A fire detection analysis method based on thermal radiation technology

Abstract

The present application relates to the technical field of thermal radiation fire detection, and a fire detection analysis method based on thermal radiation technology, comprising the following steps: S1, establishing a three-dimensional physical model of a forest area requiring fire detection; S2, collecting thermal radiation influencing factors in multiple areas to obtain influence coefficient values; selecting five time periods to collect temperature values, sunshine values, light intensity values, rainfall values and humidity values, and respectively calculating to obtain influence coefficient values of the five time periods; S3, correlating the influence coefficient values to divide weak areas of fire detection; S4, on the basis of a fire accident scene of the three-dimensional physical model, respectively calculating the influence of thermal radiation detection and smoke movement diffusion under each fire scene at different time periods, setting a high-temperature point threshold range, and determining a fire starting point area; S5, setting a fire prevention warning level, and intelligently performing inspection detection, analysis and alarm.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of thermal radiation fire detection, in particular to a fire detection and analysis method based on thermal radiation technology. BACKGROUND

[0002] Forest is one of the most important and indispensable resources for human survival and social development, and is also the protector of the ecological balance of the earth. Among the factors that endanger forests, fire is the most destructive disaster, and each fire will bring huge losses. Therefore, preventing and monitoring forest fires has become an important research focus of forest fire prevention departments around the world. At present, forest fire prevention measures generally use forest fire prevention personnel to patrol the forest area during the fire prevention period, manual observation from the lookout tower, and satellite detection, but the traditional forest fire monitoring methods have shortcomings, and new methods need to be introduced to apply to the monitoring of forest fires.

[0003] The background technology of the thermal radiation fire detection and analysis method mainly involves infrared imaging technology, image processing technology, pattern recognition technology, etc. Infrared imaging technology is one of the core technologies of the thermal radiation fire detection and analysis method. It uses infrared thermal imager and other equipment to measure the infrared radiation of the fire scene and obtains the infrared image of the object surface. Infrared imaging technology can obtain the temperature distribution image of the fire scene in real time, providing an important means for rapid detection and analysis of fire.

[0004] Image processing technology is an important supplement to infrared imaging technology. It can process and analyze the obtained infrared image and extract useful information such as temperature distribution and thermal radiation distribution. Common image processing techniques include edge detection, image segmentation, feature extraction, etc. The thermal radiation fire detection and analysis method has higher accuracy and reliability, providing strong support for fire prevention and handling.

[0005] Now the thermal imaging technology of thermal radiation fire detection is in the outdoor, it is easy to be affected by many factors, such as environmental temperature, environmental light, wind speed and humidity, all of which can cause the thermal imager to have image blur and distortion problems, and further affect the actual effect of fire detection, and even may not identify the fire point, and thus lose the best time for fire warning, leading to possible expansion of forest fire accidents. SUMMARY

[0006] The application provides a fire detection analysis method based on thermal radiation technology, which has the beneficial effects of collecting, fitting, summarizing and calculating influence factor data of different time periods, adjusting a thermal radiation monitor according to an influence coefficient value, and improving the accuracy of thermal radiation monitoring of fires.

[0007] The application provides the following technical scheme: a fire detection analysis method based on thermal radiation technology, comprising the following steps:

[0008] S1, a three-dimensional physical model of a forest area needing fire detection is established;

[0009] S2, thermal radiation influence factors in multiple areas are collected to obtain an influence coefficient value;

[0010] The thermal radiation influence factors include air temperature characteristics, sunshine characteristics, light characteristics, rain and snow characteristics, and humidity characteristics;

[0011] Temperature values, sunshine values, light intensity values, rainfall values and humidity values are collected in five time periods, and the influence coefficient values of the five time periods are respectively calculated and obtained;

[0012] S3, the influence coefficient value is associated to divide a weak area of fire detection;

[0013] S4, based on a fire accident scene of the three-dimensional physical model, the influence of the influence coefficient value on thermal radiation cruise monitoring is considered, the influence of different influence coefficients on thermal radiation detection and smoke movement diffusion is respectively calculated, the influence of thermal radiation detection and smoke movement diffusion under different influence coefficients and in each fire scene is calculated, a high-temperature point threshold range is set, and a fire starting point area is determined;

[0014] S5, a fire prevention warning level is set, and intelligent inspection detection, analysis and alarm are performed.

