A satellite remote sensing fire point identification method and device, electronic equipment and storage medium

Abstract

The application relates to the technical field of natural disaster monitoring, and discloses a satellite remote sensing fire point identification method and device, an electronic device and a storage medium, the method comprising the following steps: determining optical comprehensive reflectivity; determining a brightness temperature difference; constructing a light-heat conflict index based on the optical comprehensive reflectivity and the brightness temperature difference, the light-heat conflict index being used for quantitatively representing a physical matching relationship between optical reflection enhancement and thermal radiation mutation; removing false fire points based on the light-heat conflict index; and after the false fire points are removed, combining a dynamic environment background threshold value to complete satellite remote sensing fire point identification. The device, the electronic device and the storage medium all correspond to the method. The application solves the technical problem that it is difficult to scientifically distinguish high-reflection false fire points from high-diffuse-reflection real fire points in the prior art.

Description

Technical Field

[0001] This application relates to the field of natural disaster monitoring technology, specifically a satellite remote sensing fire point identification method, device, electronic equipment, and storage medium. Background Technology

[0002] Utilizing satellites carrying multispectral payloads such as the VIIRS sensor, which provides visible and infrared imaging radiometers, for large-scale monitoring of forest fires and wildfires around power transmission lines is a crucial technology for disaster early warning. Traditional satellite remote sensing-based fire point identification algorithms primarily rely on abnormally high thermal radiation of target pixels in the mid-infrared band and the brightness-temperature difference between the mid- and long-wave infrared bands. Its characteristics.

[0003] However, in real-world applications, complex surface environments often lead to false alarms and missed detections in algorithms. Specifically, large-area photovoltaic power stations, corrugated steel roofs, and greenhouses—materials that are not blackbody—can produce strong specular reflections under specific solar observation geometry, exhibiting obvious false thermal anomalies in the mid-infrared band. These anomalies caused by "high reflectivity" are easily misidentified as fire points by traditional algorithms. To suppress such false fire points, existing improved techniques often use static visible light or near-infrared reflectivity thresholds for filtering; that is, when the reflectivity exceeds a certain fixed threshold, the pixel is directly excluded. However, real, severe fires are often accompanied by thick smoke plumes, and dense smoke also has extremely high diffuse reflectivity. Static single-threshold filtering strategies, while eliminating photovoltaic interference, often also exclude high-threat smoky fire points, increasing the risk of missed detections.

[0004] Therefore, there is an urgent need for a technical solution that can scientifically distinguish between highly reflective false fire points and highly diffuse reflective real fire points. Summary of the Invention

[0005] The purpose of this application is to provide a satellite remote sensing fire point identification method, device, electronic device and storage medium to solve the technical problem in the prior art that it is difficult to scientifically distinguish between highly reflective false fire points and highly diffuse reflective real fire points.

[0006] To achieve the above objectives, this application provides a satellite remote sensing fire point identification method, comprising: The overall optical reflectivity is determined based on the reflectivity in the visible light band and the near-infrared band; the brightness temperature difference is determined based on the brightness temperature in the mid-infrared and long-infrared bands. A photothermal conflict index is constructed based on optical comprehensive reflectivity and brightness temperature difference. This photothermal conflict index is used to quantitatively characterize the physical matching relationship between enhanced optical reflection and abrupt changes in thermal radiation. Based on the light-heat conflict index and combined with the preset judgment rules, false fire points are eliminated. These false fire points include at least those caused by strong light reflection from a fireless surface. After eliminating false fire points, satellite remote sensing fire point identification is completed by combining preset dynamic environmental background thresholds for mid-wave infrared temperature.

[0007] To achieve the above objectives, this application also provides a satellite remote sensing fire point identification device, which applies the satellite remote sensing fire point identification method described above, including: The reflectivity and brightness temperature difference processing module is configured to: determine the overall optical reflectivity based on the reflectivity of the visible light band and the reflectivity of the near-infrared band; and determine the brightness temperature difference based on the mid-wave infrared brightness temperature and the long-wave infrared brightness temperature. The optical-thermal conflict index construction module is configured to: construct an optical-thermal conflict index based on the comprehensive optical reflectivity and brightness temperature difference. This optical-thermal conflict index is used to quantitatively characterize the physical matching relationship between optical reflection enhancement and thermal radiation abrupt change. The false fire point elimination module is configured to: eliminate false fire points based on the photothermal conflict index and in combination with preset judgment rules. The false fire points include at least those caused by strong light reflection from a fireless surface. The satellite remote sensing fire detection module is configured to: after eliminating false fire points, combine a preset dynamic environmental background threshold for mid-wave infrared temperature to complete the satellite remote sensing fire detection.

