Flame identification method for infrared thermal imaging detector

Abstract

The invention discloses a flame identification method for an infrared thermal imaging detector, which relates to the technical field of infrared thermal imaging, is used for improving the accuracy of fire identification, and comprises the following steps: obtaining a visual thermal image generated by an infrared thermal imaging detection assembly, analyzing temperature anomaly according to the thermal image, positioning a temperature anomaly point, and obtaining a flame identification result. Acquiring an included angle between an observation direction vector and a reflection direction vector of the component according to the positioning and judgment time of the temperature abnormal point, judging whether the temperature abnormal point is reflected, marking the temperature abnormal point which does not accord with the reflected light as a suspicious fire hazard monitoring point, and identifying combustible materials of the suspicious fire hazard monitoring point. Analyzing the combustion risk of the combustible at the suspicious fire monitoring point according to the combustible ignition point data and the oxygen data, and analyzing the possibility that the suspicious fire monitoring point is a flame according to the image data of the suspicious fire monitoring point; and analyzing whether a fire occurs at the suspicious fire monitoring point according to the combustion risk of the combustible at the suspicious fire monitoring point and the possibility that the suspicious fire monitoring point is flame.

Description

Technical Field

[0001] The present invention relates to the field of infrared thermal imaging technology, and particularly to a flame recognition method for an infrared thermal imaging detector. Background Technique

[0002] An infrared thermal imaging detector is a device that receives the infrared radiation energy emitted by an object, converts it into an electrical signal, and finally generates a visible thermal image. It can capture the temperature distribution on the surface of an object and display the temperature difference in different colors, so as to achieve target detection and recognition. Since the infrared thermal imaging detector is sensitive to high-temperature sources, infrared radiation generated by other high-temperature objects (such as sunlight, industrial equipment, etc.) in outdoor or industrial environments may be misjudged as a flame, resulting in a relatively high false alarm rate.

[0003] Most of the existing infrared thermal imaging detectors for flame recognition identify the flame target in the image by training a large number of labeled data. They cannot first combine the reflection data to exclude the temperature anomaly caused by reflection, and then analyze the fire risk through the ignition point data of combustibles at the temperature anomaly point and the flame possibility, resulting in a reduction in the accuracy of fire recognition.

[0004] To solve the above problems, the present invention provides a flame recognition method for an infrared thermal imaging detector. Summary of the Invention

[0005] The present invention provides a flame recognition method for an infrared thermal imaging detector, which is used to solve the technical problem that the prior art cannot first combine the reflection data to exclude the temperature anomaly caused by reflection, and then analyze the fire risk through the ignition point data of combustibles at the temperature anomaly point and the flame possibility, resulting in a reduction in the accuracy of fire recognition.

[0006] A flame recognition method for an infrared thermal imaging detector provided in the first aspect of the present invention includes: S1. Obtain the visualized thermal image generated by the infrared thermal imaging detection component, analyze the temperature anomaly according to the thermal image, and locate the temperature anomaly point; S2. Obtain the normal vector of the reflection surface according to the location and judgment time of the temperature anomaly point, obtain the incident angle and the reflection direction vector according to the position data of the sun, obtain the observation direction vector of the component according to the position data of the infrared thermal imaging detection component, and judge whether the temperature anomaly point is a reflection according to the comparison result between the included angle of the observation direction vector of the component and the reflection direction vector and the half field of view angle of the component, and mark the temperature anomaly point that does not conform to the reflection as a suspicious fire monitoring point; S3. Identify the combustibles at the suspicious fire monitoring point, and analyze the combustion risk of the combustibles at the suspicious fire monitoring point according to the ignition point data of the combustibles and the oxygen data; S4. Analyze the possibility that the suspicious fire monitoring point is a flame according to the image data of the suspicious fire monitoring point; S5. Analyze whether a fire has occurred at a suspicious fire monitoring point based on the combustion risk of combustibles at the suspicious fire monitoring point and the possibility that the suspicious fire monitoring point is a flame.

[0007] Specifically, the S1 includes the following specific steps: Obtain the visualized thermal image generated by the infrared thermal imaging detection component, perform grayscale processing on the thermal image, calculate the average gray level of the set area, compare the average gray level of the set area with the pixel threshold converted from the set temperature threshold through the mapping relationship. When the average gray level of the set area is less than the gray level threshold, it is determined that the temperature of the set area is normal. When the average gray level of the set area is greater than or equal to the gray level threshold, it is determined that the temperature of the set area is abnormal, and the positioning of the temperature abnormal point is obtained.