[0015] As an optional solution of the fire detection analysis method based on thermal radiation technology, the S1 step specifically comprises: using a drone, an infrared detector and a video monitoring instrument to completely take aerial photographs of the forest area, and collecting the forest coverage area;

[0016] An infrared thermal image of the outdoor forest area is obtained, forest cables, power distribution station equipment and forest flammable material main bodies are extracted, and the three-dimensional physical model is established;

[0017] The forest flammable material includes arbor region, shrub region, weed region, fern region, moss region, lichen region, dead standing wood region, rotten wood region, dead branch and leaf region and peat region.

[0018] As an optional solution of the fire detection analysis method based on the thermal radiation technology, five time periods are selected to collect data, and the time values are 7:00 am, 12:00 am, 4:00 pm, 7:00 pm and 00:00 am.

[0019] The influence coefficient value of 7:00 am is obtained by the following formula:

[0020] The influence coefficient value of 12:00 am is obtained by the following formula:

[0021] The influence coefficient value of 4:00 pm is obtained by the following formula:

[0022] The influence coefficient value of 7:00 pm is obtained by the following formula:

[0023] The influence coefficient value of 00:00 am is obtained by the following formula: ; wherein The influence coefficient values of the five time periods are represented by a, b, c, d and e respectively. The temperature values of the five time periods are represented by T1, T2, T3, T4 and T5 respectively. The humidity values of the five time periods are represented by H1, H2, H3, H4 and H5 respectively. The influence coefficient of temperature and humidity on infrared thermal imaging is represented by K1. ; wherein The light intensity values of the five time periods are represented by I1, I2, I3, I4 and I5 respectively. The influence coefficient of light intensity on infrared thermal imaging is represented by K2. ​​​​​​​​​​​​​​​​​​​​​​​​​ respectively represent the rainfall values of five time periods, represents the temperature influence coefficient of rainfall on infrared thermal imaging; wherein ; , , , , respectively represent the direct sunlight and horizontal angle values of five time periods, represents the temperature influence coefficient of sunshine angle on infrared thermal imaging; .

[0024] As an optional solution of the fire detection analysis method based on the thermal radiation technology, wherein the obtained , , , , respectively represent the influence coefficient values of five time periods, and the resolution compensation coefficient is calculated by correlating the collected thermal radiation image parameters; the resolution compensation coefficient MB is obtained by the following formula:

[0025] In the formula, MB1, MB2, MB3, MB4 and MB5 respectively represent the resolution compensation coefficients of five time periods; wherein represents the standard spectral brightness value; represents the standard focal length change coefficient value; represents the focal length adjustment value, and a percentage value is obtained.

[0026] As an optional solution of the fire detection analysis method based on the thermal radiation technology, wherein the S3 step specifically includes:

[0027] (1) The unmanned aerial vehicle obtains the infrared image of the forest area, and the region position of the distinguishing extraction equipment and the forest combustible is extracted;

[0028] According to the plant density of the forest combustible, the forest is divided into

[0029] The plant density is obtained by selecting a certain number of regions in the forest, measuring the number of trees in each sample, and then averaging; or the tree canopy area is obtained by the unmanned aerial vehicle, and then summed, and divided by the total area to obtain the number of trees per square meter;

[0030] According to the forest terrain, the forest is divided into flat land, slope and hillside, and the forest density of each type of terrain is measured;

[0031] (2) After calculating the forest density, the weak points are divided, and the area with more than 30% forest coverage is marked as a weak area in the three-dimensional physical model in S1. The higher the density, the faster the spread trend when the fire occurs;

[0032] (3) Remove the influence of the background in the infrared image on the diagnosis of hidden points. According to the intensity spectrum, the abnormal area with high color in the main image of the cable, power distribution station and forest flammable material to be detected is determined as a hidden point;

[0033] (4) Correlate the influence coefficient value, set the flammable risk level in combination with the weak area in (1) and (2), and mark it.

