A potential fire point identification method and device based on geostationary meteorological satellite

Abstract

The application provides a potential fire point identification method and device based on a stationary meteorological satellite, relates to the technical field of fire point identification, and comprises the following steps: acquiring stationary meteorological satellite remote sensing image data of a region to be identified within a preset time period, and determining attribute data of each pixel in the stationary meteorological satellite remote sensing image data; determining a target pixel in the stationary meteorological satellite remote sensing image data based on the attribute data, wherein the target pixel is a pixel other than a cloud pixel, a water body pixel and an absolute fire point pixel; calculating a background brightness temperature threshold value and a background brightness temperature difference threshold value of the target pixel based on a dynamic window algorithm and the attribute data; and determining a final pixel in the target pixel based on a preset condition, the background brightness temperature threshold value and the background brightness temperature difference threshold value of the target pixel, determining the final pixel and the absolute fire point pixel as potential fire points, and solving the technical problem of low identification accuracy of the existing potential fire point identification method.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fire point recognition, and in particular to a potential fire point identification method and device based on a stationary meteorological satellite. BACKGROUND

[0002] At present, the method for monitoring fire based on a stationary meteorological satellite can be divided into a fixed threshold method, an adaptive threshold method (a spatial difference method) and a time difference method. In addition to the fixed threshold method for identification by pre-setting a threshold, the adaptive threshold method and the time difference method both use a potential fire point identification method. The identification of potential fire points is based on the real-time requirement for monitoring fire by a satellite. Through a series of identification conditions, obvious non-fire point pixels are filtered out, and pixels with similar characteristics to fire point pixels are marked as potential fire point pixels as much as possible. In the subsequent fine identification process, by comparing the potential fire point pixels with the surrounding background pixels, fast and accurate fire point identification can be achieved. Therefore, the accuracy of the identification of potential fire points greatly affects the accuracy of the stationary meteorological satellite fire monitoring.

[0003] In the existing stationary meteorological satellite fire monitoring method, the identification method of potential fire points includes the fixed threshold method and the spatial context method. The fixed threshold method screens potential fire point pixels by pre-setting a threshold, but the threshold varies in different regions and seasons. If the threshold is too low, a large number of non-fire point pixels will pass the screening, increasing the subsequent calculation amount and the probability of misjudgment. If the threshold is too high, small fires will be missed, resulting in reduced identification accuracy. Therefore, the potential fire point identification method by fixed threshold screening has poor universality and low accuracy. The spatial context method screens potential fire points by comparing the brightness temperature (BT) of the target pixel and the background pixel in the mid-infrared channel and the brightness temperature difference (ΔBT) between the mid-infrared channel and the far-infrared channel. This method effectively avoids misjudgment and omission caused by inaccurate fixed threshold setting, but still has inaccurate identification. When identifying potential hot spots for large fires with multiple pixels, the BT and ΔBT of the target pixel and the background pixel are not significantly different, which may cause the pixels that should be identified as potential hot spots to be filtered out, resulting in the omission of fire point pixels. At the same time, the spatial context method does not filter out cloud, water body and absolute hot spot pixels in advance, resulting in a difference between the BT and ΔBT of the background pixel and the true BT and ΔBT that can be used for identification, which leads to misjudgment and omission when calculating the target pixel.

[0004] No effective solution has been proposed to solve the above problems. SUMMARY

[0005] Therefore, the present application aims to provide a potential fire point identification method and device based on geostationary meteorological satellite, so as to solve the problem of low identification accuracy of the existing potential fire point identification method.

[0006] In the first aspect, the embodiment of the present application provides a potential fire point identification method based on geostationary meteorological satellite, comprising: acquiring geostationary meteorological satellite remote sensing image data of a region to be identified in a preset time period, and determining attribute data of each pixel in the geostationary meteorological satellite remote sensing image data, wherein the attribute data comprises diurnal attribute, simultaneous time bright temperature average value and simultaneous time bright temperature difference average value; determining a target pixel in the geostationary meteorological satellite remote sensing image data based on the attribute data, wherein the target pixel is a pixel other than a cloud pixel, a water body pixel and an absolute fire point pixel; calculating a background bright temperature threshold value and a background bright temperature difference threshold value of the target pixel based on a dynamic window algorithm and the attribute data; determining a final pixel in the target pixel based on a preset condition, the background bright temperature threshold value and the background bright temperature difference threshold value of the target pixel, and determining the final pixel and the absolute fire point pixel as a potential fire point.

[0007] Further, the attribute data of each pixel in the geostationary meteorological satellite remote sensing image data is determined, comprising: pre-processing the geostationary meteorological satellite remote sensing image data to determine target parameters of each pixel in the geostationary meteorological satellite remote sensing image data, wherein the target parameters comprise visible light channel apparent reflectivity data, near-infrared channel apparent reflectivity data, mid-infrared channel bright temperature data, far-infrared channel bright temperature data, satellite zenith angle, satellite azimuth angle, solar zenith angle and solar zenith angle; determining the diurnal attribute of each pixel based on the target parameters and a preset identification formula, wherein the preset identification formula is DayBool is a mask file of daytime pixels, NightBool is a mask file of nighttime pixels, and ValidBool is an effectiveness mask file of geostationary meteorological satellite remote sensing image data quality meeting the use requirements, is the first channel apparent reflectivity, θ soz is the solar zenith angle; the simultaneous time bright temperature average value of each pixel is determined based on the target parameters and a bright temperature average value formula, wherein the bright temperature average value formula is wherein, is the simultaneous time bright temperature average value, and n is the number of days in the preset time period, is the simultaneous time 7th channel bright temperature value of the i-th day; the simultaneous time bright temperature difference average value of each pixel is determined based on the target parameters and a bright temperature difference average value formula, wherein the bright temperature difference average value formula is wherein, ΔBT is the brightness temperature difference, represents the 13th channel brightness temperature value at the same time on the i-th day, ΔBT i represents the brightness temperature difference on the i-th day.