[0008] Specifically, the S2 includes the following specific steps: S21. Obtain the positioning and judgment time of the temperature abnormal point, identify the reflection surface corresponding to the temperature abnormal point, obtain the reflectivity, azimuth angle, and tilt angle of the reflection surface, and obtain the normal vector of the reflection surface according to the azimuth angle and tilt angle of the reflection surface; S22. Obtain the position data of the sun, where the position data of the sun includes the solar altitude angle and the solar azimuth angle, obtain the solar incident direction vector according to the solar altitude angle and the solar azimuth angle, and obtain the incident angle and the reflection direction vector according to the normal vector of the reflection surface and the solar incident direction vector; S23. Obtain the position data of the infrared thermal imaging detection component, where the position data of the infrared thermal imaging detection component includes the azimuth angle, pitch angle, and field of view angle of the component, and obtain the component observation direction vector according to the azimuth angle and pitch angle of the component; S24. Obtain the included angle between the component observation direction vector and the reflection direction vector, and judge whether the reflected light can enter the infrared thermal imaging detection component according to the comparison result between the included angle and the half field of view angle of the component. If the included angle is less than or equal to the half field of view angle of the component, it is determined that the reflected light can enter the infrared thermal imaging detection component, and perform the operation of step S25. If the included angle is greater than the half field of view angle of the component, it is determined that the reflected light cannot enter the infrared thermal imaging detection component, and perform the operation of step S3; S25. Obtain the reflection intensity according to the incident angle and the reflectivity of the reflection surface, and obtain the theoretical temperature rise according to the reflection intensity; S26. Judge whether the temperature abnormal point is a reflected light according to the theoretical temperature rise and the actual temperature rise of the temperature abnormal point. If the theoretical temperature rise is greater than or equal to the actual temperature rise, it is determined that the temperature abnormal point is a reflected light point. If the theoretical temperature rise is less than the actual temperature rise, it is determined that the temperature abnormal point does not conform to being a reflected light, and mark the temperature abnormal point that does not conform to being a reflected light as a suspicious fire monitoring point.

[0009] Specifically, the S3 includes the following specific steps: Identify the combustibles at the suspicious fire monitoring points, obtain the ignition points of the combustibles, the minimum oxygen concentration threshold for combustion, the temperature of the current suspicious fire monitoring point, and the oxygen concentration of the current suspicious fire monitoring point, and analyze the combustion risk of the combustibles at the suspicious fire monitoring points.

[0010] Specifically, step S4 includes the following specific steps: Obtain the image after grayscale processing of the suspicious fire monitoring point, extract the characteristic data of the suspicious flame area, where the characteristic data of the suspicious flame area includes the flame area growth rate, circularity, and rectangularity, and analyze the possibility that the suspicious fire monitoring point is a flame based on the flame area growth rate, circularity, and rectangularity.

[0011] Specifically, step S5 includes the following specific steps: Obtain the fire occurrence risk based on the combustion risk of the combustibles at the suspicious fire monitoring point and the possibility that the suspicious fire monitoring point is a flame. Analyze whether a fire has occurred at the suspicious fire monitoring point based on the comparison result between the fire occurrence risk and the preset fire occurrence risk threshold. If the fire occurrence risk is less than the preset fire occurrence risk threshold, it is determined that no fire has occurred, and the indicator light is constantly green. If the fire occurrence risk is greater than or equal to the preset fire occurrence risk threshold, it is determined that a fire has occurred, and the indicator light is constantly red.

[0012] A flame recognition system for an infrared thermal imaging detector provided in the second aspect of the present invention is used to implement a flame recognition method for an infrared thermal imaging detector, and includes: a temperature anomaly positioning module, configured to obtain a visualized thermal image generated by the infrared thermal imaging detection component, analyze the temperature anomaly according to the thermal image, and locate the temperature anomaly point; A specular reflection analysis module, configured to obtain the normal vector of the reflection surface according to the positioning and judgment time of the temperature anomaly point, obtain the incident angle and the reflection direction vector according to the position data of the sun, obtain the component observation direction vector according to the position data of the infrared thermal imaging detection component, and obtain the included angle between the component observation direction vector and the reflection direction vector; A suspicious fire monitoring point analysis module, configured to determine whether the temperature anomaly point is a specular reflection according to the comparison result between the included angle between the component observation direction vector and the reflection direction vector and the half field of view angle of the component, and mark the temperature anomaly point that does not conform to the specular reflection as a suspicious fire monitoring point; A combustion risk analysis module, configured to identify the combustibles at the suspicious fire monitoring point, and analyze the combustion risk of the combustibles at the suspicious fire monitoring point according to the combustible ignition point data and oxygen data; A flame possibility analysis module, configured to analyze the possibility that the suspicious fire monitoring point is a flame according to the image data of the suspicious fire monitoring point; A fire recognition module, configured to analyze whether a fire has occurred at the suspicious fire monitoring point according to the combustion risk of the combustibles at the suspicious fire monitoring point and the possibility that the suspicious fire monitoring point is a flame.