[0034] As an optional solution of the fire detection analysis method based on thermal radiation technology, the flammable risk level includes first, second, third and fourth risk levels.

[0035] As an optional solution of the fire detection analysis method based on thermal radiation technology, the S4 step specifically includes:

[0036] Use unmanned aerial vehicle to take infrared images of forest, and collect multiple frames of images of continuous fire accident scene;

[0037] The fire accident scene image is de-noised, and the main outline of the fire light background image is obtained through binarization;

[0038] The binary image needs to be projected to find the position of the cable, power distribution station and combustible material;

[0039] According to the binarized image, the intensity spectrum is observed to preliminarily determine the color highlight area in the picture as an abnormal area:

[0040] The abnormal area is subjected to morphological processing, the motion trajectory in multiple frames of images is observed, the fire light frequency value per second, the fire light spread trend range characteristics are obtained, the smoke texture characteristics in the picture are obtained, and the smoke motion trajectory characteristics are analyzed.

[0041] As an optional solution of the fire detection analysis method based on thermal radiation technology, the fire prevention warning level is set to low, medium, high, extreme and special danger.

[0042] As an optional solution of the fire detection analysis method based on thermal radiation technology, the high temperature point threshold range is analyzed by identifying the conditions of high temperature points, only involving the brightness temperature of 4um channel, and the specific threshold is set as: T21>335K during the day; T21>305K at night; The pixel points meeting the above conditions are temporarily determined as suspected fire points;

[0043] If the T4 of the detection point is greater than (the T4 mean value of the background point + 4 times the T21 mean square deviation of the background point), and (T4-T31) of the detection point is greater than

(T11-T31) median value of the background point + 4 times (T4-T31) mean square deviation of the background point

[0044] The present application has the following beneficial effects:

[0045] 1. The fire detection analysis method based on thermal radiation technology collects the influencing factors that may affect the thermal radiation thermal imaging monitor and divides them into five time periods, counts the influence coefficient values, and after summarizing and correlation calculation, adjusts the thermal radiation monitor according to the influence coefficient values to improve the accuracy of thermal radiation monitoring of fire.

[0046] 2. The fire detection analysis method based on thermal radiation technology, after collecting the influence data of the five time periods, calculates the influence coefficient values of the five time periods to obtain 、 、 、 、 respectively, the influence coefficient values of the five time periods, and calculates the resolution compensation coefficient by correlating the collected thermal radiation image parameters; and then adjusts the spectral brightness value and focal length change coefficient of thermal imaging in real time through the resolution compensation coefficient to improve the resolution value of thermal imaging and reduce the image blur and distortion problem, so that the firelight point can be identified and the fire hazard can be quickly eliminated when the image resolution is clearer.

[0047] 3. In the S3 step of the fire detection analysis method based on thermal radiation technology, the weak area is divided according to the plant density of forest flammable material, forest terrain, cable, power distribution station and main body of forest flammable material through multi-dimensional classification to obtain the flammable risk level, so as to facilitate timely detection and monitoring management of different flammable risk level areas in the later period.

[0048] Through unmanned aerial vehicle aerial infrared imaging, multiple frames of images of continuous firelight accident scenes are collected, the images are binarized, projected, and intensity processed, then the specific threshold is compared and identified, and then the pixel points meeting the threshold condition are temporarily determined as suspected fire points. In the process of repeatedly detecting and determining fire points and analyzing smoke movement trajectory characteristics, the accuracy of detecting firelight is improved, and the situation of false alarm and unclear detection is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1A flow chart of the fire detection and analysis method based on thermal radiation technology according to the present application. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0051] Embodiment 1

[0052] Forests are one of the most important and indispensable resources for human survival and social development, and are also protectors of the ecological balance of the earth. Among the factors that endanger forests, fire is a kind of disaster with the most destructive damage, and each fire will bring huge losses. Therefore, preventing and monitoring forest fires has become an important research focus of forest fire prevention departments in various countries in the world. At present, forest fire prevention measures generally adopt sending fire prevention personnel to patrol forest areas, manual observation by watchtowers, and satellite detection during the fire prevention period. However, the traditional forest fire monitoring methods all have deficiencies, and new methods need to be introduced for application in forest fire monitoring.