[0008] To achieve the above objectives, this application also provides an electronic device, including at least one processor, at least one memory, and a data bus; The processor and the memory communicate with each other via the data bus; The memory stores program instructions that can be executed by the processor, which calls the program instructions to execute the satellite remote sensing fire detection method as described above.

[0009] To achieve the above objectives, this application also provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the satellite remote sensing fire point identification method described above.

[0010] The satellite remote sensing fire point identification method, device, electronic equipment, and storage medium of this application have the following advantages: First, they acquire visible light and near-infrared reflectance data and mid-to-long-wave infrared emissivity data from satellites and perform brightness-temperature inversion. Second, they calculate the comprehensive reflectance and mid-to-long-wave infrared temperature difference of target pixels and construct a photothermal conflict index to quantitatively characterize the physical matching relationship between enhanced optical reflection and abrupt thermal radiation changes in pixels. Finally, based on the photothermal conflict index, brightness temperature, and reflectance, they achieve multi-dimensional thermal anomaly interference removal, effectively filtering out false fire point pixels caused by highly reflective non-blackbody elements such as photovoltaic panels, metal roofs, and bare ground, while retaining real fire points accompanied by dense smoke with high diffuse reflection. This overcomes the shortcomings of traditional static single-threshold filtering that leads to missed detection of real fire points and significantly improves the reliability and environmental adaptability of wide-area remote sensing fire point monitoring. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A flowchart illustrating the satellite remote sensing fire detection method provided in this application embodiment; Figure 2 The structural block diagram of the satellite remote sensing fire point identification device provided in the embodiments of this application; in the figure: 10, reflectivity and brightness temperature difference processing module; 20, photothermal conflict index construction module; 30, false fire point elimination module; 40, satellite remote sensing fire point identification module; Figure 3 Comparison images of the same high-temperature long-wave brightness temperature difference scenario provided for the embodiments of this application; in the figures: (a) false color slice of JPSS1 satellite for false hotspots; (b) false hotspots caused by high-altitude reflection; (c) false color slice of JPSS1 satellite for real fire; (d) real fire; Figure 4 Comparison images of scenes with equivalent high reflectivity provided for embodiments of this application; in the images: (a) a false color slice of JPSS1 satellite with false hotspots; (b) a false hotspot caused by high reflectivity; (c) a false color slice of JPSS1 satellite with real fire; (d) real fire; Figure 5 Comparison of the same low medium-long wavelength brightness temperature difference scenario provided in the embodiments of this application; in the figure: (a) false color slice of JPSS1 satellite with false hotspot; (b) false hotspot caused by high reflection; (c) false color slice of JPSS1 satellite with real fire; (d) real fire.

[0013] The implementation, functional features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0014] The technical solutions in the embodiments of this application will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0015] In this document, the term "comprising" is intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0016] This embodiment addresses the challenges of remote sensing image processing and natural disaster monitoring technologies. In this field, existing technologies suffer from false alarms caused by highly reflective ground features such as photovoltaic panels and corrugated steel sheets, and the tendency of traditional static high-reflectivity threshold filtering to mistakenly delete or miss reports of real forest fires obscured by dense smoke. This embodiment provides a satellite remote sensing fire point identification method, device, electronic equipment, and storage medium. Specifically, it offers a high-confidence satellite remote sensing fire point identification solution based on the photothermal conflict index.

[0017] The technical principle behind the problem solved in this embodiment will now be explained. In satellite remote sensing fire detection, high reflectivity in the visible and near-infrared bands is often used as a feature to eliminate interference from clouds and bright ground surfaces. However, in actual operations, there are extremely contradictory physical scenarios: on the one hand, large-area photovoltaic power stations, metal roofs of factories, and other non-blackbody ground features have extremely high comprehensive reflectivity under strong solar radiation and will produce radiation distortion in the mid-infrared band, masquerading as thermal anomalies; on the other hand, real forest fires that burn fiercely are often accompanied by thick smoke plumes, and strong aerosol scattering also exhibits extremely high reflectivity characteristics. If a static high reflectivity rejection rule is used, it will inevitably lead to the incorrect filtering out of real fire points accompanied by thick smoke. Therefore, there is an urgent need for a physical identification model that can quantitatively distinguish between strong light reflection from non-fired ground surfaces and strong scattering from thick smoke from real fires.