[0013] A computer device provided in the third aspect of the present invention includes a memory and a processor. A computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of a flame recognition method for an infrared thermal imaging detector as described in any one of the above.

[0014] A computer-readable storage medium provided in the fourth aspect of the present invention has a computer program stored thereon. When the computer program is executed, it implements the steps of a flame recognition method for an infrared thermal imaging detector as described in any one of the above.

[0015] A computer program product provided in the fifth aspect of the present invention. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the steps of a flame recognition method for an infrared thermal imaging detector as described in any one of the above.

[0016] As can be seen from the above technical solutions, the present invention has the following advantages: The present invention analyzes temperature anomalies based on the thermal image generated by the infrared thermal imaging detection component, locates the temperature anomaly points, obtains the included angle between the component observation direction vector and the reflection direction vector to determine whether the temperature anomaly points are specular reflections, marks the temperature anomaly points that do not conform to specular reflections as suspicious fire monitoring points, identifies the combustibles at the suspicious fire monitoring points, analyzes the combustion risk of the combustibles at the suspicious fire monitoring points based on the ignition point data and oxygen data of the combustibles, analyzes the possibility that the suspicious fire monitoring points are flames based on the image data of the suspicious fire monitoring points, and analyzes whether a fire has occurred at the suspicious fire monitoring points based on the combustion risk of the combustibles at the suspicious fire monitoring points and the possibility that the suspicious fire monitoring points are flames, improving the accuracy of fire recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 It is a schematic flow chart of the steps of a flame recognition method for an infrared thermal imaging detector provided by the present invention; Figure 2 It is a schematic flow chart of step S2 of a flame recognition method for an infrared thermal imaging detector provided by the present invention; Figure 3Schematic structural framework diagram of a flame recognition system for an infrared thermal imaging detector provided by the present invention; Figure 4 Schematic structural framework diagram of a computer device provided by the present invention. Detailed implementation manners

[0019] An embodiment of the present invention provides a flame recognition method for an infrared thermal imaging detector, which is used to solve the technical problem that the prior art cannot first combine reflection data to exclude temperature anomalies caused by light reflection, and then analyze the fire risk through the ignition point data of combustibles at the temperature anomaly points and the flame possibility, resulting in a decrease in the accuracy of fire recognition.

[0020] In order to make the invention purpose, features, and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the embodiments described below are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0021] Please refer to Figure 1 , Figure 1 Schematic flow chart of the steps of a flame recognition method for an infrared thermal imaging detector provided by the present invention.

[0022] A flame recognition method for an infrared thermal imaging detector provided by the present invention includes: S1. Obtain the visual thermal image generated by the infrared thermal imaging detection component, analyze the temperature anomaly according to the thermal image, and locate the temperature anomaly point; In this embodiment, S1 includes the following specific steps: Obtain the visual thermal image generated by the infrared thermal imaging detection component. Infrared thermal imaging technology is a technology that detects the infrared signal of the thermal radiation of an object and converts it into an image or graph that can be distinguished by the human eye. The surface of the object emits infrared radiation according to its temperature. The infrared thermal imaging fire detector captures the radiation signal through a vanadium oxide uncooled infrared focal plane imaging detection component, and then converts the received infrared light signal into an electrical signal. After the electrical signal is processed, a thermal image that can be recognized by the human eye is generated, showing the temperature distribution of the object. The vanadium oxide uncooled infrared focal plane imaging detection component images through infrared rays with a response band of 8-14 μm, which can reduce the interference factors of non-contact temperature measurement; Perform grayscale processing on the thermal image, and calculate the average grayscale of the set area. In specific implementation, the calculation of the average grayscale of the set area can select the following formula: , where is the average gray value of the set area, is the length of the set area, is the width of the set area, is the pixel value of the coordinate point (i, j), is the total pixel value of the set area; Compare the average gray value of the set area with the pixel threshold converted from the set temperature threshold through the mapping relationship. In specific implementation, the calculation of converting the set temperature threshold into the pixel threshold through the mapping relationship can select the following formula: , where is the pixel threshold converted from the set temperature threshold through the mapping relationship, is the set temperature threshold, is the total temperature measurement span of the infrared thermal imaging fire detector. In this embodiment, the temperature measurement range of the infrared thermal imaging fire detector is -20°C to 550°C. Therefore, the total temperature measurement span is 570°C. The pixel range of the 8-bit gray image is (0, 255). Multiplying the above formula by 256 is used to uniformly map the set temperature threshold to the complete 256-pixel value interval; When the average gray value of the set area is less than the gray threshold, it is determined that the temperature of the set area is normal. When the average gray value of the set area is greater than or equal to the gray threshold, it is determined that the temperature of the set area is abnormal, and the positioning of the temperature abnormal point is obtained. In specific implementation, obtaining the positioning of the temperature abnormal point includes the distance and angle between the temperature abnormal point and the center point of the set area. The calculation of obtaining the distance between the temperature abnormal point and the center point of the set area can select the following formula: , where is the distance between the temperature abnormal point and the center point of the set area, is the abscissa of the coordinate point (i, j), is the abscissa of the center point of the set area, is the abscissa of the image moment of the temperature abnormal area, is the ordinate of the coordinate point (i, j), is the ordinate of the center point of the set area, is the ordinate of the image moment of the temperature abnormal area. The calculation of obtaining the angle can select the following formula: , where is the angle between the temperature abnormal point and the center point of the set area. The above formula calculates the distance and angle between the temperature abnormal point and the center point of the area through the image moment, improving the accuracy of the positioning of the temperature abnormal point. In this embodiment, the average gray value of the set area is calculated and compared with the pixel threshold converted from the set temperature threshold through the mapping relationship, subtracting the calculation amount of the non-key area while ensuring the coverage of the key monitoring range, and improving the efficiency of the temperature abnormal judgment.