[0008] Further, based on the attribute data, the target pixels in the static meteorological satellite remote sensing image data are determined, including: based on the attribute data, the target data and the clear sky background field data, cloud pixels in the static meteorological satellite remote sensing image data are determined, wherein the cloud pixels include daytime cloud pixels and nighttime cloud pixels; based on the attribute data, the target data and the water body mask data, cloud pixels in the static meteorological satellite remote sensing image data are determined; based on the attribute data and the target data, absolute fire point pixels in the static meteorological satellite remote sensing image data are determined, wherein the absolute fire point pixels include daytime absolute fire point pixels and nighttime absolute fire point pixels.

[0009] Further, based on the dynamic window algorithm and the attribute data, the background brightness temperature threshold and the background brightness temperature difference threshold of the target pixels are calculated, including: based on the dynamic window algorithm, the number of target pixels in a target window is determined, wherein the target window is a window of a preset size constructed with any one target pixel as the center; target pixels corresponding to target windows with a number greater than a preset threshold are determined as valid pixels, and target pixels corresponding to target windows with a number less than or equal to a preset threshold are determined as invalid pixels; based on the target pixels in the target window corresponding to the valid pixels, the average brightness temperature value and the average brightness temperature difference value of the valid pixels are calculated; based on the Otsu algorithm, the average brightness temperature value and the average brightness temperature difference value of the target pixels at the same time, the average brightness temperature value empirical threshold and the average brightness temperature difference value empirical threshold of the target pixels are determined; based on the average brightness temperature value and the average brightness temperature difference value of the valid pixels, and the average brightness temperature value empirical threshold and the average brightness temperature difference value empirical threshold of the valid pixels, the background brightness temperature threshold and the background brightness temperature difference threshold of the valid pixels are determined; the average brightness temperature value empirical threshold and the average brightness temperature difference value empirical threshold of the invalid pixels are determined as the background brightness temperature threshold and the background brightness temperature difference threshold of the invalid pixels.

[0010] Further, based on preset conditions, the background brightness temperature threshold value and the background brightness temperature difference threshold value of the target pixel, the final pixel in the target pixel is determined, including: the effective pixel in which the difference between the 7th channel brightness temperature value at the same time of the i-th day and the corresponding background brightness temperature threshold value is greater than the first preset threshold value, the difference between the brightness temperature difference at the same time of the i-th day and the corresponding background brightness temperature difference threshold value is greater than the first preset threshold value, and the 7th channel brightness temperature value at the same time of the i-th day is greater than the second preset threshold value is determined as the final pixel; the invalid pixel in which the difference between the 7th channel brightness temperature value at the same time of the i-th day and the corresponding background brightness temperature threshold value is greater than the third preset threshold value, the difference between the brightness temperature difference at the same time of the i-th day and the corresponding background brightness temperature difference threshold value is greater than the third preset threshold value, and the 7th channel brightness temperature value at the same time of the i-th day is greater than the fourth preset threshold value is determined as the final pixel.

[0011] In a second aspect, the embodiment of the present application further provides a potential fire point identification device based on a stationary meteorological satellite, comprising: an acquisition unit, a determination unit, a calculation unit and a discrimination unit, wherein the acquisition unit is configured to acquire stationary meteorological satellite remote sensing image data of a region to be discriminated in a preset time period, and determine attribute data of each pixel in the stationary meteorological satellite remote sensing image data, wherein the attribute data comprises: diurnal attribute, simultaneous brightness temperature average value and simultaneous brightness temperature difference average value; the determination unit is configured to determine a target pixel in the stationary meteorological satellite remote sensing image data based on the attribute data, wherein the target pixel is a pixel other than a cloud pixel, a water body pixel and an absolute fire point pixel; the calculation unit is configured to calculate a background brightness temperature threshold value and a background brightness temperature difference threshold value of the target pixel based on a dynamic window algorithm and the attribute data; and the discrimination unit is configured to determine a final pixel in the target pixel based on preset conditions, the background brightness temperature threshold value and the background brightness temperature difference threshold value of the target pixel, and determine the final pixel and the absolute fire point pixel as a potential fire point.

[0012] Further, the acquisition unit is configured to: pre-process the stationary meteorological satellite remote sensing image data to determine target parameters of each pixel in the stationary meteorological satellite remote sensing image data, wherein the target parameters comprise: visible light channel apparent reflectivity data, near-infrared channel apparent reflectivity data, mid-infrared channel brightness temperature data, far-infrared channel brightness temperature data, satellite zenith angle, satellite azimuth angle, sun zenith angle and sun zenith angle; and determine diurnal attributes of each pixel based on the target parameters and a preset discrimination formula, wherein the preset discrimination formula is DayBool is a mask file of daytime pixels, NightBool is a mask file of nighttime pixels, and ValidBool is an effectiveness mask file of static meteorological satellite remote sensing image data quality meeting use requirements, is the apparent reflectivity of the first channel, and soz is the solar zenith angle in degrees; based on the target parameters and the brightness temperature average value formula, the brightness temperature average value of each pixel at the same time is determined, wherein the brightness temperature average value formula is wherein, is the brightness temperature average value at the same time, and n is the number of days in the preset time period, is the 7th channel brightness temperature value of the ith day at the same time; based on the target parameters and the brightness temperature difference average value formula, the brightness temperature difference average value of each pixel at the same time is determined, wherein the brightness temperature difference average value formula is wherein, is the brightness temperature difference, represents the 13th channel brightness temperature value of the ith day at the same time, and i represents the brightness temperature difference of the ith day at the same time.

