A fire point detection algorithm combining radiation angle normalization with a priori data set

Abstract

The application relates to a fire point detection algorithm combining radiation angle normalization and a priori data set, and comprises the following steps: using a radiation transfer model to simulate the difference ratio of MODIS fire point detection bands at different satellite scanning angles and subsatellite brightness, normalizing the top atmospheric brightness at different satellite scanning angles to the MODIS subsatellite point; constructing a priori data set, the priori data set containing a sample database of fire points and non-fire points, automatically selecting fire point detection bands by comparing the radiation characteristics of the fire points and the non-fire points, and determining appropriate fire point detection thresholds according to the expected accuracy; calculating the Kappa coefficient and the weight of different fire point test conditions through the accuracy of fire point and non-fire point identification, fusing various fire point detection algorithms, and generating fire point probability values. The application can effectively reduce the significant influence of satellite scanning angles on fire points, fully excavate the fire point information contained in different band fires, and improve the fire point detection capability.

Description

Technical Field

[0001] The present invention relates to the technical field of fire point monitoring based on satellite remote sensing, and in particular to a fire point detection algorithm combining radiation angle normalization with a priori data set. Background Art

[0002] Forest fires are extremely destructive and sudden natural disasters that cause enormous losses to humans and ecosystems. To minimize the losses caused by fires, timely and accurate detection and monitoring of fire conditions are crucial. With the continuous development and increasing maturity of aerospace remote sensing technology, the use of remote sensing satellites to monitor forest fires has become a mainstream trend in forest fire prevention. Remote sensing satellites, with their high temporal and spatial resolution and ability to observe large areas, play a key role in fire monitoring. Furthermore, satellite remote sensing can provide information such as fire location, temperature, and area, helping to track the dynamic progress of fires.

[0003] The Moderate Resolution Imaging Spectroradiometer (MODIS) has 36 channels covering the visible to thermal infrared bands, with a resolution of 250 meters to 1 kilometer. It plays a vital role in fire monitoring. Currently, the most commonly used fire detection algorithms are threshold and context methods. These methods use the temperature difference between the fire point and the normal temperature ground objects in the mid-infrared and thermal infrared bands to extract fire point information. Traditional fire monitoring algorithms have two significant flaws: First, small fires are easily missed. Since the burning area of ​​small fires is small, for satellite data with relatively low resolution such as MODIS, the temperature difference between fire pixels and background pixels is not obvious at the pixel scale, and they cannot be effectively distinguished. In particular, the detection of low-intensity fires by the MODIS contextual algorithm is significantly affected by the satellite scanning angle. When the satellite observation angle is large, the spatial range obtained by the satellite sensor is larger, which reduces the proportion of small fires in the overall radiation contribution, resulting in the accuracy of small fire detection decreasing with the increase of the scanning angle; second, fixed surface heat sources are easily misidentified as fire points. The temperature of fixed heat sources is close to that of fire points, and they have similar radiation characteristics to fire points, which causes great interference to fire point detection.

[0004] The current fire point detection algorithm is insufficient in its ability to mine remote sensing data information and cannot fully mine the fire point information contained in fires burning in different bands. The accuracy of fire point detection is still greatly limited, and there are problems such as missed detection of small fire points and false detection of false fire points. Therefore, it is necessary to further improve the problems existing in the fire point detection algorithm. Summary of the Invention

[0005] To address the above issues, the present invention provides a fire detection algorithm that combines radiation angle normalization with a priori dataset. This algorithm normalizes the top-of-atmosphere data to enhance small fire information. It also uses the priori dataset to further mine fire information and determine the threshold for fire detection. The algorithm includes the following steps:

[0006] 1. Normalize the MODIS top-of-atmosphere radiation angle. Use the radiation transfer model to simulate the difference ratio between the MODIS fire detection band at different satellite scanning angles and the sub-satellite point radiance. Characterize the impact of angle changes on MODIS top-of-atmosphere radiation. Normalize the top-of-atmosphere radiance at different band scanning angles to the radiance observed at the sub-satellite point.