[0023] Exemplarily, in order to prevent coal spontaneous combustion and monitor equipment anomalies, a certain coal loading and unloading terminal installed ten infrared thermal imaging fire detectors with a field of view of 90.0° * 62.5° to comprehensively and continuously monitor the terminal conveyor belt, obtain the visualized thermal image generated by the infrared thermal imaging fire detector, perform grayscale processing on the thermal image, and obtain the average grayscale of the temperature fluctuation area. Since the conveyor belt conveys coal, combined with the characteristics of coal spontaneous combustion and safety standards, the set temperature threshold can be set to 70 - 80 °C, and it can also be adjusted up and down by 5 °C in combination with the high-temperature and high-humidity environment. For example, when the set temperature threshold is set to 80 °C, the corresponding pixel threshold is 80 °C / 570 °C × 256 ≈ 36. Obtain the distance and angle between the temperature anomaly point and the center point of the area where the average grayscale is greater than or equal to 36, and locate the temperature anomaly point.

[0024] S2. Obtain the normal vector of the reflecting surface based on the positioning and judgment time of the temperature anomaly point, obtain the incident angle and the reflected direction vector based on the position data of the sun, obtain the observation direction vector of the component based on the position data of the infrared thermal imaging detection component, and judge whether the temperature anomaly point is a reflection based on the comparison result between the included angle between the observation direction vector of the component and the reflected direction vector and the half field of view angle of the component. Mark the temperature anomaly points that do not conform to reflection as suspicious fire monitoring points; Please refer to Figure 2 , Figure 2 which is a schematic flow chart of step S2 of a flame recognition method for an infrared thermal imaging detector provided by the present invention.