[0013] Further, the determination unit is configured to: determine cloud pixels in the static meteorological satellite remote sensing image data based on the attribute data, the target data, and clear sky background field data, wherein the cloud pixels include daytime cloud pixels and nighttime cloud pixels; determine cloud pixels in the static meteorological satellite remote sensing image data based on the attribute data, the target data, and water body mask data; and determine absolute fire point pixels in the static meteorological satellite remote sensing image data based on the attribute data and the target data, wherein the absolute fire point pixels include daytime absolute fire point pixels and nighttime absolute fire point pixels.

[0014] In a third aspect, an electronic device is provided, including a memory and a processor, the memory is configured to store a program supporting the processor to execute the method in the first aspect, and the processor is configured to execute the program stored in the memory.

[0015] In a fourth aspect, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program.

[0016] In the embodiment of the present application, by acquiring the static meteorological satellite remote sensing image data of the to-be-discriminated region in a preset time period, attribute data of each pixel in the static meteorological satellite remote sensing image data is determined, wherein the attribute data includes day and night attributes, simultaneous-epoch brightness temperature average value and simultaneous-epoch brightness temperature difference average value; based on the attribute data, a target pixel in the static meteorological satellite remote sensing image data is determined, wherein the target pixel is a pixel other than a cloud pixel, a water body pixel and an absolute fire point pixel; based on a dynamic window algorithm and the attribute data, a background brightness temperature threshold and a background brightness temperature difference threshold of the target pixel are calculated; based on a preset condition, the background brightness temperature threshold and the background brightness temperature difference threshold of the target pixel, a final pixel in the target pixel is determined, and the final pixel and the absolute fire point pixel are determined as a potential fire point, so that the purpose of high-precision and rapid identification of the potential fire point is achieved, and the technical problem of insufficient identification accuracy of the potential fire point is solved, thereby realizing the technical effect of improving the accuracy of static meteorological satellite fire monitoring.

[0017] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application will be realized and achieved by the structure particularly pointed out in the description, claims and drawings.

[0018] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are described in detail as follows. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0020] Figure 1 A flow chart of a potential fire point identification method based on a static meteorological satellite provided by the embodiment of the present application;

[0021] Figure 2 A schematic diagram of a potential fire point identification device based on a static meteorological satellite provided by the embodiment of the present application;

[0022] Figure 3 A schematic diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the present application will be described clearly and completely below with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0024] Embodiment one:

[0025] According to the embodiments of the present application, an embodiment of a potential fire point identification method based on a geostationary meteorological satellite is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0026] Figure 1 is a flowchart of a potential fire point identification method based on a geostationary meteorological satellite according to an embodiment of the present application, as shown in Figure 1 The method comprises the following steps:

[0027] Step S102, acquiring geostationary meteorological satellite remote sensing image data of a region to be identified in a preset time period, and determining attribute data of each pixel in the geostationary meteorological satellite remote sensing image data, wherein the attribute data comprises day and night attributes, simultaneous-epoch average brightness temperature and simultaneous-epoch brightness temperature difference average;

[0028] Step S104, determining a target pixel in the geostationary meteorological satellite remote sensing image data based on the attribute data, wherein the target pixel is a pixel other than a cloud pixel, a water body pixel and an absolute fire point pixel;

[0029] Step S106, calculating a background brightness temperature threshold and a background brightness temperature difference threshold of the target pixel based on a dynamic window algorithm and the attribute data;

[0030] Step S108, determining a final pixel in the target pixel based on a preset condition, the background brightness temperature threshold and the background brightness temperature difference threshold of the target pixel, and determining the final pixel and the absolute fire point pixel as potential fire points.

[0031] In the embodiment of the present application, by acquiring the static meteorological satellite remote sensing image data of the to-be-discriminated region in a preset time period, attribute data of each pixel in the static meteorological satellite remote sensing image data is determined, wherein the attribute data includes diurnal attribute, simultaneous-epoch brightness temperature average value and simultaneous-epoch brightness temperature difference average value; based on the attribute data, a target pixel in the static meteorological satellite remote sensing image data is determined, wherein the target pixel is a pixel other than a cloud pixel, a water body pixel and an absolute fire point pixel; based on a dynamic window algorithm and the attribute data, a background brightness temperature threshold and a background brightness temperature difference threshold of the target pixel are calculated; based on a preset condition, the background brightness temperature threshold and the background brightness temperature difference threshold of the target pixel, a final pixel in the target pixel is determined, and the final pixel and the absolute fire point pixel are determined as a potential fire point, so that the purpose of high-precision and rapid identification of the potential fire point is achieved, and the technical problem of insufficient identification accuracy of the potential fire point is solved, thereby achieving the technical effect of accurate static meteorological satellite fire monitoring.

[0032] In the embodiment of the present application, step S102 comprises the following steps:

[0033] The static meteorological satellite remote sensing image data is preprocessed, and a target parameter of each pixel in the static meteorological satellite remote sensing image data is determined, wherein the target parameter includes visible light channel apparent reflectivity data, near-infrared channel apparent reflectivity data, mid-infrared channel brightness temperature data, far-infrared channel brightness temperature data, satellite zenith angle, satellite azimuth angle, solar zenith angle and solar zenith angle;

[0034] The visible light channel apparent reflectivity data is The near-infrared channel apparent reflectivity data is The mid-infrared channel brightness temperature data is The far-infrared channel brightness temperature data is Satellite zenith angle (SAZ), satellite azimuth angle (SAA), solar zenith angle (SOZ) and solar zenith angle (SOA) angle data.