[0007] 2. Construct a priori dataset, which includes reflectance and brightness temperature data of fire and non-fire samples. After preprocessing the MODIS data by geometric correction, radiometric brightness calculation, and brightness temperature, the US wildfire geographic data is spatiotemporally aligned with the MODIS data to form a dataset that matches the surface and satellite data.

[0008] 3. Select the fire point detection band, taking into account all bands from visible light to thermal infrared. By performing band calculations and statistical analysis on fire point and non-fire point sample data, the fire information contained in different bands and band combinations is mined, and the fire point detection band is automatically selected.

[0009] 4. Select the fire point detection threshold. Based on the prior data set of fire points and non-fire points, use computer automatic analysis technology to automatically compare the radiation characteristics of fire points and non-fire points, and automatically select the optimal threshold for the fire point test condition based on the expected accuracy;

[0010] 5. Fusion of fire detection algorithms: Based on the prior data set, the fire detection results corresponding to the single-band, multi-band and context band algorithms are obtained respectively. The Kappa coefficients of different fire point test conditions are calculated by the accuracy of fire point and non-fire point identification. The respective weights are calculated according to the Kappa coefficients of all test conditions. The weights of each band test condition and the detection results are substituted into the fusion algorithm formula for fire point detection to generate a fire point probability value. The higher the probability value, the more reliable the detection result of the fire point pixel.

[0011] As a preferred embodiment, the input of the MODTRAN model includes control operation parameters, sensor parameters, atmospheric parameters, observation geometry conditions and surface parameters. The previously known atmospheric profile type is used to simulate the top-of-atmosphere radiation difference ratio r(θ) at the sub-satellite point and different satellite scanning angles. The calculated radiation difference ratio is combined with the observation zenith angle data of the MODIS sensor, and the top-of-atmosphere radiance observed from the satellite scanning angle θ is normalized to the position directly below the MODIS satellite track:

[0012]

[0013] Where: Rad obs (θ) is the radiance of the top of the atmosphere received by MODIS at each satellite scanning angle, is the radiance normalized to the area directly below the satellite track.

[0014] As a preferred embodiment, the fire point sample database should include fires of different types and sizes and various stages of fire burning. Fire point information includes the time of fire occurrence, fire extinguishing time, longitude, latitude, fire area, etc.; the non-fire point sample database is established based on multi-time series remote sensing images. The selection of non-fire point samples should not only consider terrain factors, including terrain features such as mountains, plains, and hills, but also various land use / land cover types, including four typical surfaces: artificial surfaces, vegetation, clouds, and water bodies. Among them, artificial surfaces include cities, roads, industrial areas, etc., which are extracted using the normalized building index. Vegetation mainly includes farmland, forests, grasslands, etc., which are selected using the normalized vegetation index. Cloud pixels include thick clouds, thin clouds, broken clouds, etc. Water bodies include oceans, rivers, lakes, etc. Cloud and water pixels are selected using the cloud water mask threshold in the MODIS fire point algorithm. High-brightness surfaces such as agricultural greenhouses and smooth buildings are selected using a combination of near-infrared, short-wave infrared reflectivity and mid-infrared brightness temperature values.

[0015] As a preferred embodiment, the radiation difference between fire points and non-fire points is analyzed based on the sample database, and the MODIS sensor wavelength bands of 0.86μm, 1.65μm, 2.13μm, 3.8μm, 3.96μm, 11.03μm and 12.02μm are selected. The single-band, multi-band difference and context band combination methods are used, and the bubble method is used to automatically calculate the fire point pixel recognition accuracy to determine the band for fire detection;