[0018] In summary, this embodiment of a satellite remote sensing fire point identification method, device, electronic equipment, and storage medium breaks through dimensional barriers and proposes and constructs an Optical-Thermal Conflict Index. The mathematical model of ).

[0019] To facilitate understanding, the technical principle of the photothermal conflict index in this embodiment will now be explained. Studies have shown that although both highly reflective interference sources and actual fire points accompanied by dense smoke exhibit abnormally high overall reflectivity, their physical characteristics in the thermal radiation dimension differ fundamentally. Specifically, the thermal anomaly of highly reflective ground objects is a pseudo-anomaly passively enhanced by optical reflection; its true mid-to-long-wave infrared temperature difference, i.e., brightness temperature difference, is different. The variation is relatively small; however, in a real fire, due to intense combustion, the brightness temperature difference is much larger. It exhibits a significant step-increase characteristic. Based on the above principle, this embodiment proposes a method for constructing the photothermal conflict index. .

[0020] The satellite remote sensing fire point identification method of this embodiment will now be described.

[0021] Reference Figure 1 , Figure 1 A flowchart illustrating the satellite remote sensing fire detection method provided in this application embodiment.

[0022] like Figure 1 As shown, in a first aspect, this embodiment discloses a satellite remote sensing fire point identification method, including: S10: Determine the overall optical reflectivity based on the reflectivity in the visible light band and the near-infrared band; determine the brightness temperature difference based on the brightness temperature in the mid-infrared and long-infrared bands.

[0023] In a specific application of this embodiment, the visible light reflectance of candidate pixels is extracted for a satellite remote sensing area. and near-infrared reflectivity Calculation of optical composite reflectance based on formula The formula for calculating the overall optical reflectivity can be: in: and The spectral weighting ratio is preset based on the sensor's band response characteristics.

[0024] In the specific application of this embodiment, the mid-wave infrared brightness temperature is extracted for the aforementioned candidate pixels. and long-wave infrared brightness temperature Calculate the brightness temperature difference of the core The calculation formula can be .

[0025] Thus, this embodiment quantifies the reflection and temperature difference of the satellite remote sensing area based on S10, providing a data foundation for the construction of the photothermal conflict index.

[0026] S20: A photothermal conflict index is constructed based on the comprehensive optical reflectivity and brightness temperature difference. This photothermal conflict index is used to quantitatively characterize the physical matching relationship between enhanced optical reflection and abrupt changes in thermal radiation.

[0027] In response to the aforementioned technical principle of the photothermal conflict index, this embodiment constructs the photothermal conflict index based on optical reflection and thermodynamic distribution.

[0028] Specifically, the photothermal conflict index is determined based on the comprehensive optical reflectivity, brightness temperature difference, and average historical temperature difference; among which, the comprehensive optical reflectivity is used to quantitatively characterize the enhancement of optical reflection, and the brightness temperature difference and average historical temperature difference are used to quantitatively characterize the abrupt change in thermal radiation.

[0029] In the specific application of this embodiment, the photothermal conflict index The formula for calculation is: in: The solar-thermal conflict index; For optical overall reflectivity; The temperature difference is between mid- and long-wave infrared wavelengths. This is a preset temperature difference smoothing bias constant; This is the preset normalization scaling factor; This is a function to find the maximum value. Minimum constants to prevent data overflow during computation.

[0030] The photothermal conflict index proposed in this embodiment is now discussed. The physical principles behind the calculation formula will be explained. For highly reflective false fire points, because their actual released heat radiation is relatively small, the denominator value... Lower, or in the molecular value Extremely high, its The value will be exponentially high, reflecting the characteristics of strong light and weak heat; while for the extremely high ignition point accompanied by dense smoke, although the molecules... The value is relatively high, but due to its own intense combustion, the denominator value is low. Extremely high levels of activity can actually help to mitigate and reduce [the problem]. The value reflects the physical consistency of strong light and heat. Thus, this embodiment, based on the constructed photothermal conflict index, provides a technical foundation and data support for quantitatively distinguishing between strong light reflection from a fireless surface and strong scattering of dense smoke from a real fire.