[0053] The background technology of the thermal radiation fire detection and analysis method mainly involves infrared imaging technology, image processing technology, pattern recognition technology, etc. The infrared imaging technology is one of the core technologies of the thermal radiation fire detection and analysis method. It uses infrared thermal imagers and other equipment to measure the infrared radiation of the fire scene and obtains the infrared image of the object surface. The infrared imaging technology can obtain the temperature distribution image of the fire scene in real time, providing an important means for rapid detection and analysis of fire.

[0054] The image processing technology is an important supplement to the infrared imaging technology. It can process and analyze the obtained infrared image and extract useful information such as temperature distribution and thermal radiation distribution. Commonly used image processing technologies include edge detection, image segmentation, feature extraction, etc. The thermal radiation fire detection and analysis method has higher accuracy and reliability, providing strong support for the prevention and handling of fires.

[0055] In fire rescue, the infrared thermal imager can penetrate through thick smoke, can monitor the burning degree and spreading trend of the fire in real time, can determine the position of trapped personnel / animals, can facilitate search and rescue, and can ensure the safety of personnel / animals.

[0056] After the fire is extinguished, the smoke is large and the field of view is poor, and the human eye and visible light camera are difficult to find, and the infrared thermal imager can monitor the temperature of the forest ground after the fire and find hidden scattered fire, so as to take timely measures to extinguish the fire and control the recurrence of the fire.

[0057] The thermal imaging technology is affected by many factors when detecting fire outdoors. The following are some common factors:

[0058] Ambient temperature: Changes in ambient temperature can affect the temperature distribution of objects, thereby affecting the accuracy of thermal imaging. When used outdoors, the temperature distribution of the object surface may change greatly due to changes in air temperature, thereby affecting the effect of thermal imaging.

[0059] Ambient light: Thermal imaging technology has lower requirements for ambient light, but too strong light will still affect imaging. Under strong light, the thermal imager may have problems such as reflection and contrast, thereby affecting the effect of imaging.

[0060] Wind speed: Changes in wind speed can affect the temperature distribution of objects such as smoke and flames at the fire scene, thereby affecting the accuracy of thermal imaging. In the case of high wind speed, the thermal imager may have problems such as shaking and blurring, thereby affecting the effect of imaging.

[0061] Humidity: Changes in humidity can affect the temperature distribution of objects such as smoke and flames at the fire scene, thereby affecting the accuracy of thermal imaging. In the case of high humidity, the thermal imager may have problems such as image blurring and distortion, thereby affecting the effect of imaging.

[0062] Smoke and fog: Smoke and fog can affect the imaging effect of thermal imaging. In the case of thick smoke and fog, the thermal imager may have problems such as image blurring and distortion, thereby affecting the effect of imaging.

[0063] Therefore, when using thermal imaging technology to detect fire outdoors, the influence of the above factors needs to be considered, and appropriate measures such as increasing the protection of the equipment and adjusting the imaging parameters need to be taken to improve the accuracy and reliability of thermal imaging technology.

[0064] The present application provides the following technical scheme: a fire detection analysis method based on thermal radiation technology, please refer to Figure 1 , comprising the following steps:

[0065] S1, a three-dimensional physical model of a forest area needing fire detection is established;

[0066] S2, collect the thermal radiation influencing factors in multiple areas to obtain the influence coefficient value;

[0067] The heat radiation influencing factors include air temperature characteristics, sunshine characteristics, light characteristics, rain and snow characteristics, and humidity characteristics.

[0068] Temperature values, sunshine values, light intensity values, rainfall values, and humidity values are collected in five time periods, and influence coefficient values of the five time periods are respectively calculated.

[0069] S3, the influence coefficient values are associated to divide weak areas of fire detection.