[0016] As a preferred embodiment, in the process of determining the optimal threshold, the minimum brightness temperature value and the maximum brightness temperature value of the fire point in the fire point prior data set are statistically analyzed, and the fire point detection threshold is changed from the minimum brightness temperature value of the fire point prior data set to the maximum brightness temperature value in steps of K. As the threshold changes, the fire point pixel recognition accuracy (the fire point pixel accuracy refers to the proportion of correctly identified fire point pixels to the total number of fire point pixels) and the surface misjudgment rate (the surface misjudgment rate refers to the proportion of misjudged non-fire point pixels to the total number of non-fire point pixels) also change accordingly. When the threshold reaches a certain value, the fire point pixel recognition accuracy increases slowly with the change of the threshold, while the non-fire point pixel misjudgment rate increases significantly with the increase of the threshold. Based on the principle of the bubble method, the computer automatically selects the threshold with the highest accuracy as the optimal threshold, while limiting the non-fire point misjudgment rate a%.

[0017] As a preferred implementation, the calculation formulas for the Kappa coefficient and weight corresponding to each band algorithm are as follows:

[0018]

[0019] Among them, p a is the probability of correct classification, p e is the probability of correct classification given the relative frequencies of fire points and non-fire points. TP is the number of fire point pixels correctly detected by the algorithm, TN is the number of non-fire point pixels correctly detected by the algorithm, FP is the number of fire point pixels misjudged by the algorithm, FN is the number of non-fire point pixels misjudged by the algorithm, P is the number of fire point pixels in the fire point sample database, F is the number of non-fire point pixels in the non-fire point sample database, and W i is the weight of each band algorithm, Kappa i is the Kappa coefficient of each band algorithm, and n is the total number of all band algorithms.

[0020] As a preferred implementation, the fire point detection algorithm is integrated, the confidence level of the detection results is adjusted, and the fire probability calculation formula is adopted:

[0021]

[0022] Where G is the final result of fire point detection; F i Is the result of a single fire point test condition (if it is a fire point, F i =1, if it is not a fire point, F i =0); W i is the weight of the corresponding fire point test condition; N is the total number of fire test conditions. If the probability of the weighted synthesis result reaches 1, then this pixel is a complete fire pixel. Conversely, if the probability drops to 0, then this pixel is a complete non-fire pixel.

[0023] Due to the adoption of the above steps and methods, the technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0024] (1) Since the radiation energy received by the satellite sensor decreases with the increase of the satellite scanning angle, the detection of low-intensity fires by the MODIS context algorithm is significantly affected by the satellite scanning angle, and the accuracy of small fire point detection decreases with the increase of the scanning angle. Therefore, the present invention normalizes the MODIS top atmosphere radiation angle, normalizes the radiance of the fire point detection band at different satellite scanning angles to the radiance of the sub-satellite point, and improves the detection accuracy of small fire points.

[0025] (2) In order to make full use of the band information of MODIS and deeply explore the information differences between fire points and non-fire points, the present invention assists in determining the fire point detection threshold based on the U.S. wildfire geographic data, uses computer automation to analyze the differences in radiation characteristics between fire points and non-fire points, and automatically selects the optimal threshold for fire point detection based on the fire point recognition accuracy under the control of the desired accuracy, fully exploring the fire point information contained in fires in different bands and improving the ability of fire point detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0027] Figure 1 This is a schematic diagram of the organizational structure of the technical roadmap according to the embodiment. DETAILED DESCRIPTION

[0028] The present invention provides a fire point detection algorithm that combines radiation angle normalization with a priori data set. To make the objectives, technical solutions, and effects of the present invention more clear and explicit, the present invention is further described below. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.

[0029] Reference Figure 1 ,This embodiment provides a fire point detection algorithm that combines radiation angle normalization with a priori data set.

[0030] 1. Normalize the MODIS top-of-atmosphere radiation angle. Use the radiation transfer model to simulate the difference ratio between the MODIS fire detection band at different satellite scanning angles and the sub-satellite point radiance. Characterize the impact of angle changes on MODIS top-of-atmosphere radiation. Normalize the top-of-atmosphere radiance at different band scanning angles to the radiance observed at the sub-satellite point.