[0025] In this embodiment, S2 includes the following specific steps: S21. Obtain the positioning and judgment time of the temperature anomaly point, identify the reflecting surface corresponding to the temperature anomaly point, obtain the reflectivity, azimuth angle, and tilt angle of the reflecting surface. In specific implementation, the reflectivity of the reflecting surface is directly measured using an infrared reflectivity measuring instrument. The azimuth angle can be obtained by measuring the projection direction of the normal line of the reflecting surface on the horizontal plane with a compass (north is 0°, increasing clockwise), and the tilt angle can be obtained by measuring the angle between the reflecting surface and the horizontal plane with an inclinometer (horizontal is 0°, vertical is 90°); obtain the normal vector of the reflecting surface based on the azimuth angle and tilt angle of the reflecting surface. In specific implementation, the normal vector of the reflecting surface can be expressed as: , is the tilt angle of the reflecting surface, is the azimuth angle of the reflecting surface; S22. Obtain the position data of the sun. The position data of the sun includes the solar altitude angle and the solar azimuth angle. In specific implementation, the calculation of the solar altitude angle can select the following formula: , where is the solar altitude angle, is the local latitude, is the solar declination, is the hour angle, and the solar declination and hour angle can be obtained in real time through astronomical software or through existing calculation formulas. For example, the solar declination can be obtained through calculation, is the day of the year. For example, January 1st is 1, and the hour angle can be obtained through calculation, is the true solar time, expressed in 24-hour format. In actual calculation, it is necessary to correct according to the equation of time difference between local time and true solar time; The calculation of the solar azimuth angle can select the following formula: , where is the solar azimuth angle; Obtain the solar incident direction vector according to the solar altitude angle and solar azimuth angle. In specific implementation, the solar incident direction vector can be expressed as: ; Obtain the incident angle and reflected direction vector according to the normal vector of the reflecting surface and the solar incident direction vector; In specific implementation, the calculation of the incident angle can select the following formula: , where is the dot product between vectors; The reflected direction vector can be obtained according to the law of reflection, specifically: ; S23. Obtain the position data of the infrared thermal imaging detection component. The position data of the infrared thermal imaging detection component includes the azimuth angle, pitch angle and field of view angle of the component. In specific implementation, the azimuth angle can be obtained by measuring the horizontal direction pointed by the thermal imager lens with a compass, and the pitch angle can be obtained by measuring the angle between the lens and the horizontal plane with an inclinometer; Obtain the component observation direction vector according to the azimuth angle and pitch angle of the component; In specific implementation, the component observation direction vector can be expressed as: , is the pitch angle of the component, is the azimuth angle of the component; S24. Obtain the included angle between the component observation direction vector and the reflected direction vector. In specific implementation, the comparison between the included angle and the field of view angle of the component can select the following formula: , where is the modulus of the vector. Judge whether the reflected light can enter the infrared thermal imaging detection component according to the comparison result between the included angle and the half field of view angle of the component. The half field of view angle is the maximum allowable deviation angle of the infrared thermal imaging detection component relative to the center line. If the included angle is less than or equal to the half field of view angle of the component, it is judged that the reflected light can enter the infrared thermal imaging detection component, and the operation of step S25 is performed. If the included angle is greater than the half field of view angle of the component, it is judged that the reflected light cannot enter the infrared thermal imaging detection component, and the operation of step S3 is performed; S25. Obtain the reflection intensity based on the incident angle and the reflectivity of the reflecting surface, and obtain the theoretical temperature rise based on the reflection intensity; in specific implementation, the calculation of the reflection intensity can select the following formula: , where is the reflection intensity, is the reflectivity of the reflecting surface, is the solar irradiance, which can be measured by a solar irradiance meter or monitored by converting solar radiation into an electrical signal through the photovoltaic effect, is the area of the reflecting surface actually irradiated by the sun. The calculation of the area of the reflecting surface actually irradiated by the sun can select the following formula: , where is the area of the reflecting surface actually irradiated by the sun, is the total area of the reflecting surface, which can be measured by a laser rangefinder; The calculation of the theoretical temperature rise can select the following formula: , where is the theoretical temperature rise, is a constant, approximately 5.67×10 -8 W / (m²·K 4 ); S26. Judge whether the temperature anomaly point is caused by reflection according to the theoretical temperature rise and the actual temperature rise of the temperature anomaly point. If the theoretical temperature rise is greater than or equal to the actual temperature rise, judge that the temperature anomaly point is a reflection point. If the theoretical temperature rise is less than the actual temperature rise, judge that the temperature anomaly point does not conform to reflection, and mark the temperature anomaly point that does not conform to reflection as a suspicious fire monitoring point.

[0026] Exemplarily, a certain coal loading and unloading terminal locates a temperature anomaly point at 10 am. The azimuth angle of the reflecting surface is 150°, the tilt angle is 30°, the azimuth angle of the infrared thermal imaging fire detector is 90°, the tilt angle is 0°, the solar altitude angle is 45°, and the solar azimuth angle is 120°. Then the normal vector of the reflecting surface , the solar incident direction vector , the reflection direction vector , the component observation direction vector , the included angle between the component observation direction vector and the reflection direction vector is about 81.2°, which is greater than the half field of view angle. Therefore, the reflected light cannot enter the infrared thermal imaging detection component, and this temperature anomaly point is not caused by reflection.

[0027] S3. Identify the combustibles at the suspicious fire monitoring point, and analyze the combustion risk of the combustibles at the suspicious fire monitoring point according to the ignition point data and oxygen data of the combustibles; In this embodiment, S3 includes the following specific steps: Identify the combustibles at the suspicious fire monitoring point, obtain the ignition point of the combustibles, the threshold of the lowest oxygen concentration for combustion, the temperature of the current suspicious fire monitoring point, and the oxygen concentration of the current suspicious fire monitoring point, and analyze the combustion risk of the combustibles at the suspicious fire monitoring point. In specific implementation, the calculation of the combustion risk of the combustibles can select the following formula: , where is the combustion risk of the combustibles, is the oxygen concentration of the current suspicious fire monitoring point, is the threshold of the lowest oxygen concentration for combustion. When , the lowest oxygen concentration threshold for combustible combustion is not reached, the value is taken as 0, is the temperature of the current suspicious fire monitoring point, is the ignition point of the combustibles, and the exponents and are used to adjust the non-linear effects of temperature and oxygen concentration. In this embodiment , the above formula improves the efficiency of evaluating the risk level by analyzing the contribution degree of oxygen concentration and the proximity of the temperature of the current suspicious fire monitoring point to the ignition point; Exemplarily, the ignition point of the coal at a certain coal loading and unloading terminal is 300°, the threshold of the lowest oxygen concentration for combustion is 12%, the oxygen concentration of the current suspicious fire monitoring point detected is 16%, and the temperature of the current suspicious fire monitoring point is 84°. Then the combustion risk of the combustibles at this suspicious fire monitoring point is ×0.28≈0.093.