[0035] Based on the target parameter and a preset discrimination formula, the diurnal attribute of each pixel is determined, wherein the preset discrimination formula is DayBool is a mask file of a daytime pixel, NightBool is a mask file of a nighttime pixel, ValidBool is an effectiveness mask file of static meteorological satellite remote sensing image data quality meeting use requirements, is the first channel apparent reflectivity, θ soz is the solar zenith angle;

[0036] Determine the same time brightness temperature average value of each pixel based on the target parameter and the brightness temperature average value formula, wherein the brightness temperature average value formula is wherein, is the same time brightness temperature average value, n is the number of days in the preset time period, is the 7th channel brightness temperature value of the i-th day at the same time;

[0037] Determine the same time brightness temperature difference average value of each pixel based on the target parameter and the brightness temperature difference average value formula, wherein the brightness temperature difference average value formula is wherein, is the brightness temperature difference, is the 13th channel brightness temperature value of the i-th day at the same time, and i is the brightness temperature difference of the i-th day at the same time.

[0038] It should be noted that the static meteorological satellite data has a feature that the brightness temperature observation value of a single pixel in a period of time may be different, but in the absence of a sudden event, the observed brightness temperature of the pixel will fluctuate around the average value. Based on this principle, the historical characteristic value of each pixel after preprocessing is extracted. The historical data of m days (in the preset time) is traced back, the historical data is simply cleaned, and the same time brightness temperature average value of each pixel and the same time brightness temperature difference average value of each pixel are extracted one by one.

[0039] The static meteorological satellite remote sensing image data is preferably H8-AHI sensor remote sensing image data.

[0040] In the embodiment of the present application, step S104 comprises the following steps:

[0041] Step S11, based on the attribute data, the target data and the clear sky background field data, determine the cloud pixel in the static meteorological satellite remote sensing image data, wherein the cloud pixel comprises: daytime cloud pixel and night cloud pixel;

[0042] Step S12, based on the attribute data, the target data and the water body mask data, determine the cloud pixel in the static meteorological satellite remote sensing image data;

[0043] Step S13, based on the attribute data and the target data, determine the absolute fire point pixel in the static meteorological satellite remote sensing image data, wherein the absolute fire point pixel comprises: daytime absolute fire point pixel and night absolute fire point pixel.

[0044] In the embodiments of the present application, cloud identification is performed by using attribute data in combination with auxiliary data (clear sky background field). During the day, in combination with the apparent reflectivity of the blue light channel of the clear sky background field, and the high reflectivity of the cloud in the visible light channel and the low brightness temperature characteristic of the far infrared channel, the day cloud pixel is identified. At night, by normalizing and threshold extraction of the brightness temperature of the middle infrared channel and the brightness temperature of the far infrared channel, the night cloud pixel is identified; the identification formula is:

[0045] Day cloud pixel:

[0046] C1 = Δblue' > Thre blue ;

[0047]

[0048]

[0049]

[0050] DayCloud = (C1 or C2 or C3 or C4) and DayBool;

[0051] Night cloud pixel:

[0052]

[0053]

[0054] NightCloud = (C1 or C2) and NightBool;

[0055] Cloud pixel:

[0056] Cloud = DayCloud or NightCloud.

[0057] Wherein, Δblue' represents the difference between the reflectivity of the blue light channel of the pre-processing result and the reflectivity of the blue light channel of the clear sky background field, and the value obtained by the Retinex enhancement method; Thre blue represents the threshold value of the reflectivity of the blue light channel extracted by the Otsu algorithm; respectively represent the apparent reflectivity of the 3rd channel and the 4th channel; represents the brightness temperature value of the 15th channel; respectively represent the normalized brightness temperature values of the 7th channel and the 14th channel; Thre band07 , Thre band14 respectively represent the threshold values of the brightness temperature values of the 7th channel and the 14th channel extracted by the Otsu algorithm; K is the unit of brightness temperature Kelvin.

[0058] Resample WaterMask to 2KM pixel size using attribute data, target data and WaterMask data. Since the water area will have seasonal changes, the WaterMask file cannot identify all the water, and the missing water pixel in the mask file may cause misjudgment in the subsequent identification. Therefore, this paper conducts additional water identification conditions to detect water pixels (WaterBool); the identification formula is:

[0059]

[0060] Water = WaterMask or WaterBool;

[0061] Wherein, represents the apparent reflectance of the 6th channel; NDVI represents the normalized vegetation index; NDWI represents the normalized water index.

[0062] Finally, the attribute data and target data are used for absolute fire point identification; the identification formula is:

[0063] Day absolute fire point:

[0064]

[0065] Night absolute fire point:

[0066]

[0067] FireMask = DayFire or NightFire;

[0068] Wherein, FireMask represents the absolute fire point pixel mask identified.

[0069] The cloud, water and absolute fire point pixels identified in steps 3A, 3B and 3C are marked as non-fire pixels; the formula is:

[0070] ValidBkg = ValidBool and ~Water and ~Cloud & ~FireMask

[0071] Wherein, ValidBkg is the valid background area (i.e. target pixel) after filtering out the non-fire pixel.

[0072] In the embodiment of the present application, step S106 comprises the following steps:

[0073] Step S21, based on the dynamic window algorithm, the number of target pixels in the target window is determined, wherein the target window is a window of a predetermined size centered on any one target pixel;

[0074] Step S22, determining the target pixels corresponding to the target window with the number greater than the preset threshold as valid pixels, and determining the target pixels corresponding to the target window with the number less than or equal to the preset threshold as invalid pixels;

[0075] Step S23, calculating the average brightness temperature value and the average brightness temperature difference value of the valid pixels based on the target pixels in the target window corresponding to the valid pixels;

[0076] Step S24, determining the average brightness temperature value empirical threshold and the average brightness temperature difference value empirical threshold of the target pixels based on the Otsu algorithm, the average value of the simultaneous time brightness temperature of the target pixels and the average value of the simultaneous time brightness temperature difference;

[0077] Step S25, determining the background brightness temperature threshold and the background brightness temperature difference threshold of the valid pixels based on the average brightness temperature value and the average brightness temperature difference value of the valid pixels and the average brightness temperature value empirical threshold and the average brightness temperature difference value empirical threshold of the valid pixels;

[0078] Step S26, determining the background brightness temperature threshold and the background brightness temperature difference threshold of the invalid pixels based on the average brightness temperature value empirical threshold and the average brightness temperature difference value empirical threshold of the invalid pixels.