[0031] The inputs of the MODTRAN model include control parameters, sensor parameters, atmospheric parameters, observation geometry, and surface parameters. The radiance angle of the fire detection band is normalized. The effect of angle changes on TOA radiation is characterized by simulating the difference ratio r(θ) between different observation angles and the radiation observed at the sub-satellite point. The following formula is used:

[0032] r(θ)=[Rad(θ)-Rad nadir ] / Rad nadir

[0033] Among them, Rad(θ) and Rad nadir They are the radiance values ​​of the top of the atmosphere observed by MODIS at different satellite scanning angles and directly below the satellite track (subsatellite point);

[0034] The known atmospheric profile type is used to simulate the top-of-atmosphere radiation difference ratio r(θ) between the sub-satellite point and different satellite scanning angles. The calculated radiation difference ratio is combined with the observation zenith angle data of the MODIS sensor. The top-of-atmosphere radiance observed from the satellite scanning angle θ is normalized to the point directly below the MODIS satellite track:

[0035]

[0036] Where: Rad obs (θ) is the radiance of the top of the atmosphere received by MODIS at each satellite scanning angle, is the radiance normalized to the area directly below the satellite track.

[0037] 2. Construct a priori dataset, which includes reflectance and brightness temperature data of fire and non-fire samples. After preprocessing the MODIS data through geometric correction, radiometric calibration, and brightness temperature, the US wildfire geographic data is spatiotemporally aligned with the MODIS data to form a dataset that matches the surface and satellite data.

[0038] The fire point sample database should include fire information of different scales and different burning stages. Fires of different area levels in the wildfire data should be selected. Fire point information includes fire occurrence time, fire extinguishing time, longitude, latitude, fire area, etc.

[0039] The establishment of the non-fire point sample database is based on multi-time series remote sensing images. The selection of non-fire point samples should not only consider terrain factors, including terrain features such as mountains, plains, and hills, but also various land use / land cover types, including four typical surfaces: artificial surfaces, vegetation, clouds, and water bodies. Among them, artificial surfaces include cities, roads, industrial areas, etc., which are extracted using the normalized building index. Vegetation mainly includes farmland, forests, grasslands, etc., which are selected using the normalized vegetation index. Cloud pixels include thick clouds, thin clouds, broken clouds, etc. Water bodies include oceans, rivers, lakes, etc. Cloud and water pixels are selected using the cloud-water mask threshold in the MODIS fire point algorithm. High-brightness surfaces such as agricultural greenhouses and smooth buildings are selected using a combination of near-infrared, short-wave infrared reflectivity and mid-infrared brightness temperature values.

[0040] (1) Selection of building samples

[0041] The normalized building index (NDBI) is selected to detect buildings. It is generally believed that when the NDBI is greater than 0, the pixel point is a building.

[0042]

[0043] Where: ρ 2.1 , ρ 0.86represent the apparent reflectance of the shortwave infrared band and the near infrared band, respectively.

[0044] (2) Highlight surface selection

[0045] The algorithm of the Visible Infrared Imaging Radiometer Suite (VIIRS) 375m active fire detection product was used as a reference, and the apparent reflectance of the shortwave infrared and near infrared and the brightness temperature threshold of the 21 / 22 channels of the thermal infrared band were used for selection.

[0046] (ρ 2.1 >0.3&&ρ 2.1 >ρ 0.86 &&ρ 0.86 >0.25)&&BT4≤335K

[0047] Where: ρ 2.1 , ρ 0.86 They represent the apparent reflectance of the shortwave infrared and near-infrared bands respectively, and BT4 is the brightness temperature of the 21 / 22 channels in the mid-infrared band.

[0048] (3) Vegetation sample selection

[0049] Vegetation type selection uses the Normalized Difference Vegetation Index (NDVI) to set a threshold for selection. Pixels that meet this condition are considered to belong to the vegetation type.

[0050]

[0051] Where: ρ 0.86 , ρ 0.65 represent the apparent reflectance of the near-infrared band and the red light band, respectively.