[0028] S4. Analyze the possibility that the suspicious fire monitoring point is a flame based on the image data of the suspicious fire monitoring point; In this embodiment, S4 includes the following specific steps: Obtain the image of the suspicious fire monitoring point after grayscale processing, and extract the characteristic data of the suspicious flame area. The characteristic data of the suspicious flame area includes the flame area growth rate, circularity, and rectangularity; In specific implementation, the calculation of the flame area growth rate can select the following formula: , where is the flame area growth rate at time t1, is the flame area growth rate at time t0, is the flame area at time t1. After binarizing the image, the pixel points with pixel value 255 are screened out, and the flame area is the sum of the pixel points, is the flame area at time t0. The above formula reflects the trend of the flame spreading rapidly to the surrounding according to the flame area growth rate; The calculation of circularity can select the following formula: , where is the circularity, is the area of the flame region, is the perimeter of the flame region. The above formula calculates the degree of closeness between the shape of the flame region and a circle. Since the shape of the flame is not fixed, the closer it is to a circle, the lower the probability that it is a flame; The calculation of the rectangularity can select the following formula: , where in the formula, is the rectangularity, is the area of the minimum circumscribed rectangle of the flame region. The above formula calculates the degree of closeness between the shape of the flame region and the circumscribed rectangle. Since the flame contour is rough, the closer it is to the circumscribed rectangle, the lower the probability that it is a flame; Analyze the probability that a suspicious fire monitoring point is a flame based on the combustion risk of combustibles at the suspicious fire monitoring point and the circularity and rectangularity. In specific implementation, the calculation of the probability that a suspicious fire monitoring point is a flame can select the following formula: , where in the formula, is the probability that a suspicious fire monitoring point is a flame.

[0029] S5. Analyze whether a fire has occurred at the suspicious fire monitoring point based on the combustion risk of combustibles at the suspicious fire monitoring point and the probability that the suspicious fire monitoring point is a flame.

[0030] In this embodiment, S5 includes the following specific steps: Obtain the fire occurrence risk based on the combustion risk of combustibles at the suspicious fire monitoring point and the probability that the suspicious fire monitoring point is a flame. In specific implementation, the fire occurrence risk can select the following formula: , where in the formula, is the fire occurrence risk, and the exponents and are used to adjust the non-linear influence of the combustion risk of combustibles and the probability that the suspicious fire monitoring point is a flame. In this embodiment ; Analyze whether a fire has occurred at the suspicious fire monitoring point based on the comparison result between the fire occurrence risk and the preset fire occurrence risk threshold. In specific implementation, the fire occurrence risk threshold is obtained by calculating the average fire occurrence risk through the combustion risk of combustibles and the probability that the suspicious fire monitoring point is a flame after identifying temperature anomalies from the thermal images collected from historical fires in this area. If the fire occurrence risk is less than the preset fire occurrence risk threshold, it is judged that no fire has occurred, and the indicator light is constantly green. If the fire occurrence risk is greater than or equal to the preset fire occurrence risk threshold, it is judged that a fire has occurred, and the indicator light is constantly red.

[0031] In summary, the infrared thermal imaging fire detector used in this embodiment detects fires by analyzing the flames generated during the combustion process through video images. It adopts a vanadium oxide uncooled infrared focal plane imaging detection component and, based on video image analysis technology and artificial intelligence deep learning technology, conducts early temperature and flame detection on the protected area. It has functions such as temperature monitoring, fire warning, fire detection, video monitoring, and event detection, and can realize video display, control, storage, playback, automatic processing of alarm information, alarm recording, automatic calculation and calibration of the fire point position, and false alarm area management. It is suitable for automatic remote monitoring and early warning of fire prevention and is applicable to key areas such as forests, converter transformers, dock conveyors, energy storage power stations, and dry coal sheds.

[0032] Please refer to Figure 3 , Figure 3 which is a schematic structural framework diagram of a flame recognition system for an infrared thermal imaging detector provided by the present invention.