[0070] S4, on the basis of the fire accident scene of the three-dimensional physical model, the influence of the influence coefficient values on the heat radiation cruise monitoring is considered, the influence of different influence coefficients on the heat radiation detection and smoke movement diffusion is calculated respectively, the influence of the heat radiation detection and smoke movement diffusion under different time periods and in each fire scene is calculated, a high temperature point threshold range is set, and a fire starting point area is determined.

[0071] S5, set the fire prevention warning level, intelligent patrol detection, analysis and alarm.

[0072] In this embodiment, in S2, the influencing factors that may affect the heat radiation thermal imaging monitor are collected in S1-S5 steps, and are divided into five time periods, the influence coefficient values are counted and summarized, and the heat radiation monitor is adjusted according to the influence coefficient values to improve the accuracy of the heat radiation monitoring fire;

[0073] Embodiment 2

[0074] This embodiment is an explanation and description in embodiment 1, wherein: the S1 step specifically includes using a unmanned aerial vehicle, an infrared detector and a video monitor to completely take pictures of the forest area, collecting the forest coverage area, obtaining the infrared thermal image of the outdoor forest area, extracting the cables, power distribution station equipment and forest combustibles in the forest, and establishing a three-dimensional physical model.

[0075] The forest combustibles include arbor zone, shrub zone, weed zone, fern zone, moss zone, lichen zone, dead standing wood zone, rotten wood zone, dead branch and leaf zone, and peat zone.

[0076] The three-dimensional physical model of the forest area is set to facilitate marking and watching on the three-dimensional physical model in the process of fire detection, and each classified area, including the spreading trend, is easily predicted from the three-dimensional physical model.

[0077] Embodiment 3

[0078] This embodiment is an explanation and description in embodiment 1, wherein: five time periods are selected to collect data, and the time is respectively 7:00 am, 12:00 am, 4:00 pm, 7:00 pm and 00:00 am.

[0079] The 7:00 am influence coefficient value is obtained by the following formula: The 12:00 am influence coefficient value is obtained by the following formula: The 4:00 pm influence coefficient value is obtained by the following formula: The 7:00 pm influence coefficient value is obtained by the following formula:

[0080] The 00:00 am influence coefficient value is obtained by the following formula: , , , , respectively represent the influence coefficient values of the five time periods; , , , , respectively represent the temperature values of the five time periods; , , , , respectively represent the humidity values of the five time periods; represents the influence coefficient of temperature and humidity on infrared thermal imaging; wherein , , , , respectively represent the light intensity values of the five time periods, represents the influence coefficient of light intensity on infrared thermal imaging; wherein ; , , , , respectively represent the rainfall values of the five time periods, represents the temperature influence coefficient of rainfall on infrared thermal imaging; wherein ; , , , , respectively represent the angle values between direct sunlight and the horizontal plane in the five time periods, represents the temperature influence coefficient of the angle of sunlight on infrared thermal imaging; .

[0081] ​​In this embodiment, after collecting the influence data of the five time periods, the influence coefficient values of the five time periods are calculated, and the thermal radiation image parameters are adjusted according to the specific influence coefficient values, so as to improve the resolution value of thermal imaging, reduce the blurring and distortion of thermal imaging images.

[0082] Embodiment 4

[0083] In this embodiment, the influence coefficient values of the five time periods are obtained by calculating the influence coefficient values of the five time periods after collecting the influence data of the five time periods. 、 、 、 、 The resolution compensation coefficient is calculated by correlating the collected thermal radiation image parameters.

[0084] The resolution compensation coefficient MB is obtained by the following formula: In the formula, MB1, MB2, MB3, MB4 and MB5 represent the resolution compensation coefficients of the five time periods respectively; wherein represents the standard spectral brightness value; represents the standard focal length change coefficient value; represents the focal length adjustment value, and the percentage value is obtained.