[0052] (4) Cloud pixel selection

[0053] The cloud detection method uses the cloud detection algorithm in the latest version of the MODIS C6 algorithm. Clouds are identified using the apparent reflectance of the MODIS red and near-infrared bands and the brightness temperature of the 32nd channel of the thermal infrared band:

[0054] (ρ 0.65 +ρ 0.86 >1.2)or(BT 12 <265K)or

[0055] (ρ 0.65 +ρ 0.86 >0.7andBT 12 <285K)

[0056] Where: ρ 0.86 , ρ 0.65are the apparent reflectances of the near-infrared band and the red light band, BT 12 is the brightness temperature of 32 bands.

[0057] (5) Water pixel selection

[0058] Water body pixel detection uses the apparent reflectance of the MODIS near-infrared band and short-wave infrared band and the normalized difference vegetation index (NDVI) for extraction:

[0059]

[0060] Where: ρ 0.86 , ρ 0.65 represent the apparent reflectance of the near-infrared band and the red light band, respectively.

[0061] 3. Select the fire point detection band, taking into account all bands in the visible light to thermal infrared range, and through band calculations and statistical analysis of fire point and non-fire point sample data, dig out the fire information contained in different bands and band combinations, and automatically select the fire point detection band. For single band and multi-band, based on the sample database, the computer uses the bubbling method to automatically calculate the fire point recognition accuracy based on the reflectivity and brightness temperature data of the pre-selected single band and multi-band, and select the fire point detection band. For the bands of the context algorithm, the bubbling classification method is used to automatically calculate the accuracy of the context band in judging fire, so that the context band is selected according to the fire point discrimination effect;

[0062] 4. Select the fire point detection threshold. Based on the prior data set of fire points and non-fire points, use computer automatic analysis technology to automatically compare the radiation characteristics of fire points and non-fire points, and automatically select the optimal threshold for the fire point test condition based on the expected accuracy;

[0063] Based on the analysis of the radiation differences between fire points and non-fire points in the sample database, the MODIS sensor wavelength bands of 0.86μm, 1.65μm, 2.13μm, 3.8μm, 3.96μm, 11.03μm and 12.02μm were selected. The accuracy of fire point pixel recognition was automatically calculated using the bubble method by using single-band, multi-band difference and context band combination to determine the band for fire detection.

[0064] To determine the optimal threshold, the minimum and maximum brightness temperatures of the fire points in the fire point prior dataset are calculated. The fire detection threshold is then varied from the minimum brightness temperature in the fire point prior dataset to the maximum brightness temperature in steps of K. As the threshold changes, the fire point pixel recognition accuracy (the fire point pixel accuracy rate is the proportion of correctly identified fire point pixels to the total number of fire point pixels) and the surface misidentification rate (the surface misidentification rate is the proportion of misidentified non-fire point pixels to the total number of non-fire point pixels) also change accordingly. When the threshold reaches a certain value, the fire point pixel recognition accuracy rate increases slowly with the change in the threshold, while the non-fire point pixel misidentification rate increases significantly with the increase in the threshold. Based on the principle of the bubble method, the computer automatically selects the threshold with the highest accuracy rate as the optimal threshold, while limiting the non-fire point misidentification rate to a%.

[0065] 5. Fusion of fire detection algorithms: Based on the prior data set, the fire detection results corresponding to the single-band, multi-band and context band algorithms are obtained respectively. The Kappa coefficients of different fire point test conditions are calculated by the accuracy of fire point and non-fire point identification. The respective weights are calculated according to the Kappa coefficients of all test conditions. The weights of each band test condition and the detection results are substituted into the fusion algorithm formula for fire point detection to generate a fire point probability value. The higher the probability value, the more reliable the detection result of the fire point pixel.