[0033] A flame recognition system for an infrared thermal imaging detector provided by the present invention includes: a temperature anomaly positioning module, which is used to obtain the visual thermal image generated by the infrared thermal imaging detection component, analyze the temperature anomaly according to the thermal image, and locate the temperature anomaly point; a specular reflection analysis module, which is used to obtain the normal vector of the reflection surface according to the positioning and judgment time of the temperature anomaly point, obtain the incident angle and the reflection direction vector according to the position data of the sun, obtain the observation direction vector of the component according to the position data of the infrared thermal imaging detection component, and obtain the included angle between the observation direction vector of the component and the reflection direction vector; a suspicious fire monitoring point analysis module, which is used to judge whether the temperature anomaly point is a specular reflection according to the comparison result between the included angle between the observation direction vector of the component and the reflection direction vector and the half field of view angle of the component, and mark the temperature anomaly point that does not conform to the specular reflection as a suspicious fire monitoring point; a combustion risk analysis module, which is used to identify the combustibles at the suspicious fire monitoring point and analyze the combustion risk of the combustibles at the suspicious fire monitoring point according to the ignition point data and oxygen data of the combustibles; a flame possibility analysis module, which is used to analyze the possibility that the suspicious fire monitoring point is a flame according to the image data of the suspicious fire monitoring point; a fire recognition module, which is used to analyze whether a fire has occurred at the suspicious fire monitoring point according to the combustion risk of the combustibles at the suspicious fire monitoring point and the possibility that the suspicious fire monitoring point is a flame.

[0034] Those skilled in the art can clearly understand that for the sake of convenience and brevity of description, the specific working processes of the above-described system, module, and sub-module can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0035] Please refer to Figure 4 , Figure 4Schematic diagram of the structural framework of a computer device provided by the present invention.

[0036] An embodiment of the present invention further provides a computer device, including a memory and a processor. A computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of the above-mentioned method for flame recognition using an infrared thermal imaging detector.

[0037] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program / instructions are stored. When the computer program / instructions are executed by the processor, the steps of the above-mentioned method for flame recognition using an infrared thermal imaging detector are implemented.

[0038] An embodiment of the present invention further provides a computer program product, including a computer program / instructions. When the computer program / instructions are executed by the processor, the steps of the above-mentioned method for flame recognition using an infrared thermal imaging detector are implemented.

[0039] In several embodiments provided by the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections between each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0040] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example, and moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0041] In addition, in each embodiment of the present invention, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0042] The unit described as the separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0043] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A flame recognition method for an infrared thermal imaging detector, characterized in that: include: S1. Obtain a visualized thermal image generated by an infrared thermal imaging detection component, analyze temperature anomalies based on the thermal image, and locate temperature anomaly points; S2. Obtain the normal vector of the reflecting surface according to the location and judgment time of the temperature anomaly point, obtain the incident angle and the reflection direction vector according to the position data of the sun, obtain the component observation direction vector according to the position data of the infrared thermal imaging detection component, and determine whether the temperature anomaly point is a reflection according to the comparison result of the angle between the component observation direction vector and the reflection direction vector and the half field of view angle of the component, and mark the temperature anomaly point that does not meet the reflection as a suspicious fire monitoring point; S3. Identify the combustibles at the suspicious fire monitoring point and analyze the combustion risk of the combustibles at the suspicious fire monitoring point based on the combustible ignition point data and oxygen data; S4, analyzing the possibility that the suspicious fire monitoring point is a flame based on the image data of the suspicious fire monitoring point; S5. Analyze whether a fire has occurred at the suspicious fire monitoring point based on the combustion risk of combustibles at the suspicious fire monitoring point and the possibility that the suspicious fire monitoring point is a flame.

2. A flame recognition method for infrared thermal imaging detector according to claim 1, characterized in that: The S1 comprises the following specific steps: Obtain a visualized thermal image generated by the infrared thermal imaging detection component, perform grayscale processing on the thermal image, calculate the average grayscale of the set area, compare the average grayscale of the set area with the pixel threshold converted by the set temperature threshold through a mapping relationship, and when the average grayscale of the set area is less than the grayscale threshold, judge that the temperature of the set area is normal; when the average grayscale of the set area is greater than or equal to the grayscale threshold, judge that the temperature of the set area is abnormal, and obtain the location of the temperature anomaly point.