[0085] In this embodiment, after collecting the influence data of the five time periods, the influence coefficient values of the five time periods are obtained by calculating the influence coefficient values of the five time periods. 、 、 、 、 The resolution compensation coefficient is calculated by correlating the collected thermal radiation image parameters. Then, the spectral brightness value and the focal length change coefficient of thermal imaging are adjusted in real time by the resolution compensation coefficient, so as to improve the resolution value of thermal imaging, reduce the blurring and distortion of thermal imaging images, and facilitate the identification of fire points and the rapid elimination of fire hazards when the image resolution is clearer.

[0086] Embodiment 5

[0087] In this embodiment, the S3 step specifically includes:

[0088] (1) The unmanned aerial vehicle obtains the forest area infrared image, and extracts the region position of the equipment and the forest combustible material;

[0089] According to the plant density of the forest combustible material,

[0090] The plant density is obtained by selecting a certain number of areas in the forest, measuring the number of trees in each sample plot, and then averaging; or by obtaining the tree canopy area by drone, and then summing and dividing by the total area to obtain the number of trees per square meter;

[0091] According to the division of forest terrain, it is divided into flat land, slope and hillside, and the forest density of each type of terrain is measured;

[0092] (2) After calculating the forest density, the weak points are divided, and the areas with more than 30% forest coverage are marked as weak areas in the three-dimensional physical model in step S1. The higher the density, the faster the spread when a fire occurs;

[0093] (3) Remove the background in the infrared image to affect the diagnosis of hidden points. According to the intensity spectrum, the abnormal areas with high color highlights in the main image of the cable, power distribution station and forest flammable material to be detected are determined as hidden points;

[0094] (4) Correlate the influence coefficient value, set the flammable risk level in combination with the weak areas in (1) and (2), and mark.

[0095] Among them, the flammable risk level includes first risk level, second risk level, third risk level and fourth risk level.

[0096] First risk level: set as electrical, power distribution station and cable equipment, which is easy to cause fire due to high temperature and electrical accident, set as first risk level;

[0097] Second risk level: some forest flammable materials, dead standing wood area, rotten wood area, dry leaves area and peat area, flammable value greater than 73, forest coverage more than 30% belong to the second risk level;

[0098] Third risk level: for areas with more than 20% and not more than 30% forest coverage, which belong to the range of not easy to burn;

[0099] Fourth risk level: for areas with not more than 20% forest coverage, which belong to the low risk flammable range;

[0100] Correlate the influence coefficient value, for example: equipment one place in the slope, the night temperature is between 0°C and 5°C, the rainfall is high, and there are a small amount of rotten wood area near, the forest coverage is not more than 30%, and it is determined as the third risk level.

[0101] In this embodiment, by classifying the forest combustible plant density, forest terrain, combustible cable, power distribution station and forest combustible main body in the S3 step, the weak area is divided, and the combustible risk level is obtained, so that the area with different combustible risk levels can be detected and monitored in time in the later period.

[0102] Embodiment 6

[0103] This embodiment is an explanation in embodiment 1, wherein the S4 step specifically comprises:

[0104] Collecting multiple frames of images of continuous fire accident scenes by aerial infrared imaging of the unmanned aerial vehicle;

[0105] Performing de-noising processing on the fire accident scene images, and obtaining the approximate outline of the main body of the fire occurrence background image through binarization;

[0106] The binary image needs to be projected to find the positions of the cable, power distribution station and combustible material.

[0107] According to the binarized image, the color spectrum is observed to preliminarily determine that the color highlight area in the picture is an abnormal area.

[0108] Performing morphological processing on the abnormal area, observing the motion trajectory in multiple frames of images, obtaining the fire light frequency value per second, the fire light spread trend range characteristics, obtaining the smoke texture characteristics in the picture, and analyzing the smoke motion trajectory characteristics.

[0109] The high-temperature point threshold range is analyzed by identifying the conditions of the high-temperature point, only involving the brightness temperature of the 4um channel, and the specific threshold is set as: T21>335K during the day; T21>305K at night, and the pixel points meeting the above conditions are temporarily determined as suspected fire points.