[0079] In the embodiment of the application, the pixels in the valid background area ValidBkg are calculated one by one. The calculation is to calculate the number N of target pixels in the window range of n*m (n, m are preset values, and 50, 50 are taken here) with the target pixel as the center. If the number N of target pixels is greater than the preset value ThreN (1000 is taken here), the target pixel is marked as a valid pixel, otherwise it is marked as an invalid pixel; the calculation formula is:

[0080] ReliableBkg i =ValidBkg∩(n*m) i ;

[0081] N i =Count(ReliableBkg i );

[0082] Wherein, (n*m) i indicates the window formed with the i-th pixel as the center and n*m as the size; ReliableBkg i indicates the intersection of the (n*m) i window and the valid background area; N i indicates the number of valid background pixels in the intersection.

[0083] Then, the average brightness temperature value and the average brightness temperature difference value of the target pixels are calculated. For the valid pixels, ReliableBkg ithe average brightness temperature value and the average brightness temperature difference The formula is:

[0084]

[0085]

[0086]

[0087] Wherein, ΔBT represents the brightness temperature difference, calculated by subtracting the 7th channel brightness temperature from the 13th channel brightness temperature.

[0088] For invalid pixels, the average brightness temperature value and the average brightness temperature difference are not calculated.

[0089] After obtaining the average brightness temperature value and the average brightness temperature difference of the valid pixels, adjustment based on the empirical threshold value is performed one by one. The empirical threshold value is based on the historical brightness temperature average value and the historical brightness temperature difference average value Threshold extraction is performed using the Otsu algorithm. The adjusted average brightness temperature value and the average brightness temperature difference value are used as the background brightness temperature threshold and the background brightness temperature difference threshold for the pixel. For invalid pixels, the empirical threshold value is directly used as the background brightness temperature threshold and the background brightness temperature difference threshold for the pixel. The calculation process is as follows:

[0090] For valid pixel i:

[0091]

[0092]

[0093]

[0094]

[0095] For invalid pixel i:

[0096] Bkg_ThreBT i = ExThreBT i ;

[0097] Bkg_ThreΔBT i = ExThreΔBT i ;

[0098] Wherein, ExThreBT i represents the empirical brightness temperature threshold obtained by the Otsu algorithm based on the historical brightness temperature average value of pixel i; ExThreΔBT irepresents the empirical brightness temperature difference threshold obtained by Otsu algorithm based on the brightness temperature difference average value of the same time moment of the pixel i history, Bkg_ThreBT i represents the pixel background brightness temperature threshold obtained after adjustment of ExThreBT i represents the pixel background brightness temperature threshold obtained after adjustment of ExThreBT i represents the pixel background brightness temperature threshold obtained after adjustment of ExThreBT i represents the pixel background brightness temperature threshold obtained after adjustment of ExThreBT

[0099] In the embodiment of the present application, step S108 comprises the following steps:

[0100] Step 31, determining the valid pixel as the final pixel, if the difference between the 7th channel brightness temperature value of the same time moment of the i-th day of the valid pixel and the corresponding background brightness temperature threshold is greater than the first preset threshold, the difference between the brightness temperature difference of the same time moment of the i-th day and the corresponding background brightness temperature difference threshold is greater than the first preset threshold, and the 7th channel brightness temperature value of the same time moment of the i-th day is greater than the second preset threshold.

[0101] Step 32, determining the invalid pixel as the final pixel, if the difference between the 7th channel brightness temperature value of the same time moment of the i-th day of the invalid pixel and the corresponding background brightness temperature threshold is greater than the third preset threshold, the difference between the brightness temperature difference of the same time moment of the i-th day and the corresponding background brightness temperature difference threshold is greater than the third preset threshold, and the 7th channel brightness temperature value of the same time moment of the i-th day is greater than the fourth preset threshold.

[0102] In the embodiment of the present application, the background brightness temperature threshold and the background brightness temperature difference threshold of the target pixel are obtained, and the target pixel is calculated one by one, and the calculation formula is as follows:

[0103] For the valid pixel:

[0104]

[0105] Test2=(ΔBT i -ExThreΔBT i >4)

[0106]

[0107] PF1=Test1 and Test2 and Test3

[0108] For the invalid pixel:

[0109]

[0110] Test2=(ΔBT i -ExThreΔBT i>6)

[0111]

[0112] PF2=Test1 and Test2 and Test3

[0113] For the pixel meeting any condition 1 or condition 2, it is identified as a potential fire point. The identification formula is:

[0114] PF=PF1 or PF2

[0115] Wherein, PF represents the final pixel identified.

[0116] The absolute fire point pixel and the final pixel are calculated in a union set to obtain all potential fire point pixels. The identification formula is:

[0117] PF bool =PF∪FireMask

[0118] Wherein, PF bool represents the potential fire point pixel finally obtained after all identification conditions.