3. A flame recognition method for infrared thermal imaging detector according to claim 2, characterized in that: The S2 comprises the following specific steps: S21, obtaining the location and judgment time of the temperature anomaly point, identifying the reflecting surface corresponding to the temperature anomaly point, obtaining the reflectivity, azimuth and tilt angle of the reflecting surface, and obtaining the normal vector of the reflecting surface according to the azimuth and tilt angle of the reflecting surface; S22, obtaining the position data of the sun, wherein the position data of the sun includes the sun altitude angle and the sun azimuth angle, obtaining the sun incident direction vector according to the sun altitude angle and the sun azimuth angle, and obtaining the incident angle and the reflection direction vector according to the normal vector of the reflecting surface and the sun incident direction vector; S23, obtaining position data of the infrared thermal imaging detection component, wherein the position data of the infrared thermal imaging detection component includes the azimuth angle, pitch angle and field angle of the component, and obtaining the component observation direction vector according to the azimuth angle and pitch angle of the component; S24, obtaining the angle between the component observation direction vector and the reflection direction vector, and judging whether the reflected light can enter the infrared thermal imaging detection component according to the comparison result between the angle and the half field angle of the component; if the angle is less than or equal to the half field angle of the component, judging that the reflected light can enter the infrared thermal imaging detection component, and performing step S25; if the angle is greater than the half field angle of the component, judging that the reflected light cannot enter the infrared thermal imaging detection component, and performing step S3; S25, obtaining a reflection intensity according to the incident angle and the reflectivity of the reflection surface, and obtaining a theoretical temperature rise according to the reflection intensity; S26. Determine whether the temperature anomaly point is reflective based on the theoretical temperature rise and the actual temperature rise of the temperature anomaly point. If the theoretical temperature rise is greater than or equal to the actual temperature rise, the temperature anomaly point is determined to be a reflective point. If the theoretical temperature rise is less than the actual temperature rise, the temperature anomaly point is determined to be not reflective, and the temperature anomaly point that does not meet the reflection requirement is marked as a suspicious fire monitoring point.

4. A flame recognition method for infrared thermal imaging detector according to claim 3, characterized in that: The S3 includes the following specific steps: Identify the combustibles at the suspicious fire monitoring point, obtain the ignition point of the combustibles, the minimum oxygen concentration threshold for combustion, the current temperature of the suspicious fire monitoring point and the current oxygen concentration of the suspicious fire monitoring point to analyze the combustion risk of the combustibles at the suspicious fire monitoring point.

5. A flame recognition method for infrared thermal imaging detector according to claim 4, characterized in that: The S4 comprises the following specific steps: Obtain a grayscale image of a suspicious fire monitoring point, extract characteristic data of the suspicious flame area, wherein the characteristic data of the suspicious flame area includes flame area growth rate, circularity and rectangularity, and analyze the possibility that the suspicious fire monitoring point is a flame based on the flame area growth rate, circularity and rectangularity.

6. A flame recognition method for infrared thermal imaging detector according to claim 5, characterized in that: The S5 comprises the following specific steps: The fire risk is obtained based on the combustion risk of combustibles at the suspicious fire monitoring point and the possibility that the suspicious fire monitoring point is a flame. Whether a fire has occurred at the suspicious fire monitoring point is analyzed based on the comparison result of the fire risk and the preset fire risk threshold. If the fire risk is less than the preset fire risk threshold, it is judged that no fire has occurred. If the fire risk is greater than or equal to the preset fire risk threshold, it is judged that a fire has occurred.

7. A flame recognition system for an infrared thermal imaging detector, used to implement the flame recognition method for an infrared thermal imaging detector as claimed in any one of claims 1 to 6, characterized in that: include: The temperature anomaly positioning module is used to obtain the visualized thermal image generated by the infrared thermal imaging detection component, analyze the temperature anomaly based on the thermal image, and locate the temperature anomaly point; The reflection analysis module is used to obtain the normal vector of the reflection surface according to the location and judgment time of the temperature anomaly point, obtain the incident angle and the reflection direction vector according to the position data of the sun, obtain the component observation direction vector according to the position data of the infrared thermal imaging detection component, and obtain the angle between the component observation direction vector and the reflection direction vector; The suspicious fire monitoring point analysis module is used to determine whether the temperature abnormal point is reflective based on the comparison result of the angle between the component observation direction vector and the reflection direction vector and the component half field of view angle, and mark the temperature abnormal point that does not meet the reflection as a suspicious fire monitoring point; The combustion risk analysis module is used to identify the combustibles at the suspicious fire monitoring points and analyze the combustion risk of the combustibles at the suspicious fire monitoring points based on the combustible ignition point data and oxygen data; The flame possibility analysis module is used to analyze the possibility that the suspicious fire monitoring point is a flame based on the image data of the suspicious fire monitoring point; The fire identification module is used to analyze whether a fire occurs at a suspicious fire monitoring point based on the combustion risk of combustibles at the suspicious fire monitoring point and the possibility that the suspicious fire monitoring point is a flame.

8. A computer device, characterized in that: It comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of a flame recognition method for an infrared thermal imaging detector as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the flame recognition method for an infrared thermal imaging detector according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer is caused to execute a flame identification method for an infrared thermal imaging detector as described in any one of claims 1 to 6.

Images