration.

3. The fire extinguishing monitoring system based on image processing according to claim 2, characterized in that, The analysis unit is also used to reduce the threshold based on the difference between the smoke concentration and the preset smoke concentration, and the difference is proportional to the reduction of the threshold.

4. The fire extinguishing monitoring system based on image processing according to claim 3, characterized in that, The analysis unit is also used to increase the noise reduction ratio in image preprocessing based on the threshold, and the decrease in the threshold is proportional to the increase in the noise reduction ratio.

5. The fire extinguishing monitoring system based on image processing according to claim 1, characterized in that, The analysis unit is also used to generate corresponding processing methods based on the comparison results of the absolute value of the difference between the actual area ratio and the preset area ratio and the ratio of the preset absolute value and the preset ratio. These methods include adjusting the preset area ratio based on the collected wind speed, or determining the reason why the fire area does not meet the standard based on historical smoke and fog density, or adjusting the preset area ratio based on the height of the smoke concentration collector of the smoke collection unit.

6. The fire extinguishing monitoring system based on image processing according to claim 5, characterized in that, The analysis unit is also used to generate a corresponding processing method based on the comparison result of the ratio of the wind speed to the preset wind speed and the preset ratio, wherein: If the ratio is greater than or equal to a preset ratio, the preset area ratio is increased based on the absolute value of the difference between the ratio and the preset ratio, and the absolute value is proportional to the increase in the preset area ratio. If the ratio is less than a preset ratio, the preset area ratio is reduced based on the absolute value of the difference between the ratio and the preset ratio, and the absolute value is proportional to the reduction of the preset area ratio.

7. The fire extinguishing monitoring system based on image processing according to claim 5, characterized in that, The analysis unit is also used to generate a corresponding processing method based on the comparison between the slope of the plotted time-smoke concentration curve at the current time node and the corresponding preset slope, including adjusting the preset area ratio based on the collected wind speed, or adjusting the obtained actual area ratio based on the amount of combustibles.

8. The fire extinguishing monitoring system based on image processing according to claim 7, characterized in that, The analysis unit is also used to increase the actual area ratio based on the difference between the quantity of combustibles and the preset quantity, and the difference is proportional to the increase in the actual area ratio.

9. The fire extinguishing monitoring system based on image processing according to claim 5, characterized in that, The analysis unit is also used to reduce the preset area ratio based on the difference between the height of the image acquisition unit's image acquisition device and the preset height, and the difference is proportional to the reduction of the preset area ratio.

Images