[0031] S30: Based on the light and heat conflict index and combined with the preset judgment rules, false fire points are eliminated. These false fire points include at least those caused by strong light reflection from a fireless surface.

[0032] Specifically, the judgment rule is to calculate the index value based on a preset logical function. .

[0033] In this embodiment, the judgment rule for strong photothermal conflict aims to identify damage caused by strong photothermal conflict. In specific applications, a threshold value related to the brightness temperature of the constrained wavelength is preset. Regarding the threshold for constraining the photothermal conflict index And the threshold for constrained brightness temperature difference The index value is calculated based on a preset logic function, the mathematical expression of which is: Among them: when At that time, although the corresponding area showed some thermal anomalies, its optical reflectivity was seriously contrary to the physical laws of actual combustion, and it was judged to be specular reflective metal or photovoltaic panel, and thus eliminated. This eliminated false fire points caused by strong light reflection from a fireless surface. If so, then it shall be retained.

[0034] In this embodiment, a judgment rule for non-blackbody radiation can also be set to complete the detection of non-blackbody radiation heterogeneity. Specifically, in conjunction with the solar zenith angle constraint, spectral saturation interference pixels caused by direct solar flare radiation are further stripped away.

[0035] Based on the photothermal conflict index and combined with the preset joint judgment rules, this embodiment eliminates false fire points caused by strong light reflection from the fireless ground surface and other interference sources, providing an accurate data foundation for fire point identification.

[0036] S40: After eliminating false fire points, satellite remote sensing fire point identification is completed by combining preset dynamic environmental background thresholds for mid-wave infrared temperature.

[0037] After successfully filtering out massive amounts of high-reflectivity background noise using the S30's judgment rules for strong light and heat conflict, fire point identification can be achieved by performing temperature analysis in the remote sensing area. This enables the quantitative differentiation between strong light reflection from a fireless surface and strong scattering of dense smoke from a real fire. In response to the aforementioned technical limitations of static thresholds, this embodiment optimizes the threshold settings in the remote sensing area.

[0038] Specifically, regarding the dynamic environmental background threshold for mid-wave infrared temperature. The mathematical expression is: in: and These are the mean and standard deviation of the mid-wave infrared temperature of the potential recognition area after being eliminated by S30; This is a preset environmental fluctuation coefficient. In application, it exceeds the dynamic environmental background threshold. The pixel values ​​are the final high-confidence true fire points.

[0039] In summary, the satellite remote sensing fire detection method of this embodiment involves: first, acquiring visible light and near-infrared reflectance data and mid-to-long-wave infrared emissivity data from the satellite, and performing brightness-temperature inversion; second, calculating the comprehensive reflectance and mid-to-long-wave infrared temperature difference of the target pixel, and constructing a photothermal conflict index to quantitatively characterize the physical matching relationship between enhanced optical reflection and abrupt thermal radiation changes in the pixel; finally, using the photothermal conflict index, brightness temperature, and reflectance, multi-dimensional thermal anomaly interference is eliminated, effectively filtering out false fire pixels caused by highly reflective non-black bodies such as photovoltaic panels and metal roofs, while retaining real fire points accompanied by dense smoke with high diffuse reflection; this overcomes the shortcomings of traditional static single-threshold filtering that leads to missed detection of real fire points, and significantly improves the reliability and environmental adaptability of wide-area remote sensing fire detection.

[0040] Reference Figure 2 , Figure 2 The diagram shows the structure of the satellite remote sensing fire point identification device provided in the embodiments of this application; in the diagram: 10, reflectivity and brightness temperature difference processing module; 20, photothermal conflict index construction module; 30, false fire point elimination module; 40, satellite remote sensing fire point identification module.

[0041] like Figure 2 As shown, in a second aspect, this embodiment also discloses a satellite remote sensing fire point identification device, which applies the satellite remote sensing fire point identification method described above, including: The reflectivity and brightness temperature difference processing module 10 is configured to: determine the comprehensive optical reflectivity based on the reflectivity of the visible light band and the reflectivity of the near-infrared band; and determine the brightness temperature difference based on the mid-wave infrared brightness temperature and the long-wave infrared brightness temperature. The photothermal conflict index construction module 20 is configured to construct a photothermal conflict index based on the comprehensive optical reflectivity and brightness temperature difference. This photothermal conflict index is used to quantitatively characterize the physical matching relationship between optical reflection enhancement and thermal radiation abrupt change. The false fire point elimination module 30 is configured to: eliminate false fire points based on the photothermal conflict index and in combination with preset judgment rules. The false fire points include at least those caused by strong light reflection from a fireless surface. The satellite remote sensing fire point identification module 40 is configured to: after eliminating false fire points, combine the preset dynamic environmental background thresholds regarding mid-wave infrared temperature to complete the satellite remote sensing fire point identification.