[0119] The embodiment of the present application provides a potential fire point identification method based on a dynamic effective background window and an experience threshold value of a stationary meteorological satellite. First, the concept of a dynamic effective background window is proposed, and the effective background window of each pixel is calculated for the stationary meteorological satellite data to obtain the pixel background brightness temperature and brightness temperature difference value. Compared with the traditional single threshold value or spatial context method, the calculation accuracy of the pixel background value is improved. Secondly, based on the high time resolution characteristics of the stationary meteorological satellite, the experience threshold value correction method based on the historical observation data at the same time is proposed. The threshold value is extracted by using the Otsu algorithm, and is combined with the effective background window to improve the identification accuracy of the potential fire point. Therefore, the potential fire point identification method based on the dynamic effective background window and the experience threshold value of the stationary meteorological satellite has a great improvement effect on improving the fire monitoring accuracy of the stationary meteorological satellite.

[0120] Embodiment two:

[0121] The embodiment of the present application also provides a potential fire point identification device based on a stationary meteorological satellite. The potential fire point identification device based on the stationary meteorological satellite is used to execute the potential fire point identification method based on the stationary meteorological satellite provided in the above content of the embodiment of the present application. The following is a specific introduction of the potential fire point identification device based on the stationary meteorological satellite provided in the embodiment of the present application.

[0122] As Figure 2 shown, Figure 2A schematic diagram of the potential fire point identification device based on the stationary meteorological satellite, the potential fire point identification device based on the stationary meteorological satellite comprises: an acquisition unit 10, a determination unit 20, a calculation unit 30 and a discrimination unit 40.

[0123] The acquisition unit is used to acquire the stationary meteorological satellite remote sensing image data of a region to be discriminated in a preset time period, and determine the attribute data of each pixel in the stationary meteorological satellite remote sensing image data, wherein the attribute data comprises: diurnal attribute, simultaneous-epoch average bright temperature and simultaneous-epoch average bright temperature difference.

[0124] The determination unit is used to determine a target pixel in the stationary meteorological satellite remote sensing image data based on the attribute data, wherein the target pixel is a pixel other than a cloud pixel, a water body pixel and an absolute fire point pixel.

[0125] The calculation unit is used to calculate the background bright temperature threshold and the background bright temperature difference threshold of the target pixel based on a dynamic window algorithm and the attribute data.

[0126] The discrimination unit is used to determine a final pixel in the target pixel based on a preset condition, the background bright temperature threshold and the background bright temperature difference threshold of the target pixel, and determine the final pixel and the absolute fire point pixel as a potential fire point.

[0127] In the embodiment of the present application, the stationary meteorological satellite remote sensing image data of a region to be discriminated in a preset time period is acquired, and the attribute data of each pixel in the stationary meteorological satellite remote sensing image data is determined, wherein the attribute data comprises: diurnal attribute, simultaneous-epoch average bright temperature and simultaneous-epoch average bright temperature difference. A target pixel in the stationary meteorological satellite remote sensing image data is determined based on the attribute data, wherein the target pixel is a pixel other than a cloud pixel, a water body pixel and an absolute fire point pixel. The background bright temperature threshold and the background bright temperature difference threshold of the target pixel are calculated based on a dynamic window algorithm and the attribute data. A final pixel in the target pixel is determined based on a preset condition, the background bright temperature threshold and the background bright temperature difference threshold of the target pixel, and the final pixel and the absolute fire point pixel are determined as a potential fire point, so as to achieve the purpose of high-precision and rapid identification of the potential fire point, and solve the technical problem of insufficient identification accuracy of the potential fire point, thereby achieving the technical effect of accurate stationary meteorological satellite fire monitoring.

[0128] Embodiment three:

[0129] The embodiment of the present application also provides an electronic device comprising a memory and a processor, the memory is used to store a program supporting the processor to execute the method described in the above embodiment one, and the processor is configured to execute the program stored in the memory.

[0130] Referring to Figure 3 The embodiments of the present application also provide an electronic device 100, comprising a processor 60, a memory 61, a bus 62 and a communication interface 63, the processor 60, the communication interface 63 and the memory 61 are connected through the bus 62; the processor 60 is used for executing the executable modules stored in the memory 61, such as computer programs.

[0131] The memory 61 can contain a high-speed random access memory (RAM, Random Access Memory), and can also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 63 (which can be wired or wireless), and the Internet, a wide area network, a local network, a metropolitan area network, etc. can be used.

[0132] The bus 62 can be an ISA bus, a PCI bus or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 3 Only one bidirectional arrow is used in the above description, but it does not mean that there is only one bus or one type of bus.

[0133] The memory 61 is used for storing programs, and the processor 60 executes the programs after receiving execution instructions. The method executed by the device defined by the flow process disclosed in any of the foregoing embodiments of the present application can be applied to the processor 60 or realized by the processor 60.

[0134] The processor 60 can be an integrated circuit chip with signal processing capability. In implementation, each step of the above method can be completed by integrated logic circuit of hardware in the processor 60 or by instructions in the form of software. The processor 60 described above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. Each method, step and logic block diagram disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware code processor for execution, or a combination of hardware and software modules in the code processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium in the art. The storage medium is located in the memory 61, and the processor 60 reads the information in the memory 61, and combines the hardware to complete the steps of the above method.

[0135] Embodiment four:

[0136] The embodiments of the present application also provide a computer readable storage medium, and the computer readable storage medium stores a computer program. The computer program is run by a processor to execute the steps of the method described in the above embodiment one.

[0137] In addition, in the description of the embodiments of the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting" should be understood in a broad sense, for example, can be fixedly connected, can also be detachably connected, or integrally connected; can be mechanically connected, can also be electrically connected; can be directly connected, can also be indirectly connected through an intermediate medium, can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0138] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", and the like indicate the orientation or positional relationship shown in the drawings based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", "third" are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0139] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are only illustrative, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, and for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interfaces, devices or units, which can be electrical, mechanical or other forms.