[0066] As a preferred implementation, the calculation formulas for the Kappa coefficient and weight corresponding to each band algorithm are as follows:

[0067]

[0068] Among them, p a is the probability of correct classification, p e is the probability of correct classification given the relative frequencies of fire points and non-fire points. TP is the number of fire point pixels correctly detected by the algorithm, TN is the number of non-fire point pixels correctly detected by the algorithm, FP is the number of fire point pixels misjudged by the algorithm, FN is the number of non-fire point pixels misjudged by the algorithm, P is the number of fire point pixels in the fire point sample database, F is the number of non-fire point pixels in the non-fire point sample database, and W i is the weight of each band algorithm, Kappa i is the Kappa coefficient of each band algorithm, and n is the total number of all band algorithms.

[0069] The confidence level of the detection results is adjusted using the fire probability calculation formula:

[0070]

[0071] Where G is the final result of fire point detection; F i Is the result of a single fire point test condition (if it is a fire point, F i=1, if it is not a fire point, F i =0); W i is the weight of the corresponding fire point test condition; N is the total number of fire test conditions. If the probability of the weighted synthesis result reaches 1, then this pixel is a complete fire pixel. Conversely, if the probability drops to 0, then this pixel is a complete non-fire pixel.

[0072] This algorithm reduces the false positive rate of fires and improves the detection accuracy of small fires. Compared to MODIS fire products, it has lower misclassification and omission errors, and lower false detection rates than VIIRS fire products. Based on MODIS data, a method for normalizing radiation angles is proposed to improve the accuracy of small fires. Furthermore, based on analysis of prior datasets, fire information is deeply mined, appropriate monitoring thresholds are set, and the accuracy of fire monitoring is improved.

[0073] It should be noted that the above description is only an illustration of some embodiments of the present application and the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in this application is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, the above-mentioned features can be replaced with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A fire point detection algorithm combining radiation angle normalization with a priori data set, characterized in that: The following steps are involved: (1) The MODIS top-of-atmosphere radiation angle was normalized. The radiative transfer model was used to simulate the difference ratio between the radiance of the MODIS fire detection band at different satellite scanning angles and the sub-satellite point, to characterize the impact of angle changes on the MODIS top-of-atmosphere radiation. The top-of-atmosphere radiance at different band scanning angles was normalized to the radiance observed at the sub-satellite point. (2) Construct a priori dataset, which includes the reflectance and brightness temperature data of fire point samples and non-fire point samples. After geometric correction, radiometric brightness calculation, and brightness temperature preprocessing of MODIS data, the U.S. wildfire geographic data and MODIS data are spatiotemporally aligned to form a dataset that matches the surface and satellite data. (3) Select the fire point detection band, taking into account all bands from visible light to thermal infrared, and automatically select the fire point detection band by performing band calculations and statistical analysis on fire point and non-fire point sample data, mining the fire information contained in different bands and band combinations; (4) Selecting the fire point detection threshold, based on the prior data set of fire points and non-fire points, using computer automatic analysis technology to automatically compare the radiation characteristics of fire points and non-fire points, and automatically select the optimal threshold of the fire point test condition according to the expected accuracy; (5) Fusion of fire detection algorithms: Based on the prior data set, the fire detection results corresponding to the single-band, multi-band, and context band algorithms are obtained respectively. The Kappa coefficients of different fire point test conditions are calculated by the accuracy of fire point and non-fire point identification. The respective weights of all test conditions are calculated according to the Kappa coefficients. The weights of each band test condition and the detection results are substituted into the fusion algorithm formula for fire point detection to generate a fire point probability value. The higher the probability value, the more reliable the detection result of the fire point pixel. The calculation formulas for the Kappa coefficient and weight corresponding to each band algorithm are as follows: Among them, p a is the probability of correct classification, p e is the probability of correct classification when the relative frequency of fire points / non-fire points is known, TP is the number of fire point pixels correctly detected by the algorithm, TN is the number of non-fire point pixels correctly detected by the algorithm, FP is the number of fire point pixels misjudged by the algorithm, FN is the number of non-fire point pixels misjudged by the algorithm, P is the number of fire point pixels in the fire point sample database, N is the number of non-fire point pixels in the non-fire point sample database, and W i is the weight of each band algorithm, Kappa i is the Kappa coefficient of each band algorithm, and n is the total number of all band algorithms.