[0042] Thirdly, this embodiment also discloses an electronic device, including at least one processor, at least one memory, and a data bus; The processor and the memory communicate with each other via the data bus; The memory stores program instructions that can be executed by the processor, which calls the program instructions to execute the satellite remote sensing fire detection method as described above.

[0043] Fourthly, this embodiment also discloses a storage medium storing a computer program, which, when executed by a processor, implements the satellite remote sensing fire point identification method as described above.

[0044] It should be noted that the satellite remote sensing fire detection device, electronic device, and storage medium of this embodiment correspond to the aforementioned satellite remote sensing fire detection method. Therefore, any content not specifically described in the satellite remote sensing fire detection device, electronic device, and storage medium of this embodiment, including but not limited to functional definitions, working principles, and technical effects, can be referred to the description in the aforementioned satellite remote sensing fire detection method, and will not be repeated here.

[0045] This embodiment thus discloses a satellite remote sensing fire detection method, apparatus, electronic device, and storage medium. To further illustrate the implementation and technical effects of this embodiment, a polar-orbiting satellite equipped with a VIIRS sensor, such as NPP or JPSS1, will be used as an example.

[0046] For data extraction and brightness temperature inversion: Observational data from the VIIRS sensor were acquired, and reflectance data for the I1 band (visible light, center wavelength approximately 0.64 μm) and I2 band (near-infrared, center wavelength approximately 0.865 μm) were extracted. Emissivity data for the I4 band (mid-infrared, center wavelength approximately 3.74 μm) and I5 band (long-infrared, center wavelength approximately 11.45 μm) were also extracted. The mid-infrared and long-infrared brightness temperatures were obtained using Planck function inversion. Before logarithmic calculations, an RMS check (requiring emissivity greater than 0 and pixel validity) was introduced to prevent the underlying computing platform from throwing anomalies.

[0047] Regarding the calculation of physical characteristic parameters: the optical comprehensive reflectivity is obtained by combining the calculation methods disclosed in S10 and S20. , brightness temperature difference and the conflict index of light and heat .

[0048] Regarding interference identification and mask generation, i.e., eliminating false fire points: this embodiment sets... =320K, =1.5、 =25K, combined with the aforementioned judgment rules for strong light and heat conflict, to eliminate false fire points caused by strong light reflection from a fireless surface.

[0049] In completing satellite remote sensing fire point identification: adaptive background extraction and fire point determination are performed through S40. Specifically, after removing the aforementioned interfering pixels, thick cloud pixels, and pure water flare pixels, a 21-bit system is used. The system extracts effective background pixels using a sliding window with a resolution of 21. It calculates the mean and standard deviation of the mid-infrared temperature of the effective background pixels within the window. Based on the dynamic environmental background threshold, it outputs the final high-confidence true fire point.

[0050] This embodiment will now be described with reference to a specific case.

[0051] Case 1: Comparison of temperature difference scenarios with the same high-temperature long-wave brightness.

[0052] Reference Figure 3 , Figure 3 Comparison of high-temperature long-wave brightness temperature difference scenarios provided in the embodiments of this application; in the figure: (a) false color slice of JPSS1 satellite for false hotspots; (b) false hotspots caused by high-temperature reflection; (c) false color slice of JPSS1 satellite for real fire; (d) real fire.

[0053] like Figure 3 As shown, this embodiment is applied to a scenario with the same high and low wavelength long-wavelength brightness and temperature difference. Figure 3 In (a) and (b), the corresponding data are: I1 reflectance = 0.786754, I2 reflectance = 1.038155, mid-wave brightness temperature = 355.766174, long-wave brightness temperature = 298.530396, and the difference between mid-wave and long-wave brightness temperatures = 57.235779. =1.824909, =3.133656, therefore, =1 is eliminated, meaning it is determined to be a false hotspot caused by altitude sickness. Figure 3 In (c) and (d), the corresponding data are: mid-wave brightness temperature = 354.24884, long-wave brightness temperature = 294.444397, mid-wave and long-wave brightness temperature difference = 59.804443, visible light = 0.388212, near-infrared = 0.432286. =0.820498, =1.349405, therefore, =0 is retained and is determined to be real fire in practice.