[0140] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, i.e. they can be located in one place or distributed on multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiment scheme according to actual needs.

[0141] In addition, the functional units in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically, or two or more units can be integrated into one unit.

[0142] Finally, it should be noted that: the above-described embodiments are only specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, but not to limit them, the protection scope of the present application is not limited to this, although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any skilled person in the art can modify or easily think of changes to the technical solutions recorded in the foregoing embodiments within the technical range disclosed by the present application, or make equivalent replacement to some technical features; and these modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for identifying potential fire points based on geostationary meteorological satellites, characterized in that, include: Acquire geostationary meteorological satellite remote sensing image data of the area to be identified within a preset time period, and determine the attribute data of each pixel in the geostationary meteorological satellite remote sensing image data, wherein the attribute data includes: day and night attributes, average brightness temperature at the same time and average brightness temperature difference at the same time; Based on the attribute data, the target pixels in the geostationary meteorological satellite remote sensing image data are determined, wherein the target pixels are pixels other than cloud pixels, water body pixels and absolute fire point pixels. Based on the dynamic window algorithm and the attribute data, the background brightness temperature threshold and background brightness temperature difference threshold of the target pixel are calculated; including: determining the number of target pixels in the target window based on the dynamic window algorithm, wherein the target window is a window of a preset size constructed with any target pixel as the center; determining the target pixels corresponding to the target windows with a number greater than the preset threshold as valid pixels, and determining the target pixels corresponding to the target windows with a number less than or equal to the preset threshold as invalid pixels; and calculating the average brightness of the valid pixels based on the target pixels in the target windows corresponding to the valid pixels. The brightness temperature value and average brightness temperature difference value are calculated. Based on the Otsu algorithm, the average brightness temperature value and average brightness temperature difference value of the target pixel at the same instant are used to determine the empirical threshold values ​​for the average brightness temperature value and average brightness temperature difference value of the target pixel. Based on the average brightness temperature value and average brightness temperature difference value of the effective pixel, as well as the empirical threshold values ​​for the average brightness temperature value and average brightness temperature difference value of the effective pixel, the background brightness temperature threshold and background brightness temperature difference threshold value of the effective pixel are determined. The empirical threshold values ​​for the average brightness temperature value and average brightness temperature difference value of the invalid pixel are used to determine the background brightness temperature threshold and background brightness temperature difference threshold value of the invalid pixel. Based on preset conditions, the background brightness temperature threshold and background brightness temperature difference threshold of the target pixel are used to determine the final pixel in the target pixel, and the final pixel and the absolute fire point pixel are determined as potential fire points; including: determining the effective pixels in the effective pixels whose difference between the brightness temperature value of the 7th channel at the same time on day i and the corresponding background brightness temperature threshold is greater than a first preset threshold, whose difference between the brightness temperature difference at the same time on day i and the corresponding background brightness temperature difference threshold is greater than a first preset threshold and whose brightness temperature value of the 7th channel at the same time on day i is greater than a second preset threshold as the final pixel; determining the invalid pixels in the invalid pixels whose difference between the brightness temperature value of the 7th channel at the same time on day i and the corresponding background brightness temperature threshold is greater than a third preset threshold, whose difference between the brightness temperature difference at the same time on day i and the corresponding background brightness temperature difference threshold is greater than a third preset threshold and whose brightness temperature value of the 7th channel at the same time on day i is greater than a fourth preset threshold as the final pixel.

2. The method according to claim 1, characterized in that, The attribute data of each pixel in the geostationary meteorological satellite remote sensing image data is determined, including: The geostationary meteorological satellite remote sensing image data is preprocessed to determine the target parameters of each pixel in the geostationary meteorological satellite remote sensing image data. The target parameters include: visible light channel apparent reflectance data, near-infrared channel apparent reflectance data, mid-infrared channel brightness temperature data, far-infrared channel brightness temperature data, satellite zenith angle, satellite azimuth angle, solar zenith angle, and solar zenith angle. Based on the target parameters and the preset discrimination formula, the day and night attributes of each pixel are determined, wherein the preset discrimination formula is: , DayBool is the mask file for daytime pixels, NightBool is the mask file for nighttime pixels, and ValidBool is the valid mask file for geostationary meteorological satellite remote sensing image data whose quality meets the usage requirements. The apparent reflectance of the first channel is... The angle of the sun's zenith; Based on the target parameters and the average brightness temperature formula, the simultaneous average brightness temperature of each pixel is determined, wherein the average brightness temperature formula is as follows: ,in, This represents the average brightness temperature at the same time. The number of days within the preset time period. This represents the brightness temperature value of channel 7 at the same time on day i. Based on the target parameters and the formula for the average brightness temperature difference, the average brightness temperature difference of each pixel at the same time is determined, wherein the formula for the average brightness temperature difference is: ,in, , To brighten the temperature difference, This represents the brightness temperature value of channel 13 at the same moment on day i. This represents the temperature difference at the same time on day i.

3. The method according to claim 2, characterized in that, Based on the attribute data, the target pixels in the geostationary meteorological satellite remote sensing image data are determined, including: Based on the attribute data, the normalized brightness temperature value of the 7th channel, the normalized brightness temperature value of the 14th channel, and the clear sky background field data, cloud pixels in the geostationary meteorological satellite remote sensing image data are determined, wherein the cloud pixels include: daytime cloud pixels and nighttime cloud pixels. Based on the attribute data, normalized vegetation index, normalized water index, and water mask data, cloud pixels in the geostationary meteorological satellite remote sensing image data are determined. Based on the attribute data and the brightness temperature value of the 7th channel, the absolute fire point pixels in the geostationary meteorological satellite remote sensing image data are determined, wherein the absolute fire point pixels include: daytime absolute fire point pixels and nighttime absolute fire point pixels.