2. According to the fire point detection algorithm of claim 1, the input of the MODTRAN model includes control operation parameters, sensor parameters, atmospheric parameters, observation geometry conditions and surface parameters, and the top of the atmosphere radiation difference ratio r(θ) under different satellite scanning angles is simulated using a pre-known atmospheric profile type. The calculated radiation difference ratio is combined with the observation zenith angle data of the MODIS sensor, and the top of the atmosphere radiance observed from the satellite scanning angle θ is normalized to the position directly below the MODIS satellite track: Where: Rad obs (θ) is the radiance of the top of the atmosphere received by MODIS at each satellite scanning angle, is the radiance normalized to the area directly below the satellite track.

3. According to the fire point detection algorithm combining radiation angle normalization with a priori data set as described in claim 2, the fire point sample data set should include fires of different types and sizes and various stages of fire combustion. The fire point information includes the time of fire occurrence, fire extinguishing time, longitude, latitude, and fire area size; the establishment of the non-fire point sample database is based on multi-time series remote sensing imagery. The selection of non-fire point samples should not only consider terrain factors, including the terrain characteristics of mountains, plains, and hills, but also various land use / land cover types. It includes four typical surfaces: artificial surfaces, vegetation, clouds, and water bodies. Artificial surfaces include cities, roads, and industrial areas, which are extracted using the normalized building index. Vegetation includes farmland, forests, and grasslands, which are selected using the normalized vegetation index. Cloud pixels include thick clouds, thin clouds, and broken clouds. Water bodies include oceans, rivers, and lakes. Cloud and water pixels are selected using the cloud-water mask threshold in the MODIS fire point algorithm. The bright surfaces of agricultural greenhouses and smooth buildings are selected using a combination of near-infrared, short-wave infrared reflectivity, and mid-infrared brightness temperature values.

4. According to the fire point detection algorithm combining radiation angle normalization with a priori data set described in claim 3, the radiation difference between fire points and non-fire points is analyzed based on the sample database, the MODIS sensor wavelength bands of 0.86μm, 1.65μm, 2.13μm, 3.8μm, 3.96μm, 11.03μm and 12.02μm are selected, and the single-band, multi-band difference and context band combination methods are used. The bubble method is used to automatically calculate the fire point pixel recognition accuracy to determine the band for fire detection.

5. According to the fire point detection algorithm combining radiation angle normalization with a priori data set as described in claim 4, in the process of determining the optimal threshold, the minimum brightness temperature value and the maximum brightness temperature value of the fire point in the fire point priori data set are statistically counted, and the fire point detection threshold is changed from the minimum brightness temperature value of the fire point priori data set to the maximum brightness temperature value in a step size of K. As the threshold changes, the fire point pixel recognition accuracy and the surface misjudgment rate also change accordingly; when the threshold reaches a certain value, the fire point pixel recognition accuracy increases slowly with the change of the threshold, but the non-fire point pixel misjudgment rate increases significantly with the increase of the threshold. Based on the principle of the bubbling method, the computer automatically selects the threshold with the highest accuracy as the optimal threshold under the premise of limiting the non-fire point misjudgment rate a%.

6. According to the fire point detection algorithm combining radiation angle normalization with a priori data set described in claim 5, the fire point detection algorithm is integrated and the confidence level of the detection results is adjusted. The fire probability is calculated as follows: Where G is the final result of fire point detection; F i Is the result of single fire point test condition, if it is fire point, F i =1, if it is not a fire point, F i =0;W i is the weight of the corresponding fire point test condition; X is the total number of fire test conditions. If the probability of the weighted synthesis result reaches 1, then this pixel is a complete fire pixel. Conversely, if the probability drops to 0, then this pixel is a complete non-fire pixel.

Images