[0054] Case 2, comparing scenarios with the same high reflectivity.

[0055] Reference Figure 4 , Figure 4Comparison images of scenes with equivalent high reflectivity provided for embodiments of this application; in the images: (a) a false color slice of JPSS1 satellite with false hotspots; (b) a false hotspot caused by high reflectivity; (c) a false color slice of JPSS1 satellite with real fire; (d) real fire.

[0056] like Figure 4 As shown, this embodiment is applied to scenarios with equivalent high reflectivity. Figure 4 In (a) and (b), the corresponding data are: I1 reflectance = 0.294303, I2 reflectance = 0.459194, mid-wave brightness temperature = 338.67865, long-wave brightness temperature = 306.823975, and the difference between mid-wave and long-wave brightness temperatures = 31.854675. =0.753497, =2.293424, therefore, =1 is eliminated, meaning it is determined to be a false hotspot caused by altitude sickness. Figure 4 In (c) and (d), the corresponding data are: I1 reflectance = 0.387138, I2 reflectance = 0.465982, mid-wave brightness temperature = 356.619812, long-wave brightness temperature = 293.07254, and the difference between mid-wave and long-wave brightness temperatures = 63.547272. =0.85312, =1.321698, therefore, =0 is retained and is determined to be real fire in practice.

[0057] Case 3: Comparison with scenarios of similarly low medium-to-long wavelength brightness temperature difference.

[0058] Reference Figure 5 , Figure 5 Comparison of the same low medium-long wavelength brightness temperature difference scenario provided in the embodiments of this application; in the figure: (a) false color slice of JPSS1 satellite with false hotspot; (b) false hotspot caused by high reflection; (c) false color slice of JPSS1 satellite with real fire; (d) real fire.

[0059] like Figure 5 As shown, this embodiment is applied to scenarios with similarly low medium-to-long wavelength brightness temperature differences. Figure 5 In (a) and (b), the corresponding data are: I1 reflectance = 0.218609, I2 reflectance = 0.368532, mid-wave brightness temperature = 328.076965, long-wave brightness temperature = 301.501923, and the difference between mid-wave and long-wave brightness temperatures = 26.575043. =0.587141, =2.129249, therefore, =1 is eliminated, meaning it is determined to be a false hotspot caused by altitude sickness. Figure 5In (c) and (d), the corresponding data are: I1 reflectance = 0.078014, I2 reflectance = 0.300139, mid-wave brightness temperature = 330.67807, long-wave brightness temperature = 304.640991, and the difference between mid-wave and long-wave brightness temperatures = 26.037079. =0.378153, =1.398644, therefore, =0 is retained and is determined to be real fire in practice.

[0060] Thus, the satellite remote sensing fire point identification method, device, electronic equipment, and storage medium of this embodiment have achieved at least the following technical effects: This embodiment creatively proposes a method for accurately quantifying multidimensional physical contradictions. The index model quantifies the physical contradictions between the optical and infrared bands for the first time. It not only filters out difficult industrial false fire points such as photovoltaic panels and exposed buildings, but also retains dense smoke fire points with high reflectivity, solving the long-standing pain point of underreporting of thick smoke in the industry. To protect the purity of dynamic background calculations, pre-processed light and heat conflict rules eliminate abnormally bright heat sources such as large-area photovoltaic systems, effectively avoiding local window background averages. With variance The elevation of false fire points makes the subsequent dynamic environmental threshold extraction more closely resemble the real natural surface conditions, significantly improving the sensitivity and detection rate for initial small fire sources.

[0061] In the embodiments provided in this application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code, or any suitable combination thereof. For hardware implementation, the processor may be implemented in one or more of the following: application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, other electronic units designed to implement the functions described herein, or combinations thereof. For software implementation, some or all of the processes of the embodiments may be performed by a computer program instructing the associated hardware. During implementation, the program may be stored in a computer-readable storage medium or transmitted as one or more instructions or code on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of a computer program from one place to another. Storage media may be any available medium accessible to a computer. Computer-readable storage media may include, but are not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code having the form of instructions or data structures and accessible to a computer.