[0110] If the T4 of the detection point is greater than (the T4 average value of the background point + 4 times the T21 mean square deviation of the background point), and (T4-T31) of the detection point is greater than

(T11-T31) median value of the background point + 4 times (T4-T31) mean square deviation of the background point

[0111] In this embodiment, multiple frames of images of continuous fire accident scenes are collected by aerial infrared imaging of the unmanned aerial vehicle, the images are binarized, projected, and processed by intensity, then the specific threshold is compared and identified, and the pixel points meeting the threshold condition are temporarily determined as suspected fire points, and the background points and detection points are detected again, the process of repeatedly detecting and determining the fire points and analyzing the smoke motion trajectory characteristics promotes the accuracy of detecting the fire light and reduces the false positives and unclear detection.

[0112] Embodiment 7

[0113] This embodiment is an explanation in embodiment 1, wherein: setting fire warning levels, respectively set as low, medium, high, extreme and special danger. According to different fire warning levels, set different levels of emergency plan for fire extinguishing treatment.

[0114] The above embodiments can be realized wholly or partially by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another by wired (for example, infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center and the like containing one or more available medium sets. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, DVD) or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0115] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0116] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0117] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. The division of the units is merely logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0118] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, and can be located in one place, or can be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0119] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0120] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of a software product in essence or the part of the technical solutions that make contributions to the prior art, or part of the technical solutions. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0121] The above is merely specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0122] Finally: the above only for the preferred embodiments of the present application, and not for limiting the present application, any modification made within the spirit and principles of the present application, equivalent replacement, improvement, etc., should be included in the scope of protection of the present application.

[0123] The above only is the preferred embodiment of the present application, it should be pointed out that, for ordinary skilled in the art, without departing from the technical principles of the present application, can also make a number of improvements and refinements, these improvements and refinements should also be considered the scope of protection of the present application.

Claims

1. A method of fire detection analysis based on thermal radiation technology, characterized in that: It comprises the following steps: S1, establishing a three-dimensional physical model of a forest area requiring fire detection; S2, collecting thermal radiation influencing factors in multiple areas to obtain influence coefficient values; The thermal radiation influencing factors include air temperature characteristics, sunshine characteristics, light characteristics, rain and snow characteristics, and humidity characteristics; Temperature values, sunshine values, light intensity values, rainfall values, and humidity values are collected at five time periods to obtain influence coefficient values for each of the five time periods; S3, dividing weak areas for fire detection by associating the influence coefficient values, specifically including: (1) obtaining an infrared image of the forest area by a UAV to distinguish and extract the positions of the equipment and forest flammable materials; dividing according to the plant density of the forest flammable materials, The plant density is obtained by selecting a certain number of areas in the forest, measuring the number of trees in each sample plot, and then averaging, or by obtaining the tree canopy area by a UAV, and then summing and dividing by the total area to obtain the number of trees per square meter; dividing according to the forest terrain, into flat land, slope, and hillside, and measuring the forest density of each type of terrain; (2) after calculating the forest density, the weak points are divided, and areas with more than 30% forest coverage are marked as weak areas in the three-dimensional physical model in step S1, because the higher the density, the faster the spread trend when a fire occurs; (3) removing the influence of the background in the infrared image on the diagnosis of hidden danger points, and determining the abnormal areas with high color highlights in the images of the cables, power distribution stations, and forest flammable materials to be detected as hidden danger points according to the intensity spectrum; (4) associating the influence coefficient values, setting the flammable risk level for the weak areas in (1) and (2), and marking them; S4, considering the influence of the influence coefficient values on thermal radiation cruise monitoring based on the fire accident scene of the three-dimensional physical model, calculating the influence of different influence coefficients on thermal radiation detection and smoke movement diffusion, calculating the influence of thermal radiation detection and smoke movement diffusion in each fire scene at different time periods, setting a high temperature point threshold range, and determining the ignition point area; S5, setting a fire prevention warning level, and intelligently inspecting, detecting, analyzing, and alarming.