4. A potential fire point identification device based on geostationary meteorological satellites, characterized in that, include: The system comprises an acquisition unit, a determination unit, a calculation unit, and a discrimination unit, wherein... The acquisition unit is used to acquire geostationary meteorological satellite remote sensing image data of the area to be identified within a preset time period, and determine the attribute data of each pixel in the geostationary meteorological satellite remote sensing image data, wherein the attribute data includes: day and night attributes, average brightness temperature at the same time and average brightness temperature difference at the same time; The determining unit is used to determine the target pixels in the geostationary meteorological satellite remote sensing image data based on the attribute data, wherein the target pixels are pixels other than cloud pixels, water body pixels and absolute fire point pixels. The calculation unit is used to calculate the background brightness temperature threshold and background brightness temperature difference threshold of the target pixel based on the dynamic window algorithm and the attribute data; including: determining the number of target pixels in the target window based on the dynamic window algorithm, wherein the target window is a window of a preset size constructed with any target pixel as the center; determining the target pixels corresponding to the target windows with a number greater than the preset threshold as valid pixels, and determining the target pixels corresponding to the target windows with a number less than or equal to the preset threshold as invalid pixels; calculating the effective pixel value based on the target pixels in the target window corresponding to the valid pixels. The average brightness temperature value and average brightness temperature difference value of the target pixel are calculated. Based on the Otsu algorithm, the average brightness temperature value and average brightness temperature difference value of the target pixel at the same instant are used to determine the empirical threshold values ​​for the average brightness temperature value and average brightness temperature difference value of the target pixel. Based on the average brightness temperature value and average brightness temperature difference value of the effective pixel, as well as the empirical threshold values ​​for the average brightness temperature value and average brightness temperature difference value of the effective pixel, the background brightness temperature threshold and background brightness temperature difference threshold value of the effective pixel are determined. The empirical threshold values ​​for the average brightness temperature value and average brightness temperature difference value of the ineffective pixel are used to determine the background brightness temperature threshold and background brightness temperature difference threshold value of the ineffective pixel. The discrimination unit is used to determine the final pixel in the target pixel based on preset conditions, the background brightness temperature threshold and the background brightness temperature difference threshold of the target pixel, and to determine the final pixel and the absolute fire point pixel as potential fire points; including: determining the effective pixels in the effective pixels whose difference between the brightness temperature value of the 7th channel at the same time on day i and the corresponding background brightness temperature threshold is greater than a first preset threshold, whose difference between the brightness temperature difference at the same time on day i and the corresponding background brightness temperature difference threshold is greater than a first preset threshold and whose brightness temperature value of the 7th channel at the same time on day i is greater than a second preset threshold as the final pixel; and determining the invalid pixels in the invalid pixels whose difference between the brightness temperature value of the 7th channel at the same time on day i and the corresponding background brightness temperature threshold is greater than a third preset threshold, whose difference between the brightness temperature difference at the same time on day i and the corresponding background brightness temperature difference threshold is greater than a third preset threshold and whose brightness temperature value of the 7th channel at the same time on day i is greater than a fourth preset threshold as the final pixel.

5. The apparatus according to claim 4, characterized in that, The acquisition unit is used for: The geostationary meteorological satellite remote sensing image data is preprocessed to determine the target parameters of each pixel in the geostationary meteorological satellite remote sensing image data. The target parameters include: visible light channel apparent reflectance data, near-infrared channel apparent reflectance data, mid-infrared channel brightness temperature data, far-infrared channel brightness temperature data, satellite zenith angle, satellite azimuth angle, solar zenith angle, and solar zenith angle. Based on the target parameters and the preset discrimination formula, the day and night attributes of each pixel are determined, wherein the preset discrimination formula is: , DayBool is the mask file for daytime pixels, NightBool is the mask file for nighttime pixels, and ValidBool is the valid mask file for geostationary meteorological satellite remote sensing image data whose quality meets the usage requirements. The apparent reflectance of the first channel is... The angle of the sun's zenith; Based on the target parameters and the average brightness temperature formula, the simultaneous average brightness temperature of each pixel is determined, wherein the average brightness temperature formula is as follows: , This represents the average brightness temperature at the same time. The number of days within the preset time period. This represents the brightness temperature value of channel 7 at the same time on day i. Based on the target parameters and the formula for the average brightness temperature difference, the average brightness temperature difference of each pixel at the same time is determined, wherein the formula for the average brightness temperature difference is: ,in, , To brighten the temperature difference, This represents the brightness temperature value of channel 13 at the same moment on day i. This represents the temperature difference at the same time on day i.

6. The apparatus according to claim 5, characterized in that, The determining unit is used for: Based on the attribute data, the normalized brightness temperature value of the 7th channel, the normalized brightness temperature value of the 14th channel, and the clear sky background field data, cloud pixels in the geostationary meteorological satellite remote sensing image data are determined, wherein the cloud pixels include: daytime cloud pixels and nighttime cloud pixels. Based on the attribute data, normalized vegetation index, normalized water index, and water mask data, cloud pixels in the geostationary meteorological satellite remote sensing image data are determined. Based on the attribute data and the brightness temperature value of the 7th channel, the absolute fire point pixels in the geostationary meteorological satellite remote sensing image data are determined, wherein the absolute fire point pixels include: daytime absolute fire point pixels and nighttime absolute fire point pixels.

7. An electronic device, characterized in that, The system includes a memory and a processor, the memory being used to store a program that enables the processor to execute the method of any one of claims 1 to 3, and the processor being configured to execute the program stored in the memory.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When a computer program is run by a processor, it performs the steps of the method described in any one of claims 1 to 3.

Images