[0062] Finally, it should be noted that the above description is only a preferred embodiment of this application and is not intended to limit this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A satellite remote sensing fire point identification method, characterized in that, include: The overall optical reflectivity is determined based on the reflectivity in the visible light band and the reflectivity in the near-infrared band. The brightness temperature difference is determined based on the mid-wave infrared brightness temperature and the long-wave infrared brightness temperature. A photothermal conflict index is constructed based on optical comprehensive reflectivity and brightness temperature difference. This photothermal conflict index is used to quantitatively characterize the physical matching relationship between enhanced optical reflection and abrupt changes in thermal radiation. Based on the light-heat conflict index and combined with the preset judgment rules, false fire points are eliminated. These false fire points include at least those caused by strong light reflection from a fireless surface. After eliminating false fire points, satellite remote sensing fire point identification is completed by combining preset dynamic environmental background thresholds for mid-wave infrared temperature.

2. The satellite remote sensing fire point identification method according to claim 1, characterized in that, The formula for calculating the overall optical reflectivity is: in: The calculated overall optical reflectivity; Reflectance in the visible light band; Reflectivity in the near-infrared band; and This is the preset spectral weighting ratio.

3. The satellite remote sensing fire point identification method according to claim 1, characterized in that, The formula for calculating the brightness temperature difference is: in: The calculated brightness temperature difference; Mid-infrared brightness temperature; It is the brightness temperature of the long-wave infrared.

4. The satellite remote sensing fire point identification method according to claim 1, characterized in that, The photothermal conflict index is determined based on the comprehensive optical reflectivity, brightness temperature difference, and average historical temperature difference; among which, the comprehensive optical reflectivity is used to quantitatively characterize the enhancement of optical reflection, and the brightness temperature difference and average historical temperature difference are used to quantitatively characterize the abrupt change in thermal radiation.

5. The satellite remote sensing fire point identification method according to claim 4, characterized in that, The formula for calculating the photothermal conflict index is: in: The solar-thermal conflict index; For optical overall reflectivity; The temperature difference is between mid- and long-wave infrared wavelengths. This is a preset temperature difference smoothing bias constant; This is the preset normalization scaling factor; This is a function to find the maximum value. Minimum constants to prevent data overflow during computation.

6. The satellite remote sensing fire point identification method according to claim 5, characterized in that, The determination rule is based on calculating the index value using a preset logic function. The logical function is: in: Mid-infrared brightness temperature; The threshold value for the pre-defined constraint mid-wave infrared brightness temperature; The threshold value for the pre-defined constraint photothermal conflict index; The preset threshold for the constraint brightness temperature difference; when When, it should be removed; when If so, then it shall be retained.

7. The satellite remote sensing fire point identification method according to claim 6, characterized in that, The dynamic environment background threshold is: in: The calculated dynamic environmental background threshold; and These are the mean and standard deviation of the mid-wave infrared temperature of the potential identification region after elimination, respectively; This is the preset environmental fluctuation coefficient.

8. A satellite remote sensing fire detection device, employing the satellite remote sensing fire detection method as described in any one of claims 1 to 7, characterized in that, include: The reflectivity and brightness temperature difference processing module is configured to: determine the overall optical reflectivity based on the reflectivity of the visible light band and the reflectivity of the near-infrared band; and determine the brightness temperature difference based on the mid-wave infrared brightness temperature and the long-wave infrared brightness temperature. The optical-thermal conflict index construction module is configured to: construct an optical-thermal conflict index based on the comprehensive optical reflectivity and brightness temperature difference. This optical-thermal conflict index is used to quantitatively characterize the physical matching relationship between optical reflection enhancement and thermal radiation abrupt change. The false fire point elimination module is configured to: eliminate false fire points based on the photothermal conflict index and in combination with preset judgment rules. The false fire points include at least those caused by strong light reflection from a fireless surface. The satellite remote sensing fire detection module is configured to: after eliminating false fire points, combine a preset dynamic environmental background threshold for mid-wave infrared temperature to complete the satellite remote sensing fire detection.

9. An electronic device, characterized in that, Includes at least one processor, at least one memory, and a data bus; The processor and the memory communicate with each other via the data bus; The memory stores program instructions that can be executed by the processor, which invokes the program instructions to execute the satellite remote sensing fire detection method according to any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the satellite remote sensing fire point identification method according to any one of claims 1 to 7.

Images