2. A method of fire detection analysis based on thermal radiation technology according to claim 1, characterized in that: The S1 step specifically includes: using a UAV, an infrared detector, and a video monitor to completely aerial photograph the forest area and collect the forest coverage area; obtaining an infrared thermal image of the outdoor forest area, extracting the cables, power distribution station equipment, and forest flammable material main body, and establishing a three-dimensional physical model; The forest flammable materials include arbor zone, shrub zone, weed zone, fern zone, moss zone, lichen zone, dead standing wood zone, rotten wood zone, dead branch and leaf zone, and peat zone.

3. A method of fire detection analysis based on thermal radiation technology according to claim 2, characterized in that: Data is collected at five time periods, at 7:00 am, 12:00 am, 4:00 pm, 7:00 pm, and 00:00 am; The influence coefficient value at 7:00 am is obtained by the following formula: ； The influence coefficient value at 12:00 am is obtained by the following formula: ； The influence coefficient value at 4:00 pm is obtained by the following formula: ； The influence coefficient value at 7:00 pm is obtained by the following formula: ； The influence coefficient value of 00:00am is obtained by the following formula: ； In the formula: , , , , respectively represent the influence coefficient values of the five time periods; , , , , represent temperature values of five time periods, respectively; , , , , represent humidity values of five time periods, respectively; represents the influence coefficient of temperature and humidity on infrared thermal imaging; wherein ; In the formula: , , , , respectively represent the light intensity values of five time periods, represent the influence coefficient of light intensity on infrared thermal imaging; wherein ; , , , , represent the rainfall values of five time periods respectively, represents the temperature influence coefficient of rainfall on infrared thermal imaging; wherein ; , , , , represent the values of the angle between direct sunlight and the horizontal plane for the five time periods, respectively, represents the temperature influence coefficient of the angle of incidence on infrared thermography; .

4. A method of fire detection analysis based on thermal radiation technology according to claim 3, characterized in that: acquired , , , , the influence coefficient values of the five time periods respectively, and the resolution compensation coefficient is calculated by correlating the collected thermal radiation image parameters; The resolution compensation coefficient MB is obtained by the following formula: In the formula, MB1, MB2, MB3, MB4 and MB5 represent resolution compensation coefficients of five time periods respectively; wherein represents a standard spectral luminance value; represents a standard focal length change coefficient value; represents a focal length adjustment value, and a percentage value is obtained.

5. The method of claim 1, wherein: the method is based on thermal radiation technology. The flammable risk level includes a first risk level, a second risk level, a third risk level and a fourth risk level.

6. A method of fire detection analysis based on thermal radiation technology according to claim 1, characterized in that: The S4 step specifically includes: Collecting multiple images of continuous firelight accident scenes by using a UAV to take aerial infrared images of forests; Performing de-noising processing on the fire accident scene images to obtain the approximate outline of the main body of the firelight occurrence background image through binarization; The binary image needs to be projected to find the positions of the cable, power distribution station and combustible materials; According to the binarized image, the color spectrum is observed through intensity to preliminarily determine that the color highlight area in the picture is an abnormal area: Perform morphological processing on the abnormal area, observe the motion trajectory in multiple images, and obtain the firelight frequency value per second, the firelight spread trend range characteristics, the smoke texture characteristics in the picture, and the smoke motion trajectory characteristics.

7. The method of claim 1, wherein: the method is based on thermal radiation technology. Set the fire prevention warning levels to be low, medium, high, extreme and extremely dangerous.

8. The method of claim 1, wherein: the method is based on thermal radiation technology. The high-temperature point threshold range involves only the brightness temperature of the 4um channel through the condition analysis of identifying high-temperature points, and the specific threshold is set as: T21>335K during the day; T21>305K at night; the pixel points meeting the above conditions are temporarily determined as suspected fire points; If the T4 of the detection point is greater than (the T4 mean value of the background point + 4 times the T21 mean square deviation of the background point), and the (T4-T31) of the detection point is greater than 【(T11-T31) median value of the background point + 4 times (T4-T31) mean square deviation of the background point】, it is determined as a fire point; wherein T4, T21, T31 and T11 represent the brightness temperature values of the 4um channel, the 21um channel, the 31um channel and the 11um channel, respectively